{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T16:16:02Z","timestamp":1787242562507,"version":"build-2736575974"},"reference-count":28,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>To address the challenges of detecting sugar orange fruits in complex natural orchard environments\u2014where fruits are frequently occluded by leaves and branches and may be mutually occluded due to dense growth, leading to missed detections, false positives, and low detection confidence\u2014we propose an improved algorithm based on YOLOv8n, named YOLO-FSEP. A Spatial-Channel Synergistic Attention (SCSA) module is introduced into the main network to enhance feature extraction capabilities; the IoU loss function is replaced with Focal_SIOU to improve the detection accuracy for difficult samples; and an SE attention mechanism is embedded in the detection head, with the addition of a P6 high-resolution detection layer to optimize multi-scale object performance. Experimental results on a self-built sugar orange dataset show that, compared to the baseline YOLOv8n, the improved model achieves a 0.9% increase in accuracy, a 1.3% increase in recall, and a 3.2% increase in mAP50-95, while maintaining an inference speed of 62.6 FPS. To evaluate the model under dynamic conditions, we performed a 200-frame continuous test of the 3D localization pipeline on a laptop with a RealSense D435i camera. The average YOLO inference time was 49.90 ms, post-processing (depth extraction and 3D coordinate conversion) took 0.24 ms, and the total processing time was 50.15 ms. Given that the typical response time for a robotic arm\u2019s single positioning operation is 100\u2013200 ms, this real-time performance meets the dynamic localization requirements of sugar orange harvesting.<\/jats:p>","DOI":"10.3390\/s26123848","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T10:19:53Z","timestamp":1781691593000},"page":"3848","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["YOLO-FSEP: An Improved YOLOv8n Algorithm for Sugar Orange Detection in Orchards"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9616-5733","authenticated-orcid":false,"given":"Tianfa","family":"Deng","sequence":"first","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinchao","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingjuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faguo","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"ref_1","unstructured":"Li, L. (2024). Research on the Development of Sugar Orange Industry in Yongfu County. [Master\u2019s Thesis, Wuhan Polytechnic University]."},{"key":"ref_2","first-page":"28","article-title":"A Brief Analysis of Changes in China\u2019s Fruit Production in 2021","volume":"40","author":"Xiang","year":"2021","journal-title":"China Fruit News"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liang, Y., Jiang, W., Liu, Y., Wu, Z., and Zheng, R. (2025). Picking-Point Localization Algorithm for Citrus Fruits Based on Improved YOLOv8 Model. J. Southwest Univ. (Nat. Sci.), 15.","DOI":"10.3390\/agriculture15030237"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lv, Q., Sun, F., Bian, Y., Wu, H., Li, X., Li, X., and Zhou, J. (2025). A Lightweight Citrus Object Detection Method in Complex Environments. Agriculture, 15.","DOI":"10.3390\/agriculture15101046"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"23729","DOI":"10.1007\/s11042-020-08976-6","article-title":"A review of object detection based on deep learning","volume":"79","author":"Xiao","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, W., Shi, Y., Liu, W., and Che, Z. (2024). An Unstructured Orchard Grape Detection Method Utilizing YOLOv5s. Agriculture, 14.","DOI":"10.3390\/agriculture14020262"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nix, S., Sato, A., Madokoro, H., Yamamoto, S., Nishimura, Y., and Sato, K. (2025). Detection of Apple Trees in Orchard Using Monocular Camera. Agriculture, 15.","DOI":"10.3390\/agriculture15050564"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Loddo, A., Loddo, M., and Di Ruberto, C. (2021). A novel deep learning based approach for seed image classification and retrieval. Comput. Electron. Agric., 187.","DOI":"10.1016\/j.compag.2021.106269"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhou, M., Wang, J., and Li, B. (2022). ARG-Mask RCNN: An Infrared Insulator Fault-Detection Network Based on Improved Mask RCNN. Sensors, 22.","DOI":"10.3390\/s22134720"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhao, M., Shi, P., Ren, R., He, X., Wei, X., and Yang, H. (2022). Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN. Sensors, 22.","DOI":"10.3390\/s22031215"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bai, T., Luo, J., Zhou, S., Lu, Y., and Wang, Y. (2024). Vehicle-Type Recognition Method for Images Based on Improved Faster R-CNN Model. Sensors, 24.","DOI":"10.3390\/s24082650"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Choi, H.-T., Lee, H.-J., Kang, H., Yu, S., and Park, H.-H. (2021). SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection. Sensors, 21.","DOI":"10.3390\/s21082842"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, X., Pan, J.D., Xie, F.P., Zeng, J.P., Li, Q., Huang, X.J., Liu, D.W., and Wang, X.S. (2021). Fast and accurate green pepper detection in complex backgrounds via an improved Yolov4-tiny model. Comput. Electron. Agric., 191.","DOI":"10.1016\/j.compag.2021.106503"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, X.Y., Li, G., Chen, W.K., Liu, B.H., Chen, M., and Lu, S.L. (2022). Detection of Dense Citrus Fruits by Combining Coordinated Attention and Cross-Scale Connection with Weighted Feature Fusion. Appl. Sci., 12.","DOI":"10.3390\/app12136600"},{"key":"ref_15","unstructured":"Wang, Y. (2023). Research on Detection and Localization of Citrus in Natural Environment Based on Improved YOLOv7. [Master\u2019s Thesis, Sichuan Agricultural University]."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kong, D., Wang, J., Zhang, Q., Li, J., and Rong, J. (2023). Research on Fruit Spatial Coordinate Positioning by Combining Improved YOLOv8s and Adaptive Multi-Resolution Model. Agronomy, 13.","DOI":"10.3390\/agronomy13082122"},{"key":"ref_17","first-page":"106","article-title":"Recognition and position method of tomato picking robot based on improved YOLOv8s and RGB-D information fusion","volume":"41","author":"Fan","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Tong, Z., Zhou, Y., Li, C., Cai, C., and Rong, L. (2026). YOLO-ELS: A Lightweight Cherry Tomato Maturity Detection Algorithm. Appl. Sci., 16.","DOI":"10.3390\/app16021043"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, T., Huang, J., Niu, J., Liu, Z., Zhang, L., and Song, H. (2026). Occlusion Avoidance for Harvesting Robots: A Lightweight Active Perception Model. Sensors, 26.","DOI":"10.3390\/s26010291"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"182799","DOI":"10.1109\/ACCESS.2024.3504399","article-title":"HAFREE: A Heatmap-Based Anchor-Free Detector for Apple Defect Detection","volume":"12","author":"Han","year":"2024","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Qi, J.T., Liu, X.N., Liu, K., Xu, F.R., Guo, H., Tian, X.L., Li, M., Bao, Z.Y., and Li, Y. (2022). An improved YOLOv5 model based on visual attention mechanism: Application to recognition of tomato virus disease. Comput. Electron. Agric., 194.","DOI":"10.1016\/j.compag.2022.106780"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, J., Wu, H., Lv, D., Ma, W., Teng, H., and Chen, D. (2026). A Lightweight and High-Precision Citrus Detection Model for Unstructured Orchard Environments. Horticulturae, 12.","DOI":"10.3390\/horticulturae12060718"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lin, X., Liao, D., Du, Z., Wen, B., Wu, Z., and Tu, X. (2025). SDA-YOLO: An Object Detection Method for Peach Fruits in Complex Orchard Environments. Sensors, 25.","DOI":"10.3390\/s25144457"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Shi, J., Luo, W., Wang, X., Guo, J., and Ren, H. (2026). FDA-YOLO: A Feature Fusion and Attention-Based Network for Multiscale Tomato Maturity Detection in Real-World Agricultural Scenarios. Sensors, 26.","DOI":"10.3390\/s26113404"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sun, Q., Li, P., He, C., Song, Q., Chen, J., Kong, X., and Luo, Z. (2024). A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices. Sensors, 24.","DOI":"10.20944\/preprints202405.1950.v1"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, S. (2026). Domain-adaptive faster R-CNN for non-PPE identification on construction sites from body-worn and general images. Sci. Rep., 16.","DOI":"10.1038\/s41598-026-35148-7"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, S. (2026). Domain adaptation using transformer models for automated detection of exterior cladding materials in street view images. Sci. Rep., 16.","DOI":"10.1038\/s41598-025-32524-7"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3848\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T10:25:06Z","timestamp":1781691906000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":28,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123848"],"URL":"https:\/\/doi.org\/10.3390\/s26123848","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]}}}