{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:33:26Z","timestamp":1777340006656,"version":"3.51.4"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["SQ2022YFB4300022"],"award-info":[{"award-number":["SQ2022YFB4300022"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Drone-based object detection in adverse visual environments (AVEs) poses significant challenges that remain largely unaddressed by existing methods. Degraded image quality from fog and low-light conditions substantially impairs the detection performance of conventional algorithms optimized for ideal conditions. In this paper, we propose Physics-Guided Enhancement Mechanisms with Detection Transformer (PGEM-DETR), a novel framework tailored for drone-based object detection in AVEs. Our approach integrates physics-guided enhancement mechanisms with the DETR architecture, combining environmental prior knowledge with deep learning techniques to overcome visual degradation challenges. Extensive experiments on our comprehensive AVE-CARPK, AVE-DroneVehicle, and AVE-VisDrone datasets demonstrate that PGEM-DETR significantly outperforms state-of-the-art object detectors under adverse conditions while maintaining comparable computational efficiency. PGEM-DETR-M achieves 83.1% AP$_5{}_0$ and 58.1% AP$_5{}{}_0$:$_9{}_5$ on the AVE-CARPK dataset, surpassing YOLOV12-X by 2.7% and 2.3%, respectively, while requiring only 73% of its parameters and 69% of its computational complexity. Our lightweight PGEM-DETR-N achieves 142.7 FPS with INT8 quantization on Nvidia Jetson Orin NX, showing strong potential for UAV deployment, though real-world validation beyond simulated adverse environments is still required.<\/jats:p>","DOI":"10.1093\/jcde\/qwaf121","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:02:06Z","timestamp":1762520526000},"page":"60-74","source":"Crossref","is-referenced-by-count":2,"title":["PGEM-DETR: Physics-guided enhancement mechanism for drone-based object detection in adverse visual environments"],"prefix":"10.1093","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8752-9787","authenticated-orcid":false,"given":"Siyu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology , Wuhan 430063 , Hubei,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9800-6862","authenticated-orcid":false,"given":"Xiaohua","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology , Wuhan 430063 , Hubei,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology , Wuhan 430063 , Hubei,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6825-1453","authenticated-orcid":false,"given":"Jiale","family":"Li","sequence":"additional","affiliation":[{"name":"School of Transportation and Logistics Engineering, Wuhan University of Technology , Wuhan 430063 , Hubei,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"2026010204364051000_bib1","doi-asserted-by":"publisher","first-page":"10934","DOI":"10.48550\/arXiv.2004.10934","article-title":"Yolov4: Optimal speed and accuracy of object detection","volume-title":"arXiv preprint","author":"Bochkovskiy","year":"2020"},{"key":"2026010204364051000_bib2","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1093\/jcde\/qwaf031","article-title":"Multi-uav adaptive cooperative coverage search method based on area dynamic sensing","volume":"12","author":"Cao","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026010204364051000_bib3","first-page":"2847","article-title":"Visdrone-det2021: The vision meets drone object detection challenge results","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision\u00a0","author":"Cao","year":"2021"},{"key":"2026010204364051000_bib4","first-page":"3291","article-title":"Learning to see in the dark","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition\u00a0","author":"Chen","year":"2018"},{"key":"2026010204364051000_bib5","doi-asserted-by":"publisher","first-page":"47773","DOI":"10.1007\/s11042-023-15333-w","article-title":"Slbaf-net: Super-lightweight bimodal adaptive fusion network for uav detection in low recognition environment","volume":"82","author":"Cheng","year":"2023","journal-title":"Multimedia Tools and Applications"},{"key":"2026010204364051000_bib6","doi-asserted-by":"publisher","first-page":"4529","DOI":"10.1080\/01431161.2023.2197129","article-title":"Lightweight detection network for arbitrary-oriented vehicles in uav imagery via precise positional information encoding and bidirectional feature fusion","volume":"44","author":"Feng","year":"2023","journal-title":"International Journal of Remote