Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Vehicle Classification and Tracking based on Deep Learning

딥러닝 기반의 자동차 분류 및 추적 알고리즘

  • 안효창 ((주)이앤에이치) ;
  • 이용환 (원광대학교 디지털콘텐츠공학과)
  • Received : 2023.09.14
  • Accepted : 2023.09.18
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

Keywords

Acknowledgement

본 연구는 2023년도 정부(미래창조과학부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(과제번호: 2021R1A2C1012947).

References

  1. Tian, B., Morris, B. T., Tang M. et al., "Hierarchical and Networked Vehicle Surveillance in ITS: A Survey", IEEE Transactions on Intelligent Transportation Systems, vol.16, no.2, pp.557-580, 2014. https://doi.org/10.1109/TITS.2014.2340701
  2. Han, D., Cooper, D. B., and Hahn, H. S., "Bayesian Vehicle Class Recognition using 3-D Probe", International Journal of Automotive Technology, vol.14, no.5, pp.747-756, 2013. https://doi.org/10.1007/s12239-013-0082-3
  3. Ahn, H., and Lee, Y. H., "Performance Analysis of Object Recognition and Tracking for the Use of Surveillance System", Journal of Ambient Intelligence and Humanized Computing, vol.7, no.5, pp.673-679, 2016. https://doi.org/10.1007/s12652-015-0325-4
  4. Li, Q. L., and He, J. F., "Vehicles Detection based on Three-Frame-Difference Method and Cross-Entropy Threshold Method", Computer Engineering, vol.37, no.4, pp.172-174, 2011.
  5. Munroe, D. T., & Madden, M. G., "Multi-Class and Single-Class Classification Approaches to Vehicle Model Recognition from Images", Proceedings of the 16th Irish Conference on Artificial Intelligence and Cognitive Science, pp.1-11, 2005.
  6. Morris, B., and Trivedi, M., (2006, November). "Improved vehicle classification in long traffic video by cooperating tracker and classifier modules. In 2006 IEEE International Conference on Video and Signal Based Surveillance, pp.9-11, IEEE.
  7. Prahara, A., "Car Detection based on Road Direction on Traffic Surveillance Image", International Conference on Science in Information Technology, pp. 344-349, 2016.
  8. Sakai, Y., Oda, T., Ikeda, M., and Barolli, L., "An Object Tracking System based on SIFT and SURF Feature Extraction Methods", International Conference on Network-Based Information Systems, pp.561-565, 2015.
  9. Moranduzzo, T., and Melgani, F., "A SIFT-SVM Method for Detecting Cars in UAV Images", International Geoscience and Remote Sensing Symposium, pp. 6868-6871, 2012.
  10. Sotheeswaran, S., and Ramanan, A., "Front-View Car Detection using Vocabulary Voting and MEAN-SHIFT Search", International Conference on Advances in ICT for Emerging Regions, pp. 16-20, 2015.
  11. Lou, Z., Jiang, G., Jia, L., and Wu, C., "Monocular 3D Tracking of MEAN-SHIFT with Scale Adaptation based on Projective Geometry", International Conference on Multimedia Technology, pp. 1-4, 2010.
  12. Prahara, A., "Car Detection based on Road Direction on Traffic Surveillance Image", International Conference on Science in Information Technology, pp. 344-349, 2016.
  13. Guzman, S., Gomez, A., Diez, G., and Fernandez, D. S., "Car Detection Methodology in Outdoor Environment based on Histogram of Oriented Gradient and Support Vector Machine, 2015.
  14. Bougharriou, S., Hamdaoui, F., and Mtibaa, A., "Linear SVM classifier based HOG Car Detection", International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, pp. 241-245, 2017.
  15. Nie, Y., Sommella, P., O'Nils, M., Liguori, C., and Lundgren, J, "Automatic Detection of Melanoma with YOLO Deep Convolutional Neural Networks", International Conference on e-Health and Bioengineering, 2019.
  16. Xu, Z., Shi, H., Li, N., Xiang, C., and Zhou, H., "Vehicle Detection Under UAV Based on Optimal Dense YOLO Method", International Conference on Systems and Informatics, pp. 407-411, 2018.
  17. Lou, L., Zhang, Q., Liu, C., Sheng, M., Zheng, Y., and Liu, X., "Vehicles Detection of Traffic Flow Video Using Deep Learning", International Conference on Data Driven Control and Learning Systems Conference, pp. 1012-1017, 2019.
  18. Sajjad Ahmad Khan, Hyun Jun Lee, Huhnkuk Lim, "Enhancing Object Detection in Self-Driving Cars using a Hybrid Approach", Electronics, 12(13), 2023.
  19. Shaozhe Guo, Youshan Zhang, Yong Li, Yaojie Wang, "Multiple Object Tracking in aerial vehicle overhead video", International Conference on Advanced Electronic Materials, Computers and Software Engineering, 2022.