[1]程显毅,胡海涛,季国华,等.基于深度学习监控场景下的多尺度目标检测算法研究[J].南京师范大学学报(工程技术版),2018,18(03):033.[doi:10.3969/j.issn.1672-1292.2018.03.005]
 Cheng Xianyi,Hu Haitao,Ji Guohua,et al.Research on Algorithm of Multi-Scale Target DetectionBased on Deep Learning in Monitoring Scenario[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(03):033.[doi:10.3969/j.issn.1672-1292.2018.03.005]
点击复制

基于深度学习监控场景下的多尺度目标检测算法研究
分享到:

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

卷:
18卷
期数:
2018年03期
页码:
033
栏目:
人工智能算法与应用专栏
出版日期:
2018-09-30

文章信息/Info

Title:
Research on Algorithm of Multi-Scale Target DetectionBased on Deep Learning in Monitoring Scenario
文章编号:
1672-1292(2018)03-0033-06
作者:
程显毅12胡海涛2季国华1孙丽丽1
(1.硅湖职业技术学院计算机系,江苏 昆山 215323)(2.南通大学南通先进通信技术研究院,江苏 南通 226019)
Author(s):
Cheng Xianyi12Hu Haitao2Ji Guohua1Sun 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)
关键词:
深度学习目标检测空洞卷积核监控场景
Keywords:
deep learningtarget detectiondilated kernelof convolutionmonitoring scenarios
分类号:
TP181
DOI:
10.3969/j.issn.1672-1292.2018.03.005
文献标志码:
A
摘要:
针对监控环境下的视频图像处理存在漏检这一问题,分析现有目标检测算法中普遍使用的深度学习方法—Faster R-CNN,在VGG16卷积神经网络基础上,对深度卷积神经网络进行改进,在第一层卷积层中加入空洞卷积核,扩展神经网络的宽度,使得目标检测模型具有尺度不变性. 在深度学习平台PyTorch下对Cifar-10数据集进行了实验,实验结果显示,改进的目标检测算法具有较好的尺度不变性,在监控场景下更具优势.
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.

参考文献/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)

相似文献/References:

[1]陈 扬,曾 诚,程 成,等.一种基于CNN的足迹图像检索与匹配方法[J].南京师范大学学报(工程技术版),2018,18(03):039.[doi:10.3969/j.issn.1672-1292.2018.03.006]
 Chen Yang,Zeng Cheng,Cheng Cheng,et al.A CNN-based Approach to Footprint Image Retrieval and Matching[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(03):039.[doi:10.3969/j.issn.1672-1292.2018.03.006]
[2]王俊淑,张国明,胡 斌.基于深度学习的推荐算法研究综述[J].南京师范大学学报(工程技术版),2018,18(04):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]
 Wang Junshu,Zhang Guoming,Hu Bin.A Survey of Deep Learning Based Recommendation Algorithms[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(03):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]
[3]郝 坤,张天坤,史振威.基于时空特征的热带气旋强度预测方法[J].南京师范大学学报(工程技术版),2019,19(03):001.[doi:10.3969/j.issn.1672-1292.2019.03.001]
 Hao Kun,Zhang Tiankun,Shi Zhenwei.An Tropical Cyclone Intensity Prediction MethodBased on Spatial-Temporal Features[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):001.[doi:10.3969/j.issn.1672-1292.2019.03.001]
[4]任媛媛,张显峰,马永建,等.基于卷积神经网络的无人机遥感影像农村建筑物目标检测[J].南京师范大学学报(工程技术版),2019,19(03):029.[doi:10.3969/j.issn.1672-1292.2019.03.005]
 Ren Yuanyuan,Zhang Xianfeng,Ma Yongjian,et al.Target Detection of Rural Buildings in UAV Remote Sensing ImagesBased on Convolutional Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):029.[doi:10.3969/j.issn.1672-1292.2019.03.005]
[5]许博鸣,刘晓峰,业巧林,等.基于卷积神经网络面向自然场景建筑物识别技术的移动端应用[J].南京师范大学学报(工程技术版),2019,19(03):037.[doi:10.3969/j.issn.1672-1292.2019.03.006]
 Xu Boming,Liu Xiaofeng,Ye Qiaolin,et al.A Convolutional Neural Network Based on Mobile Application forIdentification of Buildings in Natural Scene[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):037.[doi:10.3969/j.issn.1672-1292.2019.03.006]
[6]陆 飞,沈世斌,苏晓云,等.基于改进Mask R-CNN的交通监控视频车辆检测算法[J].南京师范大学学报(工程技术版),2020,(04):044.[doi:10.3969/j.issn.1672-1292.2020.04.007]
 Lu Fei,Shen Shibin,Su Xiaoyun,et al.Vehicle Detection Algorithm Based on Improved Mask R-CNNin Traffic Surveillance Video[J].Journal of Nanjing Normal University(Engineering and Technology),2020,(03):044.[doi:10.3969/j.issn.1672-1292.2020.04.007]
[7]吴燕如,珠 杰,管美静.基于深度学习的藏文现代印刷物版面检测技术研究[J].南京师范大学学报(工程技术版),2021,(01):044.[doi:10.3969/j.issn.1672-1292.2021.01.007]
 Wu Yanru,Zhu Jie,Guan Meijing.Research on Layout Inspection Technology of ModernTibetan Prints Based on Deep Learning[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(03):044.[doi:10.3969/j.issn.1672-1292.2021.01.007]

备注/Memo

备注/Memo:
收稿日期:2018-04-18.
基金项目:国家自然科学基金(61771265)、江苏省现代教育技术研究课题(2017-R-54131)、南通大学-南通智能信息技术联合研究中心开放课题(KFKT2016B06).
通讯联系人:程显毅,博士,教授,研究方向:计算机视觉. E-mail:xycheng@ntu.edu.cn
更新日期/Last Update: 2018-09-30