3. 経路予測のカテゴリ
3
Bayesian-based Deep Learning-based Planning-based
内部状態
観測状態
Update Update
ex. model : Kalman Filter
Past Future
Prediction
model
Input
Output
ex. model : LSTM,CNN ex. Model : IRL, RRT*
Start
Goal
X
O
X
観測状態にノイズを付与した値から
未来の内部状態を更新し予測値を逐次推定
予測対象の過去の軌跡から未来の行動を学習 スタートからゴールまでの報酬値を最適化
本サーベイの対象
4. Deep Learningによる経路予測の必要な要素
4
一人称視点
車載カメラ視点
鳥瞰視点
View point
and the yellow-orange heatmaps are
n ones are ground truth multi-future
Single-Future Multi-Future
18.51 / 35.84 166.1 / 329.5
28.68 / 49.87 184.5 / 363.2
PIE JAAD
Method MSE CMSE CFMSE MSE CMSE CFM
0.5s 1s 1.5s 1.5s 1.5s 0.5s 1s 1.5s 1.5s 1.5
Linear 123 477 1365 950 3983 223 857 2303 1565 611
LSTM 172 330 911 837 3352 289 569 1558 1473 576
B-LSTM[5] 101 296 855 811 3259 159 539 1535 1447 561
PIEtraj 58 200 636 596 2477 110 399 1248 1183 478
Table 3: Location (bounding box) prediction errors over varying future time steps. MSE in pixels is ca
predicted time steps, CMSE and CFMSE are the MSEs calculated over the center of the bounding box
predicted sequence and only the last time step respectively.
MSE
Method 0.5s 1s 1.5s
Linear 0.87 2.28 4.27
LSTM 1.50 1.91 3.00
PIEspeed 0.63 1.44 2.65
Long Short-Term Memory
Convolutional Neural Network
Gated Recurrent Unit
Temporal Convolutional Network
Model
!"
!#
!$
!%!&
!'
t=t input layert=t-1 hidden layer
Input Gate
t=t output layert=t+1 hidden layer
Memory Cell
Forget Gate
Output Gate
対象クラス
対象間のインタラクション
静的環境情報
Context
5. Deep Learningによる経路予測の必要な要素
5
一人称視点
車載カメラ視点
鳥瞰視点
View point
対象クラス
対象間のインタラクション
静的環境情報
Context
Long Short-Term Memory
Convolutional Neural Network
Gated Recurrent Unit
Temporal Convolutional Network
Model
and the yellow-orange heatmaps are
n ones are ground truth multi-future
Single-Future Multi-Future
18.51 / 35.84 166.1 / 329.5
28.68 / 49.87 184.5 / 363.2
PIE JAAD
Method MSE CMSE CFMSE MSE CMSE CFM
0.5s 1s 1.5s 1.5s 1.5s 0.5s 1s 1.5s 1.5s 1.5
Linear 123 477 1365 950 3983 223 857 2303 1565 611
LSTM 172 330 911 837 3352 289 569 1558 1473 576
B-LSTM[5] 101 296 855 811 3259 159 539 1535 1447 561
PIEtraj 58 200 636 596 2477 110 399 1248 1183 478
Table 3: Location (bounding box) prediction errors over varying future time steps. MSE in pixels is ca
predicted time steps, CMSE and CFMSE are the MSEs calculated over the center of the bounding box
predicted sequence and only the last time step respectively.
MSE
Method 0.5s 1s 1.5s
Linear 0.87 2.28 4.27
LSTM 1.50 1.91 3.00
PIEspeed 0.63 1.44 2.65
!"
!#
!$
!%!&
!'
t=t input layert=t-1 hidden layer
Input Gate
t=t output layert=t+1 hidden layer
Memory Cell
Forget Gate
Output Gate
11. 複数の歩行者の移動経路を同時に予測
●
歩行者同士の衝突を避けるためにSocial-Pooling layer (S-Pooling)を提案
- 予測対象周辺の他対象の位置と中間層出力を入力
- 次時刻のLSTMの内部状態に歩行者同士の空間的関係が保持
- 衝突を避ける経路予測が可能
Social LSTM [A. Alahi+, CVPR, 2016]
11
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
GT!
SF [73]!Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
Linear!
Social-LSTM!
GT!
SF [73]!
A. Alahi, et al., “Social LSTM: Human Trajectory Prediction in Crowded Spaces,” CVPR, 2016.
12. 対象間のインタラクションに加え周囲の環境情報を考慮
●
交差点や道沿い端などの障害物領域を避ける経路予測を実現
●
CVAEでエンコードすることで複数の経路を予測可能
Ranking & Refinement Moduleで予測経路にランキング付け
●
経路を反復的に改善することで予測精度向上を図る
DESIRE [N. Lee+, CVPR, 2017]
12
Input
KLD Loss
fc
+
soft
max
r1 rtr2
fc
Y
Sample Generation Module Ranking & Re nement Module
RNN Encoder1
GRU GRU GRU
RNN Encoder2
GRU GRU GRU
RNN Decoder1
GRU GRU GRU
RNN Decoder2
GRU GRU GRU
CVAE
fc
fc
z
X
Y
Regression
Scoring
fc fc fc
Y
Y
Recon
Loss
CNN
SCF SCF SCF
Feature
Pooling
(I)
Iterative Feedback
concat
mask
addition
Figure 2. The overview of proposed prediction framework DESIRE. First, DESIRE generates multiple plausible prediction samples ˆY via a
CVAE-based RNN encoder-decoder (Sample Generation Module). Then the following module assigns a reward to the prediction samples
at each time-step sequentially as IOC frameworks and learns displacements vector ∆ ˆY to regress the prediction hypotheses (Ranking
DESIRE-S Top1
DESIRE-S Top10
DESIRE-SI Top1
DESIRE-SI Top10
Linear
RNN ED
RNN ED-SI
X
Y
Method
Linear
RNN ED
RNN ED-SI
CVAE 1
CVAE 10%
DESIRE-S-IT
DESIRE-S-IT
DESIRE-S-IT
DESIRE-S-IT
DESIRE-SI-I
DESIRE-SI-I
DESIRE-SI-I
DESIRE-SI-I
Linear
RNN ED
RNN ED-SI
CVAE 1
CVAE 10%
DESIRE-S-IT
Linear
RNN ED
RNN ED-SI
X
Y
X
Y
(a) GT
Figure 6. KITTI resul
DESIRE-S Top1
DESIRE-S Top10
DESIRE-SI Top1
DESIRE-SI Top10
Linear
RNN ED
RNN ED-SI
X
Y
真値 予測値
インタラクションあり
Top1
Top10
インタラクションなし
Top1
Top10
N. Lee, et al., “DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents,” CVPR, 2017.
13. 高速道路上で隣接する自動車同士のインタラクションを考慮した予測手法
●
インタラクション情報に空間的意味合いを持たせるConvolution Social Poolingを提案
- LSTM Encoderで得た軌跡特徴量を固定サイズのSocial Tensorに格納
- CNNでインタラクションの特徴量を求める
- 予測車の特徴量と連結し,LSTM Decoderで経路を予測
Convolutional Social-Pooling [N. Deo+, CVPRW, 2018]
13
Figure 3. Proposed Model: The encoder is an LSTM with shared weights that learns vehicle dynamics based on track histories. The
convolutional social pooling layers learn the spatial interdependencies of of the tracks. Finally, the maneuver based decoder outputs a
multi-modal predictive distribution for the future motion of the vehicle being predicted
Convolutional Social Pooling for Vehicle Trajectory Prediction
Nachiket Deo Mohan M. Trivedi
University of California, San Diego
La Jolla, 92093
ndeo@ucsd.edu mtrivedi@ucsd.edu
Abstract
Forecasting the motion of surrounding vehicles is a crit-
ical ability for an autonomous vehicle deployed in complex
traffic. Motion of all vehicles in a scene is governed by the
traffic context, i.e., the motion and relative spatial config-
uration of neighboring vehicles. In this paper we propose
an LSTM encoder-decoder model that uses convolutional
social pooling as an improvement to social pooling lay-
ers for robustly learning interdependencies in vehicle mo-
tion. Additionally, our model outputs a multi-modal predic-
tive distribution over future trajectories based on maneuver
classes. We evaluate our model using the publicly available
NGSIM US-101 and I-80 datasets. Our results show im-
provement over the state of the art in terms of RMS values
of prediction error and negative log-likelihoods of true fu-
Figure 1. Imagine the blue vehicle is an autonomous vehicle in
the traffic scenario shown. Our proposed model allows it to make
multi-modal predictions of future motion of it’s surrounding ve-
hicles, along with prediction uncertainty shown here for the red
v1[cs.CV]15May2018
N. Deo, et al., “Convolutional Social Pooling for Vehicle Trajectory Prediction,” CVPRW, 2018.
14. 歩行者の視線情報を活用した経路予測手法
●
頭部を中心とした視野角内の他対象のみPooling処理
- 予測対象の頭部方向,他対象との距離値からPooling処理する対象を選択
●
軌跡,頭部方向,インタラクション情報をLSTMへ入力
- 視野角内にいる他対象との衝突を避ける経路予測を実現
- 視線情報を任意に変更することで,任意方向に向かった経路予測が可能
MX-LSTM [I. Hasan+, CVPR, 2018]
14
3. Our approach
In this section we present the MX-LSTM, capable of
jointly forecasting positions and head orientations of an in-
dividual thanks to the presence of two information streams:
Tracklets and vislets.
3.1. Tracklets and vislets
Given a subject i, a tracklet (see Fig. 1a) ) is formed
by consecutive (x, y) positions on the ground plane,
{x
(i)
t }t=1,...,T , x
(i)
t = (x, y) ∈ R2
, while a vislet is formed
by anchor points {a
(i)
t }t=1,...,T , with a
(i)
t = (ax, ay) ∈ R2
indicating a reference point at a fixed distance r from the
corresponding x
(i)
t , towards which the face is oriented1
. In
b)
d
a)
)(i
ta
)(i
tx
)(i
t
r
)(
1
i
tx
c)
1tx
ta
tx
t
t
t
(i) (i)
e
(x,i)
t = φ x
(i)
t , Wx
e
(a,i)
t = φ a
(i)
t , Wa
where the embedding function φ consists in a
jection through the embedding weigths Wx and
D-dimensional vector, multiplied by a RELU n
where D is the dimension of the hidden space.
