{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T04:59:45Z","timestamp":1782622785263,"version":"3.54.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:00:00Z","timestamp":1716508800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:00:00Z","timestamp":1716508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s11760-024-03279-x","type":"journal-article","created":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T18:01:28Z","timestamp":1716573688000},"page":"5893-5906","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An improved YOLO algorithm with multisensing for pedestrian detection"],"prefix":"10.1007","volume":"18","author":[{"given":"Lixiong","family":"Gong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmiao","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,24]]},"reference":[{"issue":"11","key":"3279_CR1","doi-asserted-by":"publisher","first-page":"8511","DOI":"10.1007\/s00521-021-06549-8","volume":"34","author":"C Kaffash","year":"2022","unstructured":"Kaffash, C., Neda, A.G., Ali, A.B.: Road accident risk prediction using generalized regression neural network optimized with self-organizing map. Neural Comput. Appl. 34(11), 8511\u20138524 (2022)","journal-title":"Neural Comput. Appl."},{"key":"3279_CR2","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 886\u201393 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"3279_CR3","unstructured":"Nam, W., Piotr, D., Joon H.H.: Local decorrelation for improved pedestrian detection. Advances in Neural Information Processing Systems. 27 (2014)"},{"key":"3279_CR4","doi-asserted-by":"crossref","unstructured":"Ma, N., Chen, L., Hu, J.C., Shang, Q.N., Li, J.H., Zhang G.P.: Pedestrian detection based on HOG features and SVM realizes vehicle-human-environment interaction. In: Proceedings of 15th International Conference on Computational Intelligence and Security (CIS), pp. 287\u2013291(2019)","DOI":"10.1109\/CIS.2019.00067"},{"issue":"6","key":"3279_CR5","doi-asserted-by":"publisher","first-page":"2689","DOI":"10.1007\/s11760-023-02485-3","volume":"17","author":"T Kasinathan","year":"2023","unstructured":"Kasinathan, T., Uyyala, S.R.: Detection of fall armyworm (Spodoptera frugiperda) in field crops based on mask R-CNN. Signal Image Video Process. 17(6), 2689\u20132695 (2023)","journal-title":"Signal Image Video Process."},{"issue":"4","key":"3279_CR6","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1007\/s11760-021-02041-x","volume":"16","author":"X Gao","year":"2022","unstructured":"Gao, X., Shen, Z., Yang, Y.: Multi-object tracking with Siamese-RPN and adaptive matching strategy. Signal Image Video Process. 16(4), 965\u2013973 (2022)","journal-title":"Signal Image Video Process."},{"key":"3279_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107226","volume":"93","author":"I Ahmed","year":"2021","unstructured":"Ahmed, I., Ahmad, M., Ahmad, A., Jeon, G.: IoT-based crowd monitoring system: Using SSD with transfer learning. Comput. Electr. Eng. 93, 107226 (2021)","journal-title":"Comput. Electr. Eng."},{"key":"3279_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116402","volume":"98","author":"Q Yin","year":"2021","unstructured":"Yin, Q., Yang, W., Ran, M., Wang, S.: FD-SSD: an improved SSD object detection algorithm based on feature fusion and dilated convolution. Signal Process. Image Commun. 98, 116402 (2021)","journal-title":"Signal Process. Image Commun."},{"issue":"6","key":"3279_CR9","doi-asserted-by":"publisher","first-page":"3091","DOI":"10.1007\/s11760-023-02530-1","volume":"17","author":"K Pan","year":"2023","unstructured":"Pan, K., Zhao, Y., Wang, T., Yao, S.: MSNet: a lightweight multi-scale deep learning network for pedestrian re-identification. Signal Image Video Process. 17(6), 3091\u20133098 (2023)","journal-title":"Signal Image Video Process."},{"key":"3279_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, C., Chung, K. H., Kim, J.: Region-of-interest reduction using edge and depth images for pedestrian detection in urban areas. In: Proceedings of the IEEE\/CVF Conference on International SoC Design Conference (ISOCC), pp. 161\u2013162 (2018)","DOI":"10.1109\/ISOCC.2015.7401768"},{"issue":"7","key":"3279_CR11","doi-asserted-by":"publisher","first-page":"837","DOI":"10.3390\/electronics10070837","volume":"10","author":"X Jiang","year":"2021","unstructured":"Jiang, X., Gao, T., Zhu, Z., Zhao, Y.: Real-time face mask detection method based on YOLOv3. Electronics 10(7), 837 (2021)","journal-title":"Electronics"},{"issue":"15","key":"3279_CR12","doi-asserted-by":"publisher","first-page":"5903","DOI":"10.3390\/s22155903","volume":"22","author":"H Lv","year":"2022","unstructured":"Lv, H., Yan, H., Liu, K., Zhou, Z., Jing, J.: Yolov5-ac: Attention mechanism-based lightweight yolov5 for track pedestrian detection. Sensors. 22(15), 5903 (2022)","journal-title":"Sensors."