;Rat hole density serves as a significant indicator for assessing the extent of rat damage in grasslands.In the image acquisition for rat hole recognition and count near ground by deep learning,the optimal image input size and shooting angle are crucial.To address these considerations,an image acquisition device equipped with an incli-nation sensor was designed,and a dataset of 2 325 rat hole images was collected from Xilingol grassland and manual-ly annotated.The recognition performance was compared under 3 image input sizes(416 pixel ×416 pixel,608 pixel × 608 pixel,1 024 pixel × 1 024 pixel),4 shooting angles(21°,32°,41°,and 51°),and 2 target recognition mod-els(YOLOv3 and YOLOv4).The findings revealed that YOLOv4 achieved superior performance when the image in-put size was set as 416 pixel ×416 pixel.Furthermore,the recognition performance was optimal at the shooting angle of 41°,while it was the poorest at 32°.The proposed method was validated by comparing it with relevant approaches published within the past three years.These results offered valuable insights to support the development of intelligent monitoring technologies for assessing rat damage in grassland ecosystems.
关键词
目标检测/草原生态/机器视觉/鼠洞/YOLOv3模型/YOLOv4模型
Key words
object detection/grassland ecosystem/machine vision/rat hole/YOLOv3 model/YOLOv4 model
维普
万方数据