Using CNN's Gait Recognition to Strengthen Laboratory Safety Supervision
Abstract— In addition to manual management, the security measures of important facilities such as school laboratories mainly rely on human body recognition systems. Gait recognition is non-intrusive, the identification process is fast and simple, and the recognition method is less affected by clothes, which makes it suitable for laboratory's safety monitoring purposes. This paper uses the form of gait energy image to extract the gait information features of the human body. The main contribution of the paper is the improvement of existing CNN models, adding a batch-normalization layer to for better recognition. Two types of experiments were conducted. The first experiment is a comparison with previous methods using the CASIA standard dataset. The second experiment is the evaluation with our new dataset using OpenCV to collect gait information in an actual laboratory environment. The results of the experiment show that the proposed method and its application in a real environment are feasible to enhance laboratory safety monitoring.
Index Terms— gait recognition, CNN, deep learning, OpenCV
Yongjia Xu, Fuji Ren, Shun Nishide
Faculty of Engineering, Tokushima University 2-1 Minami Josanjima, JAPAN
Cite: Yongjia Xu, Fuji Ren, Shun Nishide, "Using CNN's Gait Recognition to Strengthen Laboratory Safety Supervision," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 181-188, Hong Kong, 15-17 June, 2019.