Enhancing Real-Time Object Detection in Low-Light Conditions Using Zero-DCE and Super-Resolution GANs: A YOLO-Based Approach
DOI:
https://doi.org/10.22399/ijcesen.3455Keywords:
Low-Light Image Enhancement, Zero-DCE, YOLOv8, Real-Time Object Detection , ESRGANs, Rescue and Search OperationsAbstract
Low-light conditions significantly degrade the performance of real-time object detection systems. This study proposes a novel pipeline that integrates Zero-Reference Deep Curve Estimation (Zero-DCE), which has been used to enhance the low-light image, and Enhanced Super-Resolution Generative Adversarial Networks (ESRGANs) for improving the object detection accuracy in poor illumination condition for resolution refinement. The enhanced images are then processed through a YOLO-based detector for real-time object identification. Zero-DCE is leveraged to enhance image illumination without requiring reference images or paired datasets, ensuring efficient and adaptive enhancement across diverse lighting conditions. Following enhancement, ESRGAN is applied to increase the perceptual quality and fine-grained details of the images, enabling the detection model to capture subtle features that are often lost in low-light inputs. This dual stage preprocessing significantly improves the visibility and quality of the input images, directly benefiting object detection performance. The experimental evaluation, conducted on low-light datasets, demonstrates substantial improvements in detection accuracy, precision, and recall metrics. Furthermore, the proposed pipeline maintains real-time performance that can be suitable for surveillance, autonomous navigation, and security applications.
References
[1] Kanchana, B., Peiris, R., Perera, D., Jayasinghe, D., & Kasthurirathna, D. (2021, December). Computer vision for autonomous driving. In 3rd International Conference on Advancements in Computing (ICAC) (pp. 175–180). Colombo, Sri Lanka. https://doi.org/10.1109/ICAC54203.2021.9671099
[2] Patel, R. K., Chouhan, S. S., Lamkuche, H. S., & Pranjal, P. (2024). Glaucoma diagnosis from fundus images using modified Gauss-Kuzmin-distribution-based Gabor features in 2D-FAWT. Computers and Electrical Engineering, 119, 109538. https://doi.org/10.1016/j.compeleceng.2024.109538
[3] Kesharwani, H., Mallick, T., Gupta, A., & Raj, G. (2022, May). Automated attendance system using computer vision. In 2nd International Conference on Computer Science, Engineering and Applications (ICCSEA) (pp. 1–5). Gunupur, India. https://doi.org/10.1109/ICCSEA54677.2022.9936266
[4] Sharma, A., Patel, R. K., Pranjal, P., Panchal, B., & Chouhan, S. S. (2024). Computer vision-based smart monitoring and control system for crop. (pp. 65–82).
[5] Pranjal, P., Kumar, D., Soni, A., & Chatterjee, R. S. (2023). Assessment of groundwater level using satellite-based hydrological parameters in North-West India: A deep learning approach. Earth Science Informatics, 17(3), 2129–2142. https://doi.org/10.1007/s12145-024-01263-0
[6] Kalluri, P. R., Agnew, W., Cheng, Owens, M. K., Soldaini, L., & Birhane, A. (2025). Computer-vision research powers surveillance technology. Nature. https://doi.org/10.1038/s41586-025-08972-6
[7] Singh, P., Murthy, V., Kumar, D., & Raval, S. (2024). A comprehensive review on application of drone, virtual reality and augmented reality with their application in dragline excavation monitoring in surface mines. Geomatics, Natural Hazards and Risk, 15(1), 2327399. https://doi.org/10.1080/19475705.2024.2327399
[8] Wang, W., Wu, X., Yuan, X., & Gao, Z. (2020). An experiment-based review of low-light image enhancement methods. IEEE Access, 8, 87884–87917. https://doi.org/10.1109/ACCESS.2020.2992749
[9] Kim, M., Park, D., Han, D. K., & Ko, H. (2014, January). A novel framework for extremely low-light video enhancement. In 2014 IEEE International Conference on Consumer Electronics (ICCE) (pp. 91–92). https://doi.org/10.1109/ICCE.2014.6775911
[10] Guo, J., Ma, J., García-Fernández, Á. F., Zhang, Y., & Liang, H. (2023). A survey on image enhancement for low-light images. Heliyon, 9(4), e14558.
[11] Jin, Y., Zhang, Y., Cen, Y., Li, Y., Mladenovic, V., & Voronin, V. (2021). Pedestrian detection with super-resolution reconstruction for low-quality image. Pattern Recognition, 115, 107846. https://doi.org/10.1016/j.patcog.2021.107846
[12] Bashir, S. M. A., & Wang, Y. (2021). Small object etection in remote sensing images with residual eature aggregation-based super-resolution and bject detector network. Remote Sensing, 13(9), 1854. https://doi.org/10.3390/rs13091854
[13] Ledig, C., Theis, L., Huszár, F., Caballero, J., unningham, A., Acosta, A. A., Aitken, A., Tejani, ., Totz, J., Wang, Z., & Shi, W. (2017). Photo-ealistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4681–4690).
[14] Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Loy, C. C., Qiao, Y., & Tang, X. (2019). ESRGAN: Enhanced super-resolution generative adversarial networks. In Computer Vision – ECCV 2018 Workshops. Lecture Notes in Computer Science (Vol. 11133, pp. 63–79). https://doi.org/10.1007/978-3-030-11021-5_5
[15] Wang, Z.-Z., Xie, K., Zhang, X.-Y., Chen, H.-Q., Wen, C., & He, J.-B. (2021). Small-object detection based on YOLO and dense block via image super-resolution. IEEE Access, 9, 56416–56429. https://doi.org/10.1109/ACCESS.2021.3072211
[16] Han, Y., Guo, J., Yang, H., Guan, R., & Zhang, T. (2024). SSMA-YOLO: A lightweight YOLO model with enhanced feature extraction and fusion capabilities for drone-aerial ship image detection. Drones, 8(4), 145. https://doi.org/10.3390/drones8040145
[17] Guo, C., Li, C., Guo, J., Loy, C. C., Hou, J., Kwong, S., & Cong, R. (2020). Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1780–1789).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
