Abnormal behavior recognition based on improved Gaussian mixture model and hierarchical detectors
Shuang Liu, Peng Chen, Denis Špelič · 2017
For elderly people of living alone, falls and consequent resulting physical-psychological injuries even injury-related deaths are a major health hazard. How to analyze and utilize the captured videos by public places based on image processing is one hot research topic. Abnormal fall detection consists of four parts, which are captured video pre-processing, moving object detection, fall behavior recognition and experimental analysis. In this paper, dilation and corrosion, Gaussian filtering and median filtering are adopted to complete frame image sequences preprocessing to remove noises. Then, an improved background subtraction method based on Gaussian mixture model is used to detect moving objects. Based on extracted trajectory feature and shape feature of foreground objects, three-level hierarchical detectors are utilized to complete fall behavior recognition. At last, experimental analysis is done based on testing the system performance. Image processing speeds of our system is 15 frames per second if the lights are stable, which meets the requirements of real-time detection. Moreover, both the moving objects real-time detection rate and falling behavior detection accuracy rate are more than 95% in our experiments.