Journal
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
Volume 23, Issue 8, Pages 11422-11435Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2021.3103961
Keywords
Task analysis; Clustering algorithms; Unsupervised learning; Cameras; Annotations; Space vehicles; Shape; Viewpoint-aware; progressive clustering; vehicle Re-ID; unsupervised learning
Categories
Funding
- University Synergy Innovation Program of Anhui Province [GXXT-2019-007, GXXT-2020-051]
- National Natural Science Foundation of China [61976002, 61976003, 62076003]
- Natural Science Foundation of Anhui Higher Education Institutions of China [KJ2019A0033]
Ask authors/readers for more resources
Vehicle re-identification is crucial for large-scale intelligent monitoring in smart cities, but existing methods are mostly supervised, time-consuming, and limited in real-life scenarios. Unsupervised person re-identification methods show impressive performance through domain adaption or clustering techniques, but cannot be directly applied to vehicle re-identification due to huge appearance variations in vehicle images. To address this issue, a novel viewpoint-aware clustering algorithm is proposed for unsupervised vehicle re-identification, achieving promising performance in various scenarios according to experiments on benchmark datasets.
Vehicle re-identification (Re-ID) is an active task due to its importance in large-scale intelligent monitoring in smart cities. Despite the rapid progress in recent years, most existing methods handle vehicle Re-ID task in a supervised manner, which is both time and labor-consuming and limits their application to real-life scenarios. Recently, unsupervised person Re-ID methods achieve impressive performance by exploring domain adaption or clustering-based techniques. However, one cannot directly generalize these methods to vehicle Re-ID since vehicle images present huge appearance variations in different viewpoints. To handle this problem, we propose a novel viewpoint-aware clustering algorithm for unsupervised vehicle Re-ID. In particular, we first divide the entire feature space into different subspaces according to the predicted viewpoints and then perform a progressive clustering to mine the accurate relationship among samples. Comprehensive experiments against the state-of-the-art methods on two multi-viewpoint benchmark datasets VeRi-776 and VeRi-Wild validate the promising performance of the proposed method in both with and without domain adaption scenarios while handling unsupervised vehicle Re-ID.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available