帮助 关于我们

返回检索结果

基于双模全卷积网络的行人检测算法(特邀)
Pedestrian detection algorithm based on dual-model fused fully convolutional networks(Invited)

查看参考文献17篇

罗海波 1,2,3,4   何淼 1,2,3,4 *   惠斌 1,3,4   常铮 1,3,4  
文摘 在近距离行人检测任务中,平衡算法的检测精度与检测速度对于检测算法的实际应用有着重要意义。为了快速并准确地检测出近景行人目标,提出了一种基于模型融合全卷积网络的行人检测算法。首先,通过全卷积检测网络对图像中的目标进行检测,得到一系列候选框;其次,通过弱监督训练的语义分割网络得到图像的像素级分类结果;最后,将候选框与像素级分类结果融合,完成检测。实验结果表明:算法在检测速度与精度方面都具有较高的性能。
其他语种文摘 In the task of close range pedestrian detection, the balance of the precision and speed were of great significance to the practical application of the detection algorithm. In order to detect the close range target quickly and accurately, a pedestrian detection algorithm based on fused fully convolutional network was proposed. Firstly, a fully convolutional detection network was used to detect the target in the image, and a series of candidate bounding boxes were obtained. Secondly, pixel level classification results of the image were obtained by using a semantic segmentation network with weakly supervised training. Finally, the candidate bounding boxes and the pixel level classification results were fused to complete the detection. The experimental results show that the algorithm has good performance in both the speed and the precision of detection.
来源 红外与激光工程 ,2018,47(2):0203001-1-0203001-8 【核心库】
DOI 10.3788/IRLA201847.0203001
关键词 深度学习 ; 弱监督训练 ; 行人检测 ; 语义分割
地址

1. 中国科学院沈阳自动化研究所, 辽宁, 沈阳, 110016  

2. 中国科学院大学, 北京, 100049  

3. 中国科学院光电信息处理重点实验室, 中国科学院光电信息处理重点实验室, 辽宁, 沈阳, 110016  

4. 辽宁省图像理解与视觉计算重点实验室, 辽宁省图像理解与视觉计算重点实验室, 辽宁, 沈阳, 110016

语种 中文
文献类型 研究性论文
ISSN 1007-2276
学科 自动化技术、计算机技术
文献收藏号 CSCD:6207493

参考文献 共 17 共1页

1.  Benenson R. Ten years of pedestrian detection, what have we learned. European Conference on Computer Vision,2014:613-627 被引 8 次    
2.  Zhang Difei. Infrared shiptarget recognition based on SVM classification. Infrared and Laser Engineering. (in Chinese),2016,45(1):0104004 被引 4 次    
3.  Yosinski J. How transferable are features in deep neural networks. Advances in Neural Information Processing Systems,2014:3320-3328 被引 63 次    
4.  Luo Haibo. Status and prospect of target tracking based on deep learning. Infrared and Laser Engineering. (in Chinese),2017,46(5):0502002 被引 13 次    
5.  Viola P. Robust real-time face detection. International Journal of Computer Vision,2004,57(2):137-154 被引 525 次    
6.  Dalal N. Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition. IEEE Computer Society Conference on. 1,2005:886-893 被引 1 次    
7.  Dollar P. Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(8):1532-1545 被引 105 次    
8.  Sermanet P. Overfeat: Integrated recognition, localization and detection using convolutional networks. International Conference on Learning Representations,2014 被引 7 次    
9.  Ouyang W. Joint deep learning for pedestrian detection. Proceedings of the IEEE International Conference on Computer Vision,2013:2056-2063 被引 5 次    
10.  Ren S. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149 被引 1060 次    
11.  Simonyan K. Very deep convolutional networks for large-scale image recognition. Computer Vision and Pattern Recognition,2014 被引 22 次    
12.  Angelova A. Real-time pedestrian detection with deep network cascades. BMVC. 32,2015:1-12 被引 1 次    
13.  Redmon J. You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788 被引 662 次    
14.  Shelhamer E. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651 被引 601 次    
15.  He K. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778 被引 1338 次    
16.  Lin T Y. Focal loss for dense object detection. Computer Vision and Pattern Recognition,2017 被引 2 次    
17.  Khoreva A. Simple does it: Weakly supervised instance and semantic segmentation. Computer Vision and Pattern Recognition,2016 被引 1 次    
引证文献 3 篇

1 刘天赐 基于Grassmann流形几何深度网络的图像集识别方法 红外与激光工程,2018,47(7):0703002-1-0703002-7
被引 1 次

2 姚旺 基于人眼视觉特性的深度学习全参考图像质量评价方法 红外与激光工程,2018,47(7):0703004-1-0703004-8
被引 0 次

显示所有3篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号