@article{Zhou2023, 
author = {Wan Zhou and Yijie Chen and Weihao Li and Cong Zhang and Yajun Xiong and Wei Zhan and Lan Huang and Jun Wang and Lijuan Qiu},
title = {SPP-extractor: Automatic phenotype extraction for densely grown soybean plants},
year = {2023},
journal = {The Crop Journal},
volume = {11},
number = {5},
pages = {1569-1578},
keywords = {Soybean phenotype, Branch length, Computer vision, A* algorithm, Phenotype acquisition},
url = {https://www.sciopen.com/article/10.1016/j.cj.2023.04.012},
doi = {10.1016/j.cj.2023.04.012},
abstract = {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 R2 scores of 0.93–0.99 for four phenotypic traits, based on regression on manual measurements.}
}