{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T01:53:50Z","timestamp":1792979630418,"version":"4.5.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"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. Neurorobot."],"abstract":"<jats:p>Unmanned surface vessel (USV) target detection algorithms often face challenges such as misdetection and omission of small targets due to significant variations in target scales and susceptibility to interference from complex environments. To address these issues, we propose a small target enhanced YOLOv7 (STE-YOLO) approach. Firstly, we introduce a specialized detection branch designed to identify tiny targets. This enhancement aims to improve the multi-scale target detection capabilities and address difficulties in recognizing targets of different sizes. Secondly, we present the lite visual center (LVC) module, which effectively fuses data from different levels to give more attention to small targets. Additionally, we integrate the lite efficient layer aggregation networks (L-ELAN) into the backbone network to reduce redundant computations and enhance computational efficiency. Lastly, we use Wise-IOU to optimize the loss function definition, thereby improving the model robustness by dynamically optimizing gradient contributions from samples of varying quality. We conducted experiments on the WSODD dataset and the FIOW-Img dataset. The results on the comprehensive WSODD dataset demonstrate that STE-YOLO, when compared to YOLOv7, reduces network parameters by 14% while improving AP50 and APs scores by 2.1% and 1.6%, respectively. Furthermore, when compared to five other leading target detection algorithms, STE-YOLO demonstrates superior accuracy and efficiency.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1315251","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T08:53:34Z","timestamp":1702544014000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces"],"prefix":"10.3389","volume":"17","author":[{"given":"Jie","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,12,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"YOLOv4: optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv"},{"key":"B2","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"\u201cEnd-to-end object detection with transformers,\u201d","author":"Carion","year":"2020","journal-title":"Computer Vision-ECCV 2020"},{"key":"B3","unstructured":"\u201cRun, don't walk: chasing higher flops for faster neural networks,\u201d1202112031\n            ChenJ.\n            KaoS.-h.\n            HeH.\n            ZhuoW.\n            WenS.\n            LeeC.-H.\n            ChanS.-H. G.\n          10.1109\/CVPR52729.2023.011572023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2023"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1080616","DOI":"10.1117\/12.2503030","article-title":"\u201cA maritime targets detection method based on hierarchical and multi-scale deep convolutional neural network,\u201d","author":"Chen","year":"2018","journal-title":"Tenth International Conference on Digital Image Processing (ICDIP 2018)"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/jmse11050995","article-title":"Underwater-ycc: underwater target detection optimization algorithm based on YOLOv7","author":"Chen","year":"2023","journal-title":"J. Mar. Sci. Eng"},{"key":"B6","first-page":"10953","article-title":"\u201cFlow: a dataset and benchmark for floating waste detection in inland waters,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Cheng","year":"2021"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1109\/TMM.2021.3074273","article-title":"Extended feature pyramid network for small object detection","volume":"24","author":"Deng","year":"2022","journal-title":"IEEE Trans. Multimedia"},{"key":"B8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.08430","article-title":"YOLOX: exceeding yolo series in 2021","author":"Ge","year":"2021","journal-title":"arXiv"},{"key":"B10","doi-asserted-by":"crossref","first-page":"7029","DOI":"10.1109\/CVPR.2019.00720","article-title":"\u201cNAS-FPN: learning scalable feature pyramid architecture for object detection,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ghiasi","year":"2019"},{"key":"B11","doi-asserted-by":"publisher","first-page":"19449","DOI":"10.1007\/s10489-023-04544-1","article-title":"An enhanced ssd with feature cross-reinforcement for small-object detection","volume":"53","author":"Gong","year":"2023","journal-title":"Appl. Intell"},{"key":"B12","doi-asserted-by":"crossref","first-page":"2980","DOI":"10.1109\/ICCV.2017.322","article-title":"\u201cMask R-CNN,\u201d","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV)","author":"He","year":"2017"},{"key":"B13","unstructured":"JocherG.\n            StokenA.\n            BorovecJ.\n            ChaurasiaA.\n            TaoXie ChangyuL.\n          ultralytics\/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation. Zenodo2022"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.07296","article-title":"Augmentation for small object detection","author":"Kisantal","year":"2019","journal-title":"arXiv"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.106","article-title":"\u201cFeature pyramid networks for object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":"2017"},{"key":"B16","article-title":"\u201cMicrosoft COCO: Common Objects in Context,\u201d","author":"Lin","year":"2014","journal-title":"Computer Vision - ECCV 2014. ECCV 2014. Lecture Notes in Computer Science"},{"key":"B17","first-page":"9605","article-title":"\u201cAn intriguing failing of convolutional neural networks and the coordconv solution,\u201d","author":"Liu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B18","doi-asserted-by":"crossref","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"\u201cSwin transformer: hierarchical vision transformer using shifted windows,\u201d","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Liu","year":"2021"},{"key":"B19","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1109\/CVPRW.2019.00121","article-title":"\u201cA benchmark for deep learning based object detection in maritime environments,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Moosbauer","year":"2019"},{"key":"B20","doi-asserted-by":"crossref","first-page":"4763","DOI":"10.1109\/CVPR52688.2022.00473","article-title":"\u201cBoxeR: box-attention for 2D and 3D transformers,\u201d","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Nguyen","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","article-title":"Centralized feature pyramid for object detection","volume":"32","author":"Quan","year":"2023","journal-title":"IEEE Trans. Image