{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T18:58:05Z","timestamp":1769713085904,"version":"3.49.0"},"reference-count":8,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,10,4]]},"abstract":"<jats:p>Small object detection has important application value in the fields of autonomous driving and drone scene analysis. As one of the most advanced object detection algorithms, YOLOv3 suffers some challenges when detecting small objects, such as the problem of detection failure of small objects and occluded objects. To solve these problems, an improved YOLOv3 algorithm for small object detection is proposed. In the proposed method, the dilated convolutions mish (DCM) module is introduced into the backbone network of YOLOv3 to improve the feature expression ability by fusing the feature maps of different receptive fields. In the neck network of YOLOv3, the convolutional block attention module (CBAM) and multi-scale fusion module are introduced to select the important information for small object detection in the shallow network, suppress the uncritical information, and use the fusion module to fuse the feature maps of different scales, so as to improve the detection accuracy of the algorithm. In addition, the Soft-NMS and Complete-IOU (ClOU) strategies are applied to candidate frame screening, which improves the accuracy of the algorithm for the detection of occluded objects. The experimental results on MS COCO2017, VOC2007, VOC2012 datasets and the ablation experiments on MS COCO2017 datasets demonstrate the effectiveness of the proposed method.The experimental results show that the proposed method achieves better accuracy in small object detection than the original YOLOv3 model.<\/jats:p>","DOI":"10.3233\/jifs-224530","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T11:14:10Z","timestamp":1689938050000},"page":"5807-5819","source":"Crossref","is-referenced-by-count":4,"title":["An advanced YOLOv3 method for small object detection"],"prefix":"10.1177","volume":"45","author":[{"given":"Baokai","family":"Liu","sequence":"first","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}]},{"given":"Fengjie","family":"He","sequence":"additional","affiliation":[{"name":"China Mobile Group Design Institute Co., Ltd. Shaanxi Branch, Xi\u2019an, Shaanxi, China"}]},{"given":"Shiqiang","family":"Du","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"},{"name":"College of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu, China"}]},{"given":"Jiacheng","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}]},{"given":"Wenjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}]}],"member":"179","reference":[{"issue":"Preprint","key":"10.3233\/JIFS-224530_ref2","first-page":"1","article-title":"An object detection network based on yolov4 and improved spatial attention mechanism","author":"Chen","year":"2022","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"Preprint","key":"10.3233\/JIFS-224530_ref3","first-page":"1","article-title":"Small objectdetection combining attention mechanism and a novel fpn","author":"Chen","year":"2022","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"4","key":"10.3233\/JIFS-224530_ref6","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1007\/s10044-022-01072-5","article-title":"An outstanding adaptivemulti-feature fusion yolov3 algorithm for the small target detectionin remote sensing images","volume":"25","author":"Li","year":"2022","journal-title":"Pattern Analysis and Applications"},{"key":"10.3233\/JIFS-224530_ref7","doi-asserted-by":"crossref","first-page":"104914","DOI":"10.1016\/j.engappai.2022.104914","article-title":"A lightweight vehicles detection network model based on yolov5","volume":"113","author":"Dong","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"9","key":"10.3233\/JIFS-224530_ref20","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans PAMI"},{"key":"10.3233\/JIFS-224530_ref25","doi-asserted-by":"crossref","first-page":"12993","DOI":"10.1609\/aaai.v34i07.6999","article-title":"Distance-iouloss: Faster and better learning for bounding box regression","volume":"34","author":"Zheng","year":"2020","journal-title":"Proc. AAAI"},{"issue":"3","key":"10.3233\/JIFS-224530_ref30","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1007\/s11063-021-10493-y","article-title":"Detection-oriented backbone trained from near scratch and local feature refinement for small object detection","volume":"53","author":"Yan","year":"2021","journal-title":"Neural Processing Letters"},{"key":"10.3233\/JIFS-224530_ref33","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.neucom.2019.08.089","article-title":"Using multi-label classification to improve object detection","volume":"370","author":"Gong","year":"2019","journal-title":"Neurocomputing"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-224530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T09:25:41Z","timestamp":1769678741000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-224530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,4]]},"references-count":8,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/jifs-224530","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,4]]}}}