{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T20:07:15Z","timestamp":1791317235264,"version":"4.3.1"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Pu-erh tea, valued for its ecological significance and economic worth, requires precise and efficient bud harvesting to advance intelligent agricultural operations. Accurate bud recognition and localization in complex natural environments remain critical challenges for automated harvesting systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address this, we propose ECS-Tea, a bio-inspired and lightweight detection-localization framework based on YOLOv11-Pose, tailored for Pu-erh tea bud analysis. The framework integrates four key modules: (1) a lightweight EfficientNetV2 backbone for efficient feature representation; (2) a Cross-Scale Feature Fusion (CSFF) module to strengthen multi-scale contextual information; (3) a Spatial-Channel Synergistic Attention (SCSA) mechanism for fine-grained keypoint feature modeling; and (4) an adaptive multi-frame depth fusion strategy to enhance 3D localization precision and robustness. ECS-Tea was trained and validated on a dedicated dataset for Pu-erh tea bud detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental results show that ECS-Tea achieves 98.7% target detection accuracy and 95.3% keypoint detection accuracy, with a compact architecture (3.3 MB), low computational cost (4.5 GFLOPs), and high inference speed (370.4 FPS). Compared to the baseline YOLOv11-Pose, ECS-Tea significantly improves keypoint detection performance: mAP@0.5(K) increases by 4.9%, recall R(K) by 3.8%, and precision P(K) by 3.4%, while maintaining or slightly enhancing object detection metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings demonstrate that ECS-Tea effectively balances accuracy and computational efficiency, validating the complementary contributions of its integrated modules. As a robust, real-time, and deployable solution, it bridges the gap between algorithmic sophistication and practical application, enabling high-precision tea bud harvesting in unstructured field environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2025.1697209","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:54:02Z","timestamp":1764780842000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ECS-tea: a bio-inspired high-precision detection and localization algorithm for young shoots of Pu-erh tea"],"prefix":"10.3389","volume":"16","author":[{"given":"Jianchao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailong","family":"Ti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxi","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsen","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quyun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"B1","first-page":"5470","article-title":"Mip-nerf 360: Unbounded anti-aliased neural radiance fields","author":"Barron","year":"2022"},{"key":"B2","first-page":"11682","article-title":"Seeing through fog without seeing fog: Deep multimodal sensor fusion in unseen adverse weather","author":"Bijelic","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"8438","DOI":"10.3390\/app15158438","article-title":"A review of computer vision and deep learning applications in crop growth management","volume":"15","author":"Cao","year":"2025","journal-title":"Appl. Sci."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1614881","article-title":"A detection method for synchronous recognition of string tomatoes and picking points based on keypoint detection","volume":"16","author":"Deng","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"13733","DOI":"10.1109\/CVPR46437.2021.01352","article-title":"Repvgg: Making vgg-style convnets great again","author":"Ding","year":"2021","journal-title":"In Proc. IEEE\/CVF. Conf. Comput. Vision Pattern Recognit."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.3390\/rs17121965","article-title":"RSNet: compact-align detection head embedded lightweight network for small object detection in remote sensing","volume":"17","author":"Dong","year":"2025","journal-title":"Remote Sens."},{"key":"B7","doi-asserted-by":"publisher","first-page":"112102","DOI":"10.1016\/j.engappai.2025.112102","article-title":"Industrial device-aided data collection for real-time rail defect detection via a lightweight network","volume":"161","author":"Dong","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B8","doi-asserted-by":"publisher","first-page":"108784","DOI":"10.1016\/j.compbiomed.2024.108784","article-title":"Channel prior convolutional attention for medical image segmentation","volume":"178","author":"Huang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B9","doi-asserted-by":"publisher","first-page":"129080","DOI":"10.1016\/j.neucom.2024.129080","article-title":"Integrating real-time pose estimation and PPE detection with cutting-edge deep learning for enhanced safety and rescue operations in the mining industry","volume":"618","author":"Imam","year":"2025","journal-title":"Neurocomputing"},{"key":"B10","first-page":"54","article-title":"Value evaluation and assessment of ancient tree tea\u2014Based on survey data from Kunming Xiongda Tea Market","author":"Jin","year":"2023","journal-title":"China Appraisal Journal"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2410.17725","article-title":"Yolov11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv. preprint. arXiv:2410.17725"},{"key":"B12","doi-asserted-by":"publisher","first-page":"107955","DOI":"10.1016\/j.compag.2023.107955","article-title":"Lightweight detection networks for tea bud on complex agricultural environment via improved YOLO v4","volume":"211","author":"Li","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B13","first-page":"8085","article-title":"Searching for fast model families on datacenter accelerators","author":"Li","year":"2021"},{"key":"B14","first-page":"244","article-title":"Recognition of ripened strawberries and peduncle detection based on an improved YOLO v8-Pose algorithm","volume":"54","author":"Liu","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Machinery."