Gait Recognition Based on Gait Optical Flow Network with Inherent Feature Pyramid
Source abstract
Abstract
Gait is a kind of biological behavioral characteristic which can be recognized from a distance and has gained an increased interest nowadays. Many existing silhouette-based methods ignore the instantaneous motion of gait, which is an important factor in distinguishing people with similar shapes. To further emphasize the instantaneous motion factor in human gait, the Gait Optical Flow Image (GOFI) is proposed to add the instantaneous motion direction and intensity to original gait silhouettes. The GOFI also helps to leverage both the temporal and spatial condition noises. Then, the gait features are extracted by the Gait Optical Flow Network (GOFN), which contains a Set Transition (ST) architecture to aggregate the image-level features to the set-level features and an Inherent Feature Pyramid (IFP) to exploit the multi-scaled partial features. The combined loss function is used to evaluate the similarity between different gaits. Experiments are conducted on two widely used gait datasets, the CASIA-B and the CASIA-C. The experiments show that the GOFN performs better on both datasets, which shows the effectiveness of the GOFN.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gait Recognition and Analysis · Diabetic Foot Ulcer Assessment and Management · Hand Gesture Recognition Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Funding
National Nature Science Foundation of China
References (35)
Show source-provided references
1. A Comprehensive Review of Past and Present Vision-Based Techniques for Gait Recognition10.1007/s11042-013-1574-x ↗
2. Individual Recognition Using Gait Energy Image10.1109/TPAMI.2006.38 ↗
3. Liu, J., and Zheng, N. (2007, January 2–5). Gait History Image: A Novel Temporal Template for Gait Recognition. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, Beijing, China.10.1109/ICME.2007.4284737 ↗
4. Frame Difference Energy Image for Gait Recognition with Incomplete Silhouettes10.1016/j.patrec.2009.04.012 ↗
5. Active Energy Image plus 2DLPP for Gait Recognition10.1016/j.sigpro.2010.01.024 ↗
6. 3D Convolutional Neural Networks for Human Action Recognition10.1109/TPAMI.2012.59 ↗
7. Wolf, T., Babaee, M., and Rigoll, G. (2016, January 25–28). Multi-View Gait Recognition Using 3D Convolutional Neural Networks. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.10.1109/ICIP.2016.7533144 ↗
8. Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21–26). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.
9. Chao, H., He, Y., Zhang, J., and Feng, J. (February, January 27). GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
10. Bashir, K., Xiang, T., and Gong, S. (2009, January 3). Gait Recognition Using Gait Entropy Image. Proceedings of the 3rd International Conference on Imaging for Crime Detection and Prevention (ICDP 2009), London, UK.10.1049/ic.2009.0230 ↗
11. A New View-Invariant Feature for Cross-View Gait Recognition10.1109/TIFS.2013.2252342 ↗
12. Makihara, Y., Sagawa, R., Mukaigawa, Y., Echigo, T., and Yagi, Y. (2006, January 7–13). Gait Recognition Using a View Transformation Model in the Frequency Domain. Proceedings of the 9th European Conference on Computer Vision, Graz, Austria.10.1007/11744078_12 ↗
13. Human Identification Using Temporal Information Preserving Gait Template10.1109/TPAMI.2011.260 ↗
14. Fan, C., Peng, Y., Cao, C., Liu, X., Hou, S., Chi, J., Huang, Y., Li, Q., and He, Z. (2020, January 13–19). GaitPart: Temporal Part-based Model for Gait Recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01423 ↗
15. Lin, B., Zhang, S., and Yu, X. (2021, January 11–17). Gait recognition via effective global-local feature representation and local temporal aggregation. Proceedings of the IEEE/CVF International Conference on Computer Vision 2021, Montreal, BC, Canada.10.1109/ICCV48922.2021.01438 ↗
16. Li, X., Makihara, Y., Xu, C., Yagi, Y., and Ren, M. (2020, January 13–19). Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01332 ↗
17. Fan, C., Liang, J., Shen, C., Hou, S., Huang, Y., and Yu, S. (2023, January 18–22). OpenGait: Revisiting Gait Recognition Toward Better Practicality. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00936 ↗
18. Ariyanto, G., and Nixon, M.S. (2011, January 11–13). Model-Based 3D Gait Biometrics. Proceedings of the 2011 International Joint Conference on Biometrics (IJCB), Washington, DC, USA.10.1109/IJCB.2011.6117582 ↗
19. View-Independent Human Motion Classification Using Image-Based Reconstruction10.1016/j.imavis.2008.11.008 ↗
20. Kusakunniran, W., Wu, Q., Li, H., and Zhang, J. (October, January 27). Multiple Views Gait Recognition Using View Transformation Model Based on Optimized Gait Energy Image. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, Kyoto, Japan.10.1109/ICCVW.2009.5457587 ↗
21. Teepe, T., Khan, A., Gilg, J., Herzog, F., Hörmann, S., and Rigoll, G. (2021, January 19–22). Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA.10.1109/ICIP42928.2021.9506717 ↗
22. Hou, S., Cao, C., Liu, X., and Huang, Y. (2020, January 23–28). Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition. Proceedings of the 16th European Conference, Glasgow, UK. Lecture Notes in Computer Science.10.1007/978-3-030-58545-7_22 ↗
23. View-Invariant Gait Recognition With Attentive Recurrent Learning of Partial Representations10.1109/TBIOM.2020.3031470 ↗
24. Lucas, B.D., and Kanade, T. (1981, January 24–28). An iterative image registration technique with an application to stereo vision. Proceedings of the IJCAI’81: 7th International Joint Conference on Artificial Intelligence, Vancouver, BC, Canada.
25. Two-Frame Motion Estimation Based on Polynomial Expansion10.1007/3-540-45103-X_50 ↗
26. Two-stream convolutional networks for action recognition in videos
27. Feichtenhofer, C., Pinz, A., and Zisserman, A. (2016, January 27–30). Convolutional Two-Stream Network Fusion for Video Action Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.213 ↗
28. Luo, Z., Yang, T., and Liu, Y. (2016, January 20–22). Gait Optical Flow Image Decomposition for Human Recognition. Proceedings of the 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference, Chongqing, China.10.1109/ITNEC.2016.7560427 ↗
29. Yu, S., Tan, D., and Tan, T. (2006, January 20–24). A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.
30. Tan, D., Huang, K., Yu, S., and Tan, T. (2006, January 20–24). Efficient Night Gait Recognition Based on Template Matching. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.
31. Invariant Feature Extraction for Gait Recognition Using Only One Uniform Model10.1016/j.neucom.2017.02.006 ↗
32. Multi-Task GANs for View-Specific Feature Learning in Gait Recognition10.1109/TIFS.2018.2844819 ↗
33. Gait-D: Skeleton-Based Gait Feature Decomposition for Gait Recognition10.1049/cvi2.12070 ↗
34. A Model-Based Gait Recognition Method with Body Pose and Human Prior Knowledge10.1016/j.patcog.2019.107069 ↗
35. Gait Recognition Based on Local Graphical Skeleton Descriptor With Pairwise Similarity Network10.1109/TMM.2021.3095809 ↗