Application of dimension reduction techniques for motion recognition: Construction worker behavior monitoring

In the construction industry, the unsafe actions and behavior of workers are the most significant causes of accidents. Measurement of worker behavior thus can be used as a positive indicator in assessing safety management and preventing accidents. The monitoring of worker behavior, however, has not been applied to safety management in practice due to the time-consuming and painstaking nature of this type of monitoring. To address this problem, this paper utilizes a computer vision-based approach that automatically monitors workers with video cameras installed on-site and focuses on motion recognition methods. Templates predefined through experiments are used to determine safe and unsafe poses. Using a dimension reduction technique on a set of spatio-temporal motion segments, the human motion data obtained from experiments are clustered and generalized to recognize motions. In this manner, the unsafe behavior of workers is detected and analyzed through the shape of the human skeleton and joints. The use of video cameras allows worker behavior to be monitored automatically and constantly. The measured information then can be used to reduce the frequency of unsafe behavior and potentially reduce the number of accidents.