基于模拟多曝光融合的低照度行人动作图像增强处理设计

Design of low illumination pedestrian motion image enhancement based on simulated multi exposure fusion

为提高低照度行人动作图像的自然性亮度和清晰度、降低失真率,设计了基于模拟多曝光融合的低照度行人动作图像增强处理方法。以提高图像可视化质量为目标,生成过曝光与中等曝光行人动作图像;利用模拟多曝光融合技术实现对图像的多尺度融合处理;在增强图像的光照分量后,对图像实施噪声过滤,并完成细节增强处理。对比实验表明:新方法可以使低照度行人动作图像保持良好的自然性亮度和清晰度,失真率也得到了有效控制。

In order to improve the natural brightness and clarity of low illumination pedestrian action images and reduce the distortion rate, a low illumination pedestrian action image enhancement method based on simulated multi exposure fusion is designed. With the goal of improving image visualization quality, over exposed and medium exposed pedestrian action images are generated, and multi-scale fusion processing of the images is achieved by using simulated multi exposure fusion. After enhancing the illumination components of the images, noise filtering is applied to the images and detail enhancement processing is completed.Comparative experiments show that the new method can maintain good natural brightness and sharpness of low illumination pedestrian action images, and the distortion rate is effectively controlled.