Aiming at the problems of high cost

complicated operation and low accuracy of image feature matching rate of traditional measurement method

a method of construction of human body three-dimensional foot shape by combining Kinect sensor with computer vision technology is proposed. The Kinect sensor is used to build up the measurement system to obtain depth information images at different angles. The improved Harris-SIFT algorithm is used to extract and match the feature points

and the splicing of point cloud data is completed by iterative closest point（ICP） algorithm. The results show that the method can realize the construction of human three-dimensional foot shape conveniently and accurately.