{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T21:56:26Z","timestamp":1783720586463,"version":"3.55.0"},"reference-count":40,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T00:00:00Z","timestamp":1661212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"International Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences (CAASTIP)","award":["U19A2061"],"award-info":[{"award-number":["U19A2061"]}]},{"name":"International Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences (CAASTIP)","award":["JPMJCR21U3"],"award-info":[{"award-number":["JPMJCR21U3"]}]},{"name":"National Natural Science Foundation of China","award":["U19A2061"],"award-info":[{"award-number":["U19A2061"]}]},{"name":"National Natural Science Foundation of China","award":["JPMJCR21U3"],"award-info":[{"award-number":["JPMJCR21U3"]}]},{"name":"Japan Science and Technology Agency (JST) AIP Acceleration Research","award":["U19A2061"],"award-info":[{"award-number":["U19A2061"]}]},{"name":"Japan Science and Technology Agency (JST) AIP Acceleration Research","award":["JPMJCR21U3"],"award-info":[{"award-number":["JPMJCR21U3"]}]},{"name":"Suzhou Science and Technology Association Young Scientific and Technological Talents Entrustment Project","award":["U19A2061"],"award-info":[{"award-number":["U19A2061"]}]},{"name":"Suzhou Science and Technology Association Young Scientific and Technological Talents Entrustment Project","award":["JPMJCR21U3"],"award-info":[{"award-number":["JPMJCR21U3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning is widely used in modern orchard production for various inspection missions, which helps improve the efficiency of orchard operations. In the mission of visual detection during fruit picking, most current lightweight detection models are not yet effective enough to detect multi-type occlusion targets, severely affecting automated fruit-picking efficiency. This study addresses this problem by proposing the pioneering design of a multi-type occlusion apple dataset and an augmentation method of data balance. We divided apple occlusion into eight types and used the proposed method to balance the number of annotation boxes for multi-type occlusion apple targets. Finally, a validation experiment was carried out using five popular lightweight object detection models: yolox-s, yolov5-s, yolov4-s, yolov3-tiny, and efficidentdet-d0. The results show that, using the proposed augmentation method, the average detection precision of the five popular lightweight object detection models improved significantly. Specifically, the precision increased from 0.894 to 0.974, recall increased from 0.845 to 0.972, and mAP0.5 increased from 0.982 to 0.919 for yolox-s. This implies that the proposed augmentation method shows great potential for different fruit detection missions in future orchard applications.<\/jats:p>","DOI":"10.3390\/s22176325","type":"journal-article","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T02:55:34Z","timestamp":1661309734000},"page":"6325","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Augmentation Method for High Intra-Class Variation Data in Apple Detection"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4901-2104","authenticated-orcid":false,"given":"Huibin","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3017-5464","authenticated-orcid":false,"given":"Wei","family":"Guo","sequence":"additional","affiliation":[{"name":"Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guowen","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6294-0124","authenticated-orcid":false,"given":"Yun","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sambasivan, N., Kapania, S., Highfill, H., Akrong, D., Paritosh, P., and Aroyo, L.M. (2021, January 8\u201313). Everyone wants to do the model work, not the data work: Data Cascades in High-Stakes AI. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan.","DOI":"10.1145\/3411764.3445518"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"17631","DOI":"10.1109\/ACCESS.2021.3052240","article-title":"Towards an Efficient Tomato Harvesting Robot: 3D Perception, Manipulation, and End-Effector","volume":"9","author":"Jun","year":"2021","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.compag.2016.06.022","article-title":"A review of key techniques of vision-based control for harvesting robot","volume":"127","author":"Zhao","year":"2016","journal-title":"Comput. Electron. Agric."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/1729881419897473","article-title":"Fruit recognition based on pulse coupled neural network and genetic Elman algorithm application in apple harvesting robot","volume":"17","author":"Jia","year":"2020","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/1729881420925310","article-title":"Apple harvesting robot under information technology: A review","volume":"17","author":"Jia","year":"2020","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s43154-020-00034-1","article-title":"Selective Harvesting Robotics: Current Research, Trends, and Future Directions","volume":"2","author":"Kootstra","year":"2021","journal-title":"Curr. Robot. Rep."},{"key":"ref_7","first-page":"8","article-title":"Recognition of apple targets before fruits thinning by robot based on R-FCN deep convolution neural network","volume":"35","author":"Dandan","year":"2019","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Biffi, L., Mitishita, E., Liesenberg, V., Santos, A., Gon\u00e7alves, D., Estrabis, N., Silva, J., Osco, L.P., Ramos, A., and Centeno, J. (2020). ATSS Deep Learning-Based Approach to Detect Apple Fruits. Remote Sens., 13.","DOI":"10.3390\/rs13010054"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.patrec.2021.04.022","article-title":"Deep learning-based apple detection using a suppression mask R-CNN","volume":"147","author":"Chu","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.biosystemseng.2020.07.007","article-title":"Faster R\u2013CNN\u2013based apple detection in dense-foliage fruiting-wall trees using RGB and depth features for robotic harvesting","volume":"197","author":"Fu","year":"2020","journal-title":"Biosyst. