This I-Corps team proposes the development of a real-time traffic congestion detection system from surveillance videos. The proposed technology for detecting traffic congestion involves two major components: (a) vehicle detection and tracking; and (b) event classification. The research team will use computer vision techniques for detecting vehicles in single frames. By analyzing consecutive frames, vehicle speed and relative locations will be estimated. For the classification of events, the team will use their expertise in graph kernels and machine learning. A sequence of consecutive frames can be used to create a graph, where the nodes represent vehicles labeled with local features, such as speed and location. Neighboring nodes in the graph are connected by edges labeled with the distance between their respective vehicles. A fast kernel function for graphs will be developed and used by a binary classifier which will be trained for the task of recognizing traffic congestion. As an extension, a multi-class classifier can also be trained to distinguish different types of traffic events, such as, high, moderate, or low traffic congestion, accident, or normal traffic.
The proposed product is a great opportunity for transforming state-of-the-art computational techniques into new technologies that can directly have societal and commercial impacts. A real time traffic congestion detection system has as their primary targets government agencies and departments across the nation. With a real time detector of congestion, one will be able to track simultaneously hundreds or thousands of cameras at the same time, discovering incidents that can enhance traffic management. Decision makers can use the proposed product for dynamic traffic assignment, incident discovery, and improved management of evacuation systems. Society may be impacted as a whole with savings in commuting time and delay costs. This product can also be used for developing web applications or apps for mobile devices, bringing real time traffic information to motorists.
Team "Real Time Traffic Congestion Detection" participated in the NSF Innovation Corps (I-Corps) program with the following team members: Entrepreneurial Lead Dr. Marco Alvarez Vega, Principal Investigator Dr. John Cavazos, and Business Mentor Mr. Ed Henkler. The presence of traffic congestion on US roads currently imposes increasing costs on both individual motorists and transportation systems. With congestion costs in the order of billions of dollars a year, one solution is to take advantage of current surveillance systems already installed on highways and roads. Our I-Corps team explored the commercial viability of a technology that enables the automatic detection of traffic incidents in real time. Traffic incidents like accidents, disabled vehicles, or simply objects blocking the road are leading causes for congestion on roads and highways. Furthermore, nowadays most Departments of Transportation across the nation have a wide network of cameras deployed along their roads and highways. The technology explored under this award may provide a solution that takes advantage of this infrastructure, by analyzing hundreds of video streams produced by such traffic cameras and detecting incidents in real time. Thus, our video analytics technology can be used as a powerful tool for mitigating the effects of traffic congestion. Our team participated of the I-Corps training where we conducted 129 interviews as part of our customer discovery effort. Such intense and immersive learning experience helped our team to understand the transition of our laboratory research into technology that can be commercialized as a product. After the first two weeks into training and customer discovery, we learned that our potential customers would be more interested in the automatic detection of incidents rather than software capable of detecting congestion. This will allow them to gain valuable minutes in the lifetime of an incident. For example, they told us that for every minute that a freeway lane is blocked, an estimated seven minutes of congestion result after the incident is cleared. We also narrowed our customer segments to Departments of Transportation (DOTs), which reported concrete pain points in their traffic management operations. We started to build a business model around this customer segment, which is in need of a low-cost and effective technology for mitigating the effects of congestion. We have also learned that a strong expertise from our lab, high performance computing, would have a noticeable impact on providing a low-cost technology to DOTs. The I-Corps program has provided great value for our team to identify the value propositions of our technology. We concluded that our technology should shift from congestion detection to low-cost incident detection in order to provide a competitive product in the market. Our final decision is a GO and we are currently looking forward to continue the research and technical development of our product, while at the same time strengthening our relationships with potential customers.
