5G utility pole planner using Google Street View and Mask R-CNN
Files
Accepted manuscript
Date
2020-07
Authors
Zhang, Yanyu
Alshaykh, Osama
Version
Accepted manuscript
OA Version
Citation
Y. Zhang, O. Alshaykh. 2020. "5G Utility Pole Planner Using Google Street View and Mask R-CNN." 2020 IEEE International Conference on Electro Information Technology (EIT), https://doi.org/10.1109/eit48999.2020.9208333
Abstract
With the advances of fifth-generation (5G) [1] 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[2]. In order to determine the position of the points, this paper discusses a new way to identify poles based on Mask R-CNN[3], which extends Fast R-CNNs[4] 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 [5] [6] to set 5G poles in the smart cities.