An Optimized YOLOv7-Based Object Detection Framework Leveraging Low-Light Image Enhancement to Improve Accuracy


Rasim Rasim(1*); Farhan Nurzaman(2); Yaya Wihardi(3); Herbert Siregar(4); Samialloi Nusratullo(5);

(1) Universitas Pendidikan Indonesia
(2) Universitas Pendidikan Indonesia
(3) Universitas Pendidikan Indonesia, Jalan Dr. Setiabudhi No. 229, Sukasari, Bandung 40154, Indonesia
(4) Universitas Pendidikan Indonesia
(5) Borough of Manhattan Community College
(*) Corresponding Author

  

Abstract


Low-light environments remain a persistent challenge in computer vision, often leading to notable degradation in object detection performance. This is primarily caused by reduced contrast, increased noise, and the loss of critical visual details, all of which hinder reliable feature extraction. To address these limitations, this study proposes an integrated framework that combines Zero-Reference Deep Curve Estimation (Zero-DCE) for adaptive image enhancement with the YOLOv7 architecture for efficient and accurate object detection. The study was conducted through a structured pipeline consisting of several key stages: (1) preparation of the ExDark, NOD, and LOD datasets; (2) preprocessing, including annotation and labelling; (3) low-light image enhancement using Zero-DCE; (4) dataset selection, partitioning, and utilization; (5) image resizing to ensure model compatibility; (6) model development, comprising both a baseline YOLOv7 model and an enhanced Zero-DCE + YOLOv7 configuration; and (7) performance analysis and evaluation using mean Average Precision (mAP) as the primary metric. Experimental results demonstrate that the integration of Zero-DCE with YOLOv7 improves detection performance, with mAP@0.5 increasing from 0.785 in the baseline model to 0.794. Although the improvement is modest, it is consistent and indicates the effectiveness of incorporating illumination enhancement into the preprocessing stage. In addition, this study’s contribution lies in demonstrating that the proposed framework enhances the robustness of object detection systems under challenging lighting conditions without incurring significant computational overhead.

Keywords


Object Detection; Low-light; Zero-DCE; Image Enhancement; YOLOv7

  
  

Full Text:

PDF
  

Article Metrics

Abstract view: 74 times
PDF view: 13 times 		     

Digital Object Identifier

doi  https://doi.org/10.33096/ilkom.v18i2.3102.207-220 		  

Cite

How to cite item

References


Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” Proc. IEEE, vol. 111, no. 3, pp. 257–276, 2023, doi: 10.1109/JPROC.2023.3238524.

J. Gao, H. Li, Z. Li, C. Xie, X. Ji, and Y. Zhang, “An algorithm for road target detection of autonomous vehicles based on improved YOLOv8,” Sci. Rep., vol. 15, no. 1, p. 21061, Jul. 2025, doi: 10.1038/s41598-025-06831-y.

Y. Zheng, L. Qian, J. Cao, H. Huang, W. Hou, and Y. Liu, “A reliable enhanced learning algorithm for ship detection in inland water maritime surveillance system,” Eng. Appl. Artif. Intell., vol. 159, 2025, doi: 10.1016/j.engappai.2025.111820.

C. Jiang, Y. Wang, Q. Yuan, P. Qu, and H. Li, “A 3D medical image segmentation network based on gated attention blocks and dual-scale cross-attention mechanism,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-90339-y.

P. Sonchan, N. Ratchatanantakit, N. O-Larnnithipong, M. Adjouadi, and A. Barreto, “Robust orientation estimation from mems magnetic, angular rate, and gravity (MARG) modules for human–computer interaction,” Micromachines, vol. 15, no. 4, 2024, doi: 10.3390/mi15040553.

J. Janai, F. Güney, A. Behl, and A. Geiger, “Computer Vision for Autonomous Vehicles,” Found. Trends® Comput. Graph. Vis., vol. 12, no. 1–3, pp. 1–308, Jul. 2020, doi: 10.1561/0600000079.

N. Ismail and O. A. Malik, “Real-time visual inspection system for grading fruits using computer vision and deep learning techniques,” Inf. Process. Agric., vol. 9, no. 1, pp. 24–37, Mar. 2022, doi: 10.1016/j.inpa.2021.01.005.

L. Zhou, L. Zhang, and N. Konz, “Computer Vision Techniques in Manufacturing,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 53, no. 1, pp. 105–117, Jan. 2023, doi: 10.1109/TSMC.2022.3166397.

Q. Tian and J. Zhang, “STDE-YOLOv5s: A traffic sign detection algorithm based on context information enhancement,” Discov. Artif. Intell., vol. 5, no. 1, 2025, doi: 10.1007/s44163-025-00405-7.

