首页 > 论文 > 激光与光电子学进展 > 56卷 > 18期(pp:181003--1)

基于卷积神经网络和RGB-D图像的车辆检测算法

Vehicle Detection Algorithm Based on Convolutional Neural Network and RGB-D Images

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对利用彩色图像进行车辆检测时会受到路面阴影、车辆反光和光线不足等复杂情况影响的问题,提出一种基于卷积神经网络并融合彩色与深度图像的车辆检测算法。设计单通道RG-D融合网络和双通道RGB-D融合网络两种改进模型,分别用于提高检测速度和准确度。实验使用GTA(Grand Theft Auto)车辆数据集对该算法进行测试,并与基于RGB图像的其他流行算法进行对比和分析,结果表明:与基于彩色图像的Yolo v2算法相比,利用双通道RGB-D融合网络检测的准确率和召回率分别提升5.69%和6.31%,利用单通道RG-D融合网络对单一图像的最快检测速度达到24 ms。实验证明,基于RGB-D图像的改进网络模型能够实现实时检测,并有效提高车辆检测精度。

Abstract

Aim

ing at the problem that using RGB images for vehicle detection are affected by complex conditions such as road shadow, vehicle reflection and insufficient light. The paper proposes a vehicle detection algorithm based on convolutional neural network and combination of RGB and depth images. Two improved models of single-channel RG-D and double-channel RGB-D fusion networks are designed to improve detection speed and accuracy respectively. The algorithm is tested with (Grand Theft Auto) vehicle dataset and compared with other popular algorithms based on RGB images. The results show that compared with Yolo v2 algorithm based on RGB images, detection accuracy and recall rates increase 5.69% and 6.31% respectively by double-channel RGB-D fusion network, and the fastest detection speed of single image reaches 24 ms with single-channel RG-D fusion network. Experiments show that the improved network model based on RGB-D images can achieve real-time detection and effectively improve vehicle detection accuracy.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.181003

所属栏目:图像处理

基金项目:国防科技创新特区专项;

收稿日期:2019-02-25

修改稿日期:2019-04-01

网络出版日期:2019-09-01

作者单位    点击查看

王得成:航天工程大学研究生院, 北京 101416
陈向宁:航天工程大学航天信息学院, 北京 101416
赵峰:航天工程大学研究生院, 北京 10141661618部队, 北京 100094
孙浩燃:酒泉卫星发射中心, 甘肃 酒泉 730000

联系人作者:陈向宁(18810836867@163.com)

备注:国防科技创新特区专项;

【1】Chen X. Three-dimensional plane target based on neural network recognition. Changchun: Changchun University of Science and Technology. 7-9(2011).
陈曦. 基于神经网络的三维飞机目标识别研究. 长春: 长春理工大学. 7-9(2011).

【2】Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision. 60(2), 91-110(2004).

【3】Dalal N and Triggs B. Histograms of oriented gradients for human detection. [C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR''''05), June 20-25, 2005, San Diego, CA, USA. New York: IEEE. 886-893(2005).

【4】Schuldt C, Laptev I and Caputo B. Recognizing human actions: a local SVM approach. [C]∥Proceedings of the 17th International Conference on Pattern Recognition, August 26, 2004, Cambridge, UK. New York: IEEE. 3, 32-36(2004).

【5】Lu H T and Zhang Q C. Applications of deep convolutional neural network in computer vision. Journal of Data Acquisition & Processing. 31(1), 1-17(2016).
卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述. 数据采集与处理. 31(1), 1-17(2016).

【6】Hinton G E. Reducing the dimensionality of data with neural networks. Science. 313(5786), 504-507(2006).

【7】Tu S Q, Xue Y J, Liang Y et al. Review on RGB-D image classification. Laser & Optoelectronics Progress. 53(6), (2016).
涂淑琴, 薛月菊, 梁云 等. RGB-D图像分类方法研究综述. 激光与光电子学进展. 53(6), (2016).

【8】Socher R, Huval B, Bath B et al. Convolutional-recursive deep learning for 3D object classification. [C]∥Proceedings of the 25th International Conference on Neural Information Processing Systems, December 3-6, 2012, Lake Tahoe, Nevada. USA: Curran Associated Inc. 1, 656-664(2012).

【9】Eitel A, Springenberg J T, Spinello L et al. Multimodal deep learning for robust RGB-D object recognition. [C]∥2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 28-October 2, 2015, Hamburg, Germany. New York: IEEE. 681-687(2015).

【10】Li W. Research on RGB-D object recognition via feature learning. Wuhan: Huazhong University of Science and Technology. 24-28(2016).
李威. 基于特征学习的RGB-D目标识别算法研究. 武汉: 华中科技大学. 24-28(2016).

【11】Xu X Y, Li Y C, Wu G S et al. Multi-modal deep feature learning for RGB-D object detection. Pattern Recognition. 72, 300-313(2017).

【12】Liu F, Liu P Y, Zhang J N et al. Joint detection of RGB-D images based on double flow convolutional neural network. Laser & Optoelectronics Progress. 55(2), (2018).
刘帆, 刘鹏远, 张峻宁 等. 基于双流卷积神经网络的RGB-D图像联合检测. 激光与光电子学进展. 55(2), (2018).

【13】Qu L, Wang K R, Chen L L et al. Fast road detection based on RGBD images and convolutional neural network. Acta Optica Sinica. 37(10), (2017).
曲磊, 王康如, 陈利利 等. 基于RGBD图像和卷积神经网络的快速道路检测. 光学学报. 37(10), (2017).

【14】Redmon J and Farhadi A. YOLO9000: better, faster, stronger. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI. New York: IEEE. 6517-6525(2017).

【15】Shelhamer E, Long J and Darrell T. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(4), 640-651(2017).

【16】Krizhevsky A, Sutskever I and Hinton G E. ImageNet classification with deep convolutional neural networks. [C]∥Proceedings of the 25th International Conference on Neural Information Processing Systems, December 3-6, 2012, Lake Tahoe, Nevada. New York: ACM. 1, 1097-1105(2012).

【17】Ren S Q, He K M, Girshick R et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(6), 1137-1149(2017).

【18】Liu W, Anguelov D, Erhan D et al. SSD: single shot MultiBox detector. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Berlin, Germany: Springer. 9905, 21-37(2016).

【19】Silberman N, Hoiem D, Kohli P et al. Indoor segmentation and support inference from RGBD images. ∥Fitzgibbon A, Lazebnik S, Perona P Berlin, et al. Computer vision-ECCV 2012. Lecture notes in computer science. Berlin, Heidelberg: Springer. 7576, 746-760(2012).

引用该论文

Decheng Wang,Xiangning Chen,Feng Zhao,Haoran Sun. Vehicle Detection Algorithm Based on Convolutional Neural Network and RGB-D Images[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181003

王得成,陈向宁,赵峰,孙浩燃. 基于卷积神经网络和RGB-D图像的车辆检测算法[J]. 激光与光电子学进展, 2019, 56(18): 181003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF