Reseach Article
Multi-Modal Fusion for Robust Vehicle Detection in Adverse Weather and Low-Light Scenarios using Deep Learning Techniques
| Journal of Advanced Artificial Intelligence |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 1 - Number 1 |
| Year of Publication: 2024 |
| Authors: Karthika Priya D., Deepak A., Jananie M., Muthu Krishnan J. |
10.5120/jaai202402
|
Karthika Priya D., Deepak A., Jananie M., Muthu Krishnan J. . Multi-Modal Fusion for Robust Vehicle Detection in Adverse Weather and Low-Light Scenarios using Deep Learning Techniques. Journal of Advanced Artificial Intelligence. 1, 1 ( Oct 2024), 14-20. DOI=10.5120/jaai202402
Abstract
In autonomous cars and intelligent transportation systems, vehicle identification and tracking are crucial components. Unfavorable weather conditions, such as intense snow, fog, rain, dust storms, or sandstorms, as well as low-light scenarios, pose a serious threat to the functionality of cameras since they impair driving safety by lowering visibility. The proposed system combines the strengths of the YOLO (You Only Look Once) algorithm, known for its real-time vehicle detection, with cutting-edge computer vision techniques. In response to adverse weather intricacies such as fog, rain, and reduced visibility, the study employs advanced defogging algorithms and the Cycle Generative Adversarial Network to enhance image clarity. Additionally, the research introduces a real-time adaptive defogging mechanism that dynamically adjusts its parameters based on the severity of fog or adverse weather conditions, ensuring continuous and optimal performance. This hybrid architecture capitalizes on the unique strengths of different algorithms, combining the speed of YOLO, the accuracy of Faster R-CNN, and the adaptability of Efficient Net. The implications of this research extend beyond advancing computer vision, with tangible applications in promoting road safety and minimizing traffic accidents. With critical applications in autonomous driving, surveillance, and transportation safety, this research paves the way for advancements that have a positive impact on public safety and transportation efficiency.
References
- Zhang, X., Story, B., & Rajan, D. (2021). Night time vehicle detection and tracking by fusing vehicle parts from multiple cameras. IEEE transactions on intelligent transportation systems, 23(7), 8136-8156.
- Liu, Z., Zhao, S., & Wang, X. (2023). Research on driving obstacle detection technology in foggy weather based on GCANet and feature fusion training. Sensors, 23(5), 2822.
- Zarei, N., Moallem, P., & Shams, M. (2022). Fast-Yolo-Rec: incorporating yolo-base detection and recurrent-base prediction networks for fast vehicle detection in consecutive images. IEEE Access, 10, 120592-120605.
- Wang, H., Yu, Y., Cai, Y., Chen, X., Chen, L., & Li, Y. (2020). Soft-weighted-average ensemble vehicle detection method based on single-stage and two-stage deep learning models. IEEE Transactions on Intelligent Vehicles, 6(1), 100-109.
- Wu, Y., Guan, X., Zhao, B., Ni, L., & Huang, M. (2023). Vehicle detection based on adaptive multi-modal feature fusion and cross-modal vehicle index using RGB-T images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
- Bouguettaya, A., Zarzour, H., Kechida, A., & Taberkit, A. M. (2021). Vehicle detection from UAV imagery with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 33(11), 6047-6067.
- Ju, Z., Zhang, H., Li, X., Chen, X., Han, J., & Yang, M. (2022). A survey on attack detection and resilience for connected and automated vehicles: From vehicle dynamics and control perspective. IEEE Transactions on Intelligent Vehicles
- Wang, Z., Zhan, J., Duan, C., Guan, X., Lu, P., & Yang, K. (2022). A review of vehicle detection techniques for intelligent vehicles. IEEE Transactions on Neural Networks and Learning Systems.
- Hassaballah, M., Kenk, M. A., Muhammad, K., & Minaee, S. (2020). Vehicle detection and tracking in adverse weather using a deep learning framework. IEEE transactions on intelligent transportation systems, 22(7), 4230-4242.
- Guo, Y., Liang, R. L., Cui, Y. K., Zhao, X. M., & Meng, Q. (2022). A domain‐adaptive method with cycle perceptual consistency adversarial networks for vehicle target detection in foggy weather. IET Intelligent Transport Systems, 16(7), 971-981.
- Tian, E., & Kim, J. (2023). Improved Vehicle Detection Using Weather Classification and Faster R-CNN with Dark Channel Prior. Electronics, 12(14), 3022.
- Guo, Y., Liang, R. L., Cui, Y. K., Zhao, X. M., & Meng, Q. (2022). A domain‐adaptive method with cycle perceptual consistency adversarial networks for vehicle target detection in foggy weather. IET Intelligent Transport Systems, 16(7), 971-981.
- Tian, E., & Kim, J. (2023). Improved Vehicle Detection Using Weather Classification and Faster R-CNN with Dark Channel Prior. Electronics, 12(14), 3022.
Index Terms
Keywords