Dense invariant feature based support vector ranking for cross-camera person re-identification

Recently, support vector ranking has been adopted to address the challenging person re-identification problem. However, the ranking model based on ordinary global features cannot well represent the significant variation of pose and viewpoint across camera views. To address this issue, a novel ranking method which fuses the dense invariant features is proposed in this paper to model the variation of images across camera views. An optimal space for ranking is learned by simultaneously maximizing the margin and minimizing the error on the fused features. The proposed method significantly outperforms the original support vector ranking algorithm due to the invariance of the dense invariant features, the fusion of the bidirectional features and the adaptive adjustment of parameters. Experimental results demonstrate that the proposed method is competitive with state-of-the-art methods on two challenging datasets, showing its potential for real-world person re-identification.