The system identifies and locates the stop signs.
CREDIT
RMIT University
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.
Learn more: New AI system manages road infrastructure via Google Street View
The Latest on: AI-powered object detection
via Google News
The Latest on: AI-powered object detection
- Insta360 Link review: The best webcam you can buy todayon August 2, 2022 at 12:15 pm
Insta360, a company that has staked its reputation on 360-degree cams, is revolutionizing the humble office webcam market with its latest addition, the Link. Like the Apple-branded Center Stage, ...
- How To Use iOS 16's New Door Detectionon July 31, 2022 at 2:00 am
The latest iOS 16 upgrade includes additions to Apple's magnifier tool, which helps people easily zoom into objects using, essentially, an enhanced iPhone camera. The tool will now also include ...
- AI On Raspberry Pi With The Intel Neural Compute Stickon July 30, 2022 at 5:00 pm
I’ve always been fascinated by AI and machine learning ... so I stopped there. Object detection, classification, and some type of speech recognition also appear to have compiled correctly.
- Mythic: How An Analog Processor Could Revolutionize Edge AIon July 30, 2022 at 9:14 am
Mythic: How an Analog Processor Could Revolutionize Edge AI Alberto Romero, LLM Analyst Karl Freund, Founder and Principal Analyst Cambrian-AI Research.
- EarthCam Introduces Suite of Advanced Security Serviceson July 29, 2022 at 7:17 am
Expands solutions for jobsite surveillance with perimeter detection & Central Station Monitoring EarthCam’s Suite of Advanced Jobsite Security Services Solutions for Jobsite Surveillance with ...
- A degree in data science is not important – Debdoot Mukherjee, Head of AI, Meeshoon July 28, 2022 at 3:34 am
My vision is that AI/ML models create solutions that humans can utilise in various tasks, but not replace humans in any manner ...
- SentinelOne Announces Amazon S3 Storage Sentinel for Complete Cloud Protectionon July 27, 2022 at 10:00 am
SentinelOne (NYSE: S), an autonomous cybersecurity platform company, today announced Storage Sentinel for Amazon S3, a high-performance malware prevention solution for industry-leading Amazon Simple ...
- Nvidia gets down with low code in AI Enterprise updateon July 25, 2022 at 5:48 pm
The update also extends support for Red Hat OpenShift, Domino Data Lab’s ML operations platform, and Azure’s NVads A10 v5 series virtual machines. Introduced last summer, Nvidia bills AI Enterprise as ...
- Rediscovering analog computing for achieving effective edge AI performanceon July 22, 2022 at 5:00 pm
With the exponential growth in compute requirements for edge-AI applications, digital systems are struggling ... Analog CIM systems are ideal for video analytics applications that include object ...
- Teetering on the edge of an AI revolutionon July 19, 2022 at 5:00 pm
AI in power tools and hand tools will be able to detect sub ... The NPU can run neural network algorithms for various tasks such as human pose and emotion detection, multi-object surveillance and word ...
via Bing News