期刊论文

Sui, Haigang

英文

IEEE Transactions on Intelligent Transportation Systems

1524-9050

2021

22

2

1276-1286

10.1109/TITS.2020.2968517

Manuscript received July 1, 2019; revised November 14, 2019; accepted December 17, 2019. Date of publication January 28, 2020; date of current version February 2, 2021. This work was supported by the National Natural Science Foundation of China under Grant No. 41771457. The Associate Editor for this article was W. Lin. (Corresponding author: Haigang Sui.) Xu Chen, Haigang Sui, Wenqing Feng, and Mingting Zhou are with the State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China (e-mail: 2010206190108@whu.edu.cn; haigang_sui@263.net; wq_feng@whu.edu.cn; mintyzhou@whu.edu.cn).

本校为其他机构

Vehicle re-identification supports cross-camera tracking and the location of specific vehicles in a smart city. The gallery images of vehicles are ranked based on the similarities in the appearance of objects to a vehicle query image. Previous work on vehicle re-identification has mainly focused on global or local analyses of predefined regions of vehicles to classify the vehicle images with a softmax loss function. On the one hand, separate global or predefined local regions of vehicles are often sensitive to perspective and occlusions. On the other hand, the embedding space supervised by the...