{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T16:10:41Z","timestamp":1791562241971,"version":"4.3.4"},"reference-count":34,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Technology Research and Application Demonstration of Public Rail Intermodal Intelligent Logistics Park","award":["202503AA080013"],"award-info":[{"award-number":["202503AA080013"]}]},{"name":"Research on Intelligent Perception and Mending Methods for Rotary-Cut Veneer in Plywood","award":["YJS-KCJJ-2025-24"],"award-info":[{"award-number":["YJS-KCJJ-2025-24"]}]},{"name":"Yunnan Fundamental Research Projects","award":["202501AT070245"],"award-info":[{"award-number":["202501AT070245"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Safety monitoring in container hoisting operations within rail-road intermodal logistics parks is a critical task in industrial safety management. Such scenarios are characterized by complex environments, large variations in target scales, deformable object shapes, and frequent occlusions, which pose significant challenges to visual perception systems. Conventional single-task models suffer from inherent limitations in handling low recall rates for distant small targets and insufficient adaptability to geometric deformations, making them inadequate for high-precision, real-time safety warning applications. To address these challenges, this study proposes a unified visual analysis framework that integrates semantic segmentation and object detection to enhance the recognition performance of small and deformable targets in complex operational environments, enabling real-time perception and safety warning of key objects and hazardous regions within container yards. Specifically, we introduce FSD-YOLO, a fusion-based architecture composed of the following key components. First, a SegFormer-based semantic segmentation module is employed to achieve pixel-level delineation of different operational regions. Second, an improved object detection network is developed based on the YOLOv8n architecture, incorporating: (1) the integration of C2f modules in the shallow layers of the backbone to enhance high-resolution feature extraction; (2) the embedding of C2fDCN modules within the detection head to improve modeling capability for deformable objects via deformable convolution; (3) the adoption of CARAFE upsampling operators to optimize multi-scale feature fusion; and (4) a dynamic loss-weighting strategy for small objects, where loss weights are adaptively adjusted according to target area to increase training emphasis on small-scale targets. Finally, a decision-level fusion strategy is applied to combine segmentation and detection outputs, enabling real-time safety judgment based on semantic rules. Experimental results on a self-constructed container yard dataset demonstrate that the proposed detection model achieves an mAP50-95 of 0.6433 and an mAP50 of 0.9565, significantly outperforming the baseline YOLOv8n model (mAP50-95: 0.5394, mAP50: 0.8435), thereby validating the effectiveness of the proposed framework.<\/jats:p>","DOI":"10.3390\/s26072029","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:11:14Z","timestamp":1774429874000},"page":"2029","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FSD-YOLO: A Fusion Framework for Region Segmentation and Deformable Object Detection in Container Yards"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1576-2950","authenticated-orcid":false,"given":"Linghao","family":"Dai","sequence":"first","affiliation":[{"name":"College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2216-2694","authenticated-orcid":false,"given":"Zhihong","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2676-3586","authenticated-orcid":false,"given":"Qi","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4762-6179","authenticated-orcid":false,"given":"Shihuan","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4744-2719","authenticated-orcid":false,"given":"Hongxu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"ref_1","first-page":"457","article-title":"Gantry crane scheduling and storage techniques in rail-road terminals","volume":"Volume 32","author":"Kaidabettu","year":"2021","journal-title":"Adapting to the Future: Maritime and City Logistics in the Context of Digitalization and Sustainability"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wu, F., Hu, M., Xie, F., Bu, W., and Zhang, Z. (2025). A multimodal sensor fusion and dynamic prediction-based personnel intrusion detection system for crane operations. Processes, 13.","DOI":"10.3390\/pr13124017"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1016\/j.ssci.2009.08.007","article-title":"Port safety and the container revolution: A statistical study on human factor and occupational accidents","volume":"48","author":"Fabiano","year":"2010","journal-title":"Saf. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ning, S., Ding, F., and Chen, B. (2024). Research on the method of foreign object detection for railway tracks based on deep learning. Sensors, 24.","DOI":"10.3390\/s24144483"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lee, J., and Lee, S. (2023). Construction site safety management: A computer vision and deep learning approach. Sensors, 23.","DOI":"10.3390\/s23020944"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, L., Guo, Z., Liu, Z., Zhang, Y., Cai, R., Hu, X., Yang, R., and Wang, G. (2024). Multi-Task Intelligent Monitoring of Construction Safety Based on Computer Vision. Buildings, 14.","DOI":"10.3390\/buildings14082429"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.aej.2024.08.080","article-title":"Safe operations of a reach stacker by computer vision in an automated container terminal","volume":"109","author":"Cuong","year":"2024","journal-title":"Alex. Eng. