###

计算机系统应用英文版:2022,31(7):35-45

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

深度神经网络图像目标检测算法综述

付苗苗^1,2, 邓淼磊^1,2, 张德贤^1,2

(1.河南工业大学信息科学与工程学院, 郑州 450001;2.河南省粮食信息处理国际联合实验室, 郑州 450001)

Survey on Deep Neural Network Image Target Detection Algorithms

FU Miao-Miao^1,2, DENG Miao-Lei^1,2, ZHANG De-Xian^1,2

(1.College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China;2.Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 945次下载 2323次
Received:October 14, 2021 Revised:November 08, 2021

中文摘要: 随着深度卷积神经网络优异的特征提取能力被发掘, 目标检测的进程开始以一种势不可挡的姿态向前推进, 同时, 和深度学习结合的目标检测技术取得了显著的成果, 在自动驾驶、智能化交通系统、无人机场景、军事目标检测和医学导航等现实场景中得到了广泛的应用. 本文回顾了传统目标检测算法的缺点, 介绍了常用的检测数据集以及性能评估指标, 综述了基于深度学习的目标检测经典算法, 阐述了当前目标检测的以及存在的困难与挑战, 对目标检测的未来可行的研究方向进行了展望.

中文关键词: 卷积神经网络特征提取深度学习目标检测计算机视觉

Abstract:With the exploration of the excellent feature extraction capabilities of deep convolutional neural networks, target detection has made a great stride. At the same time, the target detection technology combined with deep learning has achieved remarkable results. It has been widely used in such real scenarios as automatic driving, intelligent transportation systems, drone scenarios, military target detection, and medical navigation. The study reviews the shortcomings of traditional target detection algorithms and introduces commonly used detection data sets and performance evaluation indicators. It also summarizes classic target detection algorithms based on deep learning and elaborates on current target detection and existing difficulties and challenges. The feasible research directions in the future are prospected.

keywords: convolutional neural network (CNN) feature extraction deep learning object detection computer vision

文章编号： 中图分类号： 文献标志码：

基金项目:

引用文本：
付苗苗,邓淼磊,张德贤.深度神经网络图像目标检测算法综述.计算机系统应用,2022,31(7):35-45
FU Miao-Miao,DENG Miao-Lei,ZHANG De-Xian.Survey on Deep Neural Network Image Target Detection Algorithms.COMPUTER SYSTEMS APPLICATIONS,2022,31(7):35-45

Author Name	Affiliation	E-mail
FU Miao-Miao	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China
DENG Miao-Lei	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China
ZHANG De-Xian	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China	zdx@haut.edu.cn

Author Name	Affiliation	E-mail
FU Miao-Miao	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China
DENG Miao-Lei	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China
ZHANG De-Xian	College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China	zdx@haut.edu.cn