Background Segmentation for Vehicle Re-Identification

TL;DR

This paper introduces a background interference removal mechanism for vehicle re-identification, significantly improving accuracy by addressing background variability in large-scale scenes.

Contribution

It is the first to explicitly consider background interference in vehicle Re-ID and proposes a new framework with a vehicle segmentation dataset and BIR mechanism.

Findings

Achieved an average 9% gain on mAP over state-of-the-art methods.

Demonstrated robustness against complex backgrounds.

Constructed a new vehicle segmentation dataset.

Abstract

Vehicle re-identification (Re-ID) is very important in intelligent transportation and video surveillance.Prior works focus on extracting discriminative features from visual appearance of vehicles or using visual-spatio-temporal information.However, background interference in vehicle re-identification have not been explored.In the actual large-scale spatio-temporal scenes, the same vehicle usually appears in different backgrounds while different vehicles might appear in the same background, which will seriously affect the re-identification performance. To the best of our knowledge, this paper is the first to consider the background interference problem in vehicle re-identification. We construct a vehicle segmentation dataset and develop a vehicle Re-ID framework with a background interference removal (BIR) mechanism to improve the vehicle Re-ID performance as well as robustness against complex background in large-scale spatio-temporal scenes. Extensive experiments demonstrate the effectiveness of our proposed framework, with an average 9% gain on mAP over state-of-the-art vehicle Re-ID algorithms.