Solution of Real-Time Traffic Signs Detection Problem for Autonomous Vehicles by Using YOLOV4 And Haarcascade Algorithms

Abstract

Unmanned systems are increasingly used today to facilitate our daily lives and use time more efficiently. Therefore, this rapidly emerging and growing technology appears in every aspect of our lives with its various functions. Object recognition algorithms are one of the most important functions that we often encounter in these systems. Autonomous vehicle technologies are the latest and fastest growing technology among unmanned systems. In this study, we investigate the success rates of two different algorithms for recognizing traffic signs and markings that can be used for partially or fully autonomous vehicles. In this study, two different solutions to the problem of recognizing the signs for fully autonomous and fully autonomous vehicles, respectively, were presented and the correct identification of the markers was evaluated. The work was performed in real-time. Two different concepts were used for these products. An enclosed space where an ideal lighting environment is provided for the evaluation of models should be visualized. In addition, for the general recognition of the models, the test procedures were performed with a dataset obtained from the users and it was computed for the general recognition. In addition, this study aims to provide a better understanding of the basic working principles, the differences between machine learning and deep learning, and the contents of object recognition processes.

Keywords

• Autonomous vehicle
• YoloV4
• Haarcascade
• Object Detection

References

1. [1] Sarda A, Di̇xi̇t S, Bhan A. Object Detection for Autonomous Driving Using Yolo [You Only Look Once] Algorithm. 2021 Thi̇rd Internati̇onal Conference on Intelli̇gent Communi̇cati̇on Technologi̇es and Vi̇rtual Mobi̇le Networks (ICICV). 2021;1370-1374.
2. [2] Redmon J, Di̇vvala S, Gi̇rshi̇ck R, Farhadi̇ A. You Only Look Once: Unified, Real-Time Object Detection. Proceedi̇ngs of the IEEE Conference on Computer Vi̇si̇on and Pattern Recogni̇ti̇on (CVPR). 2016;779-788.
3. [3] R K, NS. A. Pothole and Object Detection for An Autonomous Vehicle Using Yolo. 2021 5Th Internati̇onal Conference on In-telli̇gent Computi̇ng and Control Systems (ICICCS). 2021;1585-1589.
4. [4] Gluhakovi̇ć M, Herceg M, Popovi̇c M, Kovačevi̇ć J. Vehicle Detection in The Autonomous Vehicle Environment for Poten-tial Collision Warning. 2020 Zoomi̇ng Innovati̇on in Consumer Technologi̇es Conference (ZINC). 2020;178-183.
5. [5] Chen S, Li̇n W. Embedded System Real-Time Vehicle Detec-tion Based on Improved Yolo Network. 2019 IEEE 3Rd Ad-vanced Informati̇on Management Communi̇cates, Electroni̇c and Automati̇on Control Conference (IMCEC). 2019;1400-1403.
6. [6] Xu Z, Shi̇ H, Li̇ N, Xi̇ang C, Zhou H. Vehicle Detection Under Uav Based on Optimal Dense Yolo Method. 2018 5Th Inter-nati̇onal Conference on Systems and Informatics (ICSAI). 2018;407-411.
7. [7] Valeja Y, Pathare S, Patel D, Pawar M. Traffic Sign Detection Using Clara and Yolo in Python. 2021 7Th Internati̇onal Con-ference on Advanced Computi̇ng and Communi̇cati̇on Systems (ICACCS). 2021; 367-371.
8. [8] Yang W, Zhang W. Real-Time Traffic Signs Detection Based on Yolo Network Model. 2020 Internati̇onal Conference on Cyber-Enabled Di̇stri̇buted Computi̇ng and Knowledge Di̇scovery (CyberC). 2020;354-357.

