5G Utility Pole Planner Using Google Street View and Mask R-CNN

TL;DR

This paper presents a method to identify street poles for 5G deployment using Mask R-CNN on Google Street View images, combined with an immune algorithm for optimal placement in smart cities.

Contribution

It introduces a novel pole detection approach using Mask R-CNN with Bayesian filtering and proposes an immune algorithm for strategic 5G pole placement.

Findings

Achieved 7.86% training error rate

Test error rate of 32.03% on high-resolution images

Demonstrated effective pole identification for 5G network planning

Abstract

With the advances of fifth-generation (5G) cellular networks technology, many studies and work have been carried out on how to build 5G networks for smart cities. In the previous research, street lighting poles and smart light poles are capable of being a 5G access point. In order to determine the position of the points, this paper discusses a new way to identify poles based on Mask R-CNN, which extends Fast R-CNNs by making it employ recursive Bayesian filtering and perform proposal propagation and reuse. The dataset contains 3,000 high-resolution images from google map. To make training faster, we used a very efficient GPU implementation of the convolution operation. We achieved a train error rate of 7.86% and a test error rate of 32.03%. At last, we used the immune algorithm to set 5G poles in the smart cities.