Faster And Accurate Street Repair Using Google Street View

UNIVERSITY OF MARYLAND, MARYLAND, USA. A group of software developers recently came up with a software that allows untrained crowdsourced workers from Amazon’s Mechanical Turk service (AMT) to go virtually through the streets with the help of Google Street View. That way, they are able to zoom in and out which helps them find and label the potholes, missing ramps, broken kerbs and obstructed pathways to better help people using a wheelchair or a walking aid.

With the help of the software, they are also able to provide images of the problem areas to help the local council’s road-mending crews know exactly what to fix and where to find it. At the same time, municipalities would surely be able to save time and money by simply knowing the exact problem at the exact place before they fix it. Knowing what to fix and how to fix it beforehand will give the workers enough time and preparation to fix the problem.

The project ensures that the workers will only take the right amount of materials required for the tasks that need to be done to avoid any unnecessary waste. After several tests were done, it was found out that the software helped the workers effectively spot the problem accurately by at least 93% each time.

Jon Froehlich and his colleagues at the University of Maryland in College Park are the developers behind the Google Street View marker software. They will be presenting their work at the Conference on Human Factors in Computing Systems in Paris, France this coming April.

Currently, they are also working on upgrading the software to a newer version which involves street View camera cars that will help them acquire more data as they go through streets. With this method, the accuracy in assessing different street obstructions will become even more accurate.