Luminance prior guided Low-Light 4C catenary image enhancement

Abstract

In scenarios characterized by inadequate fill lighting, catenary images captured by railway power supply 4C monitoring equipment often exhibit a phenomenon of low light, which can pose significant challenges for accurately detecting anomalies in the equipment. This, in turn, has ramifications for the smooth operation, timely maintenance, and overall safety assurance of railway systems. Recognizing this critical issue, our study introduces an innovative dual-branch priori-guided enhancement method specifically tailored for low-light catenary images obtained through powered 4C monitoring equipment. Within the multi-scale branch of our method, we leverage the powerful capabilities of convolutional neural networks (CNNs) along with the self-attention mechanism to effectively extract both local and global features from the images. This dual focus allows our model to capture intricate details and broader contextual information, enhancing its ability to understand and enhance the images. Concurrently, the pixel-wise branch of our method is designed to estimate enhancement parameters at the pixel level, enabling an adaptive and iterative enhancement process. This fine-grained approach ensures that each pixel in the image is optimized based on its unique characteristics and context, leading to more nuanced and accurate enhancements. To further inform and constrain our enhancement process, we conduct a statistical analysis of the average light intensity of images under both normal and low-light conditions. By examining the differences and correlations between image brightness under these varying light conditions, we derive statistical priors that are integrated into our method. These priors serve as valuable guidance for our model, helping it to make more informed decisions during the enhancement process. Moreover, to mitigate the challenges associated with obtaining labeled data, we adopt an unsupervised model training strategy. This approach allows our method to learn and improve without the need for extensive and costly labeling efforts, making it more practical and scalable for real-world applications. Experimental results demonstrate the superiority of our proposed method when compared to state-of-the-art approaches for low-light catenary image enhancement. Our method improves the visual quality of the images, ultimately contributing to the safety and efficiency of railway operations.