3.2. VFOA social pooling
The social pooling introduced in [3] is an eff
to let the LSTM capture how people move in
scene avoiding collisions. This work considers a
interest area around the single pedestrian, in wh
den states of the the neighbors are considered
those which are behind the pedestrian. In our ca
prove this module using the vislet information
ing which individuals to consider, by building a
tum of attention (VFOA), that is a triangle origin
x
(i)
t , aligned with a
(i)
t , and with an aperture given
gle γ and a depth d; these parameters have been
cross-validation on the training partition of the T
dataset (see Sec. 5).
Our view-frustum social pooling is a No × N
sor, in which the space around the pedestrian is d
Figure 3. Qualitative results: a) MX-LSTM b) Ablation qualitative study on Individual MX-LSTM (better in color).
I. Hasan, et al., “MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses,” CVPR, 2018.
15. グループに関するインタラクションを考慮した経路予測手法
●
運動傾向が類似する歩行者同士をグループとみなす
●
予測対象が属するグループ以外の個人の情報をPooling
- 異なるグループとの衝突を避ける経路を予測
Group-LSTM [N. Bisagno+, ECCVW, 2018]
15
Group LSTM 7
Fig. 3. Representation of the Social hidden-state tensor Hi
t . The black dot represents the pedes-
trian of interest pedi. Other pedestrians pedj (∀j = i) are shown in different color codes, namely
green for pedestrians belonging to the same set, and red for pedestrians belonging to a different
Group LSTM 9
ing to the studies in interpersonal distances [15, 10], socially correlated people tend
to stay closer in their personal space and walk together in crowded environments as
compared to pacing with unknown pedestrians. Pooling only unrelated pedestrians will
focus more on macroscopic inter-group interactions rather than intra-group dynamics,
thus allowing the LSTM network to improve the trajectory prediction performance.
Collision avoidance influences the future motion of pedestrians in a similar manner if
two pedestrians are walking together as in a group.
In Tables 2, 3 and Fig. 4, we display some demos of predicted trajectories which
highlight how our Group-LSTM is able to predict pedestrian trajectories with better
precision, showing how the prediction is improved when we pool in the social tensor of
each pedestrian only pedestrians not belonging to his group.
In Table 2, we show how the prediction of two pedestrians walking together in the
crowd improves when they are not pooled in each other’s pooling layer. When the two
pedestrians are pooled together, the network applies on them the typical repulsion force
to avoid colliding with each other. Since they are in the same group, they allow the other
pedestrian to stay closer in they personal space.
In Fig. 4 we display the sequences of two groups walking toward each other. In
Table 3, we show how the prediction for the two groups is improved with respect to the
Social LSTM. While both prediction are not very accurate, our Group LSTM perform
better because it is able to forecast how pedestrian belonging to the same group will
stay together when navigating the environment.
Name Scene Our Group-LSTM Social-LSTM
ETH
Univ
Frame
2425
Table 2. ETH dataset: the prediction is improved when pooling in the social tensor of each pedes-
trian only pedestrians not belonging to his group. The green dots represent the ground truth tra-
jectories; the blue crosses represent the predicted paths.
5 Conclusion
In this work, we tackle the problem of pedestrian trajectory prediction in crowded
scenes. We propose a novel approach, which combines the coherent filtering algorithm
with the LSTM networks. The coherent filtering is used to identify pedestrians walking
together in a crowd, while the LSTM network is used to predict the future trajectories
10 Niccol´o Bisagno, Bo Zhang and Nicola Conci
(a) (b) (c) (d)
Fig. 4. Sequences taken from the UCY dataset. It displays an interaction example between two
groups, which will be further analyzed in Table 3.
Name Scene Our Group-LSTM Social-LSTM
UCY
Univ
Frame
1025
Table 3. We display how the prediction is improved for two groups walking in opposite direc-
tions. The green dots represent the ground truth trajectories, while the blue crosses represent the
predicted paths.
N. Bisagno, et al., “Group LSTM: Group Trajectory Prediction in Crowded Scenarios,” ECCVW, 2018.
16. GANを用いて複数経路を予測する手法
●
Generator:複数の予測経路をサンプリング
- LSTM Encoderの特徴量を用いて,Pooling Moduleでインタラクション情報を出力
- 各出力とノイズベクトルを連結し,LSTM Decoderで未来の複数の予測経路を出力
●
Discriminator:予測経路と実際の経路を判別
- 敵対的に学習させることで,実際の経路と騙す予測経路を生成することを期待
Social-GAN [A. Gupta+, CVPR, 2018]
16
Figure 2: System overview. Our model consists of three key components: Generator (G), Pooling Module, and Discriminator
(D). G takes as input past trajectories Xi and encodes the history of the person i as Ht
i . The pooling module takes as input
all Htobs
i and outputs a pooled vector Pi for each person. The decoder generates the future trajectory conditioned on Htobs
i
Figure 5: Comparison between our model w
avoidance scenarios: two people meeting (1
meeting at an angle (4). For each example
to pooling, SGAN-P predicts socially accepFigure 5: Comparison between our model without pooling (SGAN, top) and with pooli
予測分布
A. Gupta, et al., “Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks,” CVPR, 2018.
17. 歩行者や自動車等の異なる移動対象とのインタラクションを考慮した予測手法
●
インタラクションに加えシーンコンテキストを共同でモデル化
- 動的と静的の2つの物体との衝突を避ける経路を予測可能
●
Multi-Agent Tensor Fusion
- CNNでシーンに関するコンテキスト情報を抽出
- 移動対象毎の位置情報から空間的グリッドにLSTMの出力を格納
- コンテキスト情報と空間的グリッドをチャネル方向に連結し,CNNでFusion
- Fusionした特徴量からLSTM Decoderで経路を予測
Multi-Agent Tensor Fusion [T. Zhao+, CVPR, 2019]
17Figure 5: Ablative results on Stanford Drone dataset. From left to right are results from MATF Multi Agent Scene, MAT
入力値 真値 予測値
T. Zhao, et al., “Multi-Agent Tensor Fusion for Contextual Trajectory Prediction,” CVPR, 2019.
18. 2つのネットワークを結合した相互学習による経路予測手法
●
Forward Prediction Network:一般的な軌道予測手法 (観測 → 予測)
●
Backward Prediction Network:一般的な軌道予測手法の逆 (予測 → 観測)
相互制約に基づいてAdversarial Attackの概念に基づくモデルを構築
●
入力軌跡をiterativeに変更
●
モデルの出力と一致させることで,新しい概念(相互攻撃)と呼ぶモデルを開発
Reciprocal Network [S. Hao+, CVPR, 2020]
18
orks for Human Trajectory Prediction
iqun Zhao, and Zhihai He
ersity of Missouri
,hezhi}@mail.missouri.edu
ward
ward
orms
y dif-
prop-
earn- Figure 1. Illustration of our idea of reciprocal learning for human
3. The generator is constructed by a decoder LSTM. Sim-
ilar to the conditional GAN [24], a white noise vector Z
is sampled from a multivariate normal distribution. Then, a
merge layer is used in our proposed network which concate-
nates all encoded features mentioned above with the noise
vector Z. We take this as the input to the LSTM decoder
to generate the candidate future paths for each human. The
discriminator is built with an LSTM encoder which takes
the input as randomly chosen trajectory from either ground
truth or predicted trajectories and classifies them as “real”
or “fake”. Generally speaking, the discriminator classifies
the trajectories which are not accurate as “fake” and forces
the generator to generate more realistic and feasible trajec-
tories.
Within the framework of our reciprocal learning for hu-
man trajectory prediction, let Gθ
: X → Y and Gφ
: Y →
Figure 4. Illustration of the proposed attack method.
S. Hao, et al., “Reciprocal Learning Networks for Human Trajectory Prediction,” CVPR, 2020.
19. Predicted Endpoint Conditioned Network (PECNet)
●
予測最終地点 (エンドポイント)を重視した学習を行う経路予測手法
- でエンドポイントを予測し,Past Encodingの出力と連結 (concat encoding)
- 連結した特徴量からSocial Pooling内の各パラメタ特徴量を取得
- 歩行者 x 歩行者のSocial Maskで歩行者間のインタラクションを求める
- concat encodingとインタラクション情報から で経路を予測
PECNet [K. Mangalam+, ECCV, 2020]
19
6 K. Mangalam, H. Girase, S. Agarwal, K. Lee, E. Adeli, J. Malik, A. Gaidon
Dlatent
PECNet: Pedestrian Endpoint Conditioned Trajectory Prediction Network 13
lower prediction error than way-points in the middle! This in a nutshell, con-
firms the motivation of this work.
E↵ect of Number of samples (K): All the previous works use K = 20 sam-
ples (except DESIRE which uses K = 5) to evaluate the multi-modal predictions
for metrics ADE & FDE. Referring to Figure 5, we see the expected decreas-
ing trend in ADE & FDE with time as K increases. Further, we observe that
our proposed method achieves the same error as the previous works with much
smaller K. Previous state-of-the-art achieves 12.58 [39] ADE using K = 20 sam-
ples which is matched by PECNet at half the number of samples, K = 10. This
further lends support to our hypothesis that conditioning on the inferred way-
point significantly reduces the modeling complexity for multi-modal trajectory
forecasting, providing a better estimate of the ground truth.
Lastly, as K grows large (K ! 1) we observe that the FDE slowly gets closer
to 0 with more number of samples, as the ground truth Gc is eventually found.
However, the ADE error is still large (6.49) because of the errors in the rest of
the predicted trajectory. This is in accordance with the observed ADE (8.24) for
the oracle conditioned on the last observed point (i.e. 0 FDE error) in Fig. 4.