},{"issue":"1","key":"3279_CR13","first-page":"136","volume":"14","author":"PB Mathayo","year":"2022","unstructured":"Mathayo, P.B., Kang, D.K.: Beta and alpha regularizers of mish activation functions for machine learning applications in deep neural networks. Int. J. Internet Broadcast. Commun. 14(1), 136\u2013141 (2022)","journal-title":"Int. J. Internet Broadcast. Commun."},{"issue":"1","key":"3279_CR14","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s00365-021-09548-z","volume":"55","author":"I Daubechies","year":"2022","unstructured":"Daubechies, I., DeVore, R., Foucart, S., Hanin, B., Petrova, G.: Nonlinear approximation and (deep) ReLU networks. Constr. Approx. 55(1), 127\u2013172 (2022)","journal-title":"Constr. Approx."},{"key":"3279_CR15","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., Fu, C.W.: SE-SSD: Self-ensembling single-stage object detector from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14494\u201314503 (2021)","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"3279_CR16","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","volume":"199","author":"P Jiang","year":"2022","unstructured":"Jiang, P., Ergu, D., Liu, F., Cai, Y., Ma, B.: A Review of Yolo algorithm developments. Procedia Comput. Sci. 199, 1066\u20131073 (2022)","journal-title":"Procedia Comput. Sci."},{"issue":"7","key":"3279_CR17","doi-asserted-by":"publisher","first-page":"786","DOI":"10.3390\/rs11070786","volume":"11","author":"YL Chang","year":"2019","unstructured":"Chang, Y.L., Anagaw, A., Chang, L., Wang, Y.C., Hsiao, C.Y., Lee, W.H.: Ship detection based on YOLOv2 for SAR imagery. Remote Sensing. 11(7), 786 (2019)","journal-title":"Remote Sensing."},{"key":"3279_CR18","doi-asserted-by":"publisher","first-page":"110227","DOI":"10.1109\/ACCESS.2020.3001279","volume":"8","author":"X Wang","year":"2020","unstructured":"Wang, X., Wang, S., Cao, J., Wang, Y.: Data-driven based tiny-YOLOv3 method for front vehicle detection inducing SPP-net. IEEE Access. 8, 110227\u2013110236 (2020)","journal-title":"IEEE Access."},{"key":"3279_CR19","doi-asserted-by":"crossref","unstructured":"Bharati, P., Pramanik, A.: Deep learning techniques\u2014R-CNN to mask R-CNN: a survey. In: Proceedings of Computational Intelligence in Pattern Recognition (CIPR), pp. 657\u2013668 (2020)","DOI":"10.1007\/978-981-13-9042-5_56"},{"key":"3279_CR20","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., Yan, J.: Grid r-cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7363\u20137372 (2019)","DOI":"10.1109\/CVPR.2019.00754"},{"key":"3279_CR21","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point r-cnn. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9775\u20139784 (2019)","DOI":"10.1109\/ICCV.2019.00987"},{"key":"3279_CR22","doi-asserted-by":"crossref","unstructured":"Schmidt, C., Athar, A., Mahadevan, S., Leibe, B.: D2conv3d: dynamic dilated convolutions for object segmentation in videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1200\u20131209 (2022)","DOI":"10.1109\/WACV51458.2022.00199"},{"key":"3279_CR23","doi-asserted-by":"publisher","first-page":"157449","DOI":"10.1109\/ACCESS.2019.2947472","volume":"7","author":"J Zhuang","year":"2019","unstructured":"Zhuang, J., Dong, Y., Bai, H., Zuo, P., Cheng, J.: Auto-selecting receptive field network for visual tracking. IEEE Access. 7, 157449\u2013157458 (2019)","journal-title":"IEEE Access."},{"key":"3279_CR24","doi-asserted-by":"publisher","first-page":"124087","DOI":"10.1109\/ACCESS.2019.2927169","volume":"7","author":"X Lei","year":"2019","unstructured":"Lei, X., Pan, H., Huang, X.: A dilated CNN model for image classification. IEEE Access. 7, 124087\u2013124095 (2019)","journal-title":"IEEE Access."},{"key":"3279_CR25","doi-asserted-by":"publisher","first-page":"24344","DOI":"10.1109\/ACCESS.2020.2971026","volume":"8","author":"S Zhai","year":"2020","unstructured":"Zhai, S., Shang, D., Wang, S., Dong, S.: DF-SSD: An improved SSD object detection algorithm based on DenseNet and feature fusion. IEEE Access. 8, 24344\u201324357 (2020)","journal-title":"IEEE Access."},{"key":"3279_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109109","volume":"125","author":"M Karnati","year":"2022","unstructured":"Karnati, M., Seal, A., Sahu, G., Yazidi, A., Krejcar, O.: A novel multi-scale based deep convolutional neural network for detecting COVID-19 from X-rays. Appl. Soft Comput. 125, 109109 (2022)","journal-title":"Appl. Soft Comput."},{"key":"3279_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108159","volume":"121","author":"X Jin","year":"2022","unstructured":"Jin, X., Xie, Y., Wei, X.S., Zhao, B.R., Chen, Z.M., Tan, X.: Delving deep into spatial pooling for squeeze-and-excitation networks. Pattern Recogn. 121, 108159 (2022)","journal-title":"Pattern Recogn."