Geospatial scientists have developed a new program to monitor street signs needing replacement or repair by tapping into Google Street View images.
The fully-automated system is trained using AI-powered object detection to identify street signs in the freely available images.
Municipal authorities currently spend large amounts of time and money monitoring and recording the geolocation of traffic infrastructure manually, a task which also exposes workers to unnecessary traffic risks.
Results just published in the journal of Computers, Environment and Urban Systemsshow the system detects signs with near 96% accuracy, identifies their type with near 98% accuracy and can record their precise geolocation from the 2D images.
Study lead author and RMIT University Geospatial Science Honours student, Andrew Campbell, said the proof-of-concept model was trained to see ‘stop’ and ‘give way'(yield) signs, but could be trained to identify many other inputs and was easily scalable for use by local governments and traffic authorities.
“(Municipal authorities) have requirements to monitor this infrastructure but currently no cheap or efficient way to do so,” Campbell said.
“By using free and open source tools, we’ve now developed a fully automated system for doing that job, and doing it more accurately.”
The team found during investigations that mandatory GPS location data in existing street sign databases was often inaccurate, sometimes up to 10m off.
“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.
Campbell credited the project’s initial concept to his industry mentor at Alpine Shire Council and RMIT Geospatial Science alumnus, Barrett Higman.
RMIT geospatial scientist and project co-lead, Dr Chayn Sun, said the fact that some councils were already attaching cameras onto rubbish trucks to gather street footage showed how valuable visual data were becoming, given what technology could now do with it.
“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,” Sun said.
“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.”
Sun said footage from other sources, like that from rubbish truck cameras or any other geo-referenced imagery of the road network collected by municipal authorities, could also be fed into the system.
“Where footage is already being gathered, our research can provide councils with an economical tool to drive insights and data from this existing resource,” she said.
The Latest on: AI-powered object detection
via Google News
The Latest on: AI-powered object detection
- Baidu’s deep-learning platform fuels the rise of industrial AIon June 22, 2020 at 8:12 am
AI is driving industrial transformation across a variety of sectors, and we’re just beginning to scratch the surface of AI capabilities. Some industrial innovations are barely noticed, such as forest ...
- Adversarial attacks against machine learning systems – everything you need to knowon June 17, 2020 at 7:35 am
The technique exploited glitches in the machine learning (ML) algorithms that power Tesla’s Lane Detection technology in order to cause it to behave erratically. Machine learning has become an ...
- Viral Disease Diagnosis Market – Development of precise rapid screening tests with improved detection time drive market growthon June 15, 2020 at 1:27 am
Common influenza, contagious infections, and serious pandemics are some of the issues that need clinical prognosis for an early detection of the infectious agent. It is thus essential to identify ...
- Why it matters that IBM is getting out of the facial recognition businesson June 10, 2020 at 7:57 pm
However, a person familiar with the matter said that IBM will limit itself to the development of visual object detection and will no longer make APIs that could be used to power facial recognition ...
- Huawei Mate 10 and Mate 10 Pro are all about AI-powered intelligent photographyon June 10, 2020 at 12:32 pm
Artificial intelligence makes Real-Time Scene and Object Recognition ... analyze the “AI-powered Bokeh Effect”, “AI-powered Digital Zoom” and “AI Motion Detection” in our upcoming ...
- 3D Printers with an AI Brainon June 8, 2020 at 3:45 am
Artificial intelligence (AI)-powered 3D printing promises to effectively bridge ... Its AiMaker attaches itself to industrial robotic arms and is able to 3D print large objects at high speed with ...
- ThermalPass and Internet of Things Inc. Featured on FOX.comon June 5, 2020 at 8:39 am
The article goes on to say how ThermalPass was inspired out of necessity and that its fever screening solution will instill confidence in those who are wary of getting back to large gatherings or ...
- ThermalPass and Internet of Things Inc. Featured on FOX.comon June 5, 2020 at 8:19 am
Unlike thermal camera technology, ThermalPass uses medical grade sensors designed to measure temperature from a distance by detecting an object's infrared energy. The company's AI-powered system ...
- Perspectives on Microscopyon June 5, 2020 at 4:18 am
What is most exciting about its integration is it enables product developers to embed software tools into AI-powered devices ... they intend to use and which objects of interest they are trying ...
- ECOVACS ROBOTICS Launches the DEEBOT OZMO T8 Family Putting AI to Work For a Better Looking Homeon May 24, 2020 at 11:04 pm
The DEEBOT OZMO T8 AIVI can automatically recognize objects ... AI-powered functions will be offered via OTA (Over the Air) Technology in the coming months, including automated detection of ...
via Bing News