DOI QR코드

DOI QR Code

Vehicle Detection at Night Based on Style Transfer Image Enhancement

  • Jianing Shen (College of Computer Internet of Things Engineering, Wuxi Taihu University) ;
  • Rong Li (College of Computer Internet of Things Engineering, Wuxi Taihu University)
  • Received : 2022.12.07
  • Accepted : 2023.02.12
  • Published : 2023.10.31

Abstract

Most vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.

Keywords

References

  1. R. Matsuo, T. Tanigawa, K. Tomooka, A. Ikeda, H. Wada, K. Maruyama, and I. Saito, "The importance of screening for sleep disordered breathing in the prevention of motor vehicle crashes: the Toon Health Study," Juntendo Medical Journal, vol. 66, no. 6, pp. 476-477, 2020. https://doi.org/10.14789/jmj.2020.66.JMJ20-A03
  2. A. D. Puzanau and D. S. Nefedov, "Synthesis of algorithm of unmanned aerial vehicle detection by acoustic noise," Doklady BGUIR, vol. 19, no. 2, pp. 65-73, 2021. https://doi.org/10.35596/1729-7648-2021-19-2-65-73
  3. J. Lei, Y. Dong, and H. Sui, "Tiny moving vehicle detection in satellite video with constraints of multiple prior information," International Journal of Remote Sensing, vol. 42, no. 11, pp. 4110-4125, 2021. https://doi.org/10.1080/01431161.2021.1887542
  4. S. Parvin, L. J. Rozario, and M. E. Islam, "Vision-based on-road nighttime vehicle detection and tracking using taillight and headlight features," Journal of Computer and Communications, vol. 9, no. 3, pp. 29-53, 2021. https://doi.org/10.4236/jcc.2021.93003
  5. M. Shu, Y. Zhong, and P. Lv, "Small moving vehicle detection via local enhancement fusion for satellite video," International Journal of Remote Sensing, vol. 42, no. 19, pp. 7189-7214, 2021. https://doi.org/10.1080/01431161.2021.1944694
  6. T. S. Kavya, Y. M. Jang, T. Peng, and S. B. Cho, "Vehicle detection and tracking from a video captured by moving host," Indian Journal of Computer Science and Engineering, vol. 11, no. 3, pp. 226-235, 2020. https://doi.org/10.21817/indjcse/2020/v11i3/201103187
  7. L. Anuj, M. T. Gopalakrishna, C. Naveena, and Y. H. Sharath Kumar, "V-DaT: a robust method for vehicle detection and tracking," Turkish Journal of Computer and Mathematics Education, vol. 12, no. 2, pp. 2492-2505, 2021. https://doi.org/10.17762/turcomat.v12i2.2092
  8. J. Feng, D. Zeng, X. Jia, X. Zhang, J. Li, Y. Liang, and L. Jiao, "Cross-frame keypoint-based and spatial motion information-guided networks for moving vehicle detection and tracking in satellite videos," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 177, pp. 116-130, 2021. https://doi.org/10.1016/j.isprsjprs.2021.05.005
  9. V. Paidi, H. Fleyeh, and R. G. Nyberg, "Deep learning-based vehicle occupancy detection in an open parking lot using thermal camera," IET Intelligent Transport Systems, vol. 14, no. 10, pp. 1295-1302, 2020. https://doi.org/10.1049/iet-its.2019.0468
  10. J. Q. Luo, H. S. Fang, F. M. Shao, Y. Zhong, and X. Hua, "Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment," Defence Technology, vol. 17, no. 4, pp. 1542-1554, 2021. https://doi.org/10.1016/j.dt.2020.10.006