Review of target detection algorithms based on deep learning

WU Xue; SONG Xiaoru; GAO Song; CHEN Chaobo

doi:10.13873/J.1000-9787(2021)02-0004-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Review of target detection algorithms based on deep learning

更新时间：2025-09-11

- Review of target detection algorithms based on deep learning
- Issue 2, Pages: 4-7+18(2021)
- 作者机构：
  
  西安工业大学电子信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2021)02-0004-04
  CLC： TP18;TP391.41
- Published：2021
- 稿件说明：
移动端阅览
WU Xue, SONG Xiaoru, GAO Song, et al. Review of target detection algorithms based on deep learning[J]. 2021, (2): 4-7+18.
DOI：

WU Xue, SONG Xiaoru, GAO Song, et al. Review of target detection algorithms based on deep learning[J]. 2021, (2): 4-7+18. DOI： 10.13873/J.1000-9787(2021)02-0004-04.

摘要

视觉目标检测作为计算机视觉的一个重要研究方向

已广泛应用于人脸检测、行人检测和无人驾驶等领域。随着大数据、计算机硬件技术和深度学习算法在图像分类中的突破性进展

基于深度学习的目标检测算法成为主流。本文综述了基于深度学习目标检测算法的研究现状和发展方向。首先介绍卷积神经网络(CNN)的研究进展和经典模型;然后对目前主流的基于深度学习的两阶段目标检测算法和单阶段目标检测算法的发展、改进和不足进行归纳;最后对深度学习目标检测两种主流算法进行比较并做出总结和未来展望。

Abstract

As an important research direction of computer vision

visual object detection has been widely used in face detection

pedestrian detection

unmanned driving and other fields. With the breakthrough of big data

computer hardware technology and deep learning in image classification

target detection algorithm based on deep learning has become the mainstream. Research status and development of target detection algorithm based on deep learning is reviewed. Research progress and classical model for convolutional neural network（ CNN） is introduced.Development

improvement and shortcomings of the current mainstream two-stage target detection algorithm and single-stage target detection algorithm based on deep learning is summarized. Compare the two main current algorithms of deep learning target detection and make a summary and future outlook.

关键词

Keywords

references

Views

5200

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of mobile terminal violation lane-crossing detection system based on information fusion

Traffic sign recognition algorithm based on double-channel CNN

Flying object recognition algorithm based on region CNN

Research on restoration technology of motion blur image

Related Author

CHEN Xin

YU Jialin

HE Junji

YU Runrun

JIANG Xiaoyan

ZHU Kaiying

JIANG Guanghao

ZHOU Wei

Related Institution

Institute of Advanced Agriculture Sciences,Peking University/Shandong Laboratory ofAdvanced Sciences in Weifang

School of Logistics Engineering,Shanghai Maritime University

School of Electronic and Electrical Engineering,Shanghai University of Engineering Science

College of Physics and Information Engineering,Fuzhou University

School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology

⁰