Skip to Main Content
Human body is a natural emitter of infrared ray. Usually the body temperature is different from that of surrounding. This leads to gray-scale difference between human body and background in infrared thermal image. So the method of infrared thermal imaging was presented to classify gaits. Firstly, infrared videos of 23 subjects were collected by using infrared thermal camera. Body silhouettes were extracted and normalized to obtain the gait feature image. Then the wavelet transform was combined with invariant moments to compute the moment parameters based on integral model. The gait feature image was simplified to extract the parameters based on the body skeleton. Finally, the parameters were applied to support vector machine for classification. This method achieved 71%~92% for the probability of correct recognition. The results showed that it was insensitive for loading objects (backpack and volleyball) to recognize gaits in infrared video. Also it is easy to detect the moving human body during the whole day.