标题：Coupled Bilinear Discriminant Projection for Cross-view Gait Recognition
作者：Ben X.; Gong C.; Zhang P.; Yan R.; Wu Q.; Meng W.
作者机构：[Ben, X] School of Information Science and Engineering, Shandong University, Qingdao, 266237, China.;[ Gong, C] Key Laboratory of Intelligent Percepti 更多
来源：IEEE Transactions on Circuits and Systems for Video Technology
关键词：Coupled bilinear discriminant projection; cross-view gait recognition; Gait recognition; image alignment
摘要：A problem that hinders good performance of general gait recognition systems is that the appearance features of gaits are more affected-prone by views than identities, especially when the walking direction of the probe gait is different from the register gait. This problem cannot be solved by traditional projection learning methods, because these methods can learn only one projection matrix, thus for the same subject, it cannot transfer cross-view gait features into similar ones. This paper presents an innovative method to overcome this problem by aligning gait energy images (GEIs) across views with the Coupled bilinear discriminant projection (CBDP). Specifically, CBDP generates the aligned gait matrix features for two views with two sets of bilinear transformation matrices, so that the original GEIs’ spatial structure information can be preserved. By iteratively maximizing the ratio of inter-class distance metric to intra-class distance metric, CBDP can learn the optimal matrix subspace where GEIs across views are aligned in both horizontal and vertical coordinates. Therefore, CBDP is also able to avoid the under-sample problem. We also theoretically prove that the upper and lower bounds of the objective function sequence of CBDP are both monotonically increasing, so the convergence of CBDP is demonstrated. In terms of accuracy, the comparative experiments on the CASIA(B) and OU-ISIR gait databases show that our method is superior to the state-of-the-art cross-view gait recognition methods. More impressively, the encouraging performance is obtained by our method even in matching a lateral-view gait with a frontal-view gait. IEEE