Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification
Achieving rapid and effective object detection in large-scale unmanned aerial vehicle (UAV) images presents a challenge. Existing methods typically split the original large UAV image into overlapping patches and perform object detection on each image patch. However, the extensive object-free backgro...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/1/29 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588642693939200 |
|---|---|
| author | Shuo Zhuang Yongxing Hou Di Wang |
| author_facet | Shuo Zhuang Yongxing Hou Di Wang |
| author_sort | Shuo Zhuang |
| collection | DOAJ |
| description | Achieving rapid and effective object detection in large-scale unmanned aerial vehicle (UAV) images presents a challenge. Existing methods typically split the original large UAV image into overlapping patches and perform object detection on each image patch. However, the extensive object-free background areas in large-scale aerial imagery reduce detection efficiency. To address this issue, we propose an efficient object detection approach for large-scale UAV aerial imagery via multi-task classification. Specifically, we develop a lightweight multi-task classification (MTC) network to efficiently identify background areas. Our method leverages bounding box label information to construct a salient region generation branch. Then, to improve the training process of the classification network, we design a multi-task loss function to optimize the parameters of the multi-branch network. Furthermore, we introduce an optimal classification threshold strategy to balance detection speed and accuracy. Our proposed MTC network can rapidly and accurately determine whether an aerial image patch contains objects, and it can be seamlessly integrated with existing detectors without the need for retraining. We conduct experiments on three datasets to verify the effectiveness and efficiency of our classification-driven detection method, including the DOTA v1.0, DOTA v2.0, and ASDD datasets. In the large-scale UAV images and ASDD dataset, our proposed method increases the detection speed by more than 30% and 130%, respectively, while maintaining good object detection performance. |
| format | Article |
| id | doaj-art-a62c0001083949899c76a4936f348be2 |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-a62c0001083949899c76a4936f348be22025-01-24T13:29:42ZengMDPI AGDrones2504-446X2025-01-01912910.3390/drones9010029Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task ClassificationShuo Zhuang0Yongxing Hou1Di Wang2School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, ChinaSchool of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaAchieving rapid and effective object detection in large-scale unmanned aerial vehicle (UAV) images presents a challenge. Existing methods typically split the original large UAV image into overlapping patches and perform object detection on each image patch. However, the extensive object-free background areas in large-scale aerial imagery reduce detection efficiency. To address this issue, we propose an efficient object detection approach for large-scale UAV aerial imagery via multi-task classification. Specifically, we develop a lightweight multi-task classification (MTC) network to efficiently identify background areas. Our method leverages bounding box label information to construct a salient region generation branch. Then, to improve the training process of the classification network, we design a multi-task loss function to optimize the parameters of the multi-branch network. Furthermore, we introduce an optimal classification threshold strategy to balance detection speed and accuracy. Our proposed MTC network can rapidly and accurately determine whether an aerial image patch contains objects, and it can be seamlessly integrated with existing detectors without the need for retraining. We conduct experiments on three datasets to verify the effectiveness and efficiency of our classification-driven detection method, including the DOTA v1.0, DOTA v2.0, and ASDD datasets. In the large-scale UAV images and ASDD dataset, our proposed method increases the detection speed by more than 30% and 130%, respectively, while maintaining good object detection performance.https://www.mdpi.com/2504-446X/9/1/29classification networkefficient object detectionlarge-scale aerial imagerymulti-task optimization |
| spellingShingle | Shuo Zhuang Yongxing Hou Di Wang Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification Drones classification network efficient object detection large-scale aerial imagery multi-task optimization |
| title | Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification |
| title_full | Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification |
| title_fullStr | Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification |
| title_full_unstemmed | Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification |
| title_short | Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification |
| title_sort | towards efficient object detection in large scale uav aerial imagery via multi task classification |
| topic | classification network efficient object detection large-scale aerial imagery multi-task optimization |
| url | https://www.mdpi.com/2504-446X/9/1/29 |
| work_keys_str_mv | AT shuozhuang towardsefficientobjectdetectioninlargescaleuavaerialimageryviamultitaskclassification AT yongxinghou towardsefficientobjectdetectioninlargescaleuavaerialimageryviamultitaskclassification AT diwang towardsefficientobjectdetectioninlargescaleuavaerialimageryviamultitaskclassification |