Vehicle Detection of Multi-source Remote Sensing Data Using Active Fine-tuning Network

TL;DR

This paper introduces a multi-source active fine-tuning framework for vehicle detection in remote sensing images, effectively leveraging diverse data sources and active learning to improve detection accuracy in challenging scenes.

Contribution

It proposes a novel unified framework combining transfer learning, segmentation, and active classification for auto-labeling and vehicle detection in multi-source remote sensing data.

Findings

Outperforms existing methods on ISPRS benchmark datasets.

Demonstrates strong generalization in dense scenes.

Effectively utilizes multi-source data for improved detection.

Abstract

Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source data for better vehicle detection is challenging. To solve the above issues, a multi-source active fine-tuning vehicle detection (Ms-AFt) framework is proposed, which integrates transfer learning, segmentation, and active classification into a unified framework for auto-labeling and detection. The proposed Ms-AFt employs a fine-tuning network to firstly generate a vehicle training set from an unlabeled dataset. To cope with the diversity of vehicle categories, a multi-source based segmentation branch is then designed to construct additional candidate object sets. The separation of high quality vehicles is realized by a designed attentive classifications network. Finally, all three branches are combined to achieve vehicle detection. Extensive experimental results conducted on two open ISPRS benchmark datasets, namely the Vaihingen village and Potsdam city datasets, demonstrate the superiority and effectiveness of the proposed Ms-AFt for vehicle detection. In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site.