Real-Time Traffic Analytics at Intersections
More and more city planners are taking into consideration smart mobility solutions to address transportation needs and central to smart transportation systems is access to real-time data. For example, self-driving cars offer independence for seniors and people with disabilities, greater road safety, cost savings through ride-sharing, increased productivity, reduced congestion, and reduced fuel use and carbon emissions. But what type of information and data is needed for city planners to accommodate smart transportation systems? Visual data is extremely rich in information and algorithms can process the data and extract the information. However, bandwidth is limited and too much time is needed to transfer visual data to remote computers for analysis. This work focused on developing computer vision algorithms for analyzing visual data and computing and sharing the resulting analytics and summary data in real-time. Algorithms were developed to understand vehicle motion in 3D space and time, and to track the pose of people in 3D. These algorithms are vital to computing analytics on real data in the presence of occlusions, cluttered scenes, and
varied lighting conditions.
Read the full study here.