Sensing"},{"key":"2026010204364051000_bib7","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.1109\/AINIT61980.2024.10581683","article-title":"Uav night target detection method based on improved yolov5","volume-title":"2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)\u00a0","author":"Gao","year":"2024"},{"key":"2026010204364051000_bib8","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026010204364051000_bib9","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/jcde\/qwaf043","article-title":"Unsupervised industrial anomaly detection using paired well-lit and low-light images","volume":"12","author":"Hoang","year":"2025","journal-title":"Journal of Computational Design and Engineering"},{"key":"2026010204364051000_bib10","first-page":"4145","article-title":"Drone-based object counting by spatially regularized regional proposal network","volume-title":"Proceedings of the IEEE International Conference on Computer Vision\u00a0","author":"Hsieh","year":"2017"},{"key":"2026010204364051000_bib11","first-page":"12787","article-title":"Monoindoor: Towards good practice of self-supervised monocular depth estimation for indoor environments","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision\u00a0","author":"Ji","year":"2021"},{"key":"2026010204364051000_bib12","article-title":"Yolov11: An overview of the key architectural enhancements","author":"Khanam","year":"2024"},{"key":"2026010204364051000_bib13","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0065-2687(08)60323-4","article-title":"Symmetric circulations of planetary atmospheres","volume-title":"Advances in Geophysics\u00a0","author":"Koschmieder","year":"1978"},{"key":"2026010204364051000_bib14","first-page":"1428A","article-title":"Lightness and retinex theory","volume":"58","author":"Land","year":"1967","journal-title":"J. Opt. Soc. Am."},{"key":"2026010204364051000_bib15","doi-asserted-by":"publisher","first-page":"5163","DOI":"10.1073\/pnas.80.16.5163","article-title":"Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image","volume":"80","author":"Land","year":"1983","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2026010204364051000_bib16","doi-asserted-by":"publisher","first-page":"68791","DOI":"10.1109\/ACCESS.2023.3293124","article-title":"Cnn-based uav detection and classification using sensor fusion","volume":"11","author":"Lee","year":"2023","journal-title":"IEEE Access"},{"key":"2026010204364051000_bib17","article-title":"Yolov13: Real-time object detection with hypergraph-enhanced adaptive visual perception","author":"Lei","year":"2025"},{"key":"2026010204364051000_bib18","first-page":"4770","article-title":"Aod-net: All-in-one dehazing network","volume-title":"Proceedings of the IEEE International Conference on Computer Vision\u00a0","author":"Li","year":"2017"},{"key":"2026010204364051000_bib19","article-title":"Yolov6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"2026010204364051000_bib20","first-page":"16794","article-title":"Large selective kernel network for remote sensing object detection","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision\u00a0\u00a0","author":"Li","year":"2023"},{"key":"2026010204364051000_bib21","doi-asserted-by":"publisher","first-page":"114602","DOI":"10.1016\/j.eswa.2021.114602","article-title":"A survey and performance evaluation of deep learning methods for small object detection","volume":"172","author":"Liu","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"2026010204364051000_bib22","article-title":"Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer","author":"Lv","year":"2024"},{"key":"2026010204364051000_bib23","doi-asserted-by":"publisher","first-page":"358","DOI":"10.17723\/aarc.52.3.n0n8078h22p4341x","article-title":"Development of the presnet subject descriptor thesaurus","author":"McNitt","year":"1989","journal-title":"The American Archivist"},{"key":"2026010204364051000_bib24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-031-34851-8_1","article-title":"Tf-net: Deep learning empowered tiny feature network for night-time uav detection","volume-title":"International Conference on Wireless and Satellite Systems\u00a0","author":"Misbah","year":"2023"},{"key":"2026010204364051000_bib25","doi-asserted-by":"publisher","first-page":"104046","DOI":"10.1016\/j.imavis.2020.104046","article-title":"Deep learning-based object detection in low-altitude uav datasets: A survey","volume":"104","author":"Mittal","year":"2020","journal-title":"Image and Vision Computing"},{"key":"2026010204364051000_bib26","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/CogMI52975.2021.00037","article-title":"A hybrid deep learning model for uavs detection