Abstract
Person Re-Identification (ReID) refers to the task of verifying the identity of a pedestrian observed from non-overlapping views of surveillance cameras networks. Recently, it has been validated that re-ranking could bring remarkable performance improvements for a person ReID system. However, the current re-ranking approaches either require feedbacks from users or suffer from burdensome computation cost. In this paper, we propose to exploit a density-adaptive smooth kernel technique to perform efficient and effective re-ranking. Specifically, we adopt a smooth kernel function to formulate the neighboring relationship amongst data samples with a density-adaptive parameter. Based on the new formulation, we present two simple yet effective re-ranking methods, termed inverse Density-Adaptive Kernel based Re-ranking (inv-DAKR) and bidirectional Density-Adaptive Kernel based Re-ranking (bi-DAKR), in which the local density information around each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR to incorporate the available extra probe samples and demonstrate that the extra probe samples are able to improve the local neighborhood and thus further refine the ranking result. Extensive experiments are conducted on six benchmark datasets, including PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. Experimental results demonstrate that our proposals are effective and efficient.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1805.07698