基于Transformer动态场景信息生成对抗网络的行人轨迹预测方法
Pedestrian Trajectory Prediction Method Using Dynamic Scene Information Based Transformer Generative Adversarial Network
查看参考文献32篇
文摘
|
行人轨迹预测是视频监控的重要组成部分,因现有方法未充分利用场景特征信息造成其预测轨迹不符合生活常识,导致行人轨迹预测精度较低出现明显偏离真实轨迹的情况.针对上述不足本文提出一种基于Transformer动态场景信息生成对抗网络(Generative Adversarial Network,GAN)的行人轨迹预测方法.该方法利用动态场景特征提取模块的卷积神经网络(Convolutional Neural Networks,CNN)模型对目标行人的动态场景信息进行特征提取,同时生成器网络中的编码器利用Transformer对行人的社会交互信息特征以及轨迹信息特征进行建模.在ETH和UCY数据集上的实验结果表明,与Social GAN模型相比,本文方法在多个场景下的平均位移误差准确率提高了25.61%,最终位移误差准确率提高了38.44%. |
其他语种文摘
|
Pedestrian trajectory prediction is an important part of video surveillance. The current methods are not accurate and sometimes violate common senses because scene information is not fully used. To eliminate the above shortcomings, this paper proposes a transformer generated adversarial network(GAN) algorithm which combines dynamic scene information with pedestrian social interaction information. The convolution neural network model of the dynamic scene extraction module is utilized to extract the dynamic scene information features of the target pedestrian, and the encoder in the generator network uses transformer to model the features of social interaction information and trajectory information of pedestrians. Experimental results on ETH and UCY datasets show that, compared with social GAN model, our method improves the accuracy of average displacement error by 25.61% and the accuracy of average final displacement error by 38.44% in multiple scenarios. |
来源
|
电子学报
,2022,50(7):1537-1547 【核心库】
|
DOI
|
10.12263/DZXB.20210762
|
关键词
|
行人轨迹预测
;
生成对抗网络
;
转换器
;
深度学习
;
长短期记忆网络
|
地址
|
1.
陕西师范大学, 现代教学技术教育部重点实验室, 陕西, 西安, 710119
2.
陕西师范大学计算机科学学院, 陕西, 西安, 710119
3.
上海交通大学航空航天学院, 上海, 200240
4.
空天地海一体化大数据应用技术国家工程实验室, 空天地海一体化大数据应用技术国家工程实验室, 陕西, 西安, 710129
5.
西北工业大学计算机学院, 陕西, 西安, 710129
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
0372-2112 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金
;
陕西省重点研发计划
;
中央高校基本科研业务
;
上海市自然科学基金
|
文献收藏号
|
CSCD:7272149
|
参考文献 共
32
共2页
|
1.
Pei Z. Human trajectory prediction in crowded scene using social-affinity long short-term memory.
Pattern Recognition,2019,93:273-282
|
CSCD被引
3
次
|
|
|
|
2.
Yamaguchi K. Who are you with and where are you going?.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2011:1345-1352
|
CSCD被引
2
次
|
|
|
|
3.
Desouza G N. Vision for mobile robot navigation: A survey.
IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24(2):237-267
|
CSCD被引
60
次
|
|
|
|
4.
Rudenko A. Human motion trajectory prediction: A survey.
The International Journal of Robotics Research,2020,39(8):895-935
|
CSCD被引
19
次
|
|
|
|
5.
李康. 基于卷积神经网络的鲁棒高精度目标跟踪算法.
电子学报,2018,46(9):2087-2093
|
CSCD被引
15
次
|
|
|
|
6.
马少雄. 基于工地场景的深度学习目标跟踪算法.
电子学报,2020,48(9):1665-1671
|
CSCD被引
1
次
|
|
|
|
7.
S C B L O. Artificial convolution neural network for medical image pattern recognition.
Neural Networks,1995,8(7/8):1201-1214
|
CSCD被引
7
次
|
|
|
|
8.
Pellegrini S. Improving data association by joint modeling of pedestrian trajectories and groupings.
Proceedings of the European Conference on Computer Vision,2010:452-465
|
CSCD被引
1
次
|
|
|
|
9.
Lerner A. Crowds by example.
Proceedings of the Computer Graphics Forum. 26(3),2007:655-664
|
CSCD被引
1
次
|
|
|
|
10.
Helbing D. Social force model for pedestrian dynamics.
Physical Review E,1995,51(5):4282-4286
|
CSCD被引
409
次
|
|
|
|
11.
Kitani K M. Activity forecasting.
Proceedings of the European Conference on Computer Vision,2012:201-214
|
CSCD被引
2
次
|
|
|
|
12.
Lee N. Desire: Distant future prediction in dynamic scenes with interacting agents.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:336-345
|
CSCD被引
9
次
|
|
|
|
13.
Pellegrini S. You'll never walk alone: Modeling social behavior for multi-target tracking.
Proceedings of the 2009 IEEE 12th International Conference on Computer Vision,2009:261-268
|
CSCD被引
3
次
|
|
|
|
14.
Moussaid M. The walking behaviour of pedestrian social groups and its impact on crowd dynamics.
Plos One,2010,5(3):e10047
|
CSCD被引
41
次
|
|
|
|
15.
Xu Y. Encoding crowd interaction with deep neural network for pedestrian trajectory prediction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:5275-5284
|
CSCD被引
1
次
|
|
|
|
16.
Zhao T. Multi-agent tensor fusion for contextual trajectory prediction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2019:12126-12134
|
CSCD被引
1
次
|
|
|
|
17.
Alahi A. Socially-aware large-scale crowd forecasting.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:2203-2210
|
CSCD被引
2
次
|
|
|
|
18.
Alahi A. Social LSTM: Human trajectory prediction in crowded spaces.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:961-971
|
CSCD被引
40
次
|
|
|
|
19.
Ballan L. Knowledge transfer for scene-specific motion prediction.
Proceedings of the European Conference on Computer Vision,2016:697-713
|
CSCD被引
1
次
|
|
|
|
20.
Liu J. Spatio-temporal LSTM with trust gates for 3d human action recognition.
Proceedings of the European Conference on Computer Vision,2016:816-833
|
CSCD被引
5
次
|
|
|
|
|