Corner Detection-Based Image Feature Extraction and Description with Application to Target Tracking

Image features extraction and description is very important for pattern recognition and image analysis. Corners in images are typical feature points and represent a lot of important information. Extracting corners accurately is significant to image processing, which can reduce much of the calculations. In this paper, a target tracking algorithm is developed which is based on the local invariant feature point extracting and representing with Harris-Laplace corner. The results of the experiments show the feasibility of the proposed method and accurately localize the target. At last it has been used to construct the intelligent transportation system.