Multipath Cluster-Based Scatterer Recognition by Object Detection Techniques Using Panoramic Images

Object detection is crucial in the field of wireless communication, as it helps in predicting the channel behavior and channel model parameters that are necessary for efficient communication. In recent years, various object detection techniques have been proposed for this purpose, ranging from traditional statistical methods to deep learning-based approaches. This paper provides a comprehensive review of object detection techniques for predicting wireless channel model parameters. Additionally, the paper discuss the advantages and limitations of different object detection frameworks such as YOLO, Faster R-CNN, and Mask R-CNN. Finally, the paper puts foward a conceptual introduction of a novel approach to utilize Faster R-CNN object detection technique andcomputer vision, to predict the scatterers and eventually estimate the channel characteristics of a wireless channel. The paper highlights the current challenges and future directions in object detection for wireless channel model parameters prediction. The dataset to train the deep learning model is generated from an example conference room environment panoramic images. The proposed approach can be applied in various wireless communication scenarios, such as 5G and beyond, to accurately predict the location of scatterers based on multipath clusters so as to optimize network design and improve the overall performance of the system.