基于深度学习的目标检测算法综述
Review of target detection algorithms based on deep learning
查看参考文献34篇
文摘
|
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。 |
其他语种文摘
|
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. |
来源
|
传感器与微系统
,2021,40(2):4-7,18 【扩展库】
|
DOI
|
10.13873/J.1000-9787(2021)02-0004-04
|
关键词
|
目标检测
;
卷积神经网络
;
两阶段目标检测算法
;
单阶段目标检测算法
|
地址
|
西安工业大学电子信息工程学院, 陕西, 西安, 710021
|
语种
|
中文 |
文献类型
|
综述型 |
ISSN
|
2096-2436 |
学科
|
自动化技术、计算机技术 |
基金
|
陕西省重点研发计划资助项目
|
文献收藏号
|
CSCD:6901258
|
参考文献 共
34
共2页
|
1.
Park S B. Content-based image classification using a neural network.
Pattern Recognition Letters,2004,25(3):287-300
|
被引
4
次
|
|
|
|
2.
Vailaya A. Automatic image orientation detection.
IEEE Transactions on Image Processing,2002,11(7):746-755
|
被引
2
次
|
|
|
|
3.
Voulodimos A. Deep learning for computer vision: A brief review.
Computational Intelligence and Neuroscience,2018,2018:1-13
|
被引
61
次
|
|
|
|
4.
Arroyo E. Attention and intention goals can mediate disruption in human-computer interaction.
Lecture Notes in Computer Science. 6947,2017:454-470
|
被引
2
次
|
|
|
|
5.
Guo Y. Deep learning for visual understanding.
Neurocomputing,2016,187(C):27-48
|
被引
28
次
|
|
|
|
6.
Nixon M S.
Feature extraction and image processing,2010
|
被引
3
次
|
|
|
|
7.
Xu Y. Sliding window and regression based cup detection in digital fundus images for glaucoma diagnosis.
Med Image Comput Comput Assist Interv,2011,14(3):1-8
|
被引
1
次
|
|
|
|
8.
成春阳. 基于多尺度角点的改进SIFT算法.
计算机应用与软件,2017,34(7):166-170
|
被引
1
次
|
|
|
|
9.
马也. 复杂背景下红外人体目标检测算法研究.
红外技术,2017,39(11):1038-1044
|
被引
3
次
|
|
|
|
10.
薛明东. 基于SVM算法的图像分类.
计算机工程与应用,2004,40(30):230-232
|
被引
4
次
|
|
|
|
11.
曹莹. AdaBoost算法研究进展与展望.
自动化学报,2013,39(6):745-758
|
被引
89
次
|
|
|
|
12.
Acharya U R. A deep convolutional neural network model to classify heartbeats.
Computers in Biology & Medicine,2017,89:389-396
|
被引
26
次
|
|
|
|
13.
Lecun Y L. Gradient-based learning applied to document recognition.
Proceedings of the IEEE,1998,86(11):2278-2324
|
被引
2031
次
|
|
|
|
14.
Krizhevsky A. ImageNet classification with deep convolutional neural networks.
International Conference on Neural Information Processing Systems,2012
|
被引
29
次
|
|
|
|
15.
Zeiler M D. Visualizing and understanding convolutional neural networks.
European Conference on Computer Vision,2013
|
被引
5
次
|
|
|
|
16.
Simonyan K. Very deep convolutional networks for large-scale image recognition.
Computer Science,2014,4(1):1-14
|
被引
34
次
|
|
|
|
17.
He K M. Deep residual learning for image recognition.
Conference on Computer Vision & Pattern Recognition,2016:770-779
|
被引
1
次
|
|
|
|
18.
Xie S. Aggregated residual transformations for deep neural networks.
IEEE Conference on Computer Vision & Pattern Recognition,2017
|
被引
1
次
|
|
|
|
19.
Gao H. Densely connected convolutional networks.
IEEE Conference on Computer Vision & Pattern Recognition,2017
|
被引
3
次
|
|
|
|
20.
黄良辉. 基于轻量级卷积神经网络的人脸识别方法.
湖南工业大学学报,2019,33(2):43-47
|
被引
3
次
|
|
|
|
|