Beyond Sharing Weights in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identification

TL;DR

This paper introduces a new UAV cross-modality vehicle re-identification benchmark and proposes a hybrid weights decoupling network to learn robust, orientation-invariant features across RGB and infrared images, addressing data and modality challenges.

Contribution

The paper presents a novel UAV cross-modality vehicle Re-ID benchmark and a hybrid weights decoupling network that effectively handles cross-modality and orientation discrepancies.

Findings

The proposed HWDNet achieves superior performance on the UCM-VeID dataset.

The benchmark provides a new challenging dataset for UAV-based vehicle Re-ID.

The method effectively learns orientation-invariant features across modalities.

Abstract

Owing to the capacity of performing full-time target search, cross-modality vehicle re-identification (Re-ID) based on unmanned aerial vehicle (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the data inadequacy issue. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with 16015 RGB and 13913 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to learn orientation-invariant feature. Comprehensive experiments are carried out to validate the effectiveness of the proposed method. The dataset and codes will be released at https://github.com/moonstarL/UAV-CM-VeID.