Wan Zhou , Yijie Chen , Weihao Li , Cong Zhang , Yajun Xiong , Wei Zhan , Lan Huang , Jun Wang , Lijuan Qiu
{"title":"SPP提取器:密生大豆植株表型的自动提取","authors":"Wan Zhou , Yijie Chen , Weihao Li , Cong Zhang , Yajun Xiong , Wei Zhan , Lan Huang , Jun Wang , Lijuan Qiu","doi":"10.1016/j.cj.2023.04.012","DOIUrl":null,"url":null,"abstract":"<div><p>Automatic collecting of phenotypic information from plants has become a trend in breeding and smart agriculture. Targeting mature soybean plants at the harvesting stage, which are dense and overlapping, we have proposed the SPP-extractor (soybean plant phenotype extractor) algorithm to acquire phenotypic traits. First, to address the mutual occultation of pods, we augmented the standard YOLOv5s model for target detection with an additional attention mechanism. The resulting model could accurately identify pods and stems and could count the entire pod set of a plant in a single scan. Second, considering that mature branches are usually bent and covered with pods, we designed a branch recognition and measurement module combining image processing, target detection, semantic segmentation, and heuristic search. Experimental results on real plants showed that SPP-extractor achieved respective <span><math><mrow><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup></mrow></math></span> scores of 0.93–0.99 for four phenotypic traits, based on regression on manual measurements.</p></div>","PeriodicalId":10790,"journal":{"name":"Crop Journal","volume":"11 5","pages":"Pages 1569-1578"},"PeriodicalIF":6.0000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"SPP-extractor: Automatic phenotype extraction for densely grown soybean plants\",\"authors\":\"Wan Zhou , Yijie Chen , Weihao Li , Cong Zhang , Yajun Xiong , Wei Zhan , Lan Huang , Jun Wang , Lijuan Qiu\",\"doi\":\"10.1016/j.cj.2023.04.012\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Automatic collecting of phenotypic information from plants has become a trend in breeding and smart agriculture. Targeting mature soybean plants at the harvesting stage, which are dense and overlapping, we have proposed the SPP-extractor (soybean plant phenotype extractor) algorithm to acquire phenotypic traits. First, to address the mutual occultation of pods, we augmented the standard YOLOv5s model for target detection with an additional attention mechanism. The resulting model could accurately identify pods and stems and could count the entire pod set of a plant in a single scan. Second, considering that mature branches are usually bent and covered with pods, we designed a branch recognition and measurement module combining image processing, target detection, semantic segmentation, and heuristic search. Experimental results on real plants showed that SPP-extractor achieved respective <span><math><mrow><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup></mrow></math></span> scores of 0.93–0.99 for four phenotypic traits, based on regression on manual measurements.</p></div>\",\"PeriodicalId\":10790,\"journal\":{\"name\":\"Crop Journal\",\"volume\":\"11 5\",\"pages\":\"Pages 1569-1578\"},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2023-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Crop Journal\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2214514123000739\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Crop Journal","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214514123000739","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
SPP-extractor: Automatic phenotype extraction for densely grown soybean plants
Automatic collecting of phenotypic information from plants has become a trend in breeding and smart agriculture. Targeting mature soybean plants at the harvesting stage, which are dense and overlapping, we have proposed the SPP-extractor (soybean plant phenotype extractor) algorithm to acquire phenotypic traits. First, to address the mutual occultation of pods, we augmented the standard YOLOv5s model for target detection with an additional attention mechanism. The resulting model could accurately identify pods and stems and could count the entire pod set of a plant in a single scan. Second, considering that mature branches are usually bent and covered with pods, we designed a branch recognition and measurement module combining image processing, target detection, semantic segmentation, and heuristic search. Experimental results on real plants showed that SPP-extractor achieved respective scores of 0.93–0.99 for four phenotypic traits, based on regression on manual measurements.
Crop JournalAgricultural and Biological Sciences-Agronomy and Crop Science
CiteScore
9.90
自引率
3.00%
发文量
638
审稿时长
41 days
期刊介绍:
The major aims of The Crop Journal are to report recent progresses in crop sciences including crop genetics, breeding, agronomy, crop physiology, germplasm resources, grain chemistry, grain storage and processing, crop management practices, crop biotechnology, and biomathematics.
The regular columns of the journal are Original Research Articles, Reviews, and Research Notes. The strict peer-review procedure will guarantee the academic level and raise the reputation of the journal. The readership of the journal is for crop science researchers, students of agricultural colleges and universities, and persons with similar academic levels.