{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T06:24:03Z","timestamp":1787207043233,"version":"build-2736575974"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"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>In a complex orchard environment, canopy apples are obscured by various factors, making it hard for apple harvesting robots to accurately determine which apples can be directly harvested. Furthermore, the complex obstruction leads to difficulties in identifying keypoints on the apples and caculating the axis direction, directly affecting the robot\u2019s determination of grasping positions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To solve these issues, a two-dimensional (2D) axis estimation method for pickable canopy apples based on a YOLO cascade network was proposed. Firstly, the study introduced SPDConv for lossless downsampling and adopts dynamic upsampling to improve segmentation boundary accuracy, constructing an instance segmentation network named the YOLO-SD model to select pickable apples according to different occlusion conditions and growth states. Secondly, the geometric center of the mask image was located using its minimum enclosing circle, and the region of interest was extracted through morphological dilation. Then, by integrating the RFAConv, SCSA attention, and MBConv modules, a keypoint detection network YOLO-RSM was constructed to extract keypoints of pickable apples. Finally, a 2D axis construction strategy was proposed, which adaptively constructs the growth axis based on the visibility of keypoints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental results show that the overall average accuracy mAP50 of the YOLO-SD model for apple segmentation reached 95.2%, and the parameter quantity was reduced to 2.47 M. The average accuracy of the YOLO-RSM model for keypoint detection has reached 90.3%, which is 2.4%, 2.6%, and 4.7% higher than that of the YOLOv8n, YOLO11n, and YOLO12n models respectively. The 2D axis estimation algorithm has an average axis angular error of 7.23\u00b0\u00a0\u00b1\u00a016.73\u00b0, and an axis estimation accuracy of 92.68%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed method can achieve high-precision canopy apple segmentation, keypoint detection, and 2D axis estimation, thus offering technical support for the picking operations of apple harvesting robots.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1904059","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:29:01Z","timestamp":1787203741000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A two-dimensional axis estimation method for pickable canopy apples based on YOLO cascade network"],"prefix":"10.3389","volume":"17","author":[{"given":"Hongwei","family":"Cui","sequence":"first","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology","place":["Luoyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meijia","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology","place":["Luoyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology","place":["Luoyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Mei","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs","place":["Nanjing, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology","place":["Luoyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengying","family":"Gu","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology","place":["Luoyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"191","DOI":"10.11975\/j.issn.1002-6819.202311200","article-title":"Recognizing and locating apple using improved BlendMask model","volume":"40","author":"Bai","year":"2024","journal-title":"Chin. Soc Agric. Eng."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.32604\/cmc.2023.044374","article-title":"Zero-DCE++ inspired object detection in less illuminated environment using improved YOLOv5","volume":"77","author":"Balasundaram","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108056","article-title":"Tomato 3D pose detection algorithm based on keypoint detection and point cloud processing","volume":"212","author":"Du","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/s22020419","article-title":"Strawberry maturity recognition algorithm combining dark channel enhancement and YOLOv5","volume":"22","author":"Fan","year":"2022","journal-title":"Sensors-Basel."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3116","article-title":"Apple estimation and recognition in complex scenes using YOLO v8","volume":"11","author":"Geng","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"B6","first-page":"2980","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/app13074160","article-title":"A review of target recognition technology for fruit picking robots: from digital image processing to deep learning","volume":"13","author":"Hua","year":"2023","journal-title":"Appl. Sci."},{"key":"B8","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/s11119-021-09846-3","article-title":"RS-Net: robust segmentation of green overlapped apples","volume":"23","author":"Jia","year":"2022","journal-title":"Precis. Agric."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110394","article-title":"CO-YOLO: A lightweight and efficient model for Camellia oleifera fruit object detection and posture determination","volume":"235","author":"Jin","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108781","article-title":"Occluded apples orientation estimator based on deep learning model for robotic harvesting","volume":"219","author":"Kok","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B11","doi-asserted-by":"publisher","first-page":"47","DOI":"10.11975\/j.issn.1002-6819.202311200","article-title":"Vision detection method for picking robots based on improved Faster R-CNN","volume":"55","author":"Li","year":"2024","journal-title":"Chin. Soc Agric. Mach."},{"key":"B12","first-page":"6004","article-title":"Learning to upsample by learning to sample","author":"Liu","year":"2023"},{"key":"B13","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":"B14","first-page":"443","article-title":"No more strided convolutions or pooling: A new CNN building block for low-resolution images and small objects","author":"Sunkara","year":"2022"},{"key":"B15","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106864","article-title":"Fusion of Mask RCNN and attention mechanism for instance segmentation of apples under complex background","volume":"196","author":"Wang","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B17","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1016\/j.aiia.2025.12.005","article-title":"LPNet: A lightweight progressive network for calyx-aware apple pose estimation in orchard environments","volume":"16","author":"Wang","year":"2026","journal-title":"Artif. Intell. Agric."},{"key":"B18","doi-asserted-by":"publisher","first-page":"106716","DOI":"10.1016\/j.compag.2022.106716","article-title":"Geometry-aware fruit grasping estimation for robotic harvesting in apple orchards","volume":"193","author":"Wang","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B19","doi-asserted-by":"publisher","first-page":"105475","DOI":"10.1016\/j.compag.2020.105475","article-title":"Using color and 3D geometry features to segment fruit point cloud and improve fruit recognition accuracy","volume":"174","author":"Wu","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B20","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.biosystemseng.2021.01.015","article-title":"A litchi fruit recognition method in a natural environment using RGB-D images","volume":"204","author":"Yu","year":"2021","journal-title":"Biosyst. Eng."},{"key":"B21","doi-asserted-by":"publisher","first-page":"113208","DOI":"10.1016\/j.patcog.2026.113208","article-title":"RFAConv: Receptive-field attention convolution for improving convolutional neural networks","volume":"176","author":"Zhang","year":"2023","journal-title":"Pattern Recognition"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109815","article-title":"Selective fruit harvesting prediction and 6D pose estimation based on YOLOv7 multi-parameter recognition","volume":"229","author":"Zhao","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1007\/s11119-022-09913-3","article-title":"Intelligent robots for fruit harvesting: recent developments and future challenges","volume":"23","author":"Zhou","year":"2022","journal-title":"Precis. Agric."},{"key":"B24","doi-asserted-by":"publisher","first-page":"188","DOI":"10.3969\/j.issn.1672-3872.2025.19.049","article-title":"Application analysis of artificial intelligence technology in agricultural machinery","volume":"56","author":"Zou","year":"2025","journal-title":"South. Agric. Mach."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1904059\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:29:03Z","timestamp":1787203743000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1904059\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":24,"alternative-id":["10.3389\/fpls.2026.1904059"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1904059","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"article-number":"1904059"}}