Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Weixing Zhang; Chandi Witharana; Weidong Li; Chuanrong Zhang; Xiaojiang Li; Jason Parent

doi:10.3390/s18082484

Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Sensors (Basel). 2018 Aug 1;18(8):2484. doi: 10.3390/s18082484.

Authors

Weixing Zhang^{1

2

3

4

5}, Chandi Witharana^{6

7}, Weidong Li⁸, Chuanrong Zhang^{9

10}, Xiaojiang Li¹¹, Jason Parent^{12

13}

Affiliations

¹ Department of Geography, University of Connecticut, Storrs, CT 06269, USA. weixing.zhang@uconn.edu.
² Center for Environmental Science and Engineering, University of Connecticut, Storrs, CT 06269, USA. weixing.zhang@uconn.edu.
³ Connecticut State Data Center, University of Connecticut, Storrs, CT 06269, USA. weixing.zhang@uconn.edu.
⁴ Department of Natural Resources and the Environment, University of Connecticut, Storrs, CT 06269, USA. weixing.zhang@uconn.edu.
⁵ Eversource Energy Center, University of Connecticut, Storrs, CT 06269, USA. weixing.zhang@uconn.edu.
⁶ Department of Natural Resources and the Environment, University of Connecticut, Storrs, CT 06269, USA. chandi.witharana@uconn.edu.
⁷ Eversource Energy Center, University of Connecticut, Storrs, CT 06269, USA. chandi.witharana@uconn.edu.
⁸ Department of Geography, University of Connecticut, Storrs, CT 06269, USA. weidong.li@uconn.edu.
⁹ Department of Geography, University of Connecticut, Storrs, CT 06269, USA. chuanrong.zhang@uconn.edu.
¹⁰ Center for Environmental Science and Engineering, University of Connecticut, Storrs, CT 06269, USA. chuanrong.zhang@uconn.edu.
¹¹ MIT Senseable City Lab, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. xiaojian@mit.edu.
¹² Department of Natural Resources and the Environment, University of Connecticut, Storrs, CT 06269, USA. jason.parent@uconn.edu.
¹³ Eversource Energy Center, University of Connecticut, Storrs, CT 06269, USA. jason.parent@uconn.edu.

Abstract

Traditional methods of detecting and mapping utility poles are inefficient and costly because of the demand for visual interpretation with quality data sources or intense field inspection. The advent of deep learning for object detection provides an opportunity for detecting utility poles from side-view optical images. In this study, we proposed using a deep learning-based method for automatically mapping roadside utility poles with crossarms (UPCs) from Google Street View (GSV) images. The method combines the state-of-the-art DL object detection algorithm (i.e., the RetinaNet object detection algorithm) and a modified brute-force-based line-of-bearing (LOB, a LOB stands for the ray towards the location of the target [UPC at here] from the original location of the sensor [GSV mobile platform]) measurement method to estimate the locations of detected roadside UPCs from GSV. Experimental results indicate that: (1) both the average precision (AP) and the overall accuracy (OA) are around 0.78 when the intersection-over-union (IoU) threshold is greater than 0.3, based on the testing of 500 GSV images with a total number of 937 objects; and (2) around 2.6%, 47%, and 79% of estimated locations of utility poles are within 1 m, 5 m, and 10 m buffer zones, respectively, around the referenced locations of utility poles. In general, this study indicates that even in a complex background, most utility poles can be detected with the use of DL, and the LOB measurement method can estimate the locations of most UPCs.

Keywords: Google Street View; deep learning; infrastructure mapping; line-of-bearing measurement; object detection; utility pole.