<![CDATA[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.]]>
