Real-Time Black Ice Detection in Drone View Using YOLOX
DOI:
https://doi.org/10.47611/jsrhs.v13i2.6831Keywords:
Object Detection, Black Ice Detection, Machine LearningAbstract
Black ice is a perilous phenomenon resulting from frozen precipitation on road surfaces. It stands as one of the most prominent contributors to winter traffic accidents since it is nearly invisible. Given these characteristics, there is a pressing need to develop automotive systems capable of detecting black ice to improve driving safety and conditions. This study proposes the deployment of two YOLOX-based models to implement real-time black ice detection from drone-view images. The proposed approach leverages YOLOX-Tiny, known for its proficiency in real-time object detection, in conjunction with YOLOX-B which is a refined version designed specifically for detecting black ice on roadways. For training and evaluating the proposed system, we collected a dataset of black ice consisting of 2,851 sample images sized at 416x416 pixels. Significantly, YOLOX-Tiny achieved an AP@[0.5:0.95] of 0.4923, whereas YOLOX-B achieved 0.4779. Additionally, we demonstrate a practical implementation of the proposed method by deploying the system on the Nvidia Jetson Orin Nano device for real-time inference. The black ice dataset we compiled is publicly available on GitHub. We expect that the proposed black ice detection system will contribute to effectively maintaining safer driving conditions.
Downloads
References or Bibliography
Ahmad, T., Cavazza, M., Matsuo, Y., & Prendinger, H. (2022). Detecting human actions in drone images using YoloV5 and stochastic gradient boosting. Sensors, 22(18), 7020.
Archet, A., Gac, N., Orieux, F., & Ventroux, N. (2023, June). Embedded AI performances of Nvidia's Jetson Orin SoC series. In 17ème Colloque National du GDR SOC2.
Bae, T.-w. (2019, Dec 21). “"Black ice" that you can't avoid even when you open your eyes... Even if there is a precautionary measure, it is a huge budget obstacle”: The Korea Economic Daily
https://www.hankyung.com/society/article/201912201477i
Bhujbal, K., & Barahate, S. (2022, May). Custom Object detection Based on Regional Convolutional Neural Network & YOLOv3 With DJI Tello Programmable Drone. In 7th International Conference on Innovation & Research in Technology & Engineering (ICIRTE).
FHWA. (2023, Feb 1). “Snow and Ice FHWA Road Weather Management”: The Federal Highway Administration (FHWA)
https://ops.fhwa.dot.gov/weather/weather_events/snow_ice.htm
Gay, D. A., & Davis, R. E. (1993). Freezing rain and sleet climatology of the southeastern USA. Climate Research, 3(3), 209-220.
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430.
Kim, H.G., Jang, .M. S, & Lee, Y. S. (2021). A black ice detection method using infrared camera and YOLO. Journal of the Korea Institute of Information and Communication Engineering, 25(12).
Kim, S. (2020). Methods to cope with thin ice (black ice) on roads in winter in the Netherlands (pp. 1-24). Korea Transport Institute.
Lee, H., Hwang, K., Kang, M., & Song, J. (2020, December). Black ice detection using CNN for the Prevention of Accidents in Automated Vehicle. In 2020 International Conference on Computational Science and Computational Intelligence (CSCI) (pp. 1189-1192). IEEE.
Lee, H., Kang, M., Song, J., & Hwang, K. (2020). The detection of black ice accidents for preventative automated vehicles using convolutional neural networks. Electronics, 9(12), 2178.
Li, Y. J., & Kang, S. K. (2021). A Black Ice Recognition in Infrared Road Images Using Improved Lightweight Model Based on MobileNetV2. Journal of the Korea Institute of Information and Communication Engineering, 25(12), 1835-1845.
Sultani, W., & Shah, M. (2021). Human action recognition in drone videos using a few aerial training examples. Computer Vision and Image Understanding, 206, 103186.
Park, G. Y., Lee, S. H., Kim, E. J., & Yun, B. Y. (2017). A case study on meteorological analysis of freezing rain and black ice formation on the load at winter. Journal of Environmental Science International, 26(7), 827-836.
Park, K.W. & Cho, B.C. (2021). Discovering and Preventing Black Ice using AI and Big Data. n.p.: Korea Transport Institute.
Wang, X., He, N., Hong, C., Wang, Q., & Chen, M. (2023). Improved YOLOX-X based UAV aerial photography object detection algorithm. Image and Vision Computing, 135, 104697.
Wang, Z., Cai, Z., & Wu, Y. (2023). An improved YOLOX approach for low-light and small object detection: PPE on tunnel construction sites. Journal of Computational Design and Engineering, 10(3), 1158-1175.
Zhang, C., Nateghinia, E., Miranda-Moreno, L. F., & Sun, L. (2022). Winter road surface condition classification using convolutional neural network (CNN): visible light and thermal image fusion. Canadian Journal of Civil Engineering, 49(4), 569-578.
Published
How to Cite
Issue
Section
Copyright (c) 2024 JINHOO OH, Justin Moon, SEOKHEE HAN; DONGHWAN SHIN
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
