Research on Object Detection Based on Deep Learning
Object detection is a core issue in the field of Machine Vision.After years of development,object detection methods based on Deep Learning technology have become a research hotspot.According to the principle and process of detection,object detection can be divided into one-stage object detection and two-stage object detection.Firstly,based on extensive literature research,the principles and ideas of mainstream object detection methods are compared.Then,the detection effects of various methods are compared using two parameters,the mAP and the FPS,and the advantages and disadvantages of common object detection methods are analyzed.Finally,predictions and prospects are made for the development of object detection.
国家科技期刊平台
NSTL
万方数据
