The Effect of Gamma Correction on the Accuracy of Vehicle Detection Using the YOLOv8 Algorithm
DOI:
https://doi.org/10.29207/resti.v10i1.7022Keywords:
image preprocessing, gamma correction, low light, vehicle detection, YOLOv8Abstract
Accurate vehicle detection under low-light conditions is a significant challenge in traffic surveillance systems and computer vision applications. Although YOLOv8 performs well under normal illumination, its accuracy decreases when processing low-light images due to reduced contrast and limited visual details. This study proposes the integration of gamma correction as a preprocessing method to enhance image brightness and improve YOLOv8 detection performance. The dataset consists of real ATCS traffic camera recordings from Medan City under varying lighting conditions. Gamma correction with three values (0.5, 1.5, and 2.0) was applied to evaluate its effect on detection accuracy. The results show that gamma 1.5 provides the best improvement, increasing mAP@0.5 by 0.14% and mAP@0.5:0.95 by 0.74%, and achieving the highest confidence score of 0.9678 while also producing more stable training convergence. The novelty of this study lies in applying gamma correction to YOLOv8 using real-world ATCS low-light data, demonstrating that simple preprocessing can enhance detection robustness without modifying the model architecture.
Downloads
References
M. Elassy, M. Al-Hattab, M. Takruri, and S. Badawi, “Intelligent transportation systems for sustainable smart cities,” Transp. Eng., vol. 16, p. 100252, Jun. 2024, doi: 10.1016/j.treng.2024.100252.
D. Oladimeji, K. Gupta, N. A. Kose, K. Gundogan, L. Ge, and F. Liang, “Smart Transportation: An Overview of Technologies and Applications,” Sensors, vol. 23, no. 8, p. 3880, Apr. 2023, doi: 10.3390/s23083880.
S. Paiva, M. Ahad, G. Tripathi, N. Feroz, and G. Casalino, “Enabling Technologies for Urban Smart Mobility: Recent Trends, Opportunities and Challenges,” Sensors, vol. 21, no. 6, p. 2143, Mar. 2021, doi: 10.3390/s21062143.
M. Meilany and R. Rahmadewi, “Implementation Of Real-Time Detection Of Facial Expressions, Age, And Gender Based On Tensorflow,” JATI, vol. 9, no. 2, pp. 3203-3209, 2025, doi: https://doi.org/10.36040/jati.v9i2.13300
Q. S. A. Wasilah, A. R. Dikananda, and D. Rohman, “Implementation of CNN Resnet50 to Detect the Quality of Fruits and Vegetables in Traditional Markets,” vol. 9, no. 3, pp. 3675-3682, 2025 doi: https://doi.org/10.36040/jati.v9i3.13349
N. Bilous, V. Malko, M. Frohme, and A. Nechyporenko, “Comparison of CNN-Based Architectures for Detection of Different Object Classes,” AI, vol. 5, no. 4, pp. 2300–2320, Nov. 2024, doi: 10.3390/ai5040113.
Ayu Wirdiani, Lennia Savitri Azzahra Lofiana, Putu Arya Dharmadi, and Oka Sudana, “Face Dermatological Disorder Identification with YoloV5 Algorithm,” J. RESTI, vol. 9 (4), pp. 721–728, doi: https://doi.org/10.29207/resti.v9i4.6237.
R. Hidayattullah, N. Suarna, I. Ali, and D. I. Efendi, “Deep Learning Algorithm Yolov8 to Improve Traffic Density Analysis,” J. Inform. Dan Tek. Elektro Terap., vol. 13, no. 2, Apr. 2025, doi: 10.23960/jitet.v13i2.5749.
M. Hussain, “YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection,” Machines, vol. 11, no. 7, p. 677, Jun. 2023, doi: 10.3390/machines11070677.
Derit Junio Marcelleno and Muhammad Pajar Kharisma Putra, “Performance Evaluation Of Yolov8 In Real-Time Vehicle Detection In Various Environmental Conditions,” J. Tek. Inform. JUTIF, pp. 269–279, 2025, doi: https://doi.org/10.52436/1.jutif.2025.6.1.3916.
K.-F. Hung and K.-P. Lin, “Bio-Inspired Dark Adaptive Nighttime Object Detection,” Biomimetics, vol. 9, no. 3, p. 158, Mar. 2024, doi: 10.3390/biomimetics9030158.
X. Liu et al., “The real-time shadow detection of the PV module by computer vision based on histogram matching and gamma transformation method,” Sci. Rep., vol. 14, no. 1, p. 21781, Sep. 2024, doi: 10.1038/s41598-024-71710-x.
D. Xu, R. Ren, H. Zhao, and S. Zhang, “Intelligent Detection of Muskmelon Ripeness in Greenhouse Environment Based on YOLO-RFEW,” Agronomy, vol. 14, no. 6, p. 1091, May 2024, doi: 10.3390/agronomy14061091.
