{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:47:11Z","timestamp":1785822431085,"version":"3.56.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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:p>Potato is an important staple crop worldwide, and accurate tuber detection is essential for intelligent harvesting, yield estimation, and quality management. During mechanized harvesting, potatoes are conveyed with large amounts of soil clods on conveyor belts. The similar appearance between soil-covered tubers and clods makes accurate identification and separation difficult under practical operating conditions. Existing methods are often limited by scale variation, object occlusion, irregular boundaries, and complex backgrounds, restricting their application in real-time harvesting systems.This study proposes DFINE-PFM, an end-to-end instance segmentation framework for automatic potato\u2013clod discrimination on harvesting conveyor belts. The framework incorporates four targeted improvements: a multi-scale feature diffusion module to enhance feature representation, a parallel large-kernel decomposition module to improve boundary extraction, a heterogeneous multi-branch convolution module to capture multi-granularity features with reduced redundancy, and an asymmetric receptive field convolution module to improve localization of small and irregular objects. A self-collected conveyor belt dataset under practical harvesting conditions was used for evaluation. DFINE-PFM achieved Precision, Recall, F1-score, and mAP values of 98.80%, 98.70%, 98.75%, and 98.03%, respectively, with an inference time of 43.41 ms. Compared with the baseline model, it improved Precision and mAP by 6.20 and 5.60 percentage points, respectively. Deployment experiments demonstrated stable real-time performance at 20 FPS under conveyor speeds of 0.1\u20130.6 m\/s. The proposed method provides an effective solution for automated potato\u2013clod separation and intelligent harvesting quality monitoring.<\/jats:p>","DOI":"10.3389\/fpls.2026.1906894","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:36:11Z","timestamp":1785821771000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DFINE-PFM: a real-time instance segmentation network for potato harvester conveyor belts"],"prefix":"10.3389","volume":"17","author":[{"given":"Qiyu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Qingdao Agricultural University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinping","family":"Mo","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Shandong Foreign Trade Vocational College","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Qingdao Agricultural University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Qingdao Agricultural University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangfei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Qingdao Agricultural University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranbing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Hainan University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Shandong Foreign Trade Vocational College","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"B1","first-page":"181","article-title":"Detection method of citrus based on deep convolution neural network","volume":"50","author":"Bi","year":"2019","journal-title":"Trans. Chin. Soc Agric.Mach."},{"key":"B2","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"B3","first-page":"6910","article-title":"Instances as queries","author":"Fang","year":"2021"},{"key":"B4","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/tpami.2019.2938758","article-title":"Res2Net: A new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B5","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv"},{"key":"B7","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.01412","article-title":"DEIM: DETR with improved matching for fast convergence","author":"Huang","year":"2025"},{"key":"B9","article-title":"Ultralytics YOLOv8[CP\/OL","author":"Jocher","year":"2023"},{"key":"B10","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"},{"key":"B11","first-page":"3041","article-title":"Mask DINO: Towards a unified transformer-based framework for object detection and segmentation","author":"Li","year":"2023"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfca.2025.108420","article-title":"Multi-task learning based approach for potato edibility detection and defect segmentation","volume":"148","author":"Li","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.899754","article-title":"The detection method of potato foliage diseases in complex background based on instance segmentation and semantic segmentation","volume":"13","author":"Li","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B14","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B15","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B16","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.115388","article-title":"A deep learning-based method for estimating the main stem length of sweet potato seedlings","volume":"238","author":"Mao","year":"2024","journal-title":"Measurement"},{"key":"B18","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"B19","article-title":"MixConv: Mixed depthwise convolutional kernels","author":"Tan","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.3390\/foods14071131","article-title":"Using a region-based convolutional neural network (R-CNN) for potato segmentation in a sorting process","volume":"14","author":"Verk","year":"2025","journal-title":"Foods"},{"key":"B21","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":"B22","first-page":"390","article-title":"CSPNet: A new backbone that can enhance learning capability of CNN","author":"Wang","year":"2020"},{"key":"B23","first-page":"13","article-title":"Integrity recognition of camellia oleifera seeds based on convolutional neural network","volume":"51","author":"Xie","year":"2020","journal-title":"Trans. Chin. Soc Agric. Mach."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108826","article-title":"Prototyping and evaluation of a novel machine vision system for real-time, automated quality grading of sweetpota-toes","volume":"219","author":"Xu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B25","first-page":"1466","article-title":"Pinwheel-shaped convolution and scale-based dynamic loss for infrared small target detection","author":"Yang","year":"2025"},{"key":"B26","first-page":"11115","article-title":"InceptionNeXt: When inception meets ConvNeXt","author":"Yu","year":"2024"},{"key":"B27","doi-asserted-by":"publisher","first-page":"109333","DOI":"10.1016\/j.jfca.2026.109333","article-title":"Geographical origin discrimination of Fructus Aurantii by visible near-infrared imaging with machine learning and explainable analysis","volume":"156","author":"Zhang","year":"2026","journal-title":"J. Food Compos. Anal."},{"key":"B28","doi-asserted-by":"publisher","first-page":"108240","DOI":"10.1016\/j.jfca.2025.108240","article-title":"Vis\/NIR spectroscopy and machine learning model for counterfeit Citri Reticulatae Pericarpium identification","volume":"148","author":"Zhang","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"B29","first-page":"1","article-title":"ByteTrack: Multi-object tracking by associating every detection box","author":"Zhang","year":"2022"},{"key":"B30","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1906894\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:36:12Z","timestamp":1785821772000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1906894\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":30,"alternative-id":["10.3389\/fpls.2026.1906894"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1906894","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"1906894"}}