{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:36:45Z","timestamp":1763811405105,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,3,24]],"date-time":"2024-03-24T00:00:00Z","timestamp":1711238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,24]],"date-time":"2024-03-24T00:00:00Z","timestamp":1711238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province under Grant","award":["2020B0909020001"],"award-info":[{"award-number":["2020B0909020001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61573113"],"award-info":[{"award-number":["61573113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11554-024-01433-9","type":"journal-article","created":{"date-parts":[[2024,3,24]],"date-time":"2024-03-24T10:01:19Z","timestamp":1711274479000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Real-time object detection method based on YOLOv5 and efficient mobile network"],"prefix":"10.1007","volume":"21","author":[{"given":"Shuai","family":"Feng","sequence":"first","affiliation":[]},{"given":"Huaming","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Huilin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wenna","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,24]]},"reference":[{"key":"1433_CR1","doi-asserted-by":"crossref","unstructured":"Bell, S., Zitnick, C.L., Bala, K., et al.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA. pp. 2874\u20132883 (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"1433_CR2","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection (2020). arXiv preprint. arXiv:2004.10934"},{"key":"1433_CR3","doi-asserted-by":"crossref","unstructured":"Cai, L., Zhao, B., Wang, Z., et al.: MaxpoolNMS: getting rid of NMS bottlenecks in two-stage object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Long Beach, CA, USA. pp. 9356\u20139364 (2019)","DOI":"10.1109\/CVPR.2019.00958"},{"key":"1433_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers. In: Proceedings of European Conference on Computer Vision(ECCV), Glasgow, UK. pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"3","key":"1433_CR5","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s11554-022-01201-7","volume":"19","author":"P Ding","year":"2022","unstructured":"Ding, P., Qian, H., Chu, S.: SlimYOLOv4: lightweight object detector based on YOLOv4. J. Real-Time Image Process. 19(3), 487\u2013498 (2022)","journal-title":"J. Real-Time Image Process."},{"issue":"4","key":"1433_CR6","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11554-023-01329-0","volume":"20","author":"P Ding","year":"2023","unstructured":"Ding, P., Qian, H., Bao, J., et al.: L-YOLOv4: lightweight YOLOv4 based on modified RFB-s and depthwise separable convolution for multi-target detection in complex scenes. J. Real-Time Image Process. 20(4), 71 (2023)","journal-title":"J. Real-Time Image Process."},{"key":"1433_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw 107, 3\u201311 (2018)","journal-title":"Neural Netw"},{"key":"1433_CR8","unstructured":"Ge, Z., Liu, S., Wang, F., et al.: YOLOX: exceeding yolo series in 2021 (2021). arXiv preprint. arXiv:2107.08430"},{"key":"1433_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision(ICCV), Santiago, Chile. pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1433_CR10","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., et al.: GhostNet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Seattle, WA, USA. pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"issue":"9","key":"1433_CR11","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1433_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision(ICCV), Venice, Italy. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1433_CR13","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Nashville, TN, USA. pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1433_CR14","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., et al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision(ICCV), Seoul, Korea (South). pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1433_CR15","unstructured":"Howard, A.G., Zhu, M., Chen, B., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint. arXiv:1704.04861"},{"key":"1433_CR16","unstructured":"Jocher, G.: YOLOv5 by Ultralytics (2020). https:\/\/github.com\/ultralytics\/yolov5"},{"key":"1433_CR17","unstructured":"Li, C., Li, L., Jiang, H., et al.: YOLOv6: a single-stage object detection framework for industrial applications (2022). arXiv preprint. arXiv:2209.02976"},{"key":"1433_CR18","unstructured":"Li C, Li L, Geng Y, et al.: YOLOv6 v3.0: a full-scale reloading (2023). arXiv preprint. arXiv:2301.05586"},{"key":"1433_CR19","doi-asserted-by":"publisher","first-page":"e1145","DOI":"10.7717\/peerj-cs.1145","volume":"8","author":"L Li","year":"2022","unstructured":"Li, L., Li, B., Zhou, H.: Lightweight multi-scale network for small object detection. PeerJ Comput. Sci. 8, e1145 (2022)","journal-title":"PeerJ Comput. Sci."