The task of object detection is to find all the objects of interest in the image and determine their categories and positions, which is one of the core problems in the field of computer vision. Target detection is divided into two series -- RCNN series and YOLO series. RCNN series is a representative algorithm based on region detection. RCNN series algorithms are mainly used in target detection. The classical target detection algorithm uses the sliding window method to judge all possible regions in turn. Selective Search method is used in RCNN to extract a series of candidate regions which are more likely to be objects in advance, and then only features are extracted from these candidate regions (using CNN) for judgment.