Design choice for VAE: We also evaluate our design choice of using the in-
ferred future way-points ˆGc for training subsequent modeules (social pooling &
prediction) instead of using the ground truth Gc. As mentioned in Section 3.2,
this is also a valid choice for training PECNet end to end. Empirically, we find
Fig. 6. Visualizing Multimodality: We show visualizations for some multi-modal
入力値 真値 予測値
K. Mangalam, et al., “It is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction,” ECCV, 2020.
Pfuture
22. 移動対象の行動による危険度をAttentionで推定し,行動の特徴に重み付け
●
Motion Encoder Moduleで対象毎の行動をエンコード
●
Location Encoder Moduleで対象毎の位置情報をエンコード
- 予測対象と全他対象の内積を求め,Softmaxで他対象の特徴に重み付け
●
2つのModuleを連結し,次時刻以降の経路を予測
CIDNN [Y. Xu+, CVPR, 2018]
22
N
th
1fc 2fc 3fc1
tS
1fc 2fc 3fci
tS
1fc 2fc 3fcN
tS
1
th
i
th
ÖÖ
,1i
ta
,i i
ta
,i N
ta
ÖÖ
1 1 1
1 2, ,..., tS S S
LSTMLSTM1
tz
1 2, ,...,i i i
tS S S
LSTMLSTMi
tz
1 2, ,...,N N N
tS S S
LSTMLSTMN
tz
ÖÖ
ÖÖ
Displacement Prediction Module
1
i
tSd +
i
tc
fc
#
ƒ
ƒ
ƒ
Location Encoder Module Motion Encoder ModuleCrowd
Interaction
ƒ #Inner
product
Scalar
multiplication
Sum
ÖÖ
ÖÖ
Figure 2. The architecture of crowd interaction deep neural network (CIDNN).
Successful Cases
Figure 3. Qualitative results: history traj
Successful Cases
Figure 3. Qualitative results: history trajectory (red), ground truth (blue
Successful Cases
Figure 3. Qualitative results: history trajectory (red), ground truth (blue), and predicted trajectories from ou
入力値 真値 予測値
Y. Xu, et al., “Encoding Crowd Interaction with Deep Neural Network for Pedestrian Trajectory Prediction,” CVPR, 2018.
23. 現時刻のインタラクション情報から予測対象の未来の予測経路を更新
●
States refinement module内の2つの機構で高精度な経路予測を実現
- 他対象との衝突を防ぐPedestrian-aware attention (PA)
- 他対象の動きから,予測対象自身が経路を選択するMotion gate (MG)
●
MGで衝突を起こしそうな対象の動きから経路を選択
●
PAで予測対象近隣の他対象に着目
SR-LSTM [P. Zhang+, CVPR, 2019]
23
5,36,39]. Vemula
from the hidden
gives an impor-
et al. [33] utilize
ght the important
pairwise velocity
who are in simi-
ms to selects mo-
strian during the
lly aware neigh-
d in previous ap-
ramework. This
lution Networks
LSTM
LSTM
LSTM
LSTMSR
t t+1
LSTM
LSTM
States refinement module
LSTM states
Input the
location to
LSTM
Ouput the
prediction
...
selects the features, where each row is related to a certain
dimension of hidden feature.
In Fig.6, the first column shows the trajectory patterns
captured by hidden features started from origin and ended
at the dots, which are extracted in similar way as Fig.2(a).
The motion gate for a feature considers pairwise input tra-
jectories with similar configurations. Some examples for
high response of the gate are shown in the other columns of
Fig.6. In these pairwise trajectory samples, the red and blue
ones are respectively the trajectories of pedestrian i and j,
and the time step we calculate the motion gate are shown
with dots (where the trajectory ends). These pairwise sam-
ples are extracted by searching from database with highest
activation for the motion gate neuron. High response of gate
means that the corresponding feature is selected.
Figure 6. Selected feature patterns by motion gate. Each row is
related to a hidden neuron (feature) of LSTM. Column 1: Activa-
tion trajectory pattern of the hidden feature. Column 2-6: Pairwise
trajectory examples (end with solid dots) having high activation to
3) Row 3: Thi
considers more
tion. 4) Row 4
hidden feature
attention on th
walk towards h
Pedestrian-
ples of the ped
LSTM in Fig.7
to the close ne
tention, 2) the
often largely fo
refinement ten
bors with grou
longer time ran
Figure 7. Illustr
magenta represe
the dashed circle
ment. Larger cir
represents the ta
ones are his/her
their walking dir
5. Conclusio
selects the features, where each row is related to a certain
dimension of hidden feature.
In Fig.6, the first column shows the trajectory patterns
captured by hidden features started from origin and ended
at the dots, which are extracted in similar way as Fig.2(a).
The motion gate for a feature considers pairwise input tra-
jectories with similar configurations. Some examples for
high response of the gate are shown in the other columns of
Fig.6. In these pairwise trajectory samples, the red and blue
ones are respectively the trajectories of pedestrian i and j,
and the time step we calculate the motion gate are shown
with dots (where the trajectory ends). These pairwise sam-
ples are extracted by searching from database with highest
activation for the motion gate neuron. High response of gate
means that the corresponding feature is selected.
3) Row 3: This case is similar to row 2. This gate element
considers more distant neighbor walking in opposite direc-
tion. 4) Row 4: The neighbor in blue is static, the selected
hidden feature shows that pedestrian i in red potentially pay
attention on this stationary neighbor in case he is about to
walk towards him/her.
Pedestrian-wise attention. We illustrate some exam-
ples of the pedestrian-wise attention expected by our SR-
LSTM in Fig.7. It shows that 1) dominant attention is paid
to the close neighbors, while the others also take slight at-
tention, 2) the attention given by the first refinement layer
often largely focuses on the close neighbors, and the second
refinement tends to strengthen the effect of farther neigh-
bors with group behavior or may influence the pedestrian in
longer time range.
Pedestrian-aware attention
Motion gate 予測対象
予測対象
P. Zhang, et al., “SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction,” CVPR, 2019.
24. 将来の経路と行動を同時に予測するモデルを提案
●
Person Behavior Module:歩行者の外見情報と骨格情報をエンコード
●
Person Interaction Module:周辺の静的環境情報と自動車等の物体情報をエンコード
●
Visual Feature Tensor Q:上記2つの特徴と過去の軌跡情報をエンコード
●
Trajectory Generator:将来の経路を予測
●
Activity Prediction:予測最終時刻の行動を予測
Next [J. Liang+, CVPR, 2019]
24
Figure 2. Overview of our model. Given a sequence of frames containing the person for prediction, our model utilizes person behavior
module and person interaction module to encode rich visual semantics into a feature tensor. We propose novel person interaction module
that takes into account both person-scene and person-object relations for joint activities and locations prediction.
3. Approach RoIAlign
CNN
Figure 6. (Better viewed in color.) Qualitative comparison between our method and the baselines. Yellow path is the observable trajectory
and Green path is the ground truth trajectory during the prediction period. Predictions are shown as Blue heatmaps. Our model also predicts
the future activity, which is shown in the text and with the person pose template.
Figure 7. (Better viewed in color.) Qualitative analysis of o
Method ETH HOTEL UN
Model
Linear 1.33 / 2.94 0.39 / 0.72 0.82
LSTM 1.09 / 2.41 0.86 / 1.91 0.61J. Liang, et al., “Peeking into the Future: Predicting Future Person Activities and Locations in Videos,” CVPR, 2019.
25. 歩行者同士のインタラクションに加え,静的環境情報を考慮した予測手法
●
Physical Attention:静的環境に関するAttentionを推定
●
Social Attention:動的物体に関するAttentionを推定
各AttentionとLSTM Encoderの出力から将来の経路を予測
SoPhie [A. Sadeghian+, CVPR, 2019]
25
Physical Attention:
!""#$
Social Attention:
!""%&
Generator
Attention Module for i-th person
GAN Module
concat.
Discriminator
LSTM
LSTM
LSTM
LSTM
LSTM
LSTM
concat.
concat.
concat.
z
z
z
decoder
1st agent
i-th agent
N-th agent
Attention Module for 1st person
Attention Module for n-th person
CNN
Feature Extractor Module
i-th agent
calc. relative
relative
relative
relativeLSTM
LSTM
LSTM
encoder
(a) (b) (c)
N-th agent
1st agent
Figure 2. An overview of SoPhie architecture. Sophie consists of three key modules including: (a) A feature extractor module, (b) An
attention module, and (c) An LSTM based GAN module.
3.3. Feature extractors where πj is the index of the other agents sorted according to
their distances to the target agent i. In this framework, each
Nexus 6 Li
Figure 3. Using the generator to sample trajectories and the discrimin
maps for SDD scenes. Maps are presented in red, and generated only
Ground Truth Social LSTM Social GAN Sophie (Ours)
Figure 4. Comparison of Sophie’s predictions against the ground
truth trajectories and two baselines. Each pedestrian is displayed
with a different color, where dashed lines are observed trajecto-A. Sadeghian, et al., “SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints,” CVPR, 2019.
