RTDOD: A large-scale RGB-thermal domain-incremental object detection dataset for UAVs

doi:10.1016/j.imavis.2023.104856

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	RTDOD: A large-scale RGB-thermal domain-incremental object detection dataset for UAVs
	Feng, Hangtao 1,2; Zhang, Lu 1,2; Zhang, Siqi 1,2; Wang, Dong 3; Yang, Xu 1,2; Liu, Zhiyong 1,2,4
刊名	IMAGE AND VISION COMPUTING
	2023-12-01
卷号	140 页码:9
关键词	Domain -incremental object detection Dataset RGB-T dataset Object detection dataset UAVs dataset Object detection
ISSN号	0262-8856
DOI	10.1016/j.imavis.2023.104856
通讯作者	Liu, Zhiyong(zhiyong.liu@ia.ac.cn)
英文摘要	Recently, visual understanding using unmanned aerial vehicles (UAVs) has gained significant attention due to its wide range of applications, including delivery, security investigation and surveillance. However, most existing UAV-based datasets only capture color images under ideal illumination and weather conditions, typically sunny days. This limitation fails to account for the complexity of real-world scenarios, such as cloudy or foggy weather, and nighttime conditions. Deep learning methods trained on color images with good lighting and weather conditions struggle to adapt to the complex visual scenes in these scenarios. Moreover, color images may not provide sufficient visual information under the complex visual scenes. To bridge this gap and meet the demands of real-world applications, we propose a large-scale RGB-Thermal Domain-incremental Object Detection (RTDOD) dataset in this paper. Our dataset includes RGB and thermal videos synchronously captured using calibrated color thermal cameras mounted on UAVs. It covers various weather conditions, from sunny to foggy to rainy, and spans from day to night. We sample and obtain approximately 16,200 pairs of images, and manually label dense annotations, including object bounding boxes and object categories. With the proposed dataset, we introduce a challenging domain-incremental object detection task. We also present a baseline approach that uses task-related gates to filter features for knowledge distillation to reduce forgetting. Experimental results on the RTDOD dataset demonstrate the effectiveness of our proposed method in domain-incremental object detection. To facilitate future research and development in domain-incremental object detection tasks on aerial images, the RTDOD dataset and our baseline model are made available at https://github.com/fenght96/RTDOD. ARTICLE INFO.
资助项目	National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100]
WOS研究方向	Computer Science ; Engineering ; Optics
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001108709000001
资助机构	National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Academy of Science
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/55119]
专题	多模态人工智能系统全国重点实验室
通讯作者	Liu, Zhiyong
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 3.Army Engn Univ PLA, Nanjing, Peoples R China 4.Nanjing Artificial Intelligence Res IA, Nanjing, Peoples R China
推荐引用方式 GB/T 7714	Feng, Hangtao,Zhang, Lu,Zhang, Siqi,et al. RTDOD: A large-scale RGB-thermal domain-incremental object detection dataset for UAVs[J]. IMAGE AND VISION COMPUTING,2023,140:9.
APA	Feng, Hangtao,Zhang, Lu,Zhang, Siqi,Wang, Dong,Yang, Xu,&Liu, Zhiyong.(2023).RTDOD: A large-scale RGB-thermal domain-incremental object detection dataset for UAVs.IMAGE AND VISION COMPUTING,140,9.
MLA	Feng, Hangtao,et al."RTDOD: A large-scale RGB-thermal domain-incremental object detection dataset for UAVs".IMAGE AND VISION COMPUTING 140(2023):9.