{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T10:50:15Z","timestamp":1774349415480,"version":"3.50.1"},"reference-count":44,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovative Human Resource Development for Local Intellectualization Program"},{"name":"The Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korea Government","award":["IITP-2024-RS-202s2-00156287, 50 and RS-2021-II212068"],"award-info":[{"award-number":["IITP-2024-RS-202s2-00156287, 50 and RS-2021-II212068"]}]},{"name":"Princess Nourah bint Abdulrahman University Researchers, Riyadh, Saudi Arabia","award":["PNURSP2026R97"],"award-info":[{"award-number":["PNURSP2026R97"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Deep learning has significantly advanced object detection and scene understanding, yet analyzing uncrewed aerial vehicle (UAV)-based hyperspectral imagery remains challenging due to its high spectral complexity and cluttered scenes. Most existing approaches address either detection or segmentation separately, or rely on limited data modalities, which constrains their effectiveness in complex aerial scenarios. To address this gap, we propose AeroResNet-Vision (ARV), a novel multimodal fusion framework for UAV imagery. ARV integrates state-of-the-art techniques into a unified pipeline: a ResNet-based DeepLabv3++ module for multi-scale semantic segmentation, classical Binary Robust Invariant Scalable Keypoints (BRISK), Maximally stable Extrema Regions (MSER) detectors for keypoint and region feature extraction, (You Only Look Once, version 8) YOLOv8 for efficient object detection, and a Vision Transformer (ViT) for context-aware classification. Additionally, image normalization and edge detection preprocessing are applied to enhance image quality and emphasize structural features. By fusing handcrafted and deep features from these components, ARV effectively handles varying object scales and complex backgrounds in aerial data. Experimental results on three benchmark datasets (ISPRS Potsdam, VEDAI, UAVid) demonstrate state-of-the-art accuracy\u2014for instance, ARV achieved 97.20%, 98.50%, and 97.60% accuracy on these datasets, respectively. These findings validate the framework\u2019s superior performance in UAV image analysis. In conclusion, the proposed multimodal approach provides a robust solution for aerial object recognition, and we recommend exploring lightweight model variants and self-supervised learning to further enhance its deployment potential.<\/jats:p>","DOI":"10.7717\/peerj-cs.3648","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T08:20:22Z","timestamp":1774340422000},"page":"e3648","source":"Crossref","is-referenced-by-count":0,"title":["A novel deep learning-based object detection along semantic segmentation on aerial imagery"],"prefix":"10.7717","volume":"12","author":[{"given":"Maha","family":"Abdelhaq","sequence":"first","affiliation":[{"name":"Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aysha","family":"Naseer","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Air University, Islamabad, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raed","family":"Alsaqour","sequence":"additional","affiliation":[{"name":"Department of Information Technology, College of Computing and Informatics, Saudi Electronic University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Jalal","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, College of Informatics, Korea University, Seoul, South Korea"},{"name":"Department of Computer Science, Air University, Islamabad, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Asif","family":"Jamal","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Air University, Islamabad, Pakistan"},{"name":"Department of Information and Communication Engineering, Chosun University, Gwangju, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aamir","family":"Nadeem","sequence":"additional","affiliation":[{"name":"Department of Intelligent Electronics and Computer Engineering, Chonnam National University, Gwangju, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2433-4473","authenticated-orcid":true,"given":"Jinsul","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Intelligent Electronics and Computer Engineering, Chonnam National University, Gwangju, Republic of South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"10.7717\/peerj-cs.3648\/ref-1","doi-asserted-by":"crossref","DOI":"10.1109\/ICACS64902.2025.10937878","article-title":"Multi-vehicles classification on aerial images using ResNet and transformer networks","author":"Ahmed","year":"2025"},{"issue":"19","key":"10.7717\/peerj-cs.3648\/ref-2","doi-asserted-by":"publisher","first-page":"14597","DOI":"10.3390\/su151914597","article-title":"Vehicle detection and classification via YOLOv8 and deep belief network over aerial image sequences","volume":"15","author":"Al Mudawi","year":"2023","journal-title":"Sustainability"},{"issue":"11","key":"10.7717\/peerj-cs.3648\/ref-3","doi-asserted-by":"publisher","first-page":"33351","DOI":"10.1007\/s11042-023-16828-2","article-title":"Automated segmentation of brain tumour images using deep learning-based model VGG19 and ResNet 101","volume":"83","author":"Ali","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.3648\/ref-4","first-page":"203","article-title":"Feature detection and extraction techniques with different similarity measures using bag of features scheme","author":"Ali","year":"2023"},{"key":"10.7717\/peerj-cs.3648\/ref-5","first-page":"83","article-title":"An