26. インタラクションを時間方向へ伝搬した予測手法
インタラクションを考慮するためにGraph Attention Network (GAT)を適用
●
GAT:グラフ構造を取り入れたAttentionに基づくGraph Convolutional Networks
- シーン全体にいる他対象の関係の重要度をAttention機構で学習
●
GATで求めた特徴を時間方向に伝播することで時空間のインタラクションを考慮
- 衝突の可能性がある対象の情報を過去の経路から導出可能
STGAT [Y. Huang+, ICCV, 2019]
26
GAT GAT GAT GAT
c
c
c
Encoder State Decoder
GAT Graph Attention Network
Concat Noisec
· · ·<latexit sha1_base64="RyHhXBLV/0cOSbkT6YVaYO8lbL8=">AAAB7XicbVBNS8NAEJ34WetX1aOXYBE8lUQFPXgoePFYwX5AG8pms2nXbnbD7kQoof/BiwdFvPp/vPlv3LY5aOuDgcd7M8zMC1PBDXret7Oyura+sVnaKm/v7O7tVw4OW0ZlmrImVULpTkgME1yyJnIUrJNqRpJQsHY4up367SemDVfyAccpCxIykDzmlKCVWj0aKTT9StWreTO4y8QvSBUKNPqVr16kaJYwiVQQY7q+l2KQE42cCjYp9zLDUkJHZMC6lkqSMBPks2sn7qlVIjdW2pZEd6b+nshJYsw4CW1nQnBoFr2p+J/XzTC+DnIu0wyZpPNFcSZcVO70dTfimlEUY0sI1dze6tIh0YSiDahsQ/AXX14mrfOaf1Hz7i+r9ZsijhIcwwmcgQ9XUIc7aEATKDzCM7zCm6OcF+fd+Zi3rjjFzBH8gfP5A60zjys=</latexit>
tobs<latexit sha1_base64="vcpPldxy0fXoWuPkuol+dvCEp1Q=">AAAB7nicbVDLSgNBEOyNrxhfUY9eBoPgKeyqYI4BLx4jmAckS5idTJIhszPLTK8QlnyEFw+KePV7vPk3TpI9aGJBQ1HVTXdXlEhh0fe/vcLG5tb2TnG3tLd/cHhUPj5pWZ0axptMS206EbVcCsWbKFDyTmI4jSPJ29Hkbu63n7ixQqtHnCY8jOlIiaFgFJ3Uxn6mIzvrlyt+1V+ArJMgJxXI0eiXv3oDzdKYK2SSWtsN/ATDjBoUTPJZqZdanlA2oSPedVTRmNswW5w7IxdOGZChNq4UkoX6eyKjsbXTOHKdMcWxXfXm4n9eN8VhLcyESlLkii0XDVNJUJP572QgDGcop45QZoS7lbAxNZShS6jkQghWX14nratqcF31H24q9VoeRxHO4BwuIYBbqMM9NKAJDCbwDK/w5iXei/fufSxbC14+cwp/4H3+ALeBj8c=</latexit>
t2<latexit sha1_base64="7ItLwn8Q8RXHU3NW/LT2SA7MEc4=">AAAB7HicbVBNS8NAEJ34WetX1aOXxSJ4KkkV7LHgxWMF0xbaUDbbTbt0swm7E6GE/gYvHhTx6g/y5r9x2+agrQ8GHu/NMDMvTKUw6Lrfzsbm1vbObmmvvH9weHRcOTltmyTTjPsskYnuhtRwKRT3UaDk3VRzGoeSd8LJ3dzvPHFtRKIecZryIKYjJSLBKFrJx0Fenw0qVbfmLkDWiVeQKhRoDSpf/WHCspgrZJIa0/PcFIOcahRM8lm5nxmeUjahI96zVNGYmyBfHDsjl1YZkijRthSShfp7IqexMdM4tJ0xxbFZ9ebif14vw6gR5EKlGXLFlouiTBJMyPxzMhSaM5RTSyjTwt5K2JhqytDmU7YheKsvr5N2veZd19yHm2qzUcRRgnO4gCvw4BaacA8t8IGBgGd4hTdHOS/Ou/OxbN1wipkz+APn8wfJU46h</latexit>
t1<latexit sha1_base64="Bdkp2HUnpwjOv5mbz6SwzTMJ8ag=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lUsMeCF48VTFtoQ9lsN+3SzSbsToQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MJXCoOt+O6WNza3tnfJuZW//4PCoenzSNkmmGfdZIhPdDanhUijuo0DJu6nmNA4l74STu7nfeeLaiEQ94jTlQUxHSkSCUbSSj4Pcmw2qNbfuLkDWiVeQGhRoDapf/WHCspgrZJIa0/PcFIOcahRM8lmlnxmeUjahI96zVNGYmyBfHDsjF1YZkijRthSShfp7IqexMdM4tJ0xxbFZ9ebif14vw6gR5EKlGXLFlouiTBJMyPxzMhSaM5RTSyjTwt5K2JhqytDmU7EheKsvr5P2Vd27rrsPN7Vmo4ijDGdwDpfgwS004R5a4AMDAc/wCm+Ocl6cd+dj2VpyiplT+APn8wfHzo6g</latexit>
t3<latexit sha1_base64="OcT9ss7O545agx6P8OIS9udeh5k=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lUsMeCF48VTFtoQ9lsN+3SzSbsToQS+hu8eFDEqz/Im//GbZuDtj4YeLw3w8y8MJXCoOt+O6WNza3tnfJuZW//4PCoenzSNkmmGfdZIhPdDanhUijuo0DJu6nmNA4l74STu7nfeeLaiEQ94jTlQUxHSkSCUbSSj4P8ejao1ty6uwBZJ15BalCgNah+9YcJy2KukElqTM9zUwxyqlEwyWeVfmZ4StmEjnjPUkVjboJ8ceyMXFhlSKJE21JIFurviZzGxkzj0HbGFMdm1ZuL/3m9DKNGkAuVZsgVWy6KMkkwIfPPyVBozlBOLaFMC3srYWOqKUObT8WG4K2+vE7aV3Xvuu4+3NSajSKOMpzBOVyCB7fQhHtogQ8MBDzDK7w5ynlx3p2PZWvJKWZO4Q+czx/K2I6i</latexit>
z
M-LSTM G-LSTM
Figure 2. The architecture of our proposed STGAT model. The framework is based on seq2seq model and consists of 3 parts: Encod
Intermediate State and Decoder. The Encoder module includes three components: 2 types of LSTMs and GAT. The Intermediate St
encapsulates the spatial and temporal information of all observed trajectories. The Decoder module generates the future trajectories bas
edestrians in a scene are considered as nodes on the
aph at every time-step. The edges on the graph repre-
st of human-human interactions.
~h1<latexit sha1_base64="16Yxx8+YpYlp2tGJX9qHHqgdbbY=">AAAB8nicbVBNS8NAEJ3Ur1q/qh69BIvgqSQq6LHoxWMF+wFtKJvtpl262Q27k0IJ+RlePCji1V/jzX/jts1Bqw8GHu/NMDMvTAQ36HlfTmltfWNzq7xd2dnd2z+oHh61jUo1ZS2qhNLdkBgmuGQt5ChYN9GMxKFgnXByN/c7U6YNV/IRZwkLYjKSPOKUoJV6/Smj2TgfZH4+qNa8ureA+5f4BalBgeag+tkfKprGTCIVxJie7yUYZEQjp4LllX5qWELohIxYz1JJYmaCbHFy7p5ZZehGStuS6C7UnxMZiY2ZxaHtjAmOzao3F//zeilGN0HGZZIik3S5KEqFi8qd/+8OuWYUxcwSQjW3t7p0TDShaFOq2BD81Zf/kvZF3b+sew9XtcZtEUcZTuAUzsGHa2jAPTShBRQUPMELvDroPDtvzvuyteQUM8fwC87HN46CkWw=</latexit>
~h5<latexit sha1_base64="R1g6gAHeZA/axOfzhGwObt3Ay0g=">AAAB8nicbVDLSsNAFJ3UV62vqks3g0VwVRIf6LLoxmUF+4A0lMn0ph06mQkzk0IJ+Qw3LhRx69e482+ctllo64ELh3Pu5d57woQzbVz32ymtrW9sbpW3Kzu7e/sH1cOjtpapotCikkvVDYkGzgS0DDMcuokCEoccOuH4fuZ3JqA0k+LJTBMIYjIULGKUGCv5vQnQbJT3s+u8X625dXcOvEq8gtRQgWa/+tUbSJrGIAzlRGvfcxMTZEQZRjnklV6qISF0TIbgWypIDDrI5ifn+MwqAxxJZUsYPFd/T2Qk1noah7YzJmakl72Z+J/npya6DTImktSAoItFUcqxkXj2Px4wBdTwqSWEKmZvxXREFKHGplSxIXjLL6+S9kXdu6y7j1e1xl0RRxmdoFN0jjx0gxroATVRC1Ek0TN6RW+OcV6cd+dj0Vpyiplj9AfO5w+UlpFw</latexit>
~h4<latexit sha1_base64="zHvzoSStxfsE4+HkOUWqlEWKApg=">AAAB8nicbVBNS8NAEN3Ur1q/qh69LBbBU0m0oMeiF48V7AekoWy2k3bpZjfsbgol5Gd48aCIV3+NN/+N2zYHbX0w8Hhvhpl5YcKZNq777ZQ2Nre2d8q7lb39g8Oj6vFJR8tUUWhTyaXqhUQDZwLahhkOvUQBiUMO3XByP/e7U1CaSfFkZgkEMRkJFjFKjJX8/hRoNs4HWSMfVGtu3V0ArxOvIDVUoDWofvWHkqYxCEM50dr33MQEGVGGUQ55pZ9qSAidkBH4lgoSgw6yxck5vrDKEEdS2RIGL9TfExmJtZ7Foe2MiRnrVW8u/uf5qYlug4yJJDUg6HJRlHJsJJ7/j4dMATV8ZgmhitlbMR0TRaixKVVsCN7qy+ukc1X3ruvuY6PWvCviKKMzdI4ukYduUBM9oBZqI4okekav6M0xzovz7nwsW0tOMXOK/sD5/AGTEZFv</latexit>
~h3<latexit sha1_base64="4MzhxHH1VdXzxV7PaR8PPHgLBTc=">AAAB8nicbVBNS8NAEN3Ur1q/qh69LBbBU0msoMeiF48V7AekoWy2m3bpZjfsTgol5Gd48aCIV3+NN/+N2zYHbX0w8Hhvhpl5YSK4Adf9dkobm1vbO+Xdyt7+weFR9fikY1SqKWtTJZTuhcQwwSVrAwfBeolmJA4F64aT+7nfnTJtuJJPMEtYEJOR5BGnBKzk96eMZuN8kDXyQbXm1t0F8DrxClJDBVqD6ld/qGgaMwlUEGN8z00gyIgGTgXLK/3UsITQCRkx31JJYmaCbHFyji+sMsSR0rYk4IX6eyIjsTGzOLSdMYGxWfXm4n+en0J0G2RcJikwSZeLolRgUHj+Px5yzSiImSWEam5vxXRMNKFgU6rYELzVl9dJ56ruNeru43WteVfEUUZn6BxdIg/doCZ6QC3URhQp9Ixe0ZsDzovz7nwsW0tOMXOK/sD5/AGRjJFu</latexit>
