首页 > 论文 > 激光与光电子学进展 > 54卷 > 8期(pp:81003--1)

基于加速区域卷积神经网络的夜间行人检测研究

Nighttime Pedestrian Detection Based on Faster Region Convolution Neural Network

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

摘要

行人检测是机器人和无人车夜间工作应用中的重要任务之一, 采用加速区域卷积神经网络框架实现夜间红外图像中的行人检测, 用区域建议网络生成候选区域, 无需单独从图像中生成候选区域。区域建议网络和用于分类以及位置精修的卷积网络中, 采用卷积层参数共享机制, 使得该框架具有端到端的优点, 因此无需手动选取目标特征, 实现了从输入图像直接到行人检测的功能。实验结果表明, 与使用传统方法和快速区域卷积神经网络相比, 使用加速区域卷积网络框架对红外图像进行行人检测的准确率从68.2%和73.4%提高到了90.9%, 检测时间从3.6 s/frame和2.3 s/frame缩短到了0.04 s/frame, 达到了实际应用中的实时性要求。

Abstract

Pedestrian detection is one of the most important tasks of robots and unmanned vehicles at nighttime. Faster region convolution neural network framework is used to realize the pedestrian detection of infrared image at nighttime. This framework uses region proposal network to generate region proposals. Therefore, it is unnecessary to generate region proposals separately from the image. The parameter sharing mechanism is adopted in the convolutional layers in region proposal network and convolutional network for classification and bounding box regression, which makes the framework an end-to-end advantage. Thus, the pedestrian detection can be implemented from the input image to the detection result directly and it is unnecessary to manually select the features of the target. Experimental results show that the proposed method increases the recognition accuracy from 68.2% and 73.4% to 90.9% and shortens the recognition time from 3.6 s/frame and 2.3 s/frame to 0.04 s/frame compared with the traditional method and fast region convolution neural network, respectively, which reaches the required real-time level in practical applications.

投稿润色
补充资料

中图分类号:TP391

DOI:10.3788/lop54.081003

所属栏目:图像处理

基金项目:国家自然科学基金(61375007)、上海市科委基础研究项目(15JC1400600)

收稿日期:2017-03-02

修改稿日期:2017-04-01

网络出版日期:--

作者单位    点击查看

叶国林:东华大学信息科学与技术学院, 上海 201620东华大学数字化纺织服装技术教育部工程研究中心, 上海 201620
孙韶媛:东华大学信息科学与技术学院, 上海 201620东华大学数字化纺织服装技术教育部工程研究中心, 上海 201620
高凯珺:东华大学信息科学与技术学院, 上海 201620东华大学数字化纺织服装技术教育部工程研究中心, 上海 201620
赵海涛:华东理工大学信息科学与工程学院, 上海 200237

联系人作者:叶国林(863939325@qq.com)

备注:叶国林(1992-), 男, 硕士研究生, 主要从事红外图像处理方面的研究。

【1】Qin Jian, Wang Meihua. Fast pedestrian proposal generation algorithm using online Gaussian model[J]. Acta Optica Sinica, 2016, 36(11): 1115001.
覃 剑, 王美华. 采用在线高斯模型的行人检测候选框快速生成方法[J]. 光学学报, 2016, 36(11): 1115001.

【2】Xu Lu, Zhao Haitao, Sun Shaoyuan. Monocular infrared image depth estimation based on deep convolutional neural networks[J]. Acta Optica Sinica, 2016, 36(7): 0715002.
许 路, 赵海涛, 孙韶媛. 基于深层卷积神经网络的单目红外图像深度估计[J]. 光学学报, 2016, 36(7): 0715002.

【3】Xu Xin, Sun Shaoyuan, Sha Yujie, et al. A method of infrared image mosaic based on improved RANSAC[J]. Laser & Optoelectronics Progress, 2014, 51(11): 111001.
徐 鑫, 孙韶媛, 沙钰杰, 等. 一种基于改进RANSAC的红外图像拼接方法[J]. 激光与光电子学进展, 2014, 51(11): 111001.

【4】Zou Fangyu, Sun Shaoyuan, Xi Lin, et al. Color stereo vision method of vehicular infrared images with depth perception[J]. Laser & Optoelectronics Progress, 2013, 50(1): 011101.
邹芳喻, 孙韶媛, 席 林, 等. 具有深度视觉感的车载红外图像彩色化方法[J]. 激光与光电子学进展, 2013, 50(1): 011101.

【5】Dalal N, Triggs B. Histograms of oriented gradients for human detection[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, 1(1): 886-893.

【6】Lin Chengzhu. Pedestrian detection based on improved boosted cascade and fusion of multiple features[D]. Xiamen: Xiamen University, 2010: 27-37.
林成竹. 基于改进的级联分类器和多特征融合的行人检测方法研究[D]. 厦门: 厦门大学, 2010: 27-37.

【7】Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[J]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.

【8】Girshick R. Fast-RCNN[J]. Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.

【9】Uijlings J R R, Sande K E A, Gevers T, et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2): 154-171.

【10】Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]. Advances in Neural Information Processing Systems, 2015: 91-99.

【11】He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]. European Conference on Computer Vision, 2014: 346-361.

引用该论文

Ye Guolin,Sun Shaoyuan,Gao Kaijun,Zhao Haitao. Nighttime Pedestrian Detection Based on Faster Region Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2017, 54(8): 081003

叶国林,孙韶媛,高凯珺,赵海涛. 基于加速区域卷积神经网络的夜间行人检测研究[J]. 激光与光电子学进展, 2017, 54(8): 081003

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