D. Zou, H. Xie, and L. Kohnke, “Navigating the future: Establishing a framework for educators’ pedagogic artificial intelligence competence,” Eur. J. Educ., vol. 60, no. 2, 2025, doi: 10.1111/ejed.70117.

M. Yang and S. Han, “ETS-YOLO: An efficient YOLO-based model for real-time traffic sign recognition,” Signal, Image Video Process., vol. 19, no. 8, 2025, doi: 10.1007/s11760-025-04276-4.

J. Qiu, W. Zhang, S. Xu, and H. Zhou, “DP-YOLO: A lightweight traffic sign detection model for small object detection,” Digit. Signal Process. A Rev. J., vol. 165, 2025, doi: 10.1016/j.dsp.2025.105311.

X. Y. Wu and T. K. F. Chiu, “Integrating learner characteristics and generative AI affordances to enhance self-regulated learning: A configurational analysis,” J. New Approaches Educ. Res., vol. 14, no. 1, 2025, doi: 10.1007/s44322-025-00028-x.

Z. Li, “Enhanced Fault Localization in Energy Systems Using an Improved MVO Algorithm and Multistrategy Optimization,” IEEE Access, vol. 13, pp. 50367–50378, 2025, doi: 10.1109/ACCESS.2025.3552761.

S. R. Alotaibi et al., “Harnessing optimization with deep learning approach on intelligent transportation system for anomaly detection in pedestrian walkways,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-99940-7.

N. Nigam, D. P. Singh, J. Choudhary, and S. Solanki, “PVD-GSTPS: Design of an efficient parallel vehicle detection based green signal time prediction system,” Discov. Comput., vol. 28, no. 1, 2025, doi: 10.1007/s10791-025-09660-9.

Y. Du, L. Chen, and X. Hao, “RL-Net: A rapid and lightweight network for detecting tiny vehicle targets in remote sensing images,” Complex Intell. Syst., vol. 11, no. 8, 2025, doi: 10.1007/s40747-025-01956-z.

M. J. Kim et al., “Comparison of artificial intelligence–derived heart age with chronological age using normal sinus electrocardiograms in patients with no evidence of cardiac disease,” J. Clin. Med., vol. 14, no. 15, 2025, doi: 10.3390/jcm14155548.

M. Alsallal et al., “Enhanced lung cancer subtype classification using attention-integrated DeepCNN and radiomic features from CT images: A focus on feature reproducibility,” Discov. Oncol., vol. 16, no. 1, 2025, doi: 10.1007/s12672-025-02115-z.

M. F. Fairuz, A. A. Alfariz, R. A. P. Bimantara, M. Irfan, and N. Setyawan, “Traffic jam monitoring system on Malang road junction using YoloV4,” in Eighth International Conference of Mathematical Sciences: Icms2024, 2025, p. 050013. doi: 10.1063/5.0260130.

C. N. Reddy, N. U. Kiran, and D. A. Sivasakthi, “Smart traffic monitoring system using YOLO,” in AIP Conference Proceedings, 2025. doi: 10.1063/5.0266726.

C. C. Chang, K. H. Huang, T. K. Lau, C. F. Huang, and C. H. Wang, “Using deep learning model integration to build a smart railway traffic safety monitoring system,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-88830-7.

M. I. Zulfiqar, A. Khalid, A. Siddig, M. J. Nawaz, and S. Saay, “Ai-driven smart shopping carts with real-time tracking and inventory forecasting for enhanced retail efficiency,” IEEE Access, vol. 13, pp. 55576–55585, 2025, doi: 10.1109/ACCESS.2025.3553854.

M. Wu et al., “Defect intelligent recognition of membrane product based on deep learning,” Meas. Control (United Kingdom), vol. 58, no. 8, pp. 1052 – 1066, 2024, doi: 10.1177/00202940241268952.

L. Zhu and X. Sheng, “On image-processing-based identification method of express logistics information,” Trait. du Signal, vol. 39, no. 3, pp. 1019–1025, 2022, doi: 10.18280/ts.390329.

R. Pravesh and B. C. Sahana, “A dual-stage deep learning framework for simultaneous fire and firearm detection in smart surveillance systems,” Results Eng., vol. 27, 2025, doi: 10.1016/j.rineng.2025.106330.

A. Ferone et al., “AiWatch: A distributed video surveillance system using artificial intelligence and digital twins technologies,” Technologies, vol. 13, no. 5, 2025, doi: 10.3390/technologies13050195.