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.aej.2025.10.023","article-title":"Robust visual-based tracking using deep learning with image enhancement for reach stackers in container terminals","volume":"132","author":"An","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_10","doi-asserted-by":"crossref","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":"ref_11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106117","DOI":"10.1016\/j.ocecoaman.2022.106117","article-title":"Exploiting high-fidelity kinematic information from port surveillance videos via a YOLO-based framework","volume":"222","author":"Xu","year":"2022","journal-title":"Ocean. Coast Manag."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"tdaf048","DOI":"10.1093\/tse\/tdaf048","article-title":"Autonomous port traffic safety orientated vehicle kinematic information exploitation via port-like videos","volume":"7","author":"Chen","year":"2025","journal-title":"Transp. Saf. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kim, H., Kim, T., Jo, W., Kim, J., Shin, J., Han, D., and Choi, Y. (2022). Multispectral benchmark dataset and baseline for forklift collision avoidance. Sensors, 22.","DOI":"10.3390\/s22207953"},{"key":"ref_18","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2025, October 15). Ultralytics YOLOv8 [Software]. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"45446","DOI":"10.1038\/s41598-025-28989-1","article-title":"Optimized YOLOv8s framework with deformable convolution for underwater object detection","volume":"15","author":"Wang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017, January 22\u201329). Deformable convolutional networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref_21","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., and Lin, D. (November, January 27). CARAFE: Content-aware reassembly of features. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Republic of Korea."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6551","DOI":"10.3934\/mbe.2023282","article-title":"Deep learning-based small object detection: A survey","volume":"20","author":"Feng","year":"2023","journal-title":"Math. Biosci. Eng."},{"key":"ref_23","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., and Girdhar, R. (2022, January 19\u201324). Masked-attention mask transformer for universal image segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tran, S.V., Lee, D., Bao, Q.L., Yoo, T., Khan, M., Jo, J., and Park, C. (2023). A Human Detection Approach for Intrusion in Hazardous Areas Using 4D-BIM-Based Spatial-Temporal Analysis and Computer Vision. Buildings, 13.","DOI":"10.3390\/buildings13092313"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105129","DOI":"10.1016\/j.autcon.2023.105129","article-title":"Computer vision-based safety risk computing and visualization on construction sites","volume":"156","author":"Hou","year":"2023","journal-title":"Automat. Constr."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ning, S., Ding, F., Chen, B., and Huang, Y. (2025). Railway Intrusion Risk Quantification with Track Semantic Segmentation and Spatiotemporal Features. Sensors, 25.","DOI":"10.3390\/s25175266"},{"key":"ref_28","first-page":"100571","article-title":"Railway obstacle intrusion warning mechanism integrating YOLO-based detection and risk assessment","volume":"38","author":"Zhang","year":"2024","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"17728","DOI":"10.1109\/JSTARS.2025.3584877","article-title":"Semantic Segmentation of Burned Areas in Sentinel-2 Satellite Imagery Using Deep Learning Transformer and Convolutional Attention Networks","volume":"18","author":"Ouadou","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"105190","DOI":"10.1016\/j.imavis.2024.105190","article-title":"LDConv: Linear deformable convolution for improving convolutional neural networks","volume":"149","author":"Zhang","year":"2024","journal-title":"Image Vis. Comput."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1109\/TMM.2021.3118216","article-title":"Exploiting Web Images for Fine-Grained Visual Recognition via Dynamic Loss Correction and Global Sample Selection","volume":"24","author":"Liu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_32","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_33","unstructured":"Kendall, A., Gal, Y., and Cipolla, R. (2018, January 18\u201323). Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, UT, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Fu, R., Hu, Q., Dong, X., Guo, Y., Gao, Y., and Li, B. (2020). Axiom-based grad-cam: Towards accurate visualization and explanation of cnns. arXiv.","DOI":"10.5244\/C.34.146"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2029\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:24:37Z","timestamp":1774430677000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072029"],"URL":"https:\/\/doi.org\/10.3390\/s26072029","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]}}}