Based on an improved Zero-DCE++ low-light enhanced object detection algorithm

Low-light image quality often suffers from noise, color distortion, and reduced contrast, challenging accurate object detection. Traditional enhancement methods can lead to over-processing and semantic information loss. This study presents an enhanced low-light image detection model based on an improved Zero-DCE++ algorithm, integrated with YOLOv8 for high-speed, accurate detection. Key improvements include the CBAM attention mechanism to enhance feature extraction in low-light areas, DCNv2 for capturing complex object details, and a Local Region Brightness Curve Enhancement Module to prevent overexposure in well-lit areas. The proposed model was tested on the Night Drone dataset, where it achieved superior performance in image quality and detection accuracy compared to state-of-the-art methods. This approach demonstrates significant potential for applications requiring reliable object detection in challenging low-light conditions.