Translator Disclaimer
9 August 2018 Three-dimensional convolutional neural networks applied to video sensor-based gait recognition
Author Affiliations +
Proceedings Volume 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018); 108061V (2018) https://doi.org/10.1117/12.2502828
Event: Tenth International Conference on Digital Image Processing (ICDIP 2018), 2018, Shanghai, China
Abstract
In this paper, we propose a novel gait representation based on 3D-CNN, i.e., learning spatio-temporal multi-scale gait identity features (GaitID) using the 3-dimensional convolutional networks. Our contributions include: 1) explore different numbers of input frames for 3D-CNN model, 2) evaluate different features and gait representations in 3D-CNN, and 3) improve the net structure to learn multi-scale gait features with low dimensions. Nearest neighbor (NN) classifier was applied to identify the gait. When compared with other existing methods, the results reported on the CASIA-B dataset demonstrated that the proposed method not only achieved a competitive performance, but also still retained the discriminative power in a very low dimension (128-D), even with a simpler classifier.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xianfu Zhang, Nuo Xu, Xurui Zhang, Shouqian Sun, and Yuping Hu "Three-dimensional convolutional neural networks applied to video sensor-based gait recognition", Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108061V (9 August 2018); https://doi.org/10.1117/12.2502828
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Action recognition based on feature-level fusion
Proceedings of SPIE (August 09 2018)
Robust 3D object model reconstruction from video
Proceedings of SPIE (April 16 2004)
Model based image coding using deformable 3D model for face...
Proceedings of SPIE (September 21 1994)

Back to Top