~h2<latexit sha1_base64="hAcukdL3sj/GIPn2AtYuEsqEXSA=">AAAB8nicbVBNS8NAEN3Ur1q/qh69LBbBU0mqoMeiF48V7AekoWy2m3bpZjfsTgol5Gd48aCIV3+NN/+N2zYHbX0w8Hhvhpl5YSK4Adf9dkobm1vbO+Xdyt7+weFR9fikY1SqKWtTJZTuhcQwwSVrAwfBeolmJA4F64aT+7nfnTJtuJJPMEtYEJOR5BGnBKzk96eMZuN8kDXyQbXm1t0F8DrxClJDBVqD6ld/qGgaMwlUEGN8z00gyIgGTgXLK/3UsITQCRkx31JJYmaCbHFyji+sMsSR0rYk4IX6eyIjsTGzOLSdMYGxWfXm4n+en0J0G2RcJikwSZeLolRgUHj+Px5yzSiImSWEam5vxXRMNKFgU6rYELzVl9dJp1H3ruru43WteVfEUUZn6BxdIg/doCZ6QC3URhQp9Ixe0ZsDzovz7nwsW0tOMXOK/sD5/AGQB5Ft</latexit>
~h6<latexit sha1_base64="Kuq84mWaskTChJNeNnyTi5aZ6oc=">AAAB8nicbVBNS8NAEN3Ur1q/qh69LBbBU0lU1GPRi8cK9gPSUDbbSbt0sxt2N4US8jO8eFDEq7/Gm//GbZuDtj4YeLw3w8y8MOFMG9f9dkpr6xubW+Xtys7u3v5B9fCorWWqKLSo5FJ1Q6KBMwEtwwyHbqKAxCGHTji+n/mdCSjNpHgy0wSCmAwFixglxkp+bwI0G+X97DrvV2tu3Z0DrxKvIDVUoNmvfvUGkqYxCEM50dr33MQEGVGGUQ55pZdqSAgdkyH4lgoSgw6y+ck5PrPKAEdS2RIGz9XfExmJtZ7Goe2MiRnpZW8m/uf5qYlug4yJJDUg6GJRlHJsJJ79jwdMATV8agmhitlbMR0RRaixKVVsCN7yy6ukfVH3Luvu41WtcVfEUUYn6BSdIw/doAZ6QE3UQhRJ9Ixe0ZtjnBfn3flYtJacYuYY/YHz+QOWG5Fx</latexit>
~h1<latexit sha1_base64="KoV/fuxRJ+UPzkEixIjJIx41qvU=">AAAB+HicbVBNS8NAEJ34WetHox69LBbRU0lU0GPRi8cK9gPaGDbbTbt0swm7m0IN+SVePCji1Z/izX/jts1BWx8MPN6bYWZekHCmtON8Wyura+sbm6Wt8vbO7l7F3j9oqTiVhDZJzGPZCbCinAna1Exz2kkkxVHAaTsY3U799phKxWLxoCcJ9SI8ECxkBGsj+XalN6YkG+aP2WnuZ27u21Wn5syAlolbkCoUaPj2V68fkzSiQhOOleq6TqK9DEvNCKd5uZcqmmAywgPaNVTgiCovmx2eoxOj9FEYS1NCo5n6eyLDkVKTKDCdEdZDtehNxf+8bqrDay9jIkk1FWS+KEw50jGapoD6TFKi+cQQTCQztyIyxBITbbIqmxDcxZeXSeu85l7UnPvLav2miKMER3AMZ+DCFdThDhrQBAIpPMMrvFlP1ov1bn3MW1esYuYQ/sD6/AHv15NC</latexit>
~12<latexit sha1_base64="7wH2WVdWISdwYnqsMTVyR5rAKM0=">AAAB+nicbVBNS8NAEJ34WetXqkcvi0XwVJIq6LHoxWMF+wFtCJvtpl262YTdTaXE/BQvHhTx6i/x5r9x2+agrQ8GHu/NMDMvSDhT2nG+rbX1jc2t7dJOeXdv/+DQrhy1VZxKQlsk5rHsBlhRzgRtaaY57SaS4ijgtBOMb2d+Z0KlYrF40NOEehEeChYygrWRfLvSn1CS9TFPRjj3M7ee+3bVqTlzoFXiFqQKBZq+/dUfxCSNqNCEY6V6rpNoL8NSM8JpXu6niiaYjPGQ9gwVOKLKy+an5+jMKAMUxtKU0Giu/p7IcKTUNApMZ4T1SC17M/E/r5fq8NrLmEhSTQVZLApTjnSMZjmgAZOUaD41BBPJzK2IjLDERJu0yiYEd/nlVdKu19yLmnN/WW3cFHGU4ARO4RxcuIIG3EETWkDgEZ7hFd6sJ+vFerc+Fq1rVjFzDH9gff4AT7aUBQ==</latexit>
~13<latexit sha1_base64="Oj5OOfl5UD0Mrh/Gd9yVwPeeGOY=">AAAB+nicbVBNS8NAEJ3Ur1q/Uj16WSyCp5KooMeiF48V7Ae0IWy2m3bpZhN2N5US81O8eFDEq7/Em//GbZuDtj4YeLw3w8y8IOFMacf5tkpr6xubW+Xtys7u3v6BXT1sqziVhLZIzGPZDbCinAna0kxz2k0kxVHAaScY3878zoRKxWLxoKcJ9SI8FCxkBGsj+Xa1P6Ek62OejHDuZ+5F7ts1p+7MgVaJW5AaFGj69ld/EJM0okITjpXquU6ivQxLzQineaWfKppgMsZD2jNU4IgqL5ufnqNTowxQGEtTQqO5+nsiw5FS0ygwnRHWI7XszcT/vF6qw2svYyJJNRVksShMOdIxmuWABkxSovnUEEwkM7ciMsISE23SqpgQ3OWXV0n7vO5e1J37y1rjpoijDMdwAmfgwhU04A6a0AICj/AMr/BmPVkv1rv1sWgtWcXMEfyB9fkDUTuUBg==</latexit>
~11<latexit sha1_base64="Z1DxO/2cTeAPqRO0wzlGCoK0+XY=">AAAB+nicbVBNS8NAEJ3Ur1q/Uj16WSyCp5KooMeiF48V7Ae0IWy2m3bpZhN2N5US81O8eFDEq7/Em//GbZuDtj4YeLw3w8y8IOFMacf5tkpr6xubW+Xtys7u3v6BXT1sqziVhLZIzGPZDbCinAna0kxz2k0kxVHAaScY3878zoRKxWLxoKcJ9SI8FCxkBGsj+Xa1P6Ek62OejHDuZ66b+3bNqTtzoFXiFqQGBZq+/dUfxCSNqNCEY6V6rpNoL8NSM8JpXumniiaYjPGQ9gwVOKLKy+an5+jUKAMUxtKU0Giu/p7IcKTUNApMZ4T1SC17M/E/r5fq8NrLmEhSTQVZLApTjnSMZjmgAZOUaD41BBPJzK2IjLDERJu0KiYEd/nlVdI+r7sXdef+sta4KeIowzGcwBm4cAUNuIMmtIDAIzzDK7xZT9aL9W59LFpLVjFzBH9gff4ATjGUBA==</latexit>
~14<latexit sha1_base64="bUiB7GM/EueyHNLIaRxhSyx8/6A=">AAAB+nicbVBNS8NAEN34WetXqkcvi0XwVBIt6LHoxWMF+wFtCJPtpl262YTdTaXE/BQvHhTx6i/x5r9x2+agrQ8GHu/NMDMvSDhT2nG+rbX1jc2t7dJOeXdv/+DQrhy1VZxKQlsk5rHsBqAoZ4K2NNOcdhNJIQo47QTj25nfmVCpWCwe9DShXgRDwUJGQBvJtyv9CSVZH3gygtzP3Hru21Wn5syBV4lbkCoq0PTtr/4gJmlEhSYclOq5TqK9DKRmhNO83E8VTYCMYUh7hgqIqPKy+ek5PjPKAIexNCU0nqu/JzKIlJpGgemMQI/UsjcT//N6qQ6vvYyJJNVUkMWiMOVYx3iWAx4wSYnmU0OASGZuxWQEEog2aZVNCO7yy6ukfVFzL2vOfb3auCniKKETdIrOkYuuUAPdoSZqIYIe0TN6RW/Wk/VivVsfi9Y1q5g5Rn9gff4AUsCUBw==</latexit>
~15<latexit sha1_base64="cC09I5yAhT8haElJRiWSguUZ4i0=">AAAB+nicbVDLSsNAFJ34rPWV6tLNYBFclcQHuiy6cVnBPqAJYTK9bYdOJmFmUikxn+LGhSJu/RJ3/o3TNgttPXDhcM693HtPmHCmtON8Wyura+sbm6Wt8vbO7t6+XTloqTiVFJo05rHshEQBZwKammkOnUQCiUIO7XB0O/XbY5CKxeJBTxLwIzIQrM8o0UYK7Io3Bpp5hCdDkgeZe5kHdtWpOTPgZeIWpIoKNAL7y+vFNI1AaMqJUl3XSbSfEakZ5ZCXvVRBQuiIDKBrqCARKD+bnZ7jE6P0cD+WpoTGM/X3REYipSZRaDojoodq0ZuK/3ndVPev/YyJJNUg6HxRP+VYx3iaA+4xCVTziSGESmZuxXRIJKHapFU2IbiLLy+T1lnNPa859xfV+k0RRwkdoWN0ilx0heroDjVQE1H0iJ7RK3qznqwX6936mLeuWMXMIfoD6/MHVEWUCA==</latexit>
~16<latexit sha1_base64="Th2k0L1quCqnOCL5jErebK97YEU=">AAAB+nicbVBNS8NAEN34WetXqkcvi0XwVBIV9Vj04rGC/YAmhM122i7dbMLuplJifooXD4p49Zd489+4bXPQ1gcDj/dmmJkXJpwp7Tjf1srq2vrGZmmrvL2zu7dvVw5aKk4lhSaNeSw7IVHAmYCmZppDJ5FAopBDOxzdTv32GKRisXjQkwT8iAwE6zNKtJECu+KNgWYe4cmQ5EHmXuaBXXVqzgx4mbgFqaICjcD+8noxTSMQmnKiVNd1Eu1nRGpGOeRlL1WQEDoiA+gaKkgEys9mp+f4xCg93I+lKaHxTP09kZFIqUkUms6I6KFa9Kbif1431f1rP2MiSTUIOl/UTznWMZ7mgHtMAtV8YgihkplbMR0SSag2aZVNCO7iy8ukdVZzz2vO/UW1flPEUUJH6BidIhddoTq6Qw3URBQ9omf0it6sJ+vFerc+5q0rVjFziP7A+vwBVcqUCQ==</latexit>
n illustration of graph attention layer. It allows a node
fferent importance to different nodes within a neigh-
propose to use another LSTM to model the temp
lations between interactions explicitly. We term t
as G-LSTM:
gt
i = G-LSTM(gt 1
i , ˆmt
i;Wg)
where ˆmt
i is from Eq. 5. Wg is the G-LSTM we
shared among all the sequences.
