AI News, Artificial intelligence and supercomputers to help alleviate urban traffic problems
- On Tuesday, June 5, 2018
- By Read More
Artificial intelligence and supercomputers to help alleviate urban traffic problems
At the IEEE International Conference on Big Data this month, they will present a new deep learning tool that uses raw traffic camera footage from City of Austin cameras to recognize objects -- people, cars, buses, trucks, bicycles, motorcycles and traffic lights -- and characterize how those objects move and interact.
The algorithm they developed for traffic analysis automatically labels all potential objects from the raw data, tracks objects by comparing them with other previously recognized objects and compares the outputs from each frame to uncover relationships among the objects.
Once researchers had developed a system capable of labeling, tracking and analyzing traffic, they applied it to two practical examples: counting how many moving vehicles traveled down a road and identifying close encounters between vehicles and pedestrians.
'The use of artificial intelligence to automatically generate traffic volumes from existing cameras would provide a much broader spatial and temporal coverage of the transportation network, facilitating the generation of valuable datasets to support innovative research and to understand the impact of traffic management and operation decisions.'
The researchers plan to explore how automation can facilitate other safety-related analyses, such as identifying locations where pedestrians cross busy streets outside of designated walkways, understanding how drivers react to different types of pedestrian-yield signage and quantifying how far pedestrians are willing to walk in order to use a walkway.
Artificial Intelligence and Supercomputers to Help Alleviate Urban Traffic Problems
At the IEEE International Conference on Big Data this month, they will present a new deep learning tool that uses raw traffic camera footage from City of Austin cameras to recognize objects – people, cars, buses, trucks, bicycles, motorcycles and traffic lights – and characterize how those objects move and interact.
“The use of artificial intelligence to automatically generate traffic volumes from existing cameras would provide a much broader spatial and temporal coverage of the transportation network, facilitating the generation of valuable datasets to support innovative research and to understand the impact of traffic management and operation decisions.” In the case of potential close encounters, researchers were able to automatically identify a number of cases where vehicles and pedestrians were in close proximity.
“We can direct our resources toward fixing problem locations before an injury or fatality occurs.” The researchers plan to explore how automation can facilitate other safety-related analyses, such as identifying locations where pedestrians cross busy streets outside of designated walkways, understanding how drivers react to different types of pedestrian-yield signage and quantifying how far pedestrians are willing to walk in order to use a walkway.
“Video data will play a key role in understanding such changes, and artificial intelligence may be central to enabling comprehensive large-scale studies that truly capture the impact of the new technologies.” -- The team built a website where the public can view examples of their detection, tracking and query tool for traffic analysis.
Using triangulation to assess a suite of tools to measure community severance
There is a lack of tools to identify and measure community severance caused by large roads and motorised traffic, despite the evidence of its negative impacts on local communities.
The analysis showed coherence between the findings from the different measurement tools applied individually, but also revealed interconnections between factors which contribute to severance, demonstrating that overall the suite is reliable for assessing community severance in urban areas.
A traffic count is commonly undertaken either automatically (with the installation of a temporary or permanent electronic traffic recording device), or manually by observers who visually count and record traffic on a hand-held electronic device or tally sheet. Traffic counts can be used by local councils to identify which routes are used most, and to either improve that road or provide an alternative if there is an excessive amount of traffic.
These methods are generally employed where vehicle speeds and volume are required without classification which require on-road sensors. Technologies for counting bicycles on roads, or bicycles and pedestrians along sidewalks or shared-use paths have progressed with the increased emphasis on the economic, environmental and social benefits of multi-modal traffic networks.
In 2004, the American private-sector firm Alta Planning and Design, in partnership with the Institute of Transportation Engineers (ITE) initiated the National Bicycle and Pedestrian Documentation Program (NBPD) as an effort to promote greater data collection for non-motorized transportation modes, establish a consistent model for data collection, and address the lack of data access and shared research. In 2013, the US Department of Transportation, Federal Highway Administration (FHWA) expanded and created a chapter on non-motorized counting for the Traffic Monitoring Guide (TMG) designed to guide planning agencies in the collection of their data.
Explore other topics in Road Safety
Fourteen percent of all traffic fatalities and an estimated 3 percent of those injured in traffic crashes were pedestrians.” (Traffic Safety Facts: Pedestrians, April 2014) – (PDF 1.20 MB) Safety is the top priority of the Department of Transportation.
The National Highway Traffic Safety Administration (NHTSA) and the Federal Highway Administration (FHWA) continue to work to raise awareness about the dangers to pedestrians and bicyclists, and to provide leadership, expertise, and resources to communities across America to combat these crashes.
Please join us to reduce traffic safety risks to pedestrians and bicyclists, and to promote programs and countermeasures to save the lives of all road users on our Nation's roadways.
- On Monday, February 24, 2020
The Future Of Transportation - Incredible Technology To Come
You will see what is the future of transportation. Actually,our cities have a lot of problems.Smogs,pollutions and traffic jams are some of these issues.
Road Traffic Library Webinar
The Road Traffic Library allows you to simulate vehicle and traffic dynamics The webinar (with ..
The Traffic Agent long version
School children are Oslo's most active walkers but is also facing the risk of accidents walking to school. We want to involve the children, helping the public sector ...
GoodVision Video Insights: Traffic Analysis via Video Extraction
Visit us at and schedule a hands-on demo session with us! This video is an example of GoodVision's unique Deep Learning ..
Safe Transportation for Every Pedestrian
Pedestrians account for an estimated 15 percent of all roadway fatalities, the majority of which are at uncontrolled crossing locations (such as non-intersections) ...
jugaad innovation। Desi Car । Home built car
This is home built car invented by Indian people. here we called it jugaad or desi car. this innovation car is very fast. boy create it by jugaadu technology. Jugaad ...
Intelligent Transportation Systems: Your Road to the Future
This video explores careers in intelligent transportation systems (ITS).
Automated Traffic Signal Performance Measures
Highway agencies typically rely on complaints or manual data collection to identify the need for signal retiming projects and their outcomes. These projects are ...
2016 Fall Seminar #8: Dedicated Short Range Communications (DSRC): What, Why, and How?
Presented by Imran Hayee, Professor, Electrical Engineering Department, University of Minnesota Duluth Please type how many people are watching at your ...
Duncan Solutions Parking & Guidance Technologies For Smart Cities - http://ow.ly/YjG530iciLW
Visit our website: Duncan Solutions is ..