Vision-Based Detection of Falls at Flat Level Surfaces

Abstract

Workers might experience fall accidents even when they are working at flat level surfaces. These accidents plus other types of fall accidents have been reported as one of the major causes for worker-related fatalities and injuries. Currently, it becomes common to set up video cameras to monitor working environments. The video cameras provide an alternative to detect fall accidents. The objective of this paper is to investigate the feasibility of detecting fall accidents of workers with video. The preliminary focus is put on the fall detection under one single monocular camera. A novel fall detection method is proposed. Under the method, workers in the videos captured by the video cameras are first detected and tracked. Their pose and shape related features are then extracted. Given a set of features, an artificial neural network (ANN) classifier is further trained to automatically determine whether a fall happens. The method has been tested and the detection precision and recall were used to evaluate the method. The test results with high detection precision and recall indicated the method effectiveness. Also, the lessons and findings from this research are expected to build a solid foundation to create a vision-based fall detection solution for safety engineers.