in day and night dual visions","volume-title":"2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI)","author":"Noor","year":"2021"},{"key":"2026010204364051000_bib27","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"2026010204364051000_bib28","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.3390\/s23031261","article-title":"Multiple attention mechanism enhanced yolox for remote sensing object detection","volume":"23","author":"Shen","year":"2023","journal-title":"Sensors"},{"key":"2026010204364051000_bib29","first-page":"529","article-title":"A review on yolov8 and its advancements","volume-title":"International Conference on Data Intelligence and Cognitive Informatics\u00a0","author":"Sohan","year":"2024"},{"key":"2026010204364051000_bib30","doi-asserted-by":"publisher","first-page":"6700","DOI":"10.1109\/TCSVT.2022.3168279","article-title":"Drone-based rgb-infrared cross-modality vehicle detection via uncertainty-aware learning","volume":"32","author":"Sun","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2026010204364051000_bib31","doi-asserted-by":"publisher","first-page":"6614","DOI":"10.1109\/ICRA57147.2024.10610273","article-title":"Hic-yolov5: Improved yolov5 for small object detection","volume-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Tang","year":"2024"},{"key":"2026010204364051000_bib32","article-title":"Yolov12: Attention-centric real-time object detectors","author":"Tian","year":"2025"},{"key":"2026010204364051000_bib33","doi-asserted-by":"publisher","first-page":"103910","DOI":"10.1016\/j.imavis.2020.103910","article-title":"Recent advances in small object detection based on deep learning: A review","volume":"97","author":"Tong","year":"2020","journal-title":"Image and Vision Computing"},{"key":"2026010204364051000_bib34","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1002\/9781119769262.ch4","article-title":"Res-se-net: Boosting performance of resnets by enhancing bridge connections","author":"Varshaneya","year":"2021","journal-title":"Machine Learning Algorithms and Applications"},{"key":"2026010204364051000_bib35","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026010204364051000_bib36","first-page":"7464","article-title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0","author":"Wang","year":"2023"},{"key":"2026010204364051000_bib37","first-page":"1","article-title":"Yolov9: Learning what you want to learn using programmable gradient information","volume-title":"European Conference on Computer Vision\u00a0","author":"Wang","year":"2024"},{"key":"2026010204364051000_bib38","doi-asserted-by":"publisher","first-page":"8205","DOI":"10.1609\/aaai.v39i8.32885","article-title":"Mamba yolo: A simple baseline for object detection with state space model","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence\u00a0","author":"Wang","year":"2025"},{"key":"2026010204364051000_bib39","first-page":"3","article-title":"Cbam: Convolutional block attention module","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Woo","year":"2018"},{"key":"2026010204364051000_bib40","doi-asserted-by":"publisher","first-page":"e0259283","DOI":"10.1371\/journal.pone.0259283","article-title":"Application of local fully convolutional neural network combined with yolo v5 algorithm in small target detection of remote sensing image","volume":"16","author":"Wu","year":"2021","journal-title":"PloS one"},{"key":"2026010204364051000_bib41","first-page":"13668","article-title":"Querydet: Cascaded sparse query for accelerating high-resolution small object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0","author":"Yang","year":"2022"},{"key":"2026010204364051000_bib42","doi-asserted-by":"publisher","first-page":"5182","DOI":"10.3390\/app11115182","article-title":"Uav detection with transfer learning from simulated data of laser active imaging","volume":"11","author":"Zhang","year":"2021","journal-title":"Applied Sciences"},{"key":"2026010204364051000_bib43","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0","author":"Zhao","year":"2024"},{"key":"2026010204364051000_bib44","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwaf121\/65246953\/qwaf121.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/1\/60\/65246953\/qwaf121.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/13\/1\/60\/65246953\/qwaf121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T09:36:50Z","timestamp":1767346610000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/13\/1\/60\/8317245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwaf121","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,11,8]]}}}