approach for vehicle\u2019s classification using BRISK feature extraction","author":"Amiruddin","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-6","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/s11063-020-10280-1","article-title":"A novel technique for segmentation of high-resolution remote sensing images based on neural networks","volume":"52","author":"Barr","year":"2020","journal-title":"Neural Processing Letters"},{"key":"10.7717\/peerj-cs.3648\/ref-7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2021.3065438","article-title":"YOLOv4-5D: an effective and efficient object detector for autonomous driving","volume":"70","author":"Cai","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.7717\/peerj-cs.3648\/ref-8","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder decoder with atrous separable convolution for semantic image segmentation","volume":"11211","author":"Chen","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"10.7717\/peerj-cs.3648\/ref-9","first-page":"2286","article-title":"ConViT: improving vision transformers with soft convolutional inductive biases","author":"D\u2019Ascoli","year":"2021"},{"key":"10.7717\/peerj-cs.3648\/ref-10","first-page":"45","article-title":"Evaluation metrics and evaluation","author":"Dalianis","year":"2018"},{"key":"10.7717\/peerj-cs.3648\/ref-11","article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.7717\/peerj-cs.3648\/ref-12","first-page":"211","article-title":"Advanced domain adaptation technique for object detection leveraging semi-automated dataset construction and enhanced YOLOv8","author":"Gomaa","year":"2024"},{"issue":"6","key":"10.7717\/peerj-cs.3648\/ref-13","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/wevj15060255","article-title":"Novel deep learning domain adaptation approach for object detection using semi-self-building dataset and modified YOLOv4","volume":"15","author":"Gomaa","year":"2024","journal-title":"World Electric Vehicle Journal"},{"key":"10.7717\/peerj-cs.3648\/ref-14","article-title":"Maximum categorical cross entropy (MCCE): a noise-robust alternative loss function to mitigate racial bias in convolutional neural networks (CNNs) by reducing overfitting","author":"Gowdra","year":"2021"},{"key":"10.7717\/peerj-cs.3648\/ref-15","doi-asserted-by":"crossref","DOI":"10.1109\/ICECT61618.2024.10581338","article-title":"Vehicle surveillance using U-NET segmentation and DeepSORT over aerial images","author":"Hanzla","year":"2024"},{"issue":"12","key":"10.7717\/peerj-cs.3648\/ref-16","doi-asserted-by":"publisher","first-page":"5349","DOI":"10.1109\/tnnls.2020.2966319","article-title":"Why ResNet works? Residuals generalize","volume":"31","author":"He","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"10.7717\/peerj-cs.3648\/ref-17","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.gltp.2021.08.027","article-title":"ResNet-50 vs VGG-19 vs training from scratch: a comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images","volume":"2","author":"Ikechukwu","year":"2021","journal-title":"Global Transitions Proceedings"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-18","doi-asserted-by":"publisher","first-page":"131437","DOI":"10.1016\/j.neucom.2025.131437","article-title":"DentSeg-EDA: a 3D tooth segmentation framework for CBCT images using enhanced dual attention","volume":"655","author":"Jamal","year":"2025","journal-title":"Neurocomputing"},{"issue":"4","key":"10.7717\/peerj-cs.3648\/ref-19","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.21923\/jesd.1087477","article-title":"U-Net based car detection method for unmanned aerial vehicles","volume":"10","author":"Katar","year":"2022","journal-title":"Journal of Engineering Science and Design"},{"issue":"10","key":"10.7717\/peerj-cs.3648\/ref-20","doi-asserted-by":"publisher","first-page":"601","DOI":"10.3390\/ijgi9100601","article-title":"Semantic segmentation of remote-sensing imagery using heterogeneous big data: international society for photogrammetry and remote sensing Potsdam and Cityscape datasets","volume":"9","author":"Kim","year":"2020","journal-title":"ISPRS International Journal of Geo-Information"},{"issue":"5","key":"10.7717\/peerj-cs.3648\/ref-21","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.29207\/resti.v7i5.5034","article-title":"MSER-vertical sobel for vehicle logo detection","volume":"7","author":"Kosala","year":"2023","journal-title":"Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)"},{"issue":"3","key":"10.7717\/peerj-cs.3648\/ref-22","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1561\/9781680831177","article-title":"Object detection and segmentation with YOLOv5 and deep learning techniques","volume":"89","author":"Li","year":"2022","journal-title":"Journal of Computer Vision"},{"issue":"13","key":"10.7717\/peerj-cs.3648\/ref-23","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.3390\/rs14133109","article-title":"RAANet: a residual ASPP with attention framework for semantic segmentation of high-resolution remote sensing images","volume":"14","author":"Liu","year":"2022","journal-title":"Remote Sensing"},{"key":"10.7717\/peerj-cs.3648\/ref-24","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/978-3-030-58555-6_13","article-title":"UAVid: A semantic segmentation dataset for UAV imagery","volume-title":"Computer Vision\u2013ECCV, 2020 Workshops","author":"Lyu","year":"2020"},{"key":"10.7717\/peerj-cs.3648\/ref-25","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","article-title":"UAVid: