Method and system for testing video analytics of a video surveillance system
Inventors
Dhamija, Vijay K. • Ghosh, Somnath • Eswara, Lalitha M.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Simulated objects are generated for display over a video stream by receiving a first user input that identifies one or more user identified regions relative to an image, tagging each of the one or more user identified regions with a corresponding region tag, receiving a second user input that is used to identify one or more simulation parameters, and identifying one or more simulation parameters based at least in part on the second user input. The method includes determining a plurality of characteristics of the simulated objects based on the simulation parameters, user identified regions and region tags. The simulated objects are superimposed on the video stream to create an augmented video stream and the augmented video stream is processed using one or more video analytics algorithms to test the effectiveness of each of the one or more video analytics algorithms.
Core Innovation
The method analyzes a selected video analytics algorithm by generating simulated objects based at least in part on that algorithm, assigning characteristics, superimposing the objects on the camera field of view to create an augmented video stream, and processing the stream with the selected algorithm. Characteristics include object type, quantity, distribution, starting point, speed, speed variation, and movement type; distributions combine at least two specified types. The background problem is not explicitly described in the provided content.
Claims Coverage
The provided relevant claims identify one independent claim with four inventive features, directed to a computer-implemented method for analyzing a selected video analytics algorithm in a facility's video surveillance system.
User selection of a video analytics algorithm
The method receives user input identifying a selected video analytics algorithm from a plurality of algorithms for execution on video captured by the camera.
Generation of simulated objects with selected characteristics
The method generates simulated objects based at least in part on the selected algorithm and determines characteristics including object type, quantity, distribution, starting point, speed, speed variation, and type of movement.
Combination of distribution types
The distribution of two or more simulated objects comprises a combination of at least two different distribution types selected from the types listed in the claim.
Superimposition and processing of the augmented video stream
The method superimposes the simulated objects with their characteristics on the camera's field of view to create an augmented video stream, then processes that stream using the selected video analytics algorithm.
The independent claim covers selection of a video analytics algorithm, generation and placement of simulated objects with specified characteristics and combined distribution types, and processing of the resulting augmented video stream.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Analyzing or testing video analytics algorithms in a facility's video surveillance system. The relevant claims identify crowd detection, crowd analytics, people count, behavior detection, intrusion detection, perimeter protection, and tailgating detection algorithms.
Interested in licensing this patent?