Xiaojun Bai
ABSTRACT
In the application of video-based pedestrian re-identification, introduced deep learning method to learn feature representation of pedestrian. In order to improve feature quality, introduced 3D convolution block as backbone network to aggregate temporal and spatial features; for issue of human body occlusion in video frames, introduced Non_Local block to capture long distance dependence between frames, and eventually eliminate the impact of occlusion. Optimal embedding scheme of 3D convolution and Non_Local block in backbone network is designed via experiments, and has proved that rich features of pedestrian can be extracted from video frames by this solution, which helps to improve the accuracy of re-identification.
- Bai Mei. Research on content-based video retrieval method[D]. Shaanxi University of Science and Technology, 2016.Google Scholar
- Feng Xia,Du Jiahao,Duan Yinong,Liu Caihua.Research review of pedestrian re-identification based on deep learning[J].Application Research of Computers,2020,37(11):3220-3226+3240.Google Scholar
- Luo Hao,Jiang Wei,Fan Xing,Zhang Si Peng.Research progress of pedestrian re-identification based on deep learning[J].Acta Automatica Sinica,2019,45(11):2032-2049.Google Scholar
- Dong Yachao, Liu Hongzhe, Bao Jun. Research progress of pedestrian re-recognition technology based on deep learning[A]. China Computer Users Association Network Application Branch. China Computer Users Association Network Application Branch 2020 24th Network New Technology and Application Year Conference Proceedings [C]. China Computer Users Association Network Application Branch: Beijing Key Laboratory of Information Service Engineering, Beijing Union University, 2020:5.Google Scholar
- Yang Feng,Xu Yu,Yin Mengxiao,Fu Jiacheng,Huang Bing,Liang Fangxuan.Summarization of pedestrian re-identification based on deep learning[J].Computer Applications,2020,40(05):1243-1252.Google Scholar
- Zhang Huaxiang,Liu Li.Review of research on pedestrian re-identification[J].Journal of Shandong Normal University (Natural Science Edition),2018,33(04):379-387.Google Scholar
- Xu Mengyang. Review of Pedestrian Re-identification Research Based on Deep Learning[A]. China Computer Users Association Network Application Branch. China Computer Users Association Network Application Branch 2018 22nd Annual Conference of New Network Technologies and Applications [C]. China Computer Users Association Network Application Branch: Beijing Key Laboratory of Information Service Engineering, Beijing Union University, 2018:4.Google Scholar
- D.Cheng,Y.Gong,S.Zhou,et al.Person re-identification by multi-channel parts-based cnn with improved triplet loss function[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 1335-1344.Google Scholar
- H.Zhao,M.Tian,S.Sun,et al.Spindle net: Person re-identification with human body region guided feature decomposition and fusion[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017,1077-1085.Google Scholar
- T.Xiao,S.Li,B.Wang,et al.Joint detection and identification feature learning for person search[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017, 3415-3424.Google Scholar
- Wang Jingwei. Research and design of pedestrian re-retrieval algorithm based on video[D]. University of Electronic Science and Technology of China, 2019.Google Scholar
- Chen Yang. Research on Pedestrian Re-identification Method Based on Video[D]. Huazhong University of Science and Technology, 2019.Google Scholar
- Pi Yang. Research on Video Image Content Matching and Retrieval[D]. Hunan University, 2017.Google Scholar
- Yangyue Zhou and Miaolei Deng, "A Review of Multiple-Person Abnormal Activity Recognition," Journal of Image and Graphics, Vol. 9, No. 2, pp. 55-60, June 2021. doi: 10.18178/joig.9.2.55-60.Google ScholarCross Ref
- Tasweer Ahmad, Junaid Rafique, Hassam Muazzam, and Tahir Rizvi, "Using Discrete Cosine Transform Based Features for Human Action Recognition," Journal of Image and Graphics, Vol. 3, No. 2, pp. 96-101, December 2015. doi: 10.18178/joig.3.2.96-101.Google ScholarCross Ref
- Muhammad Hassan, Tasweer Ahmad, Nudrat Liaqat, Ali Farooq, Syed Asghar Ali, and Syed Rizwan hassan, "A Review on Human Actions Recognition Using Vision Based Techniques," Journal of Image and Graphics, Vol. 2, No. 1, pp. 28-32, June 2014. doi: 10.12720/joig.2.1.28-32.Google ScholarCross Ref
