Wheat seedling line center line detection method based on improved YOLOv3

The invention provides a wheat seedling row center line detection method based on improved YOLOv3. The wheat seedling row center line detection method based on improved YOLOv3 comprises the following steps: step 1, detecting wheat seedling rows by using an improved YOLOv3 target detection model; step 2, extracting wheat seedling feature points in the detection frame by using the defined gray threshold; 3, using a circular scanning window to extract a wheat seedling line center point; and step 4, fitting the center points of the wheat seedlings in each column by using a least square method, and extracting the center lines of the wheat seedlings in each column. The wheat seedling line center line detection method based on the improved YOLOv3 is not influenced by weeds, shadows and illumination changes, and is also suitable for wheat seedling images with certain yaw angles. Therefore, the wheat seedling line center line detection method based on the improved YOLOv3 is wider in adaptability and more stable, and p