Robust human motion recognition from wide-angle images for video surveillance in nuclear power plants

Abstract

Installation of surveillance cameras in nuclear power plants is critical to protecting the facilities against terrorist attacks or monitoring the reactor operator. This has led to large amounts of video surveillance data, creating a demand for automatic detection of anomalies or suspicious movements. Tracking human motion from video sequences is a notable technique used for detecting anomalies in human behavior and is currently achieved with the use of a depth camera. However, depth cameras require a complicated camera system and their field of view is limited. To overcome this problem, there is a need for recognizing human motion in wide-angle images – a view that often causes distortion. In this study, we devised a method for tracking human motion through wideangle image distortion. The main contribution of this study is a methodology that automatically estimates the transformation parameters needed to improve the accuracy of motion recognition; these parameters are applied to a distorted wide-angle image in every frame. We propose a new multi-layered convolutional neural architecture for estimating the locations of human joints in images and transformation parameters simultaneously. When applied to distorted wide-angle images, the robustness of our method is demonstrated through a quantitative evaluation of human joint location prediction. In addition, we compare our method with a motion tracking system and an infrared-camera-based motion capture system to demonstrate its ability to handle wide-angle and close-range images.

Keywords

• nuclear security
• video surveillance
• human motion recognition
• convolutional neural network
• image processing