In Encoder component, two LSTMs (M-L
LSTM) are used to model the motion pattern of e
trian, and the temporal correlations of interaction
tively. We combine these two parts to accomplish
of spatial and temporal information. At time-step
are two hidden variables (m
Tobs
i , g
Tobs
i ) from two
each pedestrian. In our implementation, these two
予測対象
他対象
他対象
他対象
他対象
他対象
Y. Huang, et al., “STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction,” ICCV, 2019.
27. 複数対象を動的なグラフ構造で効率的にモデル化
●
NHE:観測時刻のNode特徴をLSTMへ入力
●
NFE:学習時にNodeの未来の真の軌跡をエンコードするためにBiLSTMを適用
●
EE:特定範囲内の全対象からAttentionを求める
- 重要度の高いEdge情報を取得
- 時刻毎にEdge情報は変動
●
各特徴からDecoderで経路を予測
- 内部のCVAEでマルチモーダルな経路を予測
- Gaussian Mixture Modelで予測経路を洗練
環境情報を追加したTrajectron++ [T. Salzmann+, ECCV, 2020]が提案
Trajectron [B. Ivanovic+, CVPR, 2019]
27
Overall, we chose to make our model part of the “graph
as architecture” methods, as a result of their stateful graph
representation (leading to efficient iterative predictions on-
line) and modularity (enabling model reuse and extensive
parameter sharing).
3. Problem Formulation
In this work, we are interested in jointly reasoning and
generating a distribution of future trajectories for each agent
in a scene simultaneously. We assume that each scene is
preprocessed to track and classify agents as well as obtain
their spatial coordinates at each timestep. As a result, each
agent i has a classification type Ci (e.g. “Pedestrian”). Let
Xt
i = (xt
i, yt
i ) represent the position of the ith
agent at time
t and let Xt
1,...,N represent the same quantity for all agents
in a scene. Further, let X
(t1:t2)
i = (Xt1
i , Xt1+1
i , . . . , Xt2
i )
denote a sequence of values for time steps t 2 [t1, t2].
As in previous works [1, 16, 49], we take as input the
previous trajectories of all agents in a scene X
(1:tobs)
1,...,N and
aim to produce predictions bX
(tobs+1:tobs+T )
1,...,N that match the
true future trajectories X
(tobs+1:tobs+T )
1,...,N . Note that we have
not assumed N to be static, i.e. we can have N = f(t).
!"/$
!%/&
!'/(!"-!% !'-!%
Legend
Modeled Node
!"/$ Node $ is of type !"
!"-!% Edge is of type !"-!%
Edge being created
Normal Edge!"/)
!"-!%
Attention
!(#$%)
!(#$')
!(#)
!(#(')
!(#(%)
!(#())
F
C
F
C
EE
NHE
NFE
Encoder
ℎ+
ℎ,
-(.|0)
1(.|0, 3)
F
C
.
!(#)
., ℎ+
4!(#(')
! #('
., ℎ+
4!(#(%)
! #(%
., ℎ+
4!(#(')
GMM GMM GMM
4!(#(%)
4!(#())
Decoder 5)
5)
5)
6(#$%)
+
8(#$%)
6(#$')
+
8(#$')
6(#)
+
8(#)
5'-5)
9(#$%)
9(#$')
9(#)
5%-5)
Legend
LSTM Cell
Modulating Function
FC Fully-Connected Layer
Projection to a GMM
Concatenation
Randomly sampled
Train time only
Predict time only
Train and Predict
GMM
MMM
M
M MM
+
Figure 2. Top: An example graph with four nodes. a is our mod-T. Salzmann, et al., “Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data,” ECCV, 2020.
B. Ivanovic, et al., “The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs,” ICCV, 2019.
28. 単純にノイズベクトルを付与すると,高い分散を持つ経路を予測してしまう
●
既存研究は真にマルチモーダルな分布を学習できていない
予測経路とノイズベクトル間の潜在的表現を学習
●
ノイズベクトルから生成した予測経路をLSTM Encoderへ入力
●
元のノイズベクトルと類似するようにマッピング
●
真にマルチモーダルな経路を生成可能
Social-BiGAT [V. Kosaraju+, NeurIPS, 2019]
28Figure 2: Architecture for the proposal Social-BiGAT model. The model consists of a single generator, two
Figure 4: Generated trajectories visualized for the S-GAN-P, Sophie, and Social-BiGAT models across four
main scenes. Observed trajectories are shown as solid lines, ground truth future movements are shown as dashed
lines, and generated samples are shown as contour maps. Different colors correspond to different pedestrians.V. Kosaraju, et al., “Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks,” NeurIPS, 2019.
29. Spatial-Temporal Graphを用いてモデル化
●
Graph Convolution Network (GCN)でインタラクションに関する特徴抽出
- 隣接行列からインタラクション情報を求める
●
GCNで得た特徴からTemporal Convolutional Network (TCN)で予測分布を出力
- LSTMは予測経路を逐次出力するが,TCNは予測経路を並列に出力
- 推論速度を大幅に改善
Social-STGCNN [A. Mohamed+, CVPR, 2020]
29
Figure 2. The Social-STGCNN Model. Given T frames, we construct the spatio-temporal graph representing G = (V, A). Then G is
forwarded through the Spatio-Temporal Graph Convolution Neural Networks (ST-GCNNs) creating a spatio-temporal embedding. Following
this, the TXP-CNNs predicts future trajectories. P is the dimension of pedestrian position, N is the number of pedestrians, T is the number
ˆA. Mohamed, et al., “Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction,” CVPR, 2020.
33. CNNを用いた予測手法
●
過去の軌跡情報をエンコードし,スパースなボクセルに格納
●
ConvolutionとMax-Poolingを複数回行い,Deconvolutionで予測経路を出力
●
Location bias mapにより特定シーンの物体情報と潜在的特徴表現で要素積をとる
- 特定シーンによって変化する歩行者の振る舞いを考慮
Behavior-CNN [S. Yi+, ECCV, 2016]
33
output of CNN, as they are of variable lengths and observed in different periods.
3 Pedestrian Behavior Modeling and Prediction
The overall framework is shown in Fig. 2. The input to our system is pedestrian
walking paths in previous frames (colored curves in Fig. 2(a)). They could be
obtained by simple trackers such as KLT [41]. They are then encoded into a
displacement volume (Fig. 2(b)) with the proposed walking behavior encoding
scheme. Behavior-CNN in Fig. 2(c) takes the encoded displacement volume as
Fig. 2. System flowchart. (a) Pedestrian walking paths in previous frames. Three exam-
ples are shown in different colors. Rectangles indicate current locations of pedestrians.
(b) The displacement volume encoded from pedestrians’ past walking paths in (a).
(c) Behavior-CNN. (d) The predicted displacement volume by Behavior-CNN. (e) Pre-
dicted future pedestrian walking paths decoded from (d).
Three bottom convolution layers, conv1, conv2, and conv3, are to be con-
volved with input data of size X × Y × 2M. conv1 contains 64 filters of size
3 × 3 × 2M, while both conv2 and conv3 contain 64 filters of size 3 × 3 × 64.
Zeros are padded to each convolution input in order to guarantee feature maps
of these layers be of the same spatial size with the input. The three bottom
convolution layers are followed by max pooling layers max-pool with stride 2.
The output size of max-pool is X/2 × Y/2 × 64. In this way, the receptive field
of the network can be doubled. Large receptive field is necessary for the task
of pedestrian walking behavior modeling because each individual’s behavior are
significantly influenced by his/her neighbors. A learnable location bias map of
size X/2×Y/2 is channel-wisely added to each of the pooled feature maps. Every
spatial location has one independent bias value shared across channels. With the
location bias map, location information of the scene can be automatically learned
by the proposed Behavior-CNN. As for the three top convolution layers, conv4
and conv5 contain 64 filters of size 3 × 3 × 64, while conv6 contains 2M∗
filters
of size 3 × 3 × 64 to output the predicted displacement volume. Zeros are also
S. Yi, et al., “Pedestrian Behavior Understanding and Prediction with Deep Neural Networks,” ECCV, 2016.
34. 1人称視点における対面の歩行者のための位置予測
●
1人称視点特有の手掛かりを位置予測に利用
1. 対面の歩行者の位置に影響するエゴモーション
2. 対面の歩行者のスケール
3. 対面の歩行者の姿勢
●
上記3つの情報を用いたマルチストリームモデルで将来の位置予測
Future localization in first-person videos [T. Yagi+, CVPR, 2018]
34
Figure 2. Future Person Localization in First-Person Videos. Given a) Tprev-frames observations as input, we b) predict future locations
of a target person in the subsequent Tfuture frames. Our approach makes use of c-1) locations and c-2) scales of target persons, d) ego-
motion of camera wearers and e) poses of the target persons as a salient cue for the prediction.
