Abstract
We propose a novel bolt-on module capable of boosting the robustness of various single compact 2D gait representations. Gait recognition is negatively influenced by covariate factors including clothing and time which alter the natural gait appearance and motion. Contrary to traditional gait recognition, our bolt-on module remedies this by a dedicated covariate factor detection and removal procedure which we quantitatively and qualitatively evaluate. The fundamental concept of the bolt-on module is founded on exploiting the pixel-wise composition of covariate factors. Results demonstrate how our bolt-on module is a powerful component leading to significant improvements across gait representations and datasets yielding state-of-the-art results.
Highlights
This paper focusses on the gait recognition problem and boosting the robustness of popular single compact 2D gait representations
We demonstrate that our bolt-on module can generalise over a diverse set single compact 2D gait representations, varying in feature content and natural robustness, to yield an average performance increase of 15.1 %
We select a mixture of traditional and recent gait representations which naturally vary in feature content and natural robustness, namely the Gait Energy Image (GEI), Gait Variance Image (GVI), Skeleton Energy Image (SEIM) and Skeleton Variance Image (SVIM) demonstrated in Fig. 1; baseline performances on which to improve are presented in Table 1 for validation on the CASIA B and TUM GAID datasets
Summary
This paper focusses on the gait recognition problem and boosting the robustness of popular single compact 2D gait representations. The initial concept of our bolt-on module [32] was designed to boost Gait Energy Image [14] robustness and continued to advance state-of-the-art results when validated [31] on a more complex dataset. With these encouraging results, we felt our bolt-on module could serve a greater purpose of dedicated covariate factor detection and removal to enhance the performance of analogous single compact 2D gait representations. This paper describes the quantitative and qualitative evaluation generalising our bolt-on module for deployment on a diverse set of single compact 2D gait representations varying in feature content and natural robustness
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
