Pedestrian Trajectory Prediction Based on Attention Mechanism and Sparse Graph Convolution

Min Chen; Kai Zeng; Tao Shen; Yan Zhu

doi:10.3788/LOP213274

Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 10 >Page 1010013 > Article

Laser & Optoelectronics Progress
Vol. 60, Issue 10, 1010013 (2023)

Pedestrian Trajectory Prediction Based on Attention Mechanism and Sparse Graph Convolution

Min Chen, Kai Zeng^*, Tao Shen, and Yan Zhu

Author Affiliations

Yunnan Key Laboratory of Computer Technologies Application, Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, Yunnan, China

show less

DOI: 10.3788/LOP213274 Cite this Article Set citation alerts

Min Chen, Kai Zeng, Tao Shen, Yan Zhu. Pedestrian Trajectory Prediction Based on Attention Mechanism and Sparse Graph Convolution[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010013 Copy Citation Text

show less

Fig. 1. Overall framework of proposed model

Download full size

Fig. 2. Deep attention mechanism

Download full size

Fig. 3. Track visualization of DAGCN and SR-LSTM

Download full size

Fig. 4. Visualization of pedestrian trajectory prediction in different scenes

Download full size

Model	ETH	HOTEL	UNIV	ZARA1	ZARA2	Average
Social LSTM^［8］	1.09/2.35	0.79/1.76	0.67/1.40	0.47/1.00	0.56/1.17	0.72/1.54
SGAN^［9］	0.87/1.62	0.67/1.37	0.76/1.52	0.35/0.68	0.42/0.84	0.61/1.21
SoPhie^［18］	0.70/1.43	0.76/1.67	0.54/1.24	0.30/0.63	0.38/0.78	0.51/1.15
PITF^［14］	0.73/1.65	0.30/0.59	0.60/1.27	0.38/0.81	0.31/0.68	0.46/1.00
GAT^［11］	0.68/1.29	0.68/1.40	0.57/1.29	0.29/0.60	0.37/0.75	0.52/1.07
Social-BIGAT^［16］	0.69/1.29	0.49/1.01	0.55/1.32	0.30/0.62	0.36/0.75	0.48/1.00
Social-STGCNN^［24］	0.64/1.11	0.49/0.85	0.44/0.79	0.34/0.53	0.30/0.48	0.44/0.75
STAR^［25］	0.56/1.11	0.26/050	0.52/1.15	0.41/0.90	0.31/0.71	0.41/0.87
SGCN^［13］	0.63/1.03	0.32/0.55	0.37/0.70	0.29/0.53	0.25/0.45	0.37/0.65
Proposed model	0.65/1.12	0.26/0.42	0.37/0.70	0.28/0.49	0.23/0.42	0.36/0.63

Table 1. ADE/FDE of different methods in ETH/UCY data set scenario

DA	SP	ETH	HOTEL	UNIV	ZARA1	ZARA2	Average
		0.94/1.53	0.62/1.21	0.68/1.43	0.47/0.79	0.43/0.87	0.63/1.17
	√	0.76/1.29	0.49/0.83	0.52/1.13	0.35/0.57	0.34/0.64	0.49/0.89
√		0.71/1.23	0.45/0.92	0.49/0.98	0.34/0.58	0.33/0.56	0.46/0.85
√	√	0.65/1.12	0.26/0.42	0.37/0.70	0.28/0.49	0.23/0.42	0.36/0.63

Table 2. Verification results of DA and SP (ADE/FDE)

Min Chen, Kai Zeng, Tao Shen, Yan Zhu. Pedestrian Trajectory Prediction Based on Attention Mechanism and Sparse Graph Convolution[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010013

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information

微信扫一扫：分享

微信扫一扫：分享