Fighting behavior identification method based on time sequence detection

• Main Authors: CAO YANG, YAN YINGYING, HAN GUOQUAN, YIN YANG
• Format: Patent
• Language: Chinese; English
• Published: 17.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides a fighting behavior recognition method based on time sequence detection. The fighting behavior recognition method comprises the following steps of inputting video data and a behavior occurrence time period, preprocessing the video data, obtaining a fighting behavior recognition model and intercepting a fighting behavior video. According to the method, the video is processed into the RGB image according to frames, and the RGB image is packaged into the. Pkl file as the input of the deep neural network, so that a large amount of data reading time can be saved; the extracted features are coded, so that the network can obtain global time information of the time sequence action; the end-to-end learning of video recognition and detection based on deep learning is realized by adopting Faster RCNN target detection, the operation speed of the network is further improved, and the accuracy of action positioning and classification is effectively ensured. 本发明提供了一种基于时间序列检测的打斗行为识别方法，包括以下步骤：输入视频数据及行为发生