Extending Appearance Based Gait Recognition with Depth Data
Source abstract
Abstract
Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gait Recognition and Analysis · Video Surveillance and Tracking Methods · Human Pose and Action Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka 51000, Croatia
Funding
European Regional Development Fund · University of Rijeka, Rijeka, Croatia
References (26)
Show source-provided references
1. The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits10.1016/j.jvcir.2013.02.006 ↗
2. Sivapalan, S., Chen, D., Denman, S., Sridharan, S., and Fookes, C. (2012, January 3–5). The Backfilled GEI—A Cross-Capture Modality Gait Feature for Frontal and Side-View Gait Recognition. Proceedings of the International Conference on Digital Image Computing Techniques and Applications (DICTA 2012), Fremantle, Australia.10.1109/DICTA.2012.6411694 ↗
3. Vision-Based Gait Recognition: A Survey10.1109/ACCESS.2018.2879896 ↗
4. Individual recognition using gait energy image10.1109/TPAMI.2006.38 ↗
5. Hofmann, M., Bachmann, S., and Rigoll, G. (2012, January 23–27). 2.5D gait biometrics using the Depth Gradient Histogram Energy Image. Proceedings of the IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Arlington, VA, USA.10.1109/BTAS.2012.6374606 ↗
6. Sivapalan, S., Chen, D., Denman, S., Sridharan, S., and Fookes, C. (2011, January 11–13). Gait energy volumes and frontal gait recognition using depth images. Proceedings of the International Joint Conference on Biometrics (IJCB 2011), Washington, DC, USA.10.1109/IJCB.2011.6117504 ↗
7. Pose Depth Volume extraction from RGB-D streams for frontal gait recognition10.1016/j.jvcir.2013.02.010 ↗
8. Borràs, R., Lapedriza, À., and Igual, L. (2012, January 25–27). Depth Information in Human Gait Analysis: An Experimental Study on Gender Recognition. Proceedings of the 9th International Conference Image Analysis and Recognition (ICIAR 2012), Aveiro, Portugal.10.1007/978-3-642-31298-4_12 ↗
9. Human Identity and Gender Recognition from Gait Sequences With Arbitrary Walking Directions10.1109/TIFS.2013.2291969 ↗
10. Gait-Based Person Identification Robust to Changes in Appearance10.3390/s130607884 ↗
11. Schöning, J., and Heidemann, G. (2016, January 27–29). Taxonomy of 3D Sensors-A Survey of State-of-the-Art Consumer 3D-Reconstruction Sensors and their Field of Applications. Proceedings of the VISIGRAPP (3: VISAPP), Rome, Italy.10.5220/0005784801920197 ↗
12. Background subtraction techniques
13. Stauffer, C., and Grimson, W.E.L. (1999, January 23–25). Adaptive background mixture models for real-time tracking. Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), Fort Collins, CO, USA.
14. KaewTraKulPong, P., and Bowden, R. (2002). An improved adaptive background mixture model for real-time tracking with shadow detection. Video-Based Surveillance Systems, Springer US.10.1007/978-1-4615-0913-4_11 ↗
15. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance10.1109/JPROC.2002.801448 ↗
16. Maddalena, L., and Petrosino, A. (2018). Background subtraction for moving object detection in rgbd data: A survey. J. Imaging, 4.10.3390/jimaging4050071 ↗
17. Arora, P., and Srivastava, S. (2015, January 19–20). Gait recognition using gait Gaussian image. Proceedings of the 2nd International Conference on Signal Processing and Integrated Networks (SPIN 2015), Noida, India.10.1109/SPIN.2015.7095388 ↗
18. Gait analysis: Normal and pathological function10.1097/01241398-199211000-00023 ↗
19. Collins, R.T., Gross, R., and Shi, J. (2002, January 21). Silhouette-based human identification from body shape and gait. Proceedings of the Fifth IEEE International Conference on Automatic Face Gesture Recognition, Washington, DC, USA.
20. Silhouette analysis-based gait recognition for human identification10.1109/TPAMI.2003.1251144 ↗
21. Human identification using gait
22. A Method of Estimating the Human Height Using Depth Images
23. Classifiers combination techniques: A comprehensive review10.1109/ACCESS.2018.2813079 ↗
24. Multiclass alpha integration of scores from multiple classifiers10.1162/neco_a_01169 ↗
25. Algorithm 909: NOMAD: Nonlinear Optimization with the MADS algorithm10.1145/1916461.1916468 ↗
26. Audet, C., and Hare, W. (2017). Derivative-Free and Blackbox Optimization, Springer International Publishing.10.1007/978-3-319-68913-5 ↗