Process"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B23","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1109\/IGARSS46834.2022.9884546","article-title":"\u201cEnhanced single-shot detector for small object detection in remote sensing images,\u201d","volume-title":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","author":"Shamsolmoali","year":"2022"},{"key":"B24","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1109\/BigComp48618.2020.00-25","article-title":"\u201cData augmentation method of object detection for deep learning in maritime image,\u201d","volume-title":"2020 IEEE International Conference on Big Data and Smart Computing (BigComp)","author":"Shin","year":"2020"},{"key":"B25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.neunet.2023.03.017","article-title":"Multi-level feature interaction and efficient non-local information enhanced channel attention for image dehazing","volume":"163","author":"Sun","year":"2023","journal-title":"Neural Netw"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3737","DOI":"10.1007\/s00521-021-06296-w","article-title":"Scale-free heterogeneous cyclegan for defogging from a single image for autonomous driving in fog","volume":"35","author":"Sun","year":"2021","journal-title":"Neural Comput. Appl"},{"key":"B27","doi-asserted-by":"crossref","first-page":"10778","DOI":"10.1109\/CVPR42600.2020.01079","article-title":"\u201cEfficientdet: scalable and efficient object detection,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tan","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1109\/TPAMI.2020.3032166","article-title":"FCOS: a simple and strong anchor-free object detector","volume":"44","author":"Tian","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B29","first-page":"24261","article-title":"\u201cMlp-mixer: an all-mlp architecture for vision,\u201d","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.10051","article-title":"Wise-IoU: bounding box regression loss with dynamic focusing mechanism","author":"Tong","year":"2023","journal-title":"arXiv"},{"key":"B31","author":"Vaswani","year":"2017"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.1109\/TIP.2023.3261749","article-title":"Precise facial landmark detection by reference heatmap transformer","volume":"32","author":"Wan","year":"2023","journal-title":"IEEE Trans. Image Process"},{"key":"B33","doi-asserted-by":"crossref","first-page":"13024","DOI":"10.1109\/CVPR46437.2021.01283","article-title":"\u201cScaled-YOLOv4: scaling cross stage partial network,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","year":"2021"},{"key":"B34","first-page":"7464","article-title":"\u201cYOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","year":"2023"},{"key":"B35","doi-asserted-by":"crossref","first-page":"9196","DOI":"10.1109\/ICCV.2019.00929","article-title":"\u201cPanet: few-shot image semantic segmentation with prototype alignment,\u201d","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang","year":"2019"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.09748","article-title":"DeepLab2: a tensorflow library for deep labeling","author":"Weber","year":"2021","journal-title":"arXiv"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.00476","article-title":"ResNet strikes back: an improved training procedure in timm","author":"Wightman","year":"2021","journal-title":"arXiv"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.15444","article-title":"DAMO-YOLO: a report on real-time object detection design","author":"Xu","year":"2022","journal-title":"arXiv"},{"key":"B39","doi-asserted-by":"crossref","first-page":"13658","DOI":"10.1109\/CVPR52688.2022.01330","article-title":"\u201cQueryDet: cascaded sparse query for accelerating high-resolution small object detection,\u201d","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yang","year":"2022"},{"key":"B40","first-page":"9656","author":"Yang","year":"2019"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093394","article-title":"\u201cScale match for tiny person detection,\u201d","author":"Yu","year":"2020","journal-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.17170","article-title":"How to train an accurate and efficient object detection model on any dataset","author":"Zalesskaya","year":"2022","journal-title":"arXiv"},{"key":"B43","doi-asserted-by":"crossref","first-page":"8510","DOI":"10.1109\/CVPR46437.2021.00841","article-title":"\u201cVarifocalnet: an iou-aware dense object detector\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang","year":"2021"},{"key":"B44","unstructured":"ZhangL.\n            LiuT.\n            DingX.\n          10.1109\/TITS.2022.32086992022"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1131392","article-title":"Automatic vessel plate number recognition for surface unmanned vehicles with marine applications","author":"Zhang","year":"2023","journal-title":"Front. Neurorobot"},{"key":"B46","doi-asserted-by":"publisher","first-page":"9259","DOI":"10.1609\/aaai.v33i01.33019259","article-title":"M2det: a single-shot object detector based on multi-level feature pyramid network","volume":"33","author":"Zhao","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.07850","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.808147","article-title":"A fusion algorithm of object detection and tracking for unmanned surface vehicles","author":"Zhou","year":"2022","journal-title":"Front. Neurorobot"},{"key":"B49","doi-asserted-by":"publisher","first-page":"723336","DOI":"10.3389\/fnbot.2021.723336","article-title":"An image-based benchmark dataset and a novel object detector for water surface object detection","volume":"15","author":"Zhou","year":"2021","journal-title":"Front. Neurorobot"},{"key":"B50","doi-asserted-by":"crossref","first-page":"9300","DOI":"10.1109\/CVPR.2019.00953","article-title":"\u201cDeformable convnets v2: more deformable, better results,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhu","year":"2019"},{"key":"B51","doi-asserted-by":"crossref","first-page":"2778","DOI":"10.1109\/ICCVW54120.2021.00312","article-title":"\u201cTPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios,\u201d","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","author":"Zhu","year":"2021"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.04159","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1315251\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T08:53:59Z","timestamp":1702544039000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1315251\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"references-count":52,"alternative-id":["10.3389\/fnbot.2023.1315251"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1315251","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,14]]},"article-number":"1315251"}}