9. [9] Mohd-Isa W, Abdullah M, Sarzi̇l M, Abdullah J, Ali̇ A, Hashi̇m N. Detection of Malaysian Traffic Signs Via Modified Yolov3 Algorithm. 2020 Internati̇onal Conference on Data Analyti̇cs for Busi̇ness and Industry: Way Towards a Sustai̇nable Econo-my (ICDABI). 2020;1-5.
10. [10] Novak B, Ili̇ć V, Pavkovi̇ć B. Yolov3 Algorithm with Addi-tional Convolutional Neural Network Trained for Traffic Sign Recognition. 2020 Zoomi̇ng Innovati̇on in Consumer Tech-nologi̇es Conference (ZINC). 2020;165-168. [11] Dewi̇ C, Chen R, Li̇u Y, Ji̇ang X, Hartomo KD. Yolov4 For Advanced Traffic Sign Recognition with Synthetic Training Da-ta Generated by Various GAN. IEEE Access. 2021;9:97228-97242.
11. [12] Çeti̇n E, Ortataş FN. Elektrikli Ve Otonom Araçlarda Makine Öğrenmesi Kullanarak Trafik Levhaları Tanıma ve Simülasyon Uygulaması. El-Cezeri̇. 2021;8(3): 1081 - 1092.
12. [13] Vi̇ola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features. Proceedi̇ngs Of The 2001 IEEE Computer Soci̇ety Conference on Computer Vi̇si̇on and Pattern Recogni̇ti̇on. 2001;I-I.
13. [14] Irawan A, Yaacob MA, Azman FA, Daud MR, Razali̇ AR, Ali̇ SNS. Vision-Based Alignment Control for Mini Forklift System in Confine Area Operation. 2018 Internati̇onal Sympo-si̇um on Agent, Multi̇-Agent Systems and Roboti̇cs (ISAMSR). 2018;1-6.
14. [15] Arunmozhi̇ A, Park J. Comparison of HOG, LBP And Haar-Like Features for On-Road Vehicle Detection. 2018 IEEE Internati̇onal Conference on Electro/Informati̇on Technology (EIT). 2018;0362-0367.
15. [16] Arunmozhi̇ A, Gotadki̇ S, Park J, Gosavi̇ U. Stop Sign and Stop Line Detection and Distance Calculation for Autonomous Vehicle Control. 2018 IEEE Internati̇onal Conference on Elec-tro/Informati̇on Technology (EIT). 2018;0356-0361.
16. [17] Caballero CUB, Beltrán ZZ. Detection Of Traffic Panels in Night Scenes Using Cascade Object Detector. 2018 Inter-nati̇onal Conference on Mechatroni̇cs, Electroni̇cs and Automo-ti̇ve Engi̇neeri̇ng (ICMEAE). 2018;32-37.
17. [18] Vi̇nothi̇ni̇ K, Jayanthy S. Road Sign Recognition System for Autonomous Vehicle Using Raspberry Pi. 2019 5Th Inter-nati̇onal Conference on Advanced Computi̇ng & Commu-ni̇cati̇on Systems (ICACCS). 2019;78-83.
18. [19] R.s. M, A SK, Vats M, S. S. Analyzing the Features of Self-Driving Cars Using Haar Classification Methodology. 2020 5Th Internati̇onal Conference on Communi̇cati̇on and Electroni̇cs Systems (ICCES). 2020;1344-1350.
19. [20] Dewi̇ C, Chen R, XJ, HY. Deep Convolutional Neural Network for Enhancing Traffic Sign Recognition Developed on YoloV4. Multi̇medi̇a Tools and Appli̇cati̇ons. 2022;(81):37821–37845.
20. [21] Aysal FE, Yıldırım K, Cengi̇̇z E. Real-Time Application of Traffic Sign Recognition Algorithm with Deep Learning. Jour-nal of Materi̇als and Mechatroni̇cs: A. 2022;3(2):275 - 289.
21. [22] Carvalho S, Humphri̇es J, Dunne N, Leahy S. Impact of Light Flickering on Object Detection Accuracy Using Convolu-tional Neural Networks. 2021 Telecoms Conference (ConfTELE). 2021;1-6.
22. [23] Shari̇fara A, Rahi̇m MSM, Ani̇si̇ Y. A General Review of Human Face Detection Including a Study of Neural Networks And Haar Feature-Based Cascade Classifier In Face Detection. 2014 Internati̇onal Symposi̇um on Bi̇ometri̇cs and Securi̇ty Technologi̇es (ISBAST). 2014;73-78.
23. [24] Bochkovski̇y A, Wang C, Li̇ao HM. Yolov4: Optimal Speed and Accuracy of Object Detection. Arxi̇v Prepri̇nt Arxi̇v:2004. 2020.