{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T12:11:06Z","timestamp":1774959066596,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Reasearch and Development Program of China","award":["2021YFD2000503"],"award-info":[{"award-number":["2021YFD2000503"]}]},{"name":"National Key Reasearch and Development Program of China","award":["32272004"],"award-info":[{"award-number":["32272004"]}]},{"name":"National Key Reasearch and Development Program of China","award":["BK20221188"],"award-info":[{"award-number":["BK20221188"]}]},{"name":"National Key Reasearch and Development Program of China","award":["CX(20)1007"],"award-info":[{"award-number":["CX(20)1007"]}]},{"name":"National Natural Science Foundation of China","award":["2021YFD2000503"],"award-info":[{"award-number":["2021YFD2000503"]}]},{"name":"National Natural Science Foundation of China","award":["32272004"],"award-info":[{"award-number":["32272004"]}]},{"name":"National Natural Science Foundation of China","award":["BK20221188"],"award-info":[{"award-number":["BK20221188"]}]},{"name":"National Natural Science Foundation of China","award":["CX(20)1007"],"award-info":[{"award-number":["CX(20)1007"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["2021YFD2000503"],"award-info":[{"award-number":["2021YFD2000503"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["32272004"],"award-info":[{"award-number":["32272004"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["BK20221188"],"award-info":[{"award-number":["BK20221188"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["CX(20)1007"],"award-info":[{"award-number":["CX(20)1007"]}]},{"name":"Jiangsu Agriculture Science and Technology Innovation Fund","award":["2021YFD2000503"],"award-info":[{"award-number":["2021YFD2000503"]}]},{"name":"Jiangsu Agriculture Science and Technology Innovation Fund","award":["32272004"],"award-info":[{"award-number":["32272004"]}]},{"name":"Jiangsu Agriculture Science and Technology Innovation Fund","award":["BK20221188"],"award-info":[{"award-number":["BK20221188"]}]},{"name":"Jiangsu Agriculture Science and Technology Innovation Fund","award":["CX(20)1007"],"award-info":[{"award-number":["CX(20)1007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Wheat, one of the most important food crops in the world, is usually harvested mechanically by combine harvesters. The impurity rate is one of the most important indicators of the quality of wheat obtained by mechanized harvesting. To realize the online detection of the impurity rate in the mechanized harvesting process of wheat, a vision system based on the DeepLabV3+ model of deep learning for identifying and segmenting wheat grains and impurities was designed in this study. The DeepLabV3+ model construction considered the four backbones of MobileNetV2, Xception-65, ResNet-50, and ResNet-101 for training. The optimal DeepLabV3+ model was determined through the accuracy rate, comprehensive evaluation index, and average intersection ratio. On this basis, an online detection method of measuring the wheat impurity rate in mechanized harvesting based on image information was constructed. The model realized the online detection of the wheat impurity rate. The test results showed that ResNet-50 had the best recognition and segmentation performance; the accuracy rate of grain identification was 86.86%; the comprehensive evaluation index was 83.63%; the intersection ratio was 0.7186; the accuracy rate of impurity identification was 89.91%; the comprehensive evaluation index was 87.18%; the intersection ratio was 0.7717; and the average intersection ratio was 0.7457. In terms of speed, ResNet-50 had a fast segmentation speed of 256 ms per image. Therefore, in this study, ResNet-50 was selected as the backbone network for DeepLabV3+ to carry out the identification and segmentation of mechanically harvested wheat grains and impurity components. Based on the manual inspection results, the maximum absolute error of the device impurity rate detection in the bench test was 0.2%, and the largest relative error was 17.34%; the maximum absolute error of the device impurity rate detection in the field test was 0.06%; and the largest relative error was 13.78%. This study provides a real-time method for impurity rate measurement in wheat mechanized harvesting.<\/jats:p>","DOI":"10.3390\/s22197627","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T05:12:21Z","timestamp":1665378741000},"page":"7627","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3+"],"prefix":"10.3390","volume":"22","author":[{"given":"Man","family":"Chen","sequence":"first","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}]},{"given":"Chengqian","family":"Jin","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}]},{"given":"Youliang","family":"Ni","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}]},{"given":"Jinshan","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}]},{"given":"Tengxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,8]]},"reference":[{"key":"ref_1","first-page":"219","article-title":"Analysis and optimization of cleaning mechanism of wheat combine harvester","volume":"52","author":"Geng","year":"2022","journal-title":"J. Jilin Univ. (Eng. Technol. Ed.)"},{"key":"ref_2","first-page":"147","article-title":"Error dynamic self-calibration method for grain yield monitoring based on combine harvester","volume":"51","author":"Zhou","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_3","first-page":"26","article-title":"Experimental study on double air outlet multi-ducts cleaning device of wheat combine harvester","volume":"36","author":"Jin","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng. (Trans. CSAE)"},{"key":"ref_4","first-page":"91","article-title":"Online monitoring method f mechanized soybean harvest quality based on machine vision","volume":"52","author":"Chen","year":"2021","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_5","first-page":"137","article-title":"Research on online identification system of rice broken impurities in combine harvester","volume":"42","author":"Chen","year":"2021","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_6","first-page":"235","article-title":"Detection and experiment on seed cotton impurity rate based on image analysis","volume":"37","author":"Wu","year":"2021","journal-title":"J. Xi\u2019an Univ. Technol."