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104289","DOI":"10.1016\/j.dib.2019.104289","article-title":"KFuji RGB-DS database: Fuji apple multi-modal images for fruit detection with color, depth and range-corrected IR data","volume":"25","author":"Vilaplana","year":"2019","journal-title":"Data Brief"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/LRA.2020.2965061","article-title":"MinneApple: A Benchmark Dataset for Apple Detection and Segmentation","volume":"5","author":"Hani","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Janowski, A., Ka\u017amierczak, R., Kowalczyk, C., and Szulwic, J. (2021). Detecting Apples in the Wild: Potential for Harvest Quantity Estimation. Sustainability, 13.","DOI":"10.3390\/su13148054"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e13866","DOI":"10.1111\/jfpe.13866","article-title":"Apple target recognition method in complex environment based on improved YOLOv4","volume":"44","author":"Ji","year":"2021","journal-title":"J. Food Process Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105380","DOI":"10.1016\/j.compag.2020.105380","article-title":"Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot","volume":"172","author":"Jia","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Luo, R., Li, Q., Deng, X., Yin, X., Ruan, C., and Jia, W. (2020). Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot. Electronics, 9.","DOI":"10.3390\/electronics9061023"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., Maleva, T., and Soloviev, V. (2020). Using YOLOv3 Algorithm with Pre- and Post-Processing for Apple Detection in Fruit-Harvesting Robot. Agronomy, 10.","DOI":"10.3390\/agronomy10071016"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108758","DOI":"10.1016\/j.scienta.2019.108758","article-title":"A method to obtain the near-large fruit from apple image in orchard for single-arm apple harvesting robot","volume":"257","author":"Lv","year":"2019","journal-title":"Sci. Hortic."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"9102","DOI":"10.1109\/ACCESS.2020.2964608","article-title":"Real-Time Apple Detection System Using Embedded Systems with Hardware Accelerators: An Edge AI Application","volume":"8","author":"Mazzia","year":"2020","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.compag.2019.01.012","article-title":"Apple detection during different growth stages in orchards using the improved YOLO-V3 model","volume":"157","author":"Tian","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2817869","DOI":"10.1155\/2021\/2817869","article-title":"Target Recognition and Trajectory Planning of Apple Harvesting Robot considering Color Multimedia Image Segmentation Algorithm","volume":"2021","author":"Wang","year":"2021","journal-title":"Adv. Multimed."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wu, L., Ma, J., Zhao, Y., and Liu, H. (2021). Apple Detection in Complex Scene Using the Improved YOLOv4 Model. Agronomy, 11.","DOI":"10.3390\/agronomy11030476"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"216772","DOI":"10.1109\/ACCESS.2020.3040423","article-title":"Apple Detection in Natural Environment Using Deep Learning Algorithms","volume":"8","author":"Xuan","year":"2020","journal-title":"IEEE Access"},{"key":"ref_24","first-page":"163","article-title":"Tracking and recognition algorithm for a robot harvesting oscillating apples","volume":"13","author":"Yang","year":"2020","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"105634","DOI":"10.1016\/j.compag.2020.105634","article-title":"Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN","volume":"176","author":"Gao","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5. Remote Sens., 13.","DOI":"10.3390\/rs13091619"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"882","DOI":"10.1109\/TNNLS.2016.2610465","article-title":"Online Nonlinear AUC Maximization for Imbalanced Data Sets","volume":"29","author":"Hu","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Mateusz","year":"2018","journal-title":"Neural Netw."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"23537","DOI":"10.1109\/ACCESS.2019.2899467","article-title":"A Parameter-Free Cleaning Method for SMOTE in Imbalanced Classification","volume":"7","author":"Yan","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s40537-020-00390-x","article-title":"Resampling imbalanced data for network intrusion detection datasets","volume":"8","author":"Bagui","year":"2021","journal-title":"J. Big Data"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"Learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"Haixiang","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Levi, G., and Hassncer, T. (2015, January 7\u201312). Age and gender classification using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition Workshops, Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.eij.2020.02.007","article-title":"A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks","volume":"22","author":"Sambasivam","year":"2021","journal-title":"Egypt. Inform. J."},{"key":"ref_34","unstructured":"He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1\u20138). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the IJCNN 2008: (IEEE World Congress on Computational Intelligence): IEEE International Joint Conference on the Neural Networks, Hong Kong, China."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref_36","unstructured":"Hasan, A., Sohel, F., Diepeveen, D., Laga, H., and Jones, M. (2022). Weed recognition using deep learning techniques on class-imbalanced imagery. Crop Pasture Sci."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ko\u0161\u010devi\u0107, K., Suba\u0161i\u0107, M., and Lon\u010dari\u0107, S. (2020, January 17\u201319). Guiding the Illumination Estimation Using the Attention Mechanism. Proceedings of the 2020 2nd Asia Pacific Information Technology Conference, Bali, Indonesia.","DOI":"10.1145\/3379310.3379329"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"84239","DOI":"10.1109\/ACCESS.2020.2992121","article-title":"Deep Learning-Based Illumination Estimation Using Light Source Classification","volume":"8","author":"Koscevic","year":"2020","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.biosystemseng.2011.07.005","article-title":"Design and control of an apple harvesting robot","volume":"110","author":"Zhao","year":"2011","journal-title":"Biosyst. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Mukhiddinov, M., Abdusalomov, A.B., and Cho, J. (2022). Automatic Fire Detection and Notification System Based on Improved YOLOv4 for the Blind and Visually Impaired. Sensors, 22.","DOI":"10.3390\/s22093307"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6325\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:13:53Z","timestamp":1760141633000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,23]]},"references-count":40,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22176325"],"URL":"https:\/\/doi.org\/10.3390\/s22176325","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,23]]}}}