Detection of wheat scab fungus spores utilizing the Yolov5-ECA-ASFF network structure.

•Fewer studies have been conducted to achieve rapid detection and identification of Fusarium germinate spores of wheat blast using deep learning algorithms.•In order to solve the problems of small density and difficult positioning of spore image targets, an improved Yolov5-ECA-ASFF target detection algorithm is proposed.•Yolov5-ECA-ASFF achieves good recognition results in multi-target detection and complex background, and the average recognition accuracy reaches 98.57%.•The method of this study can accurately detect and identify wheat scab spores when multiple mixed spores coexist.