},{"key":"ref_7","first-page":"116","article-title":"Research on the identification of wheat grain varieties based on feature selection","volume":"43","author":"Feng","year":"2022","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_8","first-page":"590","article-title":"Wheat variety recognition method based on same position segmentation of transmitted light and reflected light images","volume":"34","author":"Yan","year":"2022","journal-title":"Acta Agric. Zhejiangensis"},{"key":"ref_9","first-page":"281","article-title":"Yield monitoring for grain combine harvester based on monocular vision","volume":"52","author":"Zeng","year":"2021","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_10","first-page":"174","article-title":"Segmentation of impurity rice grain images based on U-Net model","volume":"36","author":"Chen","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng. (Trans. CSAE)"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.biosystemseng.2019.04.022","article-title":"Detection of damaged wheat kernels using an impact acoustic signal processing technique based on Gaussian modelling and an improved extreme learning machine algorithm","volume":"184","author":"Guo","year":"2019","journal-title":"Biosyst. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105299","DOI":"10.1016\/j.compag.2020.105299","article-title":"Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat","volume":"172","author":"Moghimia","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_13","first-page":"281","article-title":"Wheat varieties identification based on a deep learning approach","volume":"20","author":"Laabassi","year":"2021","journal-title":"J. Saudi Soc. Agric. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"118397","DOI":"10.1016\/j.foreco.2020.118397","article-title":"Individual tree detection and species classification of Amazonian palms using UAV images and deep learning","volume":"475","author":"Ferreira","year":"2020","journal-title":"For. Ecol. Manag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.biosystemseng.2021.11.014","article-title":"A backlight and deep learning based method for calculating the number of seeds per silique","volume":"213","author":"Zhao","year":"2022","journal-title":"Biosyst. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105845","DOI":"10.1016\/j.compag.2020.105845","article-title":"Automatic extraction of wheat lodging area based on transfer learning method and deeplabv3+ network","volume":"179","author":"Zhang","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101583","DOI":"10.1016\/j.ecoinf.2022.101583","article-title":"Eff-UNet++: A novel architecture for plant leaf segmentation and counting","volume":"68","author":"Bhagat","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"101715","DOI":"10.1016\/j.ecoinf.2022.101715","article-title":"Extraction of soybean planting area based on feature fusion technology of multi-source low altitude unmanned aerial vehicle images","volume":"70","author":"Yang","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105931","DOI":"10.1016\/j.compag.2020.105931","article-title":"Detection of impurities in wheat using terahertz spectral imaging and convolutional neural networks","volume":"181","author":"Shen","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","first-page":"22","article-title":"High spectral inversion of wheat impurities rate for grain combine harvester","volume":"35","author":"Chen","year":"2019","journal-title":"Trans. Chin. Soc. Agric. Eng. (Trans. CSAE)"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106443","DOI":"10.1016\/j.compag.2021.106443","article-title":"Segmentation of abnormal leaves of hydroponic lettuce based on DeepLabV3+ for robotic sorting","volume":"190","author":"Wu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_22","first-page":"229","article-title":"Recognition of grape growing areas in multispectral images based on band enhanced DeepLabv3+","volume":"38","author":"Sun","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Eng. (Trans. CSAE)"},{"key":"ref_23","first-page":"143","article-title":"Rice lodging recognition method based on UAV remote sensing combined with the improved DeepLabV3+ model","volume":"27","author":"Mu","year":"2022","journal-title":"J. China Agric. Univ."},{"key":"ref_24","first-page":"209","article-title":"Identification of fusarium head blight in wheat based on image processing and Deeplabv3+ model","volume":"42","author":"Dai","year":"2021","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_25","first-page":"833","article-title":"Encoder-Decoder with atrous separable convolution for semantic image segmentation","volume":"11211","author":"Chen","year":"2018","journal-title":"Eur. Conf. Comput. Vis."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"116402","DOI":"10.1016\/j.image.2021.116402","article-title":"FD-SSD: An improved SSD object detection algorithm based on feature fusion and dilated convolution","volume":"98","author":"Yin","year":"2021","journal-title":"Signal Process. Image Commun."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7627\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:48:14Z","timestamp":1760143694000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":26,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197627"],"URL":"https:\/\/doi.org\/10.3390\/s22197627","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,8]]}}}