},{"key":"1433_CR20","unstructured":"Li, Z., Zhou, F.: FSSD: feature fusion single shot multibox detector (2017). arXiv preprint. arXiv:1712.00960"},{"key":"1433_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, HI, USA. pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1433_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision(ICCV), Venice, Italy. pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1433_CR23","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection (2019). arXiv preprint. arXiv:1911.09516"},{"key":"1433_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: SSD: single shot multibox detector. In: Proceedings of European Conference on Computer Vision(ECCV), Amsterdam, The Netherlands. pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1433_CR25","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., et al.: ShuffleNet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"issue":"2","key":"1433_CR26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11554-023-01264-0","volume":"20","author":"F Qi","year":"2023","unstructured":"Qi, F., Wang, Y., Tang, Z., et al.: Real-time and effective detection of agricultural pest using an improved YOLOv5 network. J. Real-Time Image Process. 20(2), 33 (2023)","journal-title":"J. Real-Time Image Process."},{"issue":"1","key":"1433_CR27","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11554-023-01258-y","volume":"20","author":"H Qian","year":"2023","unstructured":"Qian, H., Wang, H., Feng, S., et al.: FESSD: SSD target detection based on feature fusion and feature enhancement. J. Real-Time Image Process. 20(1), 2 (2023)","journal-title":"J. Real-Time Image Process."},{"key":"1433_CR28","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.C., Yuille, A.: Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In; Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Nashville, TN, USA. pp. 10213\u201310224 (2021)","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"1433_CR29","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, HI, USA. pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1433_CR30","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement (2018). arXiv preprint. arXiv:1804.02767"},{"key":"1433_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA. pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"1433_CR32","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans Pattern Anal Mach. Intell"},{"key":"1433_CR33","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et al.: MobileNetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Salt Lake City, UT, USA. pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1433_CR34","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA. pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"1433_CR35","unstructured":"Tan, M., Le, Q.V.: MixConv: mixed depthwise convolutional kernels (2019). arXiv preprint. arXiv:1907.09595"},{"key":"1433_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Seattle, WA, USA. pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1433_CR37","unstructured":"Tang, Y., Han, K., Guo, J., et al.: GhostNetv2: enhance cheap operation with long-range attention (2022). arXiv preprint. arXiv:2211.12905"},{"key":"1433_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C., Tong, X., Gao, R., et al.: Mobile-YOLO: a lightweight and efficient implementation of object detector based on YOLOv4. Adv. Comput. Sci. Eng. Educ. 134, 221\u2013234 (2022)","DOI":"10.1007\/978-3-031-04812-8_19"},{"key":"1433_CR39","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., et al.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPR), Seattle, WA, USA. pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"1433_CR40","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-yolov4: Scaling cross stage partial network. Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition(CVPR), Nashville, TN, USA. pp. 13,029\u201313,038 (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"1433_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Vancouver, Canada. pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1433_CR42","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., et al.: PANet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"1433_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., et al.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Seattle, WA, USA. pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1433_CR44","unstructured":"Xu, X., Jiang, Y., Chen, W., et al.: DAMO-YOLO: a report on real-time object detection design (2022). arXiv preprint. arXiv:2211.15444"},{"key":"1433_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., et al.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Salt Lake City, UT, USA. pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1433_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Sheng, T., Wang, Y., et al.: M2det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence(AAAI), Honolulu, Hawaii, USA. pp. 9259\u20139266 (2019)","DOI":"10.1609\/aaai.v33i01.33019259"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01433-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01433-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01433-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T12:33:39Z","timestamp":1712320419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01433-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,24]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["1433"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01433-9","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"type":"print","value":"1861-8200"},{"type":"electronic","value":"1861-8219"}],"subject":[],"published":{"date-parts":[[2024,3,24]]},"assertion":[{"value":"15 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This declaration is not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"56"}}