{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T06:49:16Z","timestamp":1775112556804,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T00:00:00Z","timestamp":1662681600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the NingXia key research and development program","award":["2019BBF02009"],"award-info":[{"award-number":["2019BBF02009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Branch identification is key to the robotic pruning system for apple trees. High identification accuracy and the positioning of junction points between branch and trunk are important prerequisites for pruning with a robotic arm. Recently, with the development of deep learning, Transformer has been gradually applied to the field of computer vision and achieved good results. However, the effect of branch identification based on Transformer has not been verified so far. Taking Swin-T and Resnet50 as a backbone, this study detected and segmented the trunk, primary branch and support of apple trees on the basis of Mask R-CNN and Cascade Mask R-CNN. The results show that, when Intersection over Union (IoU) is 0.5, the bbox mAP and segm mAP of Cascade Mask R-CNN Swin-T are the highest, which are 0.943 and 0.940; as for the each category identification, Cascade Mask R-CNN Swin-T shows no significant difference with the other three algorithms in trunk and primary branch; when the identified object is a support, the bbox AP and segm AP of Cascade Mask R-CNN Swin-T is significantly higher than that of other algorithms, which are 0.879 and 0.893. Next, Cascade Mask R-CNN SW-T is combined with Zhang &amp; Suen to obtain the junction point. Compared with the direct application of Zhang &amp; Suen algorithm, the skeleton obtained by this method is advantaged by trunk diameter information, and its shape and junction points position are closer to the actual apple trees. This model and method can be applied to follow-up research and offer a new solution to the robotic pruning system for apple trees.<\/jats:p>","DOI":"10.3390\/rs14184495","type":"journal-article","created":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T04:54:41Z","timestamp":1662699281000},"page":"4495","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Branch Identification and Junction Points Location for Apple Trees Based on Deep Learning"],"prefix":"10.3390","volume":"14","author":[{"given":"Siyuan","family":"Tong","sequence":"first","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]},{"given":"Yang","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]},{"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4370-7009","authenticated-orcid":false,"given":"Yaxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9845-3790","authenticated-orcid":false,"given":"Feng","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]},{"given":"Chao","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106931","DOI":"10.1016\/j.asoc.2020.106931","article-title":"An algorithm for automatic dormant tree pruning","volume":"99","author":"Strnad","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.scienta.2016.03.046","article-title":"Mechanical winter pruning of grapevine: Physiological bases and applications","volume":"204","author":"Poni","year":"2016","journal-title":"Sci. Hortic."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"952","DOI":"10.5424\/sjar\/2014124-5795","article-title":"Effect of mechanical pruning on the yield and quality of \u2018fortune\u2019 mandarins","volume":"12","author":"Torregrosa","year":"2014","journal-title":"Span. J. Agric. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"106383","DOI":"10.1016\/j.compag.2021.106383","article-title":"Technological advancements towards developing a robotic pruner for apple trees: A review","volume":"189","author":"Zahid","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_5","first-page":"1","article-title":"Review on technology and equipment of mechanization in hilly orchard","volume":"51","author":"Zheng","year":"2020","journal-title":"Trans. Chin. Soc. Agric."},{"key":"ref_6","unstructured":"Lehnert, R. (2022, March 15). Robotic Pruning. Good Fruit Grower. Available online: https:\/\/www.goodfruit.com\/robotic-pruning."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"He, L., and Schupp, J. (2018). Sensing and automation in pruning of apple trees: A review. Agronomy, 8.","DOI":"10.3390\/agronomy8100211"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"11173","DOI":"10.1016\/j.ijleo.2016.09.044","article-title":"Apple tree branch segmentation from images with small gray-level difference for agricultural harvesting robot","volume":"127","author":"Ji","year":"2016","journal-title":"Optik"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1002\/rob.21680","article-title":"A Robot System for Pruning Grape Vines","volume":"34","author":"Botterill","year":"2017","journal-title":"J. Field Rob."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.compind.2018.03.002","article-title":"Automatic segmentation of trees in dynamic outdoor environments","volume":"98","author":"Tabb","year":"2018","journal-title":"Comput. Ind."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.compag.2014.02.013","article-title":"Identification of pruning branches in tall spindle apple trees for automated pruning","volume":"103","author":"Karkee","year":"2014","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1002\/rob.21679","article-title":"Modeling dormant fruit trees for agricultural automation","volume":"34","author":"Medeiros","year":"2017","journal-title":"J. Field Rob."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.compag.2017.02.017","article-title":"High-precision 3D detection and reconstruction of grapes from laser range data for efficient phenotyping based on supervised learning","volume":"135","author":"Mack","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.compag.2018.10.029","article-title":"Branch detection for apple trees trained in fruiting wall architecture using depth features and Regions-Convolutional Neural Network (R-CNN)","volume":"155","author":"Zhang","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105384","DOI":"10.1016\/j.compag.2020.105384","article-title":"Multi-class object detection using faster R-CNN and estimation of shaking locations for automated shake-and-catch apple harvesting","volume":"173","author":"Zhang","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1002\/rob.21998","article-title":"Computer vision-based tree trunk and branch identification and shaking points detection in Dense-Foliage canopy for automated harvesting of apples","volume":"38","author":"Zhang","year":"2020","journal-title":"J. Field Rob."