{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:58:05Z","timestamp":1777276685555,"version":"3.51.4"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Under low-light conditions, the accuracy of drone-view object detection algorithms is frequently compromised by noise and insufficient illumination. Herein, we propose a parallel neural network that concurrently performs image enhancement and object detection for drone-view object detection in nighttime environments. Our innovative coevolutionary framework establishes bidirectional gradient propagation pathways between network modules, improving the robustness of feature representations through the joint optimization of the photometric correction and detection objectives. The illumination enhancement network employs Zero-DCE++, which adaptively adjusts the brightness distribution without requiring paired training data. In our model, object detection is performed using a lightweight YOLOv5 architecture that exhibits good detection accuracy while maintaining real-time performance. To further optimize feature extraction, we introduce a spatially adaptive feature modulation module and a high- and low-frequency adaptive feature enhancement block. The former dynamically modulates the input features through multiscale feature fusion, enhancing the ability of the model to perceive local and global information. The latter module enhances semantic representation and edge details through the parallel processing of spatial contextual information and feature refinement. Experiments on the two data sets of VisDrone2019 (Night) and Drone Vehicle (Night) show that the proposed method improves 3.13 and 3.1% compared with the traditional YOLOv5 method mAP@0.5:0.95, and improves 6.3 and 2% in mAP@0.5, especially in the extreme low light and high noise environment.<\/jats:p><jats:p>Thus, the proposed parallel model is an efficient and reliable solution for drone-based nighttime visual monitoring.<\/jats:p>","DOI":"10.3389\/frai.2025.1622100","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:28:13Z","timestamp":1758518893000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Parallel joint encoding for drone-view object detection under low-light conditions"],"prefix":"10.3389","volume":"8","author":[{"given":"Liwen","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyu","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"ref1","author":"Cao","year":"2021"},{"key":"ref2","author":"Chen","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"106077","DOI":"10.1016\/j.sysconle.2025.106077","article-title":"Reinforcement-learning-based control framework for leader-following cascade formation of multiple perturbed surface vehicles","volume":"200","author":"Dao","year":"2025","journal-title":"Syst. Control Lett."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550298","article-title":"Geryon: edge assisted real-time and robust object detection on drones via mmWave radar and camera fusion","volume":"6","author":"Deng","year":"2022","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref6","author":"Guo","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1093\/comjnl\/bxab055","article-title":"Ledet: a single-shot real-time object detector based on low-light image enhancement","volume":"64","author":"Hao","year":"2021","journal-title":"Comput. J."},{"key":"ref8","author":"Hendrycks","year":"2016"},{"key":"ref9","author":"Hu","year":"2018"},{"key":"ref10","author":"Hu","year":"2018"},{"key":"ref11","author":"Jin","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3543270","article-title":"DREB-net: dual-stream restoration embedding blur-feature fusion network for high-mobility UAV object detection","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"111171","DOI":"10.1016\/j.automatica.2023.111171","article-title":"Off-policy inverse Q-learning for discrete-time antagonistic unknown systems","volume":"155","author":"Lian","year":"2023","journal-title":"Automatica"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"653","DOI":"10.3390\/drones8110653","article-title":"Li-yolo: an object detection algorithm for UAV aerial images in low-illumination scenes","volume":"8","author":"Liu","year":"2024","journal-title":"Drones"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1007\/s11263-020-01418-8","article-title":"Benchmarking low-light image enhancement and beyond","volume":"129","author":"Liu","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"108972","DOI":"10.1016\/j.ast.2024.108972","article-title":"On-policy and off-policy Q-learning strategies for spacecraft systems: an approach for time-varying discrete-time without controllability assumption of augmented system","volume":"146","author":"Nguyen","year":"2024","journal-title":"Aerosp. Sci. Technol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2252","DOI":"10.1002\/rnc.7083","article-title":"Formation control scheme with reinforcement learning strategy for a group of multiple surface vehicles","volume":"34","author":"Nguyen","year":"2024","journal-title":"Int. J. Robust. Nonlinear Control."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.3390\/rs16132465","article-title":"A small-object detection model based on improved YOLOv8s for UAV image scenarios","volume":"16","author":"Ni","year":"2024","journal-title":"Remote Sens"},{"key":"ref19","author":"Nie","year":"2019"},{"key":"ref20","author":"Shi","year":"2016"},{"key":"ref21","author":"Wang","year":"2020"},{"key":"ref22","author":"Wang","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"4580","DOI":"10.3390\/rs15184580","article-title":"Smff-yolo: a scale-adaptive yolo algorithm with multi-level feature fusion for object detection in uav scenes","volume":"15","author":"Wang","year":"2023","journal-title":"Remote Sens"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"3807","DOI":"10.1002\/rnc.6597","article-title":"Reinforcement learning-based optimal trajectory tracking control of surface vessels under input saturations","volume":"33","author":"Wei","year":"2023","journal-title":"Int. J. Robust. Nonlinear Control."},{"key":"ref25","author":"Xiong","year":"2022"},{"key":"ref26","author":"Xu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s44196-024-00632-3","article-title":"Small object detection in UAV images based on Yolov8n","volume":"17","author":"Xu","year":"2024","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref28","author":"Zamir","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1934","DOI":"10.1109\/TPAMI.2022.3167175","article-title":"Learning enriched features for fast image restoration and enhancement","volume":"2022","author":"Zamir","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.3390\/electronics12143141","article-title":"Yolov7-uav: an unmanned aerial vehicle image object detection algorithm based on improved yolov7","volume":"12","author":"Zeng","year":"2023","journal-title":"Electronics"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1622100\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:28:14Z","timestamp":1758518894000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1622100\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":30,"alternative-id":["10.3389\/frai.2025.1622100"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1622100","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"article-number":"1622100"}}