|Table of Contents|

Research on Algorithm of Multi-Scale Target DetectionBased on Deep Learning in Monitoring Scenario(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2018年03期
Page:
33-
Research Field:
人工智能算法与应用专栏
Publishing date:

Info

Title:
Research on Algorithm of Multi-Scale Target DetectionBased on Deep Learning in Monitoring Scenario
Author(s):
Cheng Xianyi1; 2; Hu Haitao2; Ji Guohua1; Sun Lili1
(1.Department of Computer,Silicon Lake Vocational and Technical College,Kunshan 215323,China)(2.Nantong Research Institute for Advanced Communication Technologies,Nantong University,Nantong 226019,China)
Keywords:
deep learning; target detection; dilated kernelof convolution; monitoring scenarios
PACS:
TP181
DOI:
10.3969/j.issn.1672-1292.2018.03.005
Abstract:
In view of a problem of missed inspection in the video image processing under the monitoring environment,we analyze the deep learning method commonly used in existing target detection algorithms-Faster R-CNN,and improve a deep convolution neural network based on VGG16 convolution neural network. Expanding the width of the neural network,by adding an empty core to the first volume layer,makes the target detection model have scale invariance. The Cifar-10 dataset is tested on the in-depth learning platform PyTorch. The experimental results show that the improved target detection algorithm has a better scale invariance and has more advantages in the monitoring scene.

References:

[1] 赵玉吉. 基于视频序列的运动目标检测与跟踪算法研究[D]. 扬州:扬州大学,2017.
ZHAO Y J. Research on motion target detection and tracking algorithm based on video sequence[D]. Yangzhou:Yangzhou University,2017.(in Chinese).
[2]VIOLA P,JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai,USA,2001.
[3]DALAL N,TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego,USA,2005.
[4]SHIGO A. Support vector machines for pattern classification[M]. New York:Springer,2012.
[5]ROSS G. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago,Chile,2015.
[6]HINTERSTOISSER S,LEPETIT V,ILIC S,et al. Dominant orientation templates for real-time detection of textureless objects[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). San Francisco,USA,2010.
[7]万维. 基于深度学习的目标检测算法研究及应用[D]. 成都:电子科技大学,2015.
WAN W. Research and application of target detection algorithm based on in-depth learning[D]. Chengdu:University of Electronic Technology,2015.(in Chinese)
[8]吴慧. 基于深度学习的遥感影像目标检测[D]. 哈尔滨:哈尔滨工业大学,2016.
WU H. Target detection of remote sensing imaging based on in-depth learning[D]. Harbin:Harbin Institute of Technology,2016.(in Chinese)
[9]ROSS G,JEFF D. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE translations on pattern analysis and machine intelligence,2016,38(1):142-158.
[10]HE K,ZHANG X,REN S,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1904-1916.
[11]潘广贞,孙艳青,王凤. 基于Fast RCNN模型的车辆阴影去除[J]. 计算机工程与设计,2018(3):819-823.
PAN G Z,SUN Y Q,WANG F. Removal of vehicle shadow based on fast RCNN model[J]. Computer engineering and design,2018(3):819-823.(in Chinese).
[12]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. Montreal,Canada,2015:91-99.
[13]桑军,郭沛,项志立,等. Faster R-CNN的车型识别分析[J]. 重庆大学学报,2017,40(7):32-36.
SANG J,GUO P,XIANG Z L,et al. Vehicle detection based on faster-RCNN[J]. Journal of Chongqing university,2017,40(7):32-38.(in Chinese).
[14]ABDELGHAFFAR A A. Influence of sinusoidal and square voltages on partial discharge inception in geometries with point-like termination[J]. High voltage,2018,15(3):31-37.
[15]廖星宇.深度学习入门之PyTorch[M]. 北京:电子工业出版社,2017.
LIAO X Y. PyTorch of deep learning[M]. Beijing:Electronic Industry Press,2017.(in Chinese)

Memo

Memo:
-
Last Update: 2018-09-30