Algorithm 1: pseudo-code of the proposed model

Input: An image to be detected

Output: An image with detection results

1:     Resize the input image to 416 × 416 and normalize it.

2:     Pass the processed image through the backbone network to extract features.

3:     Feed the extracted features into the network model (backbone, neck, and head) to obtain candidate bounding boxes.

4:     For each candidate bounding box:               Perform classification and bounding box regression;               Decode the regression results to determine the final position of the bounding box;               Apply DIoU-NMS to filter out overlapping detections;               Map the detection result onto the original image.

5:     Return the image with the overlaid detection results.