AUTHOR=Zang Hecang , Wang Yanjing , Ru Linyuan , Zhou Meng , Chen Dandan , Zhao Qing , Zhang Jie , Li Guoqiang , Zheng Guoqing 

TITLE=Detection method of wheat spike improved YOLOv5s based on the attention mechanism

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.993244

DOI=10.3389/fpls.2022.993244

ISSN=1664-462X

ABSTRACT=In wheat breeding, spike number is a key indicator for evaluating wheat yield, and timely and accurate acquisition of wheat spike number is of great practical significance for yield prediction. In actual production, the method of using artificial field survey to count wheat spike is time-consuming and labor-intensive. Therefore, this paper proposes a method based on YOLOv5s with an improved attention mechanism, which can accurately detect the number of small-scale wheat spikes and better solve the problems of occlusion and cross-overlapping of wheat spike. This method introduces an efficient channel attention module (ECA) in the C3 module of the backbone structure of the YOLOv5s network model; at the same time, the global attention mechanism module (GCM) is inserted between the neck structure and the head structure; the attention mechanism can be more Effectively extract feature information and suppress useless information. The result shows that in the wheat spike counting task, the accuracy of the improved YOLOv5s model is increased by 9.3% compared with the standard YOLOv5s; The accuracy is improved by 3.92%. Therefore, the improved YOLOv5s method improves the applicability in complex field environments, and provides a technical reference for automatic identification of wheat spike number and yield estimation.