帮助 关于我们

返回检索结果

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

裴炤 1,2   邱文涛 2   王淼 3 *   马苗 2   张艳宁 4,5  
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    
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    
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    
4.  Rudenko A. Human motion trajectory prediction: A survey. The International Journal of Robotics Research,2020,39(8):895-935 CSCD被引 19    
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    
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    
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    
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    
9.  Lerner A. Crowds by example. Proceedings of the Computer Graphics Forum. 26(3),2007:655-664 CSCD被引 1    
10.  Helbing D. Social force model for pedestrian dynamics. Physical Review E,1995,51(5):4282-4286 CSCD被引 409    
11.  Kitani K M. Activity forecasting. Proceedings of the European Conference on Computer Vision,2012:201-214 CSCD被引 2    
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    
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    
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    
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    
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    
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    
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    
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    
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    
引证文献 5

1 杜泉成 行人轨迹预测方法关键问题研究:现状及展望 智能科学与技术学报,2023,5(2):143-162
CSCD被引 0 次

2 钱惠敏 TCSNGAN:基于Transformer和谱归一化CNN的图像生成模型 计算机应用研究,2024,41(4):1221-1227
CSCD被引 0 次

显示所有5篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号