Enhancing Computer Vision for Public Safety Challenge

Create a new line of research in computer vision to develop life-saving tools for public safety

Other Funding
  • Program Type
    Other Funding

The Public Safety Communications Research (PSCR) Division of the National Institute of Standards and Technology (NIST) is hosting the Enhancing Computer Vision for Public Safety Challenge focused on advancing the capacity of no-reference (NR) metrics and computer vision algorithms for image and video quality analysis, to support public safety missions. PSCR will award prizes valued up to $240,000 to winning contestants. The First Responders Network Authority is partnering with PSCR on this challenge. The contestants will provide: 1) datasets of images or videos showing impairments that cause computer vision applications to fail, and 2) innovative methods to estimate the failure rate of computer vision algorithms on these images or videos. These solutions will provide the computer vision and NR metric research communities training datasets to ultimately improve analytics for public safety.

PSCR 2021 Burak Ozer

Dr. Ozer is a winner of the PSCR's Enhancing Computer Vision for Public Safety Challenge. In this challenge, PSCR asked solvers to create datasets with camera impairments and an innovative method to assess computer vision failure rates for those media. Assessment data could then be used by a computer vision system to deploy complex mitigation strategies, such as zooming, panning, or switching computer vision systems. Dr. Ozer’s database demonstrates many camera-based water level and velocity calculation smart camera systems/algorithms that are deployed around different water bodies, e.g. rivers, canals in Asia and in the USA.

Future Phases

Check out an overview of each competition phase below - complete rules for each phase will be released as the competition progresses.

Let’s Get Started.

To apply or join the program, please submit an application.