Cross-camera complementary vehicle matching via feature expandsion for video forensics

In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is first extracted based on ASIFT (affine and scale-invariant feature transform) for each detected vehicle in a camera network. Then, the ASIFT feature is expanded via a special vehicle database. As a result, cross-camera vehicle matching with the help of complementary part can be greatly improved. Experimental results demonstrate the effectiveness of the proposed algorithm and the feasibility to video forensics applications.