Channel-wise
Concatenation
Input
Output
Location-Scale Stream Ego-Motion Stream Pose Stream
Figure 3. Proposed Network Architecture. Blue blocks corre-
tain direction at a constant speed, our best guess based on
only previous locations would be to expect them to keep go-
ing in that direction in subsequent future frames too. How-
ever, visual distances in first-person videos can correspond
to different physical distances depending on where people
are observed in the frame.
In order to take into account this perspective effect, we
propose to learn both locations and scales of target peo-
ple jointly. Given a simple assumption that heights of
people do not differ too much, scales of observed peo-
ple can make a rough estimate of how large movements
they made in the actual physical world. Formally, let
Lin = (lt0−Tprev+1, . . . , lt0 ) be a history of previous tar-
get locations. Then, we extend each location lt ∈ R2
+ of
a) Input
b) Prediction
e) Pose
c-1) Location
c-2) Scale
d) Ego-motion
Figure 2. Future Person Localization in First-Person Videos. Given a) Tprev-frames observations as input, we b) predict future locations
of a target person in the subsequent Tfuture frames. Our approach makes use of c-1) locations and c-2) scales of target persons, d) ego-
motion of camera wearers and e) poses of the target persons as a salient cue for the prediction.
Channel-wise
Concatenation
Input
Output
Location-Scale Stream Ego-Motion Stream Pose Stream
Figure 3. Proposed Network Architecture. Blue blocks corre-
spond to convolution/deconvolution layers while gray blocks de-
scribe intermediate deep features.
tain direction at a constant speed, our best guess based on
only previous locations would be to expect them to keep go-
ing in that direction in subsequent future frames too. How-
ever, visual distances in first-person videos can correspond
to different physical distances depending on where people
are observed in the frame.
In order to take into account this perspective effect, we
propose to learn both locations and scales of target peo-
ple jointly. Given a simple assumption that heights of
people do not differ too much, scales of observed peo-
ple can make a rough estimate of how large movements
they made in the actual physical world. Formally, let
Lin = (lt0−Tprev+1, . . . , lt0 ) be a history of previous tar-
get locations. Then, we extend each location lt ∈ R2
+ of
a target person by adding the scale information of that per-
son st ∈ R+, i.e., xt = (lt , st) . Then, the ‘location-
scale’ input stream in Figure 3 learns time evolution in
Xin = (xt0−Tprev+1, . . . , xt0 ), and the output stream gen-
erates Xout = (xt0+1 − xt0 , . . . , xt0+Tfuture
− xt0 ).
Ground Truth OursSocial LSTMInput NNeighbor
Past observations Predictions
(a)
(b)
(c)
(d)
(e)
Figure 5. Visual Examples of Future Person Localization. Using locations (shown with solid blue lines), scales and poses of target
people (highlighted in pink, left column) as well as ego-motion of camera wearers in the past observations highlighted in blue, we predict
locations of that target (the ground-truth shown with red crosses with dotted red lines) in the future frames highlighted in red. We compared
T. Yagi, et al., “Future Person Localization in First-Person Videos,” CVPR, 2018.
35. 車載カメラ映像に映る歩行者の将来の位置を予測する手法
●
歩行者の矩形領域,自車の移動量,車載カメラ画像を入力
●
歩行者の将来の矩形領域を出力
OPPU [A. Bhattacharyya+, CVPR, 2018]
35
Figure 2: Two stream architecture for prediction of future pedestrian bounding boxes.
ion of Pedestrian Trajectories sequence ˆv (containing information about past pedestrian
Last Observation: t Prediction: t + 5 Prediction: t + 10 Prediction: t + 15
Figure 4: Rows 1-3: Point estimates. Blue: Ground-truth, Red: Kalman Filter (Table 1 row 1), Yellow: One-stream model
(Table 1 row 4), Green: Two-stream model (mean of predictive distribution, Table 4 row 3). Rows 4-6: Predictive distributions
of our two-stream model as heat maps. (Link to video results in the Appendix).
sequences have low error (note, log(530) ≈ 6.22 the MSE that, the predicted uncertainty upper bounds the error of the
A. Bhattacharyya, et al., “Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty,” CVPR, 2018.
36. 自動車検出,追跡,経路予測を同時に推論するモデルを提案
●
3D点群データを入力に使用
- 3次元空間でスパースな特徴表現
- ネットワークの計算コストを抑制
- リアルタイムで3つのタスクを同時に計算可能
Fast and Furious [W. Luo+, CVPR, 2018]
36
Real Time End-to-End 3D Detection, Tracking and Motion
orecasting with a Single Convolutional Net
Wenjie Luo, Bin Yang and Raquel Urtasun
Uber Advanced Technologies Group
University of Toronto
{wenjie, byang10, urtasun}@uber.com
ract
a novel deep neural network
about 3D detection, track-
iven data captured by a 3D
about these tasks, our holis-
occlusion as well as sparse
h performs 3D convolutions
bird’s eye view representa-
is very efficient in terms of
n. Our experiments on a new
ed in several north american
W. Luo, et al., “Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net,” CVPR, 2018.
38. 一般道における自動車の経路予測手法
●
異なるシーンコンテキストを考慮するCNNとGRUによるモデルを提案
- 予測車・他車の位置,コンテキスト,道路情報をチャネル方向に連結
- 連結したテンソルを時刻毎にCNNでエンコード
- エンコードした特徴をGRUで時間方向へ伝播し,将来の経路を予測
Rules of the Road [J. Hong+, CVPR, 2019]
38
Figure 2: Entity and world context representation. For an example scene (visualized left-most), the world is represented with
the tensors shown, as described in the text.
ontext representation. For an example scene (visualized left-most), the world is represented with
bed in the text.
One-shot (b) with RNN decoder
(a) Gaussian Regression (b) GMM-CVAE
Figure 4: Examples of Gaussian Regression and GMM-CVAE methods. Ellipses represent a standard deviation of uncertainty, a
only drawn for the top trajectory; only trajectories with probability > 0.05 are shown, with cyan the most probable.We see that uncer
ellipses are larger when turning than straight, and often follow the direction of velocity. In the GMM-CVAE example, different sa
シーン例 予測車の位置 他車の位置 コンテキスト 道路情報
J. Hong, et al., “Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions,” CVPR, 2019.
39. 複数の尤もらしい経路を予測するMultiverseを提案
●
過去のセマンティックラベルと固定グリッドをHistory Encoder (HE)へ入力
- Convolution Recurrent Neural Networkで時空間特徴をエンコード
- セマンティックラベルを入力することで,ドメインシフトに対して強固になる
●
HEの出力と観測最終のセマンティックラベルをCoarse Location Decoder (CLD)へ入力
- GATでグリッドの各格子に重み付けし,重みマップを生成
●
Fine Location Decoder (FLD)でグリッドの各格子に距離ベクトルを格納
- CLD同様,GATで各格子に重み付け
●
FLDとCLDから複数の経路を予測
Multiverse [J. Liang+, CVPR, 2020]
39
Figure 2: Overview of our model. The input to the model is the ground truth location history, and a set of video frames,
which are preprocessed by a semantic segmentation model. This is encoded by the “History Encoder” convolutional RNN.J. Liang, et al., “The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction,” CVPR, 2020.
41. 経路予測で最も使用されるデータセット
41
ETH Dataset UCY Dataset Stanford Drone Dataset
• サンプル数:786
市街地の歩行者を撮影したデータセット 市街地の歩行者を撮影したデータセット
• シーン数:2
• 対象種類
- pedestrian
• サンプル数:750
• シーン数:3
• 対象種類
- pedestrian
スタンフォード大学構内を撮影したデータセット
• サンプル数:10,300
• シーン数:8
• 対象種類
- pedestrian, car, cyclist, bus, skater, cart
R. Alexandre, et al., “Learning Social Etiquette: Human Trajectory Understanding in Crowded Scenes,” ECCV, 2016.
A. Lerner, et al., “Crowds by Example,” CGF, 2007.
S. Pellegrini, et al., “You’ll Never Walk Alone: Modeling Social Behavior for Multi-target Tracking,” ICCV, 2009.
42. 固定カメラやドローンで撮影
●
豊富なデータを取得できるため,非常に大規模なデータセット
俯瞰視点のデータセット
42
lts from NN+map(prior) m-
aseline. The orange trajectory
Red represents ground truth for
n represents the multiple fore-
3 s. Top left: The car starts to
Argoverse Dataset
The inD Dataset: A Drone Dataset of Naturalistic
Road User Trajectories at German Intersections
Julian Bock1, Robert Krajewski1, Tobias Moers2, Steffen Runde1, Lennart Vater1 and Lutz Eckstein1
Fig. 1: Exemplary result of road user trajectories in the inD dataset. The position and speed of each road user is measured
accurately over time and shown by bounding boxes and tracks. For privacy reasons, the buildings were made unrecognizable.
Abstract—Automated vehicles rely heavily on data-driven
methods, especially for complex urban environments. Large
datasets of real world measurement data in the form of road
user trajectories are crucial for several tasks like road user
prediction models or scenario-based safety validation. So far,
though, this demand is unmet as no public dataset of urban
road user trajectories is available in an appropriate size, quality
and variety. By contrast, the highway drone dataset (highD) has
recently shown that drones are an efficient method for acquiring
naturalistic road user trajectories. Compared to driving studies
or ground-level infrastructure sensors, one major advantage of
using a drone is the possibility to record naturalistic behavior,
as road users do not notice measurements taking place. Due to
the ideal viewing angle, an entire intersection scenario can be
measured with significantly less occlusion than with sensors at
ground level. Both the class and the trajectory of each road
user can be extracted from the video recordings with high
precision using state-of-the-art deep neural networks. Therefore,
we propose the creation of a comprehensive, large-scale urban
intersection dataset with naturalistic road user behavior using
camera-equipped drones as successor of the highD dataset. The
resulting dataset contains more than 11500 road users including
vehicles, bicyclists and pedestrians at intersections in Germany
and is called inD. The dataset consists of 10 hours of measurement
data from four intersections and is available online for non-
commercial research at: http://www.inD-dataset.com
1The authors are with the Automated Driving Department, Institute for
Automotive Engineering RWTH Aachen University (Aachen, Germany).
