期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 22, 期 3, 页码 1919-1931出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2020.3042558
关键词
Feature extraction; Visualization; Training; Measurement; Annotations; Task analysis; Semantics; Multi-view modeling; multi-center learning; deep metric learning; multi-view vehicle re-identification
资金
- National Key Research and Development Program of China [2019YFB2204200]
- National Natural Science Foundation of China [61972030]
In this paper, a multi-center metric learning framework is proposed for addressing the issue of feature representation in multi-view vehicle Re-ID, solving the subproblems of cross-view matching and cross-vehicle matching by modeling latent view clusters and introducing different loss functions. Extensive experimental evaluations demonstrate the superiority of the proposed framework compared to existing state-of-the-arts on three widely used benchmarks.
Multi-view vehicle re-identification (Re-ID) aims to retrieve all images of a target vehicle from a large gallery where the vehicles are captured from non-overlapping cameras. However, the drastic variation in vehicle appearance under different viewpoints greatly affects the performance of the multi-view vehicle Re-ID model, so the key issue in multi-view vehicle Re-ID is learning an effective feature representation that is robust to both dramatic intra-class variability and small inter-class variability. To achieve this goal, we have proposed a multi-center metric learning framework for multi-view vehicle Re-ID. In our approach, we model latent views from vehicle visual appearance directly without any extra labels except ID. Firstly, we introduce several latent view clusters for a vehicle to model latent multi-view information and each view cluster has a learnable center. Then multi-view vehicle matching task can be transformed into two subproblems, cross-view matching and cross-target matching. Finally, an intra-class ranking loss with cross-view center constraint and a cross-class ranking loss with cross-vehicle center constraint are proposed to address the two subproblems, respectively. Extensive experimental evaluations on three widely used benchmarks show the superiority of the proposed framework in contrast to a series of existing state-of-the-arts.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据