Enhancing Object Detection in Adverse Weather for Autonomous Driving with YOLOv9

Prerna Saini, Anusha Dixit, Deepak Kumar Sharma

Abstract


The integration of autonomous vehicles (AVs) within the society has been a topic of interest since the 1950s when the trials on the first advanced driver assistance system (ADAS) began. The promise of autonomous driving systems is based on their ability to traverse with human-level perception, especially object detection in driving environments. This is essential for safe and reliable navigation but adverse weather conditions like sandstorms, rain, dense fog, and heavy snowfall hinder the robustness of the perception system. To address the problem of low visibility in adverse weathers like these, our proposed approach implemented feature extraction using content-based information retrieval (CBIR) for contrast enhancement and Enhanced Super Resolution Generative Adversarial Networks (ESRGAN) for image restoration. Further, YOLOv9 - the latest breakthrough in object detection was used. This work was the first initiative taken towards exploring the implementation of adverse weather driving dataset on Yolov9. The methodology was successful in achieving an average precision of 97.17% in detecting objects across all weathers with an overall mean Average Precision (mAP) of 72.87. These encouraging results might prove to be beneficial for safer and more reliable autonomous vehicle operation in diverse weather conditions.

Keywords


adverse weather; autonomous driving; image enhancement; object detection; YOLOv9

Full Text:

PDF

References


C. Yao Wang, I-H. Yeh, H.-Yuan M. Liao, 2024. "YOLOv9: Learning What You Want to Learn Using Programable Gradient Information", Available open access Online at Cornell University, New York, USA, 29 Feb: 1-18. DOI: https://arxiv.org/pdf/2402.13616.

Kenk M.A. and Hasaballah Mahmoud, 2020 “DAWN: Vehicle Detection in Adverse Weather Nature Dataset,” Available open access Online at Cornell University, New York, USA, 12 Aug: 1–6. DOI: https://arxiv.org/abs/2008.05402.

Chen F., and Chen S., 2011. “Reliability-based assessment of vehicle safety in adverse driving conditions,” Transp. Res. Emerg. Technol.(19), Feb. 2011: 156–168.

Appiah Emmanuel Orwusu and Mensah Solomon, 2024, “Object detection in adverse weather condition for autonomous vehicles,” Multimedia Tools and Appl. 83 (9): 28235–28261.

D. Dai, Z. Chen, P. Bao, and J. Wang, 2021. “A review of 3d object detection for autonomous driving of electric vehicles,” World Electr. Veh. J., 12 (3).

Patel Vatsa S., Agrawal K., and Nguyen Tam V., 2024. “A Comprehensive Analysis of Object Detectors in Adverse Weather Conditions,” in 58th Annual Conference on Information Science and System (CISS), 13-15 March: 1–6.

Abbas Syed Mazhar and Dr. Singh Shailendra N., 2018. “Region-based Object Detection and Classification using Faster R-CNN,” in 4th Conference on Computational Intelligence & Communication Technology, IEEE, 9-10 Feb: 1–6

I. V. Fanthony, Z. Husin, H. Hikmarika, S. Dwijayanti, and B. Y. Suprapto, 2021. “YOLO Algorithm-Based Surrounding Object Identification on Autonomous Electric Vehicle,” Int. Conf. Electr. Eng. Comput. Sci. Informatics, October 2021: 151–156.

Liu W., et al., 2022 “Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions,” in Proceedings of the AAAI Conf. on Artificial Intelligence, volume 36, 28 Jun: 1792–1800.

Pavithra P. P., R.K. Bhanu, and Safinaz S., 2024. “RIOD:Reinforced Image-based Object Detection for Unruly Weather Conditions,” Engineering Technology Application Science Research, 14 (1), Feb 2024: 13052–13057.

Bachute M.R. and Subhedar J.M., 2021. “Autonomous Driving Architectures: Insights of Machine Learning and Deep Learning Algorithms,” Machine Learning with Appl., volume 6, Sep 2021: 100-164.

Nguyen V. D., et al. 2020. “Robust Vehicle Detection Under Adverse Weather Conditions Using Auto-encoder Feature,” 2020 International Journal of Machine Learning and Computing, 10 (4), Jul 2020: 549–555.

Fabio Cuzzolin, Andrew Bradley, Valentina Mușat, I. Fursa, P. Newman, 2021 “Multi-weather city: Adverse weather stacking for autonomous driving,” in 2021 International Conf. on Computer Vision Workshops (ICCVW): 2906–2915.

Roboflow. Available online: https://roboflow.com/

Ancuti C. O., et al. 2019. "Dense haze: A benchmark for image dehazing with dense-haze and haze-free images", in IEEE International Conference on Image Processing (ICIP), Sep. 2019: 22-25.

Sarath C. Yenigalla, Rao K. Srinivasa, and Ngangbam P. S., 2023. “Implementation of Content-Based Image Retrieval Using Artificial Neural Networks,” in Engineering Proceedings, 13 March, 2023.

X. Wang, K. Yu, et al. 2018. “ESRGAN: Enhanced super-resolution generative adversarial networks,” in Proceedings of the Europen Conf. on CV Workshop, Germany: 63–79.