Target detection belongs to a basic component of computer vision field, which predicts the specific types of targets and their positions that may exist in the image, frames the target to be detected with bounding box, and outputs the position of the bounding box and the class confidence of the target. Object detection is an extension of image classification function. Image classification is responsible for identifying the types of objects contained in the image, and object detection further predicts the positions of these objects. At the same time, object detection is also the basis of other high-level computer vision tasks such as semantic segmentation, object tracking, and behavior recognition. Since the VJ face recognition model in 2001, object detection has experienced 20 years of development.