Reported in the paper, “New AI system manages road infrastructure via Google Street View”, released by RMIT University in the ScienceDaily journal, geospatial scientists have developed a new program to monitor street signs needing replacement or repair by tapping into Google Street View images. The paper submits that the program will save time and money for municipal authorities who are required to monitor street signs yet do not have an efficient and inexpensive way to do so.
Outlined in the abstract, “this paper explores the possibility of using deep learning to produce an autonomous system for detecting traffic signs on GSV images to assist in traffic assets monitoring and maintenance. By leveraging Google’s Street View API, this research offers an economic approach of building purposeful street sign computer vision datasets.”
The full paper can be sourced here: https://www.sciencedaily.com/releases/2019/06/190618094313.htm.