Camera Motion Estimation and Moving Object Detection Based on Local Feature Tracking

摘要

This paper describes an approach for the camera motion estimation and moving object detection via tracking of the local image regions through the image sequence. The propose algorithm consists of two parts. First image of the sequence is used to compose a triangular grid which vertices are used as a feature points. Grid is optimized in order to increase number of elements in the regions with higher level of details. This grid is then used as an initial for the next frame in order to track local features. Neighborhood of each vertex is used to generate color distribution model which is used as a feature vector for tracking. In the second part of the proposed algorithm grids of two consistent frames used to estimate motion of correspondent grid vertices in order to form a motion field. This field is used to find dominant motions and make assumptions for background-foreground motion. Background motion is then used to estimate camera motion parameters.