},{"key":"3279_CR28","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.neucom.2021.10.024","volume":"468","author":"H Xue","year":"2022","unstructured":"Xue, H., Sun, M., Liang, Y.: ECANet: explicit cyclic attention-based network for video saliency prediction. Neurocomputing 468, 233\u2013244 (2022)","journal-title":"Neurocomputing"},{"key":"3279_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: 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, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"3279_CR30","doi-asserted-by":"crossref","unstructured":"Xu, J., Li, Z., Du, B., Zhang, M., Liu, J.: Reluplex made more practical: Leaky ReLU. In: Proceedings of the IEEE Symposium on Computers and Communications (ISCC), pp. 1\u20137 (2020)","DOI":"10.1109\/ISCC50000.2020.9219587"},{"key":"3279_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6054\u20136063 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"issue":"12","key":"3279_CR32","doi-asserted-by":"publisher","first-page":"5349","DOI":"10.1109\/TNNLS.2020.2966319","volume":"31","author":"F He","year":"2020","unstructured":"He, F., Liu, T., Tao, D.: Why resnet works? Residuals generalize. IEEE Trans. Neural Netw. Learn. Syst. 31(12), 5349\u20135362 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3279_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021)","journal-title":"Expert Syst. Appl."},{"key":"3279_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: Faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34, No. 07, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"3279_CR35","unstructured":"Bochkovskiy, A., Wang, C. Y., Liao, H. Y. M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3279_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Proceedings of the Computer Vision\u2013ECCV European Conference. Part V 13, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3279_CR37","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"3279_CR38","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 304\u2013311 (2009)","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"3279_CR39","doi-asserted-by":"crossref","unstructured":"Sun, J., Ge, H., Zhang, Z.: AS-YOLO: An improved YOLOv4 based on attention mechanism and SqueezeNet for person detection. In: 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Vol. 5, pp. 1451\u20131456 (2021)","DOI":"10.1109\/IAEAC50856.2021.9390855"},{"key":"3279_CR40","unstructured":"Xue, N., Niu, L., Li, Z.: Pedestrian detection with modified R-FCN. In: Proceedings of the UAE Graduate Students Research Conference 2021 (UAEGSRC\u20192021)"},{"issue":"25","key":"3279_CR41","doi-asserted-by":"publisher","first-page":"17445","DOI":"10.1007\/s11042-020-08725-9","volume":"79","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Zhou, W., Wang, Y., Xu, L.: A real-time recognition method of static gesture based on DSSD. Multimed. Tools Appl. 79(25), 17445\u201317461 (2020)","journal-title":"Multimed. Tools Appl."},{"issue":"4","key":"3279_CR42","doi-asserted-by":"publisher","first-page":"587","DOI":"10.3390\/e25040587","volume":"25","author":"Y Dai","year":"2023","unstructured":"Dai, Y., Liu, W.: GL-YOLO-Lite: a novel lightweight fallen person detection model. Entropy 25(4), 587 (2023)","journal-title":"Entropy"},{"key":"3279_CR43","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021.\u00a0arXiv preprint arXiv:2107.08430 (2021)"},{"key":"3279_CR44","unstructured":"Ultralytics. YOLOv5. Available online: https:\/\/github.com\/ultralytics\/yolov5. Accessed 1 June 2022"},{"issue":"4","key":"3279_CR45","doi-asserted-by":"publisher","first-page":"623","DOI":"10.3390\/sym13040623","volume":"13","author":"H Fu","year":"2021","unstructured":"Fu, H., Song, G., Wang, Y.: Improved YOLOv4 marine target detection combined with CBAM. Symmetry. 13(4), 623 (2021)","journal-title":"Symmetry."},{"key":"3279_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107446","volume":"107","author":"M Feng","year":"2020","unstructured":"Feng, M., Zhang, L., Lin, X., Gilani, S.Z., Mian, A.: Point attention network for semantic segmentation of 3D point clouds. Pattern Recogn. 107, 107446 (2020)","journal-title":"Pattern Recogn."},{"key":"3279_CR47","doi-asserted-by":"crossref","unstructured":"Yin, M., Yao, Z., Cao, Y., Li, X., Zhang, Z., Lin, S., Hu, H.: Disentangled non-local neural networks. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16, pp. 191\u2013207 (2020)","DOI":"10.1007\/978-3-030-58555-6_12"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03279-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03279-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03279-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:55:16Z","timestamp":1732042516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03279-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,24]]},"references-count":47,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["3279"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03279-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4089256\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,24]]},"assertion":[{"value":"13 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2024","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}