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3657282","article-title":"Lightweight deep learning for resource-constrained environments: A survey","volume":"56","author":"Liu","year":"2024","journal-title":"ACM Comput. Surveys."},{"key":"B16","doi-asserted-by":"publisher","first-page":"100072","DOI":"10.1016\/j.plaphe.2025.100072","article-title":"A keypoint-based method for detecting weed growth points in corn field environments","volume":"7","author":"Liu","year":"2025","journal-title":"Plant Phenomics"},{"key":"B17","first-page":"455","article-title":"Automatic body-size measurement method for group-raised pigs based on an improved YOLO v5-pose algorithm","volume":"56","author":"Liu","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Machinery."},{"key":"B18","volume-title":"Geographical indication product\u2014Pu-erh tea (GB\/T 22111\u20142008)","year":"2008"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129866","article-title":"SCSA: Exploring the synergistic effects between spatial and channel attention","volume":"634","author":"Si","year":"2025","journal-title":"Neurocomputing"},{"key":"B20","first-page":"104383","article-title":"Grad-CAM: The impact of large receptive fields and other caveats","volume-title":"Computer Vision and Image Understanding","author":"Santos","year":"2025"},{"key":"B21","doi-asserted-by":"publisher","first-page":"108649","DOI":"10.1016\/j.compag.2024.108649","article-title":"Crop plant automatic detecting based on in-field images by lightweight DFU-Net model","volume":"217","author":"Shi","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big. Data"},{"key":"B23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.biosystemseng.2023.06.007","article-title":"An improved YOLOv5-based method for multi-species tea shoot detection and picking point location in complex backgrounds","volume":"231","author":"Shuai","year":"2023","journal-title":"Biosyst. Eng."},{"key":"B24","doi-asserted-by":"publisher","first-page":"129866","DOI":"10.1016\/j.neucom.2025.129866","article-title":"SCSA: Exploring the synergistic effects between spatial and channel attention","volume":"634","author":"Si","year":"2025","journal-title":"Neurocomputing"},{"key":"B25","first-page":"8922","article-title":"LoFTR: Detector-free local feature matching with transformers","author":"Sun","year":"2021"},{"key":"B26","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B27","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","author":"Tan","year":"2021"},{"key":"B28","first-page":"275","article-title":"Study on the current status of the conservation of ancient tea tree resources in Yunnan","volume":"44","author":"Tang","year":"2022","journal-title":"Fujian. Tea."},{"key":"B29","first-page":"16558","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B30","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fsufs.2023.1172543","article-title":"A review on the application of computer vision and machine learning in the tea industry","volume":"7","author":"Wang","year":"2023","journal-title":"Front. Sustain. Food Syst."},{"key":"B32","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","author":"Wang","year":"2022"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1503033","article-title":"YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7","volume":"15","author":"Wang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B34","first-page":"5610","article-title":"Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo","author":"Wei","year":"2021"},{"key":"B35","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"Woo","year":"2018"},{"key":"B36","first-page":"10734","article-title":"Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search","author":"Wu","year":"2019"},{"key":"B37","doi-asserted-by":"publisher","first-page":"106547","DOI":"10.1016\/j.compag.2021.106547","article-title":"Detection and classification of tea buds based on deep learning","volume":"192","author":"Xu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B38","first-page":"32","article-title":"Mountains, forests, tea, and villages: The world-bound Jingmai Mountain","author":"Yang","year":"2024","journal-title":"Hum. Settlements."},{"key":"B39","doi-asserted-by":"publisher","first-page":"31168","DOI":"10.1038\/s41598-024-82529-x","article-title":"Lightweight tea bud detection method based on improved YOLOv5","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"B40","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"B41","first-page":"15","article-title":"Research progress on the effective utilization of Yunnan tea resources","volume":"45","author":"Zhou","year":"2017","journal-title":"Jiangsu. Agric. Sci."},{"key":"B42","first-page":"12897","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"B43","doi-asserted-by":"publisher","first-page":"2412","DOI":"10.3390\/agronomy13092412","article-title":"Detection and localization of tea bud based on improved YOLOv5s and 3D point cloud processing","volume":"13","author":"Zhu","year":"2023","journal-title":"Agronomy"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1697209\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:54:04Z","timestamp":1764780844000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1697209\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":43,"alternative-id":["10.3389\/fpls.2025.1697209"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1697209","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"article-number":"1697209"}}