{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T02:41:54Z","timestamp":1747190514112,"version":"3.40.5"},"reference-count":34,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T00:00:00Z","timestamp":1640649600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Project of SGCC","award":["5600-202046347A-0-0-00"],"award-info":[{"award-number":["5600-202046347A-0-0-00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Scientific Programming"],"published-print":{"date-parts":[[2021,12,28]]},"abstract":"<jats:p>The traditional image object detection algorithm applied in power inspection cannot effectively position power components, and the accuracy of recognition is low in scenes with some interference. In this research, we proposed a data-driven power detection method based on the improved YOLOv4-tiny model, which combined the ResNet-D module and the adjusted Res-CBAM to the backbone network of the existing YOLOv4-tiny module. We replaced the CSPOSANet module in the YOLOv4-tiny backbone network with the ResNet-D module to reduce the FLOPS required by the model. At the same time, the adjusted Res-CBAM whose feature fusion ways were replaced with stacking in the channels was combined as an auxiliary classifier. Finally, the features of five different receptive scales were used for prediction, and the display of the results was optimized by merging the prediction boxes. In the experiment, 57134 images collected on the power inspection line were processed and labeled, and the default anchor boxes were re-clustered, and the speed and accuracy of the model were evaluated by video and validation set of 3459 images. Processing multiple pictures and videos collected from the power inspection projects, we re-clustered the default anchor box and tested the speed and accuracy of the model. The results show that compared with the original YOLOv4-tiny model, the accuracy of our method that can position objects under occlusion and complex lighting conditions is guaranteed while the detection speed is about 13% faster.<\/jats:p>","DOI":"10.1155\/2021\/4447271","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T22:35:59Z","timestamp":1640730959000},"page":"1-11","source":"Crossref","is-referenced-by-count":2,"title":["A Decision Support System for Power Components Based on Improved YOLOv4-Tiny"],"prefix":"10.1155","volume":"2021","author":[{"given":"Yangyang","family":"Tian","sequence":"first","affiliation":[{"name":"State Grid Henan Electric Power Research Institute, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-9534","authenticated-orcid":true,"given":"Wandeng","family":"Mao","sequence":"additional","affiliation":[{"name":"State Grid Henan Electric Power Research Institute, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoguang","family":"Yuan","sequence":"additional","affiliation":[{"name":"State Grid Henan Electric Power Research Institute, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diming","family":"Wan","sequence":"additional","affiliation":[{"name":"State Grid Henan Electric Power Research Institute, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2628-9730","authenticated-orcid":true,"given":"Yuanhui","family":"Chen","sequence":"additional","affiliation":[{"name":"Shandong University of Science and Technology, Qingdao 266000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.3390\/s16111854"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2856627"},{"issue":"2","key":"3","first-page":"99","article-title":"Based on the improvement of SIFT algorithm, transmission line hang-up fault detection","volume":"29","author":"C. He","year":"2021","journal-title":"International Electronic Elements"},{"issue":"11","key":"4","first-page":"96","article-title":"An insulator image recognition method based on SIFT- BOW model","volume":"41","author":"H. Zhang","year":"2020","journal-title":"Laser Journal"},{"key":"5","first-page":"1","article-title":"Review on Mounted UAV for Transmission Line Inspection. Power System Technology","author":"S. U. I. Yu","year":"2020"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.19678\/j.issn.1000-3428.0059872"},{"key":"7","first-page":"2545","article-title":"Overview of visual defect detection of transmission line components","volume":"11","author":"Z. Zhenbing","year":"2021","journal-title":"Journal of Image and Graphics"},{"key":"8","first-page":"1","article-title":"Electric power inspection image enhancement based on E-FCNN","volume":"54","author":"W. Bai","year":"2020","journal-title":"Electric power"},{"key":"9","first-page":"1","article-title":"Real-time track planning for power pole inspection based on hybrid algorithm","author":"H. Zheng","year":"2020","journal-title":"Electric power"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1813\/1\/012036"},{"issue":"1","key":"11","first-page":"254","article-title":"A face detection based on Haar and skin color segmentation algorithms","volume":"42","author":"Y. Cheng","year":"2021","journal-title":"Journal of Ordnance Equipment Engineering"},{"issue":"2","key":"12","first-page":"127","article-title":"Pedestrian detection algorithm based on cascading feature classifier","volume":"42","author":"H. Xu","year":"2021","journal-title":"Research and Exploration in Laboratory"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.10491"},{"issue":"6","key":"14","first-page":"106","article-title":"Face recognition algorithm based on SIFT sparse representation","volume":"34","author":"Y. Zhu","year":"2020","journal-title":"Journal of Xi\u2019an Polytechnic University"},{"key":"15","first-page":"67","article-title":"Research on license plate positioning and parallelization based on SIFT algorithm","volume":"11","author":"D. Zhu","year":"2020","journal-title":"Network Security Technology & Application"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"19","first-page":"1674","article-title":"Face mask detection algorithm based on HSV+HOG features and SVM","volume":"1-11","author":"Y. He","year":"2021","journal-title":"Journal of Measurement Science and Instrumentation"},{"issue":"3","key":"20","first-page":"73","article-title":"Pedestrian detection based on HOG and SVM","volume":"6","author":"X. Ren","year":"2021","journal-title":"Science and technology innovation"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.81"},{"first-page":"1440","article-title":"Fast r-cnn","author":"R. Girshick","key":"22"},{"article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","year":"2015","author":"S. Ren","key":"23"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.324"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00442"},{"first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"J. Redmon","key":"27"},{"article-title":"Yolov4: optimal speed and accuracy of object detection","year":"2020","author":"A. Bochkovskiy","key":"28"},{"article-title":"Yolov3: an incremental improvement","year":"2018","author":"J. Redmon","key":"29"},{"article-title":"Scaled-YOLOv4: scaling cross stage partial network","year":"2020","author":"C. Y. Wang","key":"30"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00065"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"33","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1017\/S0027763000001240","article-title":"Flops","volume":"113","author":"J. Koll\u00e1r","year":"1989","journal-title":"Nagoya Mathematical Journal"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["Scientific Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/4447271.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/4447271.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/4447271.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T22:36:19Z","timestamp":1640730979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/sp\/2021\/4447271\/"}},"subtitle":[],"editor":[{"given":"Zeeshan","family":"Pervez","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,12,28]]},"references-count":34,"alternative-id":["4447271","4447271"],"URL":"https:\/\/doi.org\/10.1155\/2021\/4447271","relation":{},"ISSN":["1875-919X","1058-9244"],"issn-type":[{"type":"electronic","value":"1875-919X"},{"type":"print","value":"1058-9244"}],"subject":[],"published":{"date-parts":[[2021,12,28]]}}}