A Review of the Impacts of Defogging on Deep Learning-Based Object Detectors in Self-Driving Cars

被引:6
|
作者
Ogunrinde, Isaac [1 ]
Bernadin, Shonda [1 ]
机构
[1] FAMU FSU Coll Engn, Elect & Comp Engn Dept, Tallahassee, FL 32310 USA
来源
关键词
self-driving cars; adverse weather; fog; object detection; convolutional neural network; yolov3; WEATHER CONDITIONS; FOG; VISIBILITY; VISION;
D O I
10.1109/SOUTHEASTCON45413.2021.9401941
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Autonomous Vehicle (AV) technologies are faced with several challenges under adverse weather conditions such as snow, fog, rain, sun glare, etc. Object detection under adverse weather conditions is one of the most critical issues facing autonomous driving. Several state-of-the-art Convolutional Neural Network (CNN) based object detection algorithms have been employed in autonomous vehicles and promising results have been established under favorable weather conditions. However, results from the literature show that the accuracy and performance of these CNN-based object detectors under adverse weather conditions tend to diminish rapidly. This problem continues to raise major concerns in the research and automotive community. In this paper, the foggy weather condition is our case study. The goal of this work is to investigate how defogging and restoring the quality of foggy images can improve the performance of CNN-based real-time object detectors. We employed a Cycle consistent Generative Adversarial Network (CycleGAN)-based image fog removal technique [1] to defog, improve the visibility and the quality of the foggy images. We train our YOLOv3 algorithm using the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset [2]. Using the trained YOLOv3 network, we perform object detection on the original foggy images and restored images. We compare the performances of the object detector under no fog, moderate fog, and heavy fog conditions. Our results show that detection performance improved significantly under moderate fog and there was no significant improvement under heavy fog conditions.
引用
收藏
页码:425 / 432
页数:8
相关论文
共 50 条
  • [1] An Improved Deep Learning Solution for Object Detection in Self-Driving Cars
    Mobahi, Mina
    Sadati, Seyed Hossein
    [J]. 2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 316 - 320
  • [2] Design and Application of Deep Learning-Based Crash Damage Prediction Model for Self-Driving Cars
    Zhang, Wenxia
    Wang, Zhixue
    [J]. Journal of Autonomous Vehicles and Systems, 2023, 3 (02):
  • [3] A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods
    Ni, Jianjun
    Chen, Yinan
    Chen, Yan
    Zhu, Jinxiu
    Ali, Deena
    Cao, Weidong
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (08):
  • [4] A Review of Machine Learning Techniques Utilised in Self-Driving Cars
    Dhaif, Zahraa Salah
    El Abbadi, Nidhal K.
    [J]. Iraqi Journal for Computer Science and Mathematics, 2024, 5 (01): : 205 - 219
  • [5] Deep Learning-Based Lane-Keeping Assist System for Self-Driving Cars Using Transfer Learning and Fine Tuning
    Hong, Phuc Phan
    Khanh, Huy Hua
    Vinh, Nghi Nguyen
    Trung, Nguyen Nguyen
    Quoc, Anh Nguyen
    Ngoc, Hoang Tran
    [J]. JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2024, 15 (03) : 322 - 329
  • [6] Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues
    Gupta, Abhishek
    Anpalagan, Alagan
    Guan, Ling
    Khwaja, Ahmed Shaharyar
    [J]. Array, 2021, 10
  • [7] Attention-Based Deep Learning Approach for Pedestrian Detection in Self-Driving Cars
    AlZoubi, Wael Ahmad
    Desale, Girish Bhagwant
    Bakyarani, E. Sweety
    Kumari, C. R. Uma
    Nimma, Divya
    Swetha, K.
    Bala, B. Kiran
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (08) : 923 - 932
  • [8] Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues
    Gupta, Abhishek
    Anpalagan, Alagan
    Guan, Ling
    Khwaja, Ahmed Shaharyar
    [J]. ARRAY, 2021, 10
  • [9] Deep Learning for Self-Driving Cars: Chances and Challenges Extended Abstract
    Rao, Qing
    Frtunikj, Jelena
    [J]. PROCEEDINGS 2018 IEEE/ACM 1ST INTERNATIONAL WORKSHOP ON SOFTWARE ENGINEERING FOR AI IN AUTONOMOUS SYSTEMS (SEFAIAS), 2018, : 35 - 38
  • [10] Predicting Steering Actions for Self-Driving Cars Through Deep Learning
    Ou, Chaojie
    Bedawi, Safaa Mahmoud
    Koesdwiady, Arief B.
    Karray, Fakhri
    [J]. 2018 IEEE 88TH VEHICULAR TECHNOLOGY CONFERENCE (VTC-FALL), 2018,