A review of object detection based on deep learning

被引:3
作者
Youzi Xiao
Zhiqiang Tian
Jiachen Yu
Yinshu Zhang
Shuai Liu
Shaoyi Du
Xuguang Lan
机构
[1] Xi’an Jiaotong University,School of Software Engineering
[2] Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics
来源
Multimedia Tools and Applications | 2020年 / 79卷
关键词
Object detection; Deep learning; Deep convolutional neural networks; Computer vision;
D O I
暂无
中图分类号
学科分类号
摘要
With the rapid development of deep learning techniques, deep convolutional neural networks (DCNNs) have become more important for object detection. Compared with traditional handcrafted feature-based methods, the deep learning-based object detection methods can learn both low-level and high-level image features. The image features learned through deep learning techniques are more representative than the handcrafted features. Therefore, this review paper focuses on the object detection algorithms based on deep convolutional neural networks, while the traditional object detection algorithms will be simply introduced as well. Through the review and analysis of deep learning-based object detection techniques in recent years, this work includes the following parts: backbone networks, loss functions and training strategies, classical object detection architectures, complex problems, datasets and evaluation metrics, applications and future development directions. We hope this review paper will be helpful for researchers in the field of object detection.
引用
收藏
页码:23729 / 23791
页数:62
相关论文
共 205 条
[1]  
Alexe B(2012)Measuring the objectness of image windows IEEE Transactions on Pattern Analysis and Machine Intelligence 34 2189-2202
[2]  
Deselaers T(2008)Classification with a reject option using a hinge loss J Mach Learn Res 9 1823-1840
[3]  
Ferrari V(2013)Representation learning: a review and new perspectives IEEE Transactions on Pattern Analysis and Machine Intelligence 35 1798-1828
[4]  
Bartlett PL(1997)Multitask learning Mach Learn 28 41-75
[5]  
Wegkamp MH(2014)Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature Geosci Model Dev 7 1247-1250
[6]  
Bengio Y(2015)Contextualizing object detection and classification IEEE Transactions on Pattern Analysis and Machine Intelligence 37 13-27
[7]  
Courville A(2016)Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images IEEE Trans Geosci Remote Sens 54 7405-7415
[8]  
Vincent P(1995)Support vector machine Mach Learn 20 273-297
[9]  
Caruana R(2005)A tutorial on the cross-entropy method Ann Oper Res 134 19-67
[10]  
Chai T(2012)Pedestrian detection: an evaluation of the state of the art IEEE Transactions on Pattern Analysis and Machine Intelligence 34 743-761