- A. Klaser, M. Marszałek, C. Schmid. A spatio-temporal descriptor based on 3d-gradients[C]. BMVC 2008-19th British Machine Vision Conference. British Machine Vision Association, 2008,275:1-10.Google ScholarCross Ref
- P. Scovanner, S. Ali, M. Shah. A 3-dimensional sift descriptor and its application to action recognition[C]. Proceedings of the 15th ACM international conference on Multimedia, 2007, 357-360.Google ScholarDigital Library
- T. Wang, S. Gong, X. Zhu, Person re-identification by video ranking[C]. European Conference on Computer Vision. Springer, Cham, 2014, 688-703.Google Scholar
- N. Mc Laughlin, J. Martinez del Rincon, P. Miller. Recurrent convolutional network for video-based person re-identification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 1325-1334.Google Scholar
- Y. Yan, B. Ni, Z. Song, Person re-identification via recurrent feature aggregation[C]. European Conference on Computer Vision, Springer, Cham, 2016, 701-716.Google Scholar
- Z. Zhou, Y. Huang, W. Wang, See the forest for the trees: Joint spatial and temporal recurrent neural networks for video-based person re-identification[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, 4747-4756.Google Scholar
- Naresh Kumar and Nagarajan Sukavanam, "Motion Trajectory for Human Action Recognition Using Fourier Temporal Features of Skeleton Joints," Journal of Image and Graphics, Vol. 6, No. 2, pp. 174-180, December 2018. doi: 10.18178/joig.6.2.174-180.Google ScholarCross Ref
- Tran D, Bourdev L, Fergus R , Learning Spatio-Temporal Features with 3D Convolutional Networks[J]. 2014.Google Scholar
- Qiu Z , Yao T , Mei T . Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks[J]. 2017 IEEE International Conference on Computer Vision (ICCV), 2017.Google ScholarCross Ref
- Seyma Yucer and Yusuf Sinan Akgul, "3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning," Journal of Image and Graphics, Vol. 6, No. 1, pp. 21-26, June 2018. doi: 10.18178/joig.6.1.21-26.Google ScholarCross Ref
- Y. Liu, Z. Yuan, W. Zhou, Spatial and Temporal Mutual Promotion for Video-based Person Re-identification[J]. ar Xiv preprint ar Xiv, 2018, 1812.10305.Google Scholar
- Gu X,H Chang,Ma B,et al.Appearance-Preserving 3D Convolution for Video-based Person Re-identification[M]. 2020.Google Scholar
- Li Shuang, Bak S, Carr P, et al.Diversity regularized spatiotemporal attention for video-based person re-identification[C]/ /Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE Computer Society, 2018: 369-378.Google Scholar
- HERMANS A, BEYER L, LEIBE B, In Defense of the Triplet Loss for Person Re-Identification [EB/OL]. [2020-04-12].Google Scholar
- Sun Y, Zheng L, Yang Y, et al. Beyond part models:Per son retrieval with refined part pooling(and a strong convolutional baseline)[C]//Proceedings of the European Conference on Computer Vision, 2018: 480-496.Google Scholar
- Zheng Z, Yang X, Yu Z, et al. Joint discriminative and generative learning for person re-identification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019:2138-2147.Google Scholar
Recommendations
Pedestrian Re-identification Algorithm Based on Visual Attention-positive Sample Generation Network Deep Learning Model
Highlights- This paper proposes a re-identification method based on visual common attention mechanism
AbstractIn view of the strong generalizability and self-learning capabilities of deep learning models, many scholars have studies how to apply deep learning theory in the pedestrian re-identification field. However, a number of problems ...
Lightweight convolutional neural network-based pedestrian detection and re-identification in multiple scenarios
AbstractPedestrian detection and re-identification technology is a research hotspot in the field of computer vision. This technology currently has issues such as insufficient pedestrian expression ability, occlusion, diverse pedestrian attitude, and ...
Cross-domain unsupervised pedestrian re-identification based on multi-view decomposition
AbstractGreat improvement has been made in pedestrian re-identification, but the test results in unknown domain are not satisfactory. This is because the pedestrian Re-ID model does not learn good common features between different domains. We found that ...
Comments