基于深度学习的目标检测研究综述
Survey of Object Detection Based on Deep Learning
查看参考文献69篇
|
文摘
|
目标检测是计算机视觉领域内的热点课题,在机器人导航、智能视频监控及航天航空等领域都有广泛的应用.本文首先综述了目标检测的研究背景、意义及难点,接着对基于深度学习目标检测算法的两大类进行综述,即基于候选区域和基于回归算法.对于第一类算法,先介绍了基于区域的卷积神经网络(Region with Convolutional Neural Network,R-CNN)系列算法,然后从四个维度综述了研究者在R-CNN系列算法基础上所做的研究:对特征提取网络的改进研究、对感兴趣区域池化层的改进研究、对区域提取网络的改进研究、对非极大值抑制算法的改进研究.对第二类算法分为YOLO(You Only Look Once)系列、SSD(Single Shot multibox Detector)算法及其改进研究进行综述.最后根据当前目标检测算法在发展更高效合理的检测框架的趋势下,展望了目标检测算法未来在无监督和未知类别物体检测方向的研究热点. |
|
其他语种文摘
|
Object detection is a hot topic in the field of computer vision,and has been widely used in robot navigation,intelligent video surveillance,aerospace,and other fields.The research background,significance and challenges of object detection were introduced.Then the object detection algorithms based on deep learning were reviewed according to two categories:candidate region-based and regression-based.For the candidate region-based algorithms,we first introduced the R-CNN(Region with Convolutional Neural Network)based series of algorithms,and then the R-CNN based methods were overviewed from four dimensions:the research of feature extraction networks,the region of interesting pooling researches,improved works based on region proposal networks,and some improved approaches of non maximum suppression algorithms.Next,the regression-based algor ithms were surveyed in terms of YOLO(You Only Look Once)series and SSD(Single Shot multibox Detector)series.Finally,according to the current trend of object detection algorithms that are developing more efficient and reasonable detection frameworks,the future research focuses of unsupervised and unknown category object detection directions were prospected. |
|
来源
|
电子学报
,2020,48(6):1230-1239 【核心库】
|
|
DOI
|
10.3969/j.issn.0372-2112.2020.06.026
|
|
关键词
|
目标检测
;
深度学习
;
特征提取
;
计算机视觉
;
视频监控
;
图像处理
;
卷积神经网络
|
|
地址
|
江西理工大学信息工程学院, 江西, 赣州, 341000
|
|
语种
|
中文 |
|
文献类型
|
综述型 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
江西省机器视觉及智能系统重点实验室
;
江西省赣州市"科技创新人才计划"项目
|
|
文献收藏号
|
CSCD:6770187
|
参考文献 共
69
共4页
|
|
1.
Li Liu.
Deep Learning for Generic Object Detection:A Survey,2018
|
CSCD被引
1
次
|
|
|
|
|
2.
Dalal N. Histograms of oriented gradients for human detection.
Proce edings of IEEE Conference on Computer Vision and Pattern Recognition,2005:886-893
|
CSCD被引
1
次
|
|
|
|
|
3.
Lowe D G. Distinctive image features from scale-invariant key points.
Intern ational Journal of Computer Vision,2004,60(2):91-110
|
CSCD被引
4682
次
|
|
|
|
|
4.
Lienhart R. An extended set of haar-like features for rapid object detecti on.
Proceedings of the International Conference on Image Processing,2002:900-903
|
CSCD被引
2
次
|
|
|
|
|
5.
Shawe-Taylor J.
An Introduction to Support Vector Machines and Oth er Kernel-based Learning Methods,2000
|
CSCD被引
1
次
|
|
|
|
|
6.
Freund Y. Experiments with a new boosting algorithm.
Internation al Conference on Machine Learning,1996:148-156
|
CSCD被引
1
次
|
|
|
|
|
7.
Liaw A. Classification and regression by random-forest.
R News,2002,2(3):18-22
|
CSCD被引
269
次
|
|
|
|
|
8.
姜维. 基于深度学习的场景文字检测综述.
电子学报,2019,47(5):1152-1161
|
CSCD被引
11
次
|
|
|
|
|
9.
Sharma K U. A review and an approach for object detection in images.
International Journal of Computational Vision and Robotics,2017,7(1/2):196-237
|
CSCD被引
5
次
|
|
|
|
|
10.
毕威. 基于图像显著轮廓的目标检测.
电子学报,2019,45(8):1902-1910
|
CSCD被引
1
次
|
|
|
|
|
11.
Chahal K S.
A Survey of Modern Object Detection Literature Using Deep Learni ng,2018
|
CSCD被引
1
次
|
|
|
|
|
12.
Oksuz Kemal.
Imbalance Problems in Object Detection: A Review,2019
|
CSCD被引
1
次
|
|
|
|
|
13.
Zhao Z Q. Object detection with deep learning:A review.
IEEE Transactions on Neural Networks and Learning Systems,2019,30(11):3212-3232
|
CSCD被引
112
次
|
|
|
|
|
14.
Ren S. Faster R-CNN:towards real-time object detection wi th region proposal networks.
IEEE Trans Pattern Anal Mach Intell,2015,39(6):1137-1149
|
CSCD被引
191
次
|
|
|
|
|
15.
Girshick R. Rich feature hierarchies for accurate objec t detection and semantic segmentation.
Computer Vision and Pattern Recogniti on,2014:580-587
|
CSCD被引
1
次
|
|
|
|
|
16.
周飞燕. 卷积神经网络研究综述.
计算机学报,2017,40(6):1229-1251
|
CSCD被引
577
次
|
|
|
|
|
17.
Krizhevsky A. ImageNet classification with deep convolutio nal neural networks.
Neural Information Processing Systems,2012,141(5):1097-1105
|
CSCD被引
3074
次
|
|
|
|
|
18.
Uijlingd J R. Selective search for object recognition.
International Journal of Computer Vision,2013,104(2):154-171
|
CSCD被引
1
次
|
|
|
|
|
19.
Everingham M. The pascal visual object classes (VOC) challenge.
International Journal of Computer Vision,2010,88(2):303-338
|
CSCD被引
703
次
|
|
|
|
|
20.
He K. Spatial pyramid pooling in deep convolutional networks for visual recognition.
Proceedings of the European Conference on Computer V ision,2014:346-361
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问