Recent progresses on object detection: a brief review

Abstract

Object detection, aiming at locating objects from a large number of specific categories in natural images, is a fundamental but challenging task in the field of computer vision. Recent years have seen significant progress of object detection using deep CNN mainly due to its robust feature representation ability. The goal of this paper is to provide a simple but comprehensive survey of the recent improvements in object detection in the era of deep learning. More than 100 key contributions are investigated mainly from five directions: architecture diagram, contextual reasoning, multi-layer exploiting, training strategy, and others which includes some other progress like real-time object detectors and works borrowing the idea from RNN and GAN. We discuss comprehensive but straightforward experimental comparisons under widely used benchmarks and metrics. This review finishes by providing promising trends for future research.