[1]柳胜超,王夏黎,王丽红,等.基于 Faster R-CNN 的交通警察目标检测研究[J].计算机技术与发展,2021,31(04):80-85.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 014]
　LIU Sheng-chao,WANG Xia-li,WANG Li-hong,et al.Research on Target Detection of Traffic Police Based on Faster R-CNN[J].,2021,31(04):80-85.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 014]
点击复制

基于 Faster R-CNN 的交通警察目标检测研究()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年04期
页码:
80-85
栏目:
图形与图像
出版日期:
2021-04-10

文章信息/Info

Title:
Research on Target Detection of Traffic Police Based on Faster R-CNN
文章编号:
1673-629X(2021)04-0080-06
作者:
柳胜超1 ; 王夏黎1 ; 王丽红1 ; 柳秋萍2
1. 长安大学 信息工程学院,陕西 西安 710061;
2. 陕西航天动力高科技股份有限公司,陕西 西安 710077
Author(s):
LIU Sheng-chao1 ; WANG Xia-li1 ; WANG Li-hong1 ; LIU Qiu-ping2
1. School of Information Engineering,Chang’an University,Xi’an 710061,China;
2. Shaanxi Aerospace Power High-tech Co. ,Ltd. ,Xi’ an 710077,China
关键词:
目标检测与定位; 深度学习; 图像预处理; SSD 网络; Faster R-CNN 网络
Keywords:
target detection and localization; deep learning; image preprocessing; SSD network; faster R-CNN network
分类号:
TP391. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 04. 014
摘要:
针对自动驾驶技术的高速发展与日渐复杂的交通系统网络缺少能够准确检测与定位交通警察的方法,将基于深度学习对在复杂环境中交通警察的准确检测与定位进行研究,? 该研究一方面对于有效保障交通警察的人身安全和提高通行效率具有积极的促进作用, 另一方面为后续的交通警察手势的识别提供重要的检测基础。 但是在实际的应用当 中交通警察一般处于复杂的场景当中,比如干扰人群、强光环境、复杂的天气,都会对交通警察的准确检测与定位造成影响。因此,该文首先通过对交通警察图像去噪和 Gamma 曲线校正的预处理方式来增强图像中的关键特征信息并排除噪声对图像的影响,然后分别对基于 SSD 网络模型的方法、基于 HOG 特征提取和 SVM 分类的方法、基于 Faster R-CNN 网络模型的方法进行实验,然后对三种方法进行对比,得出了基于 Faster R-CNN 网络模型的检测速度为 61. 523 ms,检测准确率为98.75% ,均高于其他 两种方法。
Abstract:
In view of the rapid development of autonomous driving technology and the increasingly complex transportation system network,there is a lack of methods that can accurately detect and locate traffic police. We will study the accurate detection and location of traffic police in complex environments based on deep learning. Effectively protecting the traffic police’s personal safety and improving traffic efficiency have a positive role in promoting,on the other hand,it provides an important detection basis? for the subsequent trafficpolice’s gesture recognition. However, in actual applications, the traffic police are generally in complex scenes, such as interfering crowds,strong light environments and complex weather,which will affect the accurate detection and positioning of the traffic police.Therefore,we firstly preprocess the traffic police images to enhance the key feature information in the image and eliminate the influence of noise on the image,and then separately experiment on the method based on SSD network model, the method based on HOG feature extraction and SVM classification and the method based on Faster R-CNN network model. Comparing the three methods,it is concludedthat the detection speed based on the Faster R-CNN network model is 61. 523 ms,and the detection accuracy rate is 98. 75% ,which ishigher than the other two methods.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(04):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(04):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(04):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(04):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(04):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(04):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(04):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(04):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(04):7.

更新日期/Last Update: 2020-04-10