A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification

TL;DR

This paper introduces a dual-pooling attention module that enhances vehicle re-identification in UAV images by capturing fine-grained features from both channel and spatial perspectives, addressing challenges posed by high-altitude aerial views.

Contribution

It proposes a novel dual-pooling attention (DpA) module with channel and spatial branches, improving local feature extraction for UAV vehicle Re-ID.

Findings

Improves vehicle re-identification accuracy on UAV datasets.

Effectively captures discriminative features despite high-altitude imaging.

Demonstrates superior performance over existing methods on VeRi-UAV and VRU datasets.

Abstract

Vehicle re-identification (Re-ID) involves identifying the same vehicle captured by other cameras, given a vehicle image. It plays a crucial role in the development of safe cities and smart cities. With the rapid growth and implementation of unmanned aerial vehicles (UAVs) technology, vehicle Re-ID in UAV aerial photography scenes has garnered significant attention from researchers. However, due to the high altitude of UAVs, the shooting angle of vehicle images sometimes approximates vertical, resulting in fewer local features for Re-ID. Therefore, this paper proposes a novel dual-pooling attention (DpA) module, which achieves the extraction and enhancement of locally important information about vehicles from both channel and spatial dimensions by constructing two branches of channel-pooling attention (CpA) and spatial-pooling attention (SpA), and employing multiple pooling operations to enhance the attention to fine-grained information of vehicles. Specifically, the CpA module operates between the channels of the feature map and splices features by combining four pooling operations so that vehicle regions containing discriminative information are given greater attention. The SpA module uses the same pooling operations strategy to identify discriminative representations and merge vehicle features in image regions in a weighted manner. The feature information of both dimensions is finally fused and trained jointly using label smoothing cross-entropy loss and hard mining triplet loss, thus solving the problem of missing detail information due to the high height of UAV shots. The proposed method's effectiveness is demonstrated through extensive experiments on the UAV-based vehicle datasets VeRi-UAV and VRU.