H. C. Tsai, Y. W. P. Hong, and J. P. Sheu, “Completion time minimization for UAV-enabled surveillance over multiple restricted regions,” IEEE Trans. Mob. Comput., vol. 22, no. 12, pp. 6907–6920, 2023, doi: 10.1109/TMC.2022.3200732.

M. B. V. Bell, A. N. Radford, R. Rose, H. M. Wade, and A. R. Ridley, “The value of constant surveillance in a risky environment,” Proc. R. Soc. B Biol. Sci., vol. 276, no. 1669, pp. 2997–3005, 2009, doi: 10.1098/rspb.2009.0276.

K. Wang, Z.-H. Han, K.-S. Zhang, and W.-P. Song, “An efficient geometric constraint handling method for surrogate-based aerodynamic shape optimization,” Eng. Appl. Comput. Fluid Mech., vol. 17, no. 1, 2023, doi: 10.1080/19942060.2022.2153173.

A. Yi and N. Anantrasirichai, “A comprehensive study of object tracking in low-light environments,” Sensors, vol. 24, no. 13, 2024, doi: 10.3390/s24134359.

H. Tang et al., “Target search for joint local and high-level semantic information based on image preprocessing enhancement in indoor low-light environments,” ISPRS Int. J. Geo-Information, vol. 12, no. 10, 2023, doi: 10.3390/ijgi12100400.

J. Zhang, J. Peng, X. Kong, S. Wang, and J. Hu, “Vehicle spatiotemporal distribution identification in low-light environment based on image enhancement and object detection,” Adv. Eng. Informatics, vol. 65, 2025, doi: 10.1016/j.aei.2025.103165.

Z. Xiong, M. Wang, R. Kan, and J. Zhang, “YOLO-SAR: An enhanced multi-scale ship detection method in low-light environments,” Appl. Sci., vol. 15, no. 13, 2025, doi: 10.3390/app15137288.

S. Agrawal, R. Panda, P. K. Mishro, and A. Abraham, “A novel joint histogram equalization based image contrast enhancement,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 4, pp. 1172–1182, 2022, doi: 10.1016/j.jksuci.2019.05.010.

L. Liu, Z. F. Pang, and Y. Duan, “Retinex based on exponent-type total variation scheme,” Inverse Probl. Imaging, vol. 12, no. 5, pp. 1199–1217, 2018, doi: 10.3934/ipi.2018050.

K. Chang and L. Yan, “LLNet: A fusion classification network for land localization in real-world scenarios,” Remote Sens., vol. 14, no. 8, 2022, doi: 10.3390/rs14081876.

R. Ye, G. Shao, Z. Yang, Y. Sun, Q. Gao, and T. Li, Detection model of tea disease severity under low light intensity based on YOLOv8 and EnlightenGAN, vol. 13, no. 10. 2024. doi: 10.3390/plants13101377.

C. Guo et al., “Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2020, pp. 1777–1786. doi: 10.1109/CVPR42600.2020.00185.

G. Wang, Y. Guo, and T. Hu, “Enhancing low-light object detection through domain adaptation and image enhancement,” Vis. Comput., vol. 41, no. 14, pp. 11947–11958, 2025, doi: 10.1007/s00371-025-04136-9.

Y. Liu, S. Li, L. Zhou, H. Liu, and Z. Li, “Dark-YOLO: A low-light object detection algorithm integrating multiple attention mechanisms,” Appl. Sci., vol. 15, no. 9, 2025, doi: 10.3390/app15095170.

Y. P. Loh and C. S. Chan, “Getting to know low-light images with the Exclusively Dark dataset,” Comput. Vis. Image Underst., vol. 178, pp. 30–42, Jan. 2019, doi: 10.1016/j.cviu.2018.10.010.

P. P. Anoop and R. Deivanathan, “Advancements in low light image enhancement techniques and recent applications,” J. Vis. Commun. Image Represent., vol. 103, p. 104223, Aug. 2024, doi: 10.1016/j.jvcir.2024.104223.

C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2023, pp. 7464–7475. doi: 10.1109/CVPR52729.2023.00721.

Z. Cui et al., “You Only Need 90K Parameters to Adapt Light: a Light Weight Transformer for Image Enhancement and Exposure Correction,” BMVC 2022 - 33rd Br. Mach. Vis. Conf. Proc., 2022, doi: https://doi.org/10.48550/arXiv.2205.14871.

H. Guo, T. Lu, and Y. Wu, “Dynamic low-light image enhancement for object detection via end-to-end training,” in Proceedings - International Conference on Pattern Recognition, 2020, pp. 5611–5618. doi: 10.1109/ICPR48806.2021.9412802.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Rasim Rasim, Farhan Nurzaman, Yaya Wihardi, Herbert Siregar, Samialloi Nusratullo

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.