JUN 18, 2019 9:53 AM PDT

AI System Monitors Street Signs via Google Street View

WRITTEN BY: Nouran Amin

Using Google Street View Images, a new program was developed to monitor street signs needing replacement or repair. The newly developed fully-automated system uses an artificial intelligence model powered by object detection to identify street signs in the freely available images. The development can save time and money while importantly keeping municipal workers safe from unnecessary exposure to traffic risks.

"(Municipal authorities) have requirements to monitor this infrastructure but currently no cheap or efficient way to do so," says Andrew Campbell, study lead author and RMIT University Geospatial Science student. "By using free and open source tools, we've now developed a fully automated system for doing that job, and doing it more accurately."

Learn more about how Google maps function:

 

 

"Tracking these signs manually by people who may not be trained geoscientists introduces human error into the database. Our system, once set up, can be used by any spatial analyst -- you just tell the system which area you want to monitor and it looks after it for you," Campbell said.

The system can detect signs with an estimated 96% accuracy, identifies the type of sign with a near 98% accuracy and can record precise geolocation from 2D images. The system can also be trained for other inputs for use by local governments and traffic authorities. Findings were reported in the journal of Computers, Environment and Urban Systems.

"This imagery is critical for local governments in monitoring and managing assets and with the huge amount of geospatial applications flourishing, this information will only become more valuable," says RMIT geospatial scientist and project co-lead, Dr Chayn Sun. "Ours is one of several early applications for this to meet a specific industry need but a whole lot more will emerge in coming years. Where footage is already being gathered, our research can provide councils with an economical tool to drive insights and data from this existing resource.”

Source: Science Daily

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 03, 2019
Cancer
DEC 03, 2019
Using deep learning to find the patterns of cancer
Research published recently in the journal Life Science Alliance uses deep learning to analyze genomic data from colorectal tumors to ameliorate diagnosis ...
DEC 06, 2019
Technology
DEC 06, 2019
Molecular Eraser Increases Data Storage Efficiency
Researchers at the University of Alberta in Canada have explained a hydrogen-related novel method that takes advantage of a natural physical phenomenon to ...
DEC 07, 2019
Genetics & Genomics
DEC 07, 2019
New Tool Rapidly Detects Unintended Gene Changes from CRISPR
CRISPR is one of the most promising technologies under development to treat deadly inherited conditions such as cystic fibrosis and sickle cell disease. No...
DEC 09, 2019
Neuroscience
DEC 09, 2019
Russian Cows Use VR Headsets to Increase Milk Production
Harsh weather conditions, particularly those found during winter months, are known to lead to a decrease in milk production among cows. To tackle this, Rus...
DEC 16, 2019
Technology
DEC 16, 2019
Headphones That Warn You of Danger
It’s a common seen—people wearing headphones or earbuds with their faces glued to their phones as the cross the street unaware of their surroun...
FEB 03, 2020
Technology
FEB 03, 2020
The Demand for Drone Delivery is High
Many consumers are demanding drones for delivery of their products. But how realistic is drone delivery? A study published in the INFORMS journal Transport...
Loading Comments...