当前位置: X-MOL 学术Neurocomputing › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Density-Adaptive Kernel based Efficient Reranking Approaches for Person Reidentification
Neurocomputing ( IF 5.5 ) Pub Date : 2020-10-01 , DOI: 10.1016/j.neucom.2020.05.096
Ruopei Guo , Chun-Guang Li , Yonghua Li , Jiaru Lin , Jun Guo

Person reidentification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views in a surveillance camera network. It has recently been validated that reranking can achieve remarkable performance improvements in person ReID systems. However, current reranking approaches either require feedback from users or suffer from burdensome computational costs. In this paper, we propose to exploit a density-adaptive smooth kernel technique to achieve efficient and effective reranking. Specifically, we adopt a smooth kernel function to formulate the neighbor relationships among data samples with a density-adaptive parameter. Based on this new formulation, we present two simple yet effective reranking methods, termed \emph{inverse} density-adaptive kernel based reranking (inv-DAKR) and \emph{bidirectional} density-adaptive kernel based reranking (bi-DAKR), in which the local density information in the vicinity of each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR methods to incorporate the available extra probe samples and demonstrate that when and why these extra probe samples are able to improve the local neighborhood and thus further refine the ranking results. Extensive experiments are conducted on six benchmark datasets, including: PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. The experimental results demonstrate that our proposals are effective and efficient.

中文翻译:

用于人员重新识别的基于密度自适应内核的有效重排序方法

行人重新识别 (ReID) 是指验证从监控摄像头网络中非重叠视图观察到的行人身份的任务。最近已经证实,重新排名可以在个人 ReID 系统中实现显着的性能改进。然而,当前的重新排序方法要么需要用户的反馈,要么面临繁重的计算成本。在本文中,我们建议利用密度自适应平滑核技术来实现高效和有效的重新排序。具体来说,我们采用平滑核函数来制定具有密度自适应参数的数据样本之间的邻居关系。基于这个新公式,我们提出了两种简单而有效的重新排序方法,被称为 \emph{inverse} 基于密度自适应内核的重排序(inv-DAKR)和 \emph{bidirectional} 基于密度自适应内核的重排序(bi-DAKR),其中每个画廊样本附近的局部密度信息是优雅的被利用。此外,我们扩展了提议的 inv-DAKR 和 bi-DAKR 方法以合并可用的额外探针样本,并证明这些额外的探针样本何时以及为何能够改善局部邻域,从而进一步优化排名结果。在六个基准数据集上进行了广泛的实验,包括:PRID450s、VIPeR、CUHK03、GRID、Market-1501 和 Mars。实验结果表明我们的建议是有效和高效的。其中每个画廊样本附近的局部密度信息被优雅地利用。此外,我们扩展了提议的 inv-DAKR 和 bi-DAKR 方法以合并可用的额外探针样本,并证明这些额外的探针样本何时以及为何能够改善局部邻域,从而进一步优化排名结果。在六个基准数据集上进行了广泛的实验,包括:PRID450s、VIPeR、CUHK03、GRID、Market-1501 和 Mars。实验结果表明我们的建议是有效和高效的。其中每个画廊样本附近的局部密度信息被优雅地利用。此外,我们扩展了提议的 inv-DAKR 和 bi-DAKR 方法以合并可用的额外探针样本,并证明这些额外的探针样本何时以及为何能够改善局部邻域,从而进一步优化排名结果。在六个基准数据集上进行了广泛的实验,包括:PRID450s、VIPeR、CUHK03、GRID、Market-1501 和 Mars。实验结果表明我们的建议是有效和高效的。在六个基准数据集上进行了广泛的实验,包括:PRID450s、VIPeR、CUHK03、GRID、Market-1501 和 Mars。实验结果表明我们的建议是有效和高效的。在六个基准数据集上进行了大量实验,包括:PRID450s、VIPeR、CUHK03、GRID、Market-1501 和 Mars。实验结果表明我们的建议是有效和高效的。
更新日期:2020-10-01
down
wechat
bug