Comparative Analysis of YOLOv7 for Improved Object Detection of Road Markings in Low-Light Conditions: Leveraging CLAHE for Low-Light Image Enhancement
Authors: 
John Paul Quilingking Tomas, Angela Gabrielle Carbonell, Carl Patrick Adrian Aguas, Karelle Mizzy BersabalAuthors Info & Claims
John Paul Quilingking Tomas, Angela Gabrielle Carbonell, Carl Patrick Adrian Aguas, Karelle Mizzy BersabalAuthors Info & ClaimsPages 123 - 128
Abstract
Road markings are crucial for ensuring road safety, especially in challenging conditions such as low-light environments. This study investigates the efficacy of Low-Light Image Enhancement (LLIE) techniques, particularly Contrast Limited Adaptive Histogram Equalization (CLAHE), in enhancing road marking detection accuracy. Leveraging the YOLOv7 algorithm, the researchers trained and evaluated models using original and enhanced datasets. The findings suggest that while CLAHE enhances visibility and improves the overall image quality, models trained on the original dataset achieved slightly higher performance metrics in certain classes. However, further analysis of the results reveals nuanced differences in detection accuracy across different lighting conditions. These findings highlight the complex interplay between image enhancement techniques and object detection algorithms in road marking detection.
References
[1]
Norjan Ismail Abbas. 2019. Understand 17 common road markings in the Philippines. philkotse.com. Retrieved from https://philkotse.com/safe-driving/understand-17-common-road-markings-in-the-philippines-4790
[2]
Dan-Sebastian Bacea and Florin Oniga. 2023. Road Marking Real-Time Detection with a Single Stage Object Detector. 2023 IEEE 19th International Conference on Intelligent Computer Communication and Processing (ICCP) (October 2023). https://doi.org/10.1109/iccp60212.2023.10398733
[3]
Rung-Ching Chen, Christine Dewi, Yong-Cun Zhuang, and Jeang-Kuo Chen. 2023. Contrast limited adaptive histogram equalization for recognizing road marking at night based on Yolo models. IEEE Access 11, (January 2023), 92926–92942. https://doi.org/10.1109/access.2023.3309410
[4]
Christine Dewi, Rung-Ching Chen, Yong-Cun Zhuang, and Henoch Juli Christanto. 2022. YoloV5 Series Algorithm for road marking sign Identification. Big Data and Cognitive Computing 6, 4 (December 2022), 149. https://doi.org/10.3390/bdcc6040149
[5]
Shuo Ding, Yingying Xing, Hong Lang, Tian Wen, and Jian Lü. 2022. Line-Structured Light Rut Detection of Asphalt Pavement with Pavement Markings Interference under Strong Light. Journal of Transportation Engineering 148, 2 (June 2022). https://doi.org/10.1061/jpeodx.0000341
[6]
Elham Eslami and Hae‐Bum Yun. 2022. Improvement of multiclass classification of pavement objects using intensity and range images. Journal of Advanced Transportation 2022, (August 2022), 1–20. https://doi.org/10.1155/2022/4684669
[7]
Toan Minh Hoang, Phong Nguyen-Ha, Noi Quang Truong, Young Won Lee, and Kang Ryoung Park. 2019. Deep RetinaNET-Based detection and classification of road markings by visible light camera sensors. Sensors 19, 2 (January 2019), 281. https://doi.org/10.3390/s19020281
[8]
Oshada Jayasinghe, Sahan Hemachandra, Damith Anhettigama, Shenali Kariyawasam, Ranga Rodrigo, and Peshala Jayasekara. 2022. CEYMO: See More on Roads - a novel benchmark dataset for road marking detection. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (January 2022). https://doi.org/10.1109/wacv51458.2022.00344
[9]
Petru Soviany and Radu Tudor Ionescu. 2018. Optimizing the trade-off between Single-Stage and Two-Stage object detectors using image difficulty prediction. arXiv (Cornell University) (March 2018). https://doi.org/10.48550/arXiv.1803.08707
[10]
Juan R. Terven and Diana-Margarita Córdova-Esparza. 2023. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction 5, 4 (April 2023), 1680–1716. https://doi.org/10.3390/make5040083
[11]
Nguyen D. Vo, Vy Nguyen-Thao Le, Thien C. Lai, Khanh B. T. Duong, and Yen Tran. 2022. Empirical study of the performance of object detection methods on road marking Dataset. 2022 RIVF International Conference on Computing and Communication Technologies (RIVF) (December 2022). https://doi.org/10.1109/rivf55975.2022.10013909
[12]
Joanne M. Wood. 2019. Nighttime driving: visual, lighting and visibility challenges. Ophthalmic and Physiological Optics 40, 2 (December 2019), 187–201. https://doi.org/10.1111/opo.12659
[13]
Xing-Yu Ye, Dza-Shiang Hong, Hung-Hao Chen, Pei‐Yung Hsiao, and Li-Chen Fu. 2020. A two-stage real-time YOLOv2-based road marking detector with lightweight spatial transformation-invariant classification. Image and Vision Computing 102, (October 2020), 103978. https://doi.org/10.1016/j.imavis.2020.103978
[14]
Shuen Zhao, Zhikun Gong, and Zhao De-You. 2023. Traffic signs and markings recognition based on lightweight convolutional neural network. The Visual Computer (March 2023). https://doi.org/10.1007/s00371-023-02801-5
Index Terms
- Comparative Analysis of YOLOv7 for Improved Object Detection of Road Markings in Low-Light Conditions: Leveraging CLAHE for Low-Light Image Enhancement
Recommendations
A Low-light Image Enhancement Method Balancing Brightness Boosting and Noise Smoothing
CSAI '22: Proceedings of the 2022 6th International Conference on Computer Science and Artificial IntelligenceImages captured in low-light or uneven lighting environments need to use low-light image enhancement techniques to boost brightness and contrast for high-quality improved results. Some existing low-light image enhancement methods over-enhance the image ...
Low-light image enhancement using inverted image normalized by atmospheric light
Highlights- This paper presents a novel low-light image enhancement algorithm using the inverted image normalized by atmospheric light.
- A mathematical connection between the Retinex theory and the atmospheric scattering model by normalizing an ...
AbstractImages captured under low-light conditions are characterized by problems, including low brightness, low contrast, and color distortion. Low-light image enhancement, aims to enhance visual effects for the benefit of subsequent image processing and ...
Perceptual Quality Assessment of Low-light Image Enhancement
Low-light image enhancement algorithms (LIEA) can light up images captured in dark or back-lighting conditions. However, LIEA may introduce various distortions such as structure damage, color shift, and noise into the enhanced images. Despite various ...
Comments
Information & Contributors
Information
Published In
April 2024
491 pages
ISBN:9798400717055
DOI:10.1145/3669754
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICCAI 2024
ICCAI 2024: 2024 10th International Conference on Computing and Artificial Intelligence
April 26 - 29, 2024
Bali Island, Indonesia
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 17Total Downloads
- Downloads (Last 12 months)17
- Downloads (Last 6 weeks)6
Reflects downloads up to 26 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format