Automatic extraction of height and stride parameters for human recognition

Human gait is a new biometric indicator in visual surveillance system. It can recognize individuals as the way they walk. In the walking process, the human body shows regular periodic variation, such as upper and lower limbs, knee point, thigh point, stride parameters (stride length, cadence, gait cycle), height, etc. which reflects the individual´s unique movement pattern. Height is one of the important features from the several gait features which is not influenced by the camera performance, distance and clothing style of the subject. Stride parameters are the function of height. This paper compares the recognition rate of subjects using one of the stride parameter known as stride length and height variation signal. Direct Linear Transformation (DLT) method and neighborhood technique are applied to get height variation and stride length variation signal of each subject respectively. The variations of height signal and stride length are further analyzed using various transforms: DHT, DFT, and DCT. Euclidian distance and MSE are computed on feature vectors to recognize an individual. The height parameter gives better recognition rate as compared to stride parameter.