J. Wang, Y. Li, Y. Wang, H. Lv, and X. Lu, “Video Sequence Image Matching Algorithm Based on Adaptive Gamma Correction,” J. Phys. Conf. Ser., vol. 2400, no. 1, p. 012042, Dec. 2022, doi: 10.1088/1742-6596/2400/1/012042.
S. Saepudin, N. Sujana, M. M. Mutoffar, and A. A. Haryanto, “Performance Analysis Of Yolov8 Optimization Of Roboflow For Detecting Emotional Facial Expressions With Machine Learning,” Naratif J. Nas. Ris. Apl. Dan Tek. Inform., vol. 6, no. 2, pp. 115–124, Dec. 2024, doi: 10.53580/naratif.v6i2.292.
S. G. Zain and A. Ardilla, “Detection Of Vehicle Type And License Plate With Convolutional Neural Network Model Yolov7,” J. Tek. Inform. JUTIF, vol. 5(6), pp. 621–636, 2024, doi: https://doi.org/10.52436/1.jutif.2024.5.2.XX.
B.-A. Awaluddin, C.-T. Chao, and J.-S. Chiou, “Investigating Effective Geometric Transformation for Image Augmentation to Improve Static Hand Gestures with a Pre-Trained Convolutional Neural Network,” Mathematics, vol. 11, no. 23, p. 4783, Nov. 2023, doi: 10.3390/math11234783.
K. Park, M. Chae, and J. H. Cho, “Image Pre-Processing Method of Machine Learning for Edge Detection with Image Signal Processor Enhancement,” Micromachines, vol. 12, no. 1, p. 73, Jan. 2021, doi: 10.3390/mi12010073.
J. Singnoo and G. D. Finlayson, “Understanding the Gamma Adjustment of Images,” Color Imaging Conf., vol. 18, no. 1, pp. 134–139, Jan. 2010, doi: 10.2352/CIC.2010.18.1.art00024.
P. Y. Putra, A. S. Arifianto, Z. E. Fitri, and T. D. Puspitasari, “Detecting Trucks In Videos Using The Tiny-Yolo v4 Method,” J. Inform. Polinema, vol. 9, no. 2, pp. 215–222, Feb. 2023, doi: 10.33795/jip.v9i2.1243.
B. D. Prasetya, E. P. Amalia, P. D. Juliana, and R. K. Niswatin, “Web-based Object Detection Implementation for Waste Classification Using YOLOv8,” Seminar Nasional Teknologi & Sains (STAINS), vol. 4, no. 1, 2025, doi: https://doi.org/10.29407/m7yxsp77
L. Palupi, E. Ihsanto, and F. Nugroho, “Validation and Evaluation Analysis of Ginger Variant Object Detection Model Using Yolov5 Algorithm,” J. Inf. Syst. Res. JOSH, vol. 5, no. 1, pp. 234–241, Oct. 2023, doi: 10.47065/josh.v5i1.4380.
E. B. T. Wea and D. Ariatmanto, "Accuracy Analysis of Object Detection Using TensorFlow with the Single Shot Detection Method for Animated Character Recognition in the Movie Battle of Surabaya,” J. Pendidik. Dan Teknol. Indones. JPTI, vol. 5(7), pp. 2101–2115, 2025, doi: https://doi.org/10.52436/1.905.
G. Zhang, Y. Peng, and J. Li, “YOLO-MARS: An Enhanced YOLOv8n for Small Object Detection in UAV Aerial Imagery,” Sensors, vol. 25, no. 8, p. 2534, Apr. 2025, doi: 10.3390/s25082534.
Viviana Fransisca and Handri Santoso, “Application of Gamma Correction in Improving Night Object Detection in the YOLOv5 Algorithm,” Build. Inform. Technol. Sci. BITS, vol. 5(1), 2023, doi: 10.47065/bits.v5i1.3553.
Jiang Zetao, Xiao Yun, Zhang Shaoqin, Zhu Linghong, He Yuting, and Zhai Fengshuo, “Low-Illumination Object Detection Method Based on Dark-YOLO,” J. Comput.-Aided Des. Comput. Graph., vol. 35(3), pp. 441–451, 2023, doi: 10.3724/SP.J.1089.2023.19354.
Z. Han, Z. Yue, and L. Liu, “3L-YOLO: A Lightweight Low-Light Object Detection Algorithm,” Appl. Sci., vol. 15, no. 1, p. 90, Dec. 2024, doi: 10.3390/app15010090.
J. Wang et al., “Research on Improved YOLOv5 for Low-Light Environment Object Detection,” Electronics, vol. 12, no. 14, p. 3089, Jul. 2023, doi: 10.3390/electronics12143089.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





