Anti-shielding object detection method in dense scene based on fisheye camera

The invention provides an anti-shielding object detection method in a dense scene based on a fisheye camera, and the method comprises the following steps: collecting and marking an original image in an original scene, and obtaining a mask of a single object; based on the object mask, synthesizing the image according to a shielding relation based on the spatial position relation between the objects and a preset shielding priority, and obtaining a synthesized data set; dividing the synthetic data set into a plurality of sub-data sets with different identification difficulties according to the identification difficulty of the object; performing data enhancement on the synthesized data set; training an object detection network by adopting the synthesized data set after data enhancement; and inputting a to-be-detected image into the trained object detection network to obtain an object detection result. According to the method, the data acquisition cost can be greatly reduced, different types can be randomly added,