The traffic sign detection algorithm based on region of interest extraction and double filter

被引：0

作者：

Yu D. ^{[1
]}

Kang J. ^{[2
]}

Cao Z. ^{[3
]}

Nayyar A. ^{[4
]}

机构：

[1] Department of Information Technology, Henan Polytechnic University, Zhengzhou

[2] Department of Architectural Engineering, Henan College of Transportation, Hengzhou

[3] Department of Art and Design, Zhengzhou University of Aeronautics, Zhengzhou

[4] Department of Computer Science, Duy Tan University, Da Nang

来源：

Recent Advances in Computer Science and Communications | 2021年 / 14卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Context aware filter; Double filter; Maximally stable extremal regions; Region of interest; Traffic sign detection; Wave equation;

D O I：

10.2174/2213275912666190823112357

中图分类号：

学科分类号：

摘要：

Objective: In order to solve the current traffic sign detection problem due to the interference of various complex factors, as it is difficult to effectively carry out the correct detection of traffic signs, a traffic sign detection algorithm based on the region of interest extraction and double filter is designed. Methods: First, in order to reduce environmental interference, the input image is preprocessed to enhance the main color of each logo. Secondly, in order to improve the extraction ability of Regions Of Interest, a Region Of Interest (ROI) detector based on Maximally Stable Extremal Regions (MSER) and Wave Equation (WE) is used, and candidate regions are selected through the ROI detector. Then, an effective HOG (Histogram of Oriented Gradient) descriptor is introduced as the detection feature of traffic signs, and SVM (Support Vector Machine) is used to classify them into traffic signs or background. Finally, the context-aware filter and the traffic light filter are used to further identify the false traffic signs and improve the detection accuracy. In the GTSDB database, three kinds of traffic signs, which are indicative, prohibited and dangerous, are tested. Results: The results show that the proposed algorithm has a higher detection accuracy and robustness compared with the current traffic sign recognition technology. © 2021 Bentham Science Publishers.

引用

页码：793 / 802

页数：9

共 15 条

[1]

Rehlaender P., Gavneet M. S., Andreas C., Traffi S., Sign detection using r-cnn, Rec. Advan. Big Data Deep Learn, pp. 226-235, (2019)

[2]

Jiancheng X. X., Smart data driven traffic sign detection method based on adaptive color threshold and shape symmetry, Future Gener. Comput. Syst, 94, pp. 381-391, (2019)

[3]

Garcia A. A., Garcia J. A. A., Luis M., Morillo S., Evaluation of deep neural networks for traffic sign detection systems, Neurocomput, 316, pp. 332-344, (2018)

[4]

Shufang Z., Tong Z., Traffic sign detection and recognition based on residual single shot multibox detector model, J. Zhejiang Univers, 53, 5, (2019)

[5]

Toy G., Barnes N., Fast shape-based road sign detection for a driver assistance system, IEEE Intell. Rob. Syst, pp. 70-75, (2014)

[6]

Miao X. D., Li S. M., Opponent-color based traffic sign detection, Chinese J. Sci. Instrum, 33, 1, pp. 56-61, (2014)

[7]

Woong J. W., Lee M., Son J. W., Implementation of road traffic

[8]

signs detection based on saliency map model, IEEE Intell. Veh. Sympos, pp. 542-547, (2015)

[9]

Zhang G. H., Huang K., Zhang B., A natural scene text extraction method based on mser and swt, J. Xi’an Jiaotong Univers, 36, 1, pp. 1-6, (2018)

[10]

Matas J., Chum O., Urban M., Robust wide-baseline stereo from maximally stable extremal regions, Image Vis. Comput, 22, 10, pp. 761-767, (2014)

← 1 2 →