(E-mail: {bock, krajewski, steffen.runde, vater, eckstein}@ika.rwth-
aachen.de).
2The author is with the Automated Driving Department, fka GmbH
(Aachen, Germany). (E-mail: tobias.moers@fka.de).
Index Terms—Dataset, Trajectories, Road Users, Machine
Learning
I. INTRODUCTION
Automated driving is expected to reduce the number and
severity of accidents significantly [13]. However, intersections
are challenging for automated driving due to the large com-
plexity and variety of scenarios [15]. Scientists and companies
are researching how to technically handle those scenarios by
an automated driving function and how to proof safety of
these systems. An ever-increasing proportion of the approaches
to tackle both challenges are data-driven and therefore large
amounts of measurement data are required. For example, re-
cent road user behaviour models, which are used for prediction
or simulation, use probabilistic approaches based on large
scale datasets [2], [11]. Furthermore, current approaches for
safety validation of highly automated driving such as scenario-
based testing heavily rely on large-scale measurement data on
trajectory level [3], [5], [17].
However, the widely used ground-level or on-board
measurement methods have several disadvantages. These
include that road users can be (partly) occluded by other
road users and do not behave naturally as they notice being
part of a measurement due to conspicuous sensors [5].
We propose to use camera-equipped drones to record road
user movements at urban intersections (see Fig. 2). Drones
with high-resolution cameras allow to record traffic from a
arXiv:1911.07602v1[cs.CV]18Nov2019
inD Dataset
ysis. The red trajectories are single-future method predictions and the yellow-orange heatmaps are
ctions. The yellow trajectories are observations and the green ones are ground truth multi-future
etails.
Method Single-Future Multi-Future
Our full model 18.51 / 35.84 166.1 / 329.5
The Forking Paths Dataset
Figure 7: Example output of the motion prediction solution
supplied as part of the software development kit. A convo-
lution neural network takes rasterised scenes around nearby
vehicles as input, and predicts their future motion.
ity and multi-threading to make it suitable for distributed
machine learning.
Customisable scene visualisation and rasterisation.
We provide several functions to visualise and rasterise
Lyft Level 5 Dataset
• サンプル数:300K
• シーン数:113
• 対象種類
• 追加情報
- car
- 車線情報,地図データ,センサー情報
• サンプル数:13K
• シーン数:4
• 対象種類
- pedestrian, car, cyclist
• サンプル数:3B
• シーン数:170,000
• 対象種類
• 追加情報
- pedestrian, car, cyclist
- 航空情報
- セマンティックラベル
• サンプル数:0.7K
• シーン数:7
• 対象種類
• 追加情報
- pedestrian
- 複数経路情報
- セマンティックラベル
一般道を撮影したデータセット 交差点を撮影したデータセット
一般道を撮影したデータセット シミュレータで作成されたデータセット
J. Houston, et al., “One Thousand and One Hours: Self-driving Motion Prediction Dataset,” CoRR, 2020.
J. Bock, et al., “The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections,” CoRR, 2019.
M.F. Chang, et al., “Argoverse: 3D Tracking and Forecasting with Rich Maps,” CVPR, 2019.
J. Liang, et al., “The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction,” CVPR, 2020.
43. 自動車前方の移動対象の経路予測を目的
車載カメラ視点のデータセット
43
• サンプル数:1.8K
• シーン数:53
• 対象種類
• 追加情報
- pedestrian
- 車両情報,インフラストラクチャ
一般道を撮影したデータセット
Apolloscape DatasetFigure 3. Example scenarios of the TITAN Dataset: a pedestrian bounding box with tracking ID is shown in , vehicle bounding b
with ID is shown in , future locations are displayed in . Action labels are shown in different colors following Figure 2.
centric views captured from a mobile platform.
In the TITAN dataset, every participant (individuals,
vehicles, cyclists, etc.) in each frame is localized us-
ing a bounding box. We annotated 3 labels (person, 4-
wheeled vehicle, 2-wheeled vehicle), 3 age groups for per-
son (child, adult, senior), 3 motion-status labels for both 2
and 4-wheeled vehicles, and door/trunk status labels for 4-
wheeled vehicles. For action labels, we created 5 mutually
exclusive person action sets organized hierarchically (Fig-
ure 2). In the first action set in the hierarchy, the annota-
tor is instructed to assign exactly one class label among 9
atomic whole body actions/postures that describe primitive
action poses such as sitting, standing, standing, bending,
etc. The second action set includes 13 actions that involve
single atomic actions with simple scene context such as jay-
walking, waiting to cross, etc. The third action set includes
7 complex contextual actions that involve a sequence of
atomic actions with higher contextual understanding, such
agent i at each past time step from 1 to Tobs, where (cu,
and (lu, lv) represent the center and the dimension of
bounding box, respectively. The proposed TITAN fram
work requires three inputs as follows: Ii
t=1:Tobs
for the
tion detector, xi
t for both the interaction encoder and p
object location encoder, and et = {αt, ωt} for the eg
motion encoder where αt and ωt correspond to the accel
ation and yaw rate of the ego-vehicle at time t, respective
During inference, the multiple modes of future bound
box locations are sampled from a bi-variate Gaussian g
erated by the noise parameters, and the future ego-motio
ˆet are accordingly predicted, considering the multi-mo
nature of the future prediction problem.
Henceforth, the notation of the feature embedding fu
tion using multi-layer perceptron (MLP) is as follows: Φ
without any activation, and Φr, Φt, and Φs are associa
with ReLU, tanh, and a sigmoid function, respectively.
TITAN Dataset
LSTM 172 330 911 837 3352 289 569 155
B-LSTM[5] 101 296 855 811 3259 159 539 153
PIEtraj 58 200 636 596 2477 110 399 124
Table 3: Location (bounding box) prediction errors over varying future time steps. M
predicted time steps, CMSE and CFMSE are the MSEs calculated over the center of
predicted sequence and only the last time step respectively.
Method 0.5
Linear 0.8
LSTM 1.5
PIEspeed 0.6
Table 4: Speed predict
on the PIE dataset. Las
results are reported in km
is generally better on bou
degrees of freedom.
Context in trajector
PIE Dataset Figure 5: Illustration of our TrafficPredict (TP) method on camera-based images. T
conditions and traffic situations. We only show the trajectories of several instances in
drawn in green and the prediction results of other methods (ED,SL,SA) are shown w
trajectories of our TP algorithm (pink lines) are the closest to ground truth in most of
stance layer to ca
instances and use
larities of moveme
type and guide the
in spatial and tem
ferred in our desig
previous state-of-t
racy of trajectory p
heterogeneous tra
一般道を撮影したデータセット 一般道を撮影したデータセット
• サンプル数:81K
• シーン数:100,000
• 対象種類
- pedestrian, car, cyclist
• サンプル数:645K
• シーン数:700
• 対象種類
• 追加情報
- pedestrian, car, cyclist
- 行動ラベル,歩行者の年齢
Y. Ma, et al., “TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents,” AAAI, 2019.
A. Rasouli, et al., “PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction, ” ICCV, 2019.
S. Malla, et al., “TITAN: Future Forecast using Action Priors,” CVPR, 2020.
45. 予測された矩形領域と真の矩形領域の中心座標で評価
●
車載カメラ映像における経路予測で利用
●
矩形領域の重なり率からF値で評価もできる
評価指標
45
Displacement Error Negative log-likelihood
Mean Square Error Collision rate
(a) Average Displacement Error (b) Final Displacement ErrorADE FDE
真値と予測値とのユークリッド距離誤差
●
Average Displacement Error (ADE):予測時刻間の平均誤差
●
Final Displacement Error (FDE):予測最終時刻の誤差
!"#$
…
!"#&
#ofSamples:'
Prediction Horizon: (
Figure 5. An illustration of our probabilistic evaluation methodol-
ogy. It uses kernel density estimates at each timestep to compute
the log-likelihood of the ground truth trajectory at each timestep,
averaging across time to obtain a single value.
Figure 6. Mean NLL for each dataset. Error bars are bootstrapped
95% confidence intervals. 2000 trajectories were sampled per
model at each prediction timestep. Lower is better.
ADE and FDE are useful metrics for comparing determinis-
tic regressors, they are not able to compare the distributions
produced by generative models, neglecting aspects such as
variance and multimodality [40]. To bridge this gap in eval-
Dataset
ADE / FDE,
SGAN [16]
ETH 0.64 / 1.13
Hotel 0.43 / 0.91
Univ 0.53 / 1.12
Zara 1 0.29 / 0.58
Zara 2 0.27 / 0.56
Average 0.43 / 0.86
Table 1. Quantitative ADE and
metric where N = 100.
Both of our methods signi
the ETH datasets, the UCY
(P <.001; two-tailed t-test
and SGAN’s mean NLL). On
Full model is identical in pe
same t-test). However, on th
model performs worse than
We believe that this is caused
tions more often than in other
truth trajectories to frequentl
tions whereas SGAN’s highe
to have density there. Acros
uration outperforms our zbes
model’s full multimodal mo
for strong performance on th
We also evaluated our m
to determine how much the p
prediction horizon. The resu
be seen, our Full model sig
at every timestep (P <.001;
ence between our and SGAN
推定した分布の元での真値の対数尤度の期待値
●
ADEとFDEで複数経路を評価するのはマルチモーダル性を無視
●
Negative log-likelihoodで複数経路の予測の評価指標として利用
truth
prediction
MSE
L2 norm
L2 norm
真値 予測値
従来の評価指標
提案する評価指標
2つのDisplacement Errorで評価
非線形経路のDisplacement Error,2つの物体との衝突率で評価
L2 norm
L2 norm
真値 予測値
従来の評価指標
提案する評価指標
2つのDisplacement Errorで評価
Displacement Errorは全サンプルに対し平均を求める
●
インタラクション情報がどの予測経路に効果的か評価できない
予測値が各物体と衝突したか否かの衝突率で評価
●
動的物体:映像中の他対象
●
静的物体:建物や木などの障害物
動的物体 静的物体