Vision Aided Channel Prediction for Vehicular Communications: A Case Study of Received Power Prediction Using RGB Images

The communication scenarios and channel characteristics of 6G will be more complex and difficult to characterize. Conventional methods for channel prediction face challenges in achieving an optimal balance between accuracy, practicality, and generalizability. Additionally, they often fail to effectively leverage environmental features. Within the framework of integration communication and artificial intelligence as a pivotal development vision for 6G, it is imperative to achieve intelligent prediction of channel characteristics. Vision-aided methods have been employed in various wireless communication tasks, excluding channel prediction, and have demonstrated enhanced efficiency and performance. In this paper, we propose a visionaided two-stage model for channel prediction in millimeter wave vehicular communication scenarios, specifically realizing accurate received power prediction utilizing solely RGB images. First, we acquire the original image and channel data (mainly received power) of the propagation environment via RGB cameras and channel measurements. In stage 1, redundant data is filtered and synchronized to yield one-to-one channel-image data pairs. The image data is then fed into YOLOv8 network, which extracts key vehicle features—such as size, shape, and location—using three typical computer vision methods (including object detection, instance segmentation and binary mask). These processed images are input into the ResNets for training and testing in stage 2, with the received power serving as the label and expected output. Finally, we conduct five experiments to evaluate the performance of proposed model, demonstrating its feasibility, accuracy and generalization capabilities. The model proposed in this paper offers novel solutions for achieving intelligent channel prediction in vehicular communications.