Image Exposure Correction Based on Dual Feature Fusion for Intelligent Transportation

In the field of intelligent transportation, the quality of images captured by surveillance cameras can be affected by the lighting conditions of the scene, resulting in the loss of critical information, which in turn leads to a lack of reliable image evidence for subsequent traffic enforcement. However, existing image exposure correction methods have problems such as color distortion and blurry details in the corrected image. Therefore, this article proposes a dual feature fusion image exposure correction method for intelligent transportation, which extracts relevant features through global subnet and exposure subnet, respectively. Among them, the former introduces the feature attention mechanism to extract global features of the image, improving the overall brightness and color of the corrected image; the latter is based on the Unet network structure and introduces a multi-scale attention mechanism to extract exposure features at different scales in the image, improving the detailed texture of the corrected image; Finally, image exposure correction is achieved by fusing the dual features and mapping them to the image space. The experimental results show that this method has a PSNR of 21.8015 dB, SSIM of 0.8677, and NIQE of 11.7118 on the MSEC dataset, all of which are superior to existing exposure correction methods. It can effectively restore image color information and detail textures, proving that this method has good exposure correction effect.