a semantic segmentation dataset for UAV imagery","volume":"165","author":"Lyu","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.7717\/peerj-cs.3648\/ref-26","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3372190","article-title":"Efficient multi-object recognition using GMM segmentation feature fusion approach","author":"Naseer","year":"2024"},{"key":"10.7717\/peerj-cs.3648\/ref-27","first-page":"512","article-title":"What is being transferred in transfer learning?","volume":"33","author":"Neyshabur","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.7717\/peerj-cs.3648\/ref-28","first-page":"1","article-title":"Vehicle detection in aerial imagery using a miniature CNN architecture","author":"Ozturk","year":"2021"},{"issue":"9","key":"10.7717\/peerj-cs.3648\/ref-29","doi-asserted-by":"publisher","first-page":"14224","DOI":"10.1109\/tits.2022.3155072","article-title":"The drone scheduling problem: a systematic state-of-the-art review","volume":"23","author":"Pasha","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.7717\/peerj-cs.3648\/ref-30","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1109\/access.2023.3234281","article-title":"Smart traffic monitoring through pyramid pooling vehicle detection and filter-based tracking on aerial images","volume":"11","author":"Rafique","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3648\/ref-31","first-page":"779","article-title":"You only look once: unified, 546 real-time object detection","author":"Redmon","year":"2016"},{"issue":"8","key":"10.7717\/peerj-cs.3648\/ref-32","doi-asserted-by":"publisher","first-page":"3146","DOI":"10.1080\/01431161.2020.1871100","article-title":"A semantic segmentation method with category boundary for land use and land cover (LULC) mapping of very-high-resolution (VHR) remote sensing images","volume":"42","author":"Su","year":"2021","journal-title":"International Journal of Remote Sensing"},{"key":"10.7717\/peerj-cs.3648\/ref-33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.07628","article-title":"Faster RER-CNN: application to the detection of vehicles in aerial images","author":"Terrail","year":"2018"},{"issue":"17","key":"10.7717\/peerj-cs.3648\/ref-34","doi-asserted-by":"publisher","first-page":"4709","DOI":"10.3390\/s20174709","article-title":"An improved FBPN-based detection network for vehicles in aerial images","volume":"20","author":"Wang","year":"2020","journal-title":"Sensors"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-35","doi-asserted-by":"publisher","first-page":"7600","DOI":"10.1038\/s41598-023-34379-2","article-title":"A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved U-Net","volume":"13","author":"Wang","year":"2023","journal-title":"Scientific Reports"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-36","doi-asserted-by":"publisher","first-page":"e0261582","DOI":"10.1371\/journal.pone.0261582","article-title":"An improved DeepLabv3++ semantic segmentation algorithm with multiple loss constraints","volume":"17","author":"Wang","year":"2022","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj-cs.3648\/ref-37","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3385985","article-title":"Oriented object detection via contextual dependence mining and penalty-incentive allocation","author":"Xie","year":"2024"},{"issue":"12","key":"10.7717\/peerj-cs.3648\/ref-38","doi-asserted-by":"publisher","first-page":"15171","DOI":"10.1109\/tpami.2023.3319634","article-title":"Mutual-assistance learning for object detection","volume":"45","author":"Xie","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-39","doi-asserted-by":"publisher","first-page":"123","DOI":"10.2139\/ssrn.4402770","article-title":"Enhancing vision transformers with multi-scale feature fusion for image classification","volume":"34","author":"Xu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.7717\/peerj-cs.3648\/ref-40","article-title":"VEDAI: a dataset for vehicle detection in aerial imagery","author":"Yang","year":"2018"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42452-021-04897-7","article-title":"A novel ResNet101\u00a0model based on dense dilated convolution for image classification","volume":"4","author":"Zhang","year":"2022","journal-title":"SN Applied Sciences"},{"issue":"1","key":"10.7717\/peerj-cs.3648\/ref-42","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1093\/comjnl\/bxac171","article-title":"A hybrid-convolution spatial-temporal recurrent network for traffic flow prediction","volume":"10","author":"Zhang","year":"2022","journal-title":"The Computer Journal"},{"issue":"11","key":"10.7717\/peerj-cs.3648\/ref-43","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/tnnls.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.7717\/peerj-cs.3648\/ref-44","first-page":"1473","article-title":"Scene-aware label graph learning for multi-label image classification","author":"Zhu","year":"2023"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3648.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3648.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3648.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3648.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T08:20:31Z","timestamp":1774340431000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":44,"alternative-id":["10.7717\/peerj-cs.3648"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3648","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]},"article-number":"e3648"}}