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105277","DOI":"10.1016\/j.compag.2020.105277","article-title":"Deep learning based segmentation for automated training of apple trees on trellis wires","volume":"170","author":"Majeed","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105308","DOI":"10.1016\/j.compag.2020.105308","article-title":"Determining grapevine cordon shape for automated green shoot thinning using semantic segmentation-based deep learning networks","volume":"171","author":"Majeed","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105671","DOI":"10.1016\/j.compag.2020.105671","article-title":"Estimating the trajectories of vine cordons in full foliage canopies for automated green shoot thinning in vineyards","volume":"176","author":"Majeed","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105952","DOI":"10.1016\/j.compag.2020.105952","article-title":"Semantic segmentation for partially occluded apple trees based on deep learning","volume":"181","author":"Chen","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105469","DOI":"10.1016\/j.compag.2020.105469","article-title":"Integrated detection of citrus fruits and branches using a convolutional neural network","volume":"174","author":"Yang","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105296","DOI":"10.1016\/j.compag.2020.105296","article-title":"Segmentation and 3d reconstruction of rose plants from stereoscopic images","volume":"171","author":"Gallego","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105192","DOI":"10.1016\/j.compag.2019.105192","article-title":"A visual detection method for nighttime litchi fruits and fruiting stems","volume":"169","author":"Liang","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106484","DOI":"10.1016\/j.compag.2021.106484","article-title":"Automatic branch detection of jujube trees based on 3D reconstruction for dormant pruning using the deep learning-based method","volume":"190","author":"Ma","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106622","DOI":"10.1016\/j.compag.2021.106622","article-title":"Semantics-guided skeletonization of upright fruiting offshoot trees for robotic pruning","volume":"192","author":"You","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","article-title":"Cascade R-CNN: High quality object detection and instance segmentation","volume":"43","author":"Cai","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. arXiv.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2789","DOI":"10.1007\/s11694-022-01396-0","article-title":"Swin-MLP: A strawberry appearance quality identification method by Swin Transformer and multi-layer perceptron","volume":"16","author":"Zheng","year":"2022","journal-title":"J. Food Meas. Charact."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, Z., Luo, L., Zhu, W., Chen, J., and Wang, W. (2021). SwinGD: A Robust Grape Bunch Detection Model Based on Swin Transformer in Complex Vineyard Environment. Horticulturae, 7.","DOI":"10.3390\/horticulturae7110492"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yuan, W., and Xu, W. (2021). MSST-Net: A Multi-Scale Adaptive Network for Building Extraction from Remote Sensing Images Based on Swin Transformer. Remote Sens., 13.","DOI":"10.3390\/rs13234743"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Xu, X., Feng, Z., Cao, C., Li, M., Wu, J., Wu, Z., Shang, Y., and Ye, S. (2021). An Improved Swin Transformer-Based Model for Remote Sensing Object Detection and Instance Segmentation. Remote Sens., 13.","DOI":"10.3390\/rs13234779"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, J., Zhang, R., Li, Z., Lin, Q., and Wang, X. (2022). UATNet: U-Shape Attention-Based Transformer Net for Meteorological Satellite Cloud Recognition. Remote Sens., 14.","DOI":"10.3390\/rs14010104"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Xiao, X., Guo, W., Chen, R., Hui, Y., Wang, J., and Zhao, H. (2022). A Swin Transformer-Based Encoding Booster Integrated in U-Shaped Network for Building Extraction. Remote Sens., 14.","DOI":"10.3390\/rs14112611"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, W., Zhang, T., Yang, Z., and Li, J. (2021). Efficient Transformer for Remote Sensing Image Segmentation. Remote Sens., 13.","DOI":"10.3390\/rs13183585"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Xia, R., Chen, J., Huang, Z., Wan, H., Wu, B., Sun, L., Yao, B., Xiang, H., and Xing, M. (2022). CRTransSar: A Visual Transformer Based on Contextual Joint Representation Learning for SAR Ship Detection. Remote Sens., 14.","DOI":"10.3390\/rs14061488"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Liu, P., Song, Y., Chai, M., Han, Z., and Zhang, Y. (2021). Swin\u2013UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface. Materials, 14.","DOI":"10.3390\/ma14247504"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"103689","DOI":"10.1016\/j.compind.2022.103689","article-title":"Cas-VSwin transformer: A variant swin transformer for surface-defect detection","volume":"140","author":"Gao","year":"2022","journal-title":"Comput. Ind."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liao, Z., Fan, N., and Xu, K. (2022). Swin Transformer Assisted PriorAttention Network for Medical Image Segmentation. Appl. Sci., 12.","DOI":"10.3390\/app12094735"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, Y., Lin, X., Dong, J., Cheng, T., and Liang, J. (2022). SwinBTS: A Method for 3D Multimodal Brain Tumor Segmentation Using Swin Transformer. Brain Sci., 12.","DOI":"10.3390\/brainsci12060797"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.21273\/HORTSCI12158-17","article-title":"A method for quantifying whole-tree pruning severity in mature tall spindle apple plantings","volume":"52","author":"Schupp","year":"2017","journal-title":"HortScience Horts."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision (ECCV \u203216), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_44","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, \u0141., and Polosukhin, I. (2017, January 12). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1145\/357994.358023","article-title":"A fast parallel algorithm for thinning digital patterns","volume":"27","author":"Zhang","year":"1984","journal-title":"Commun. ACM"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/18\/4495\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:28:05Z","timestamp":1760142485000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/18\/4495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,9]]},"references-count":45,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["rs14184495"],"URL":"https:\/\/doi.org\/10.3390\/rs14184495","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,9]]}}}