US 12,424,077 B2
Stampede detection
Aleksey Lipchin, Newton, MA (US); Maksim Bolonkin, Waltham, MA (US); Keshav T. Seshadri, Medford, MA (US); and Sergey Veselkov, Ashland, MA (US)
Assigned to MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed by MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed on Aug. 1, 2023, as Appl. No. 18/363,579.
Prior Publication US 2025/0046175 A1, Feb. 6, 2025
Int. Cl. G06K 9/00 (2022.01); G06T 7/20 (2017.01); G06V 10/25 (2022.01); G06V 20/52 (2022.01); G08B 21/22 (2006.01)
CPC G08B 21/22 (2013.01) [G06T 7/20 (2013.01); G06V 10/25 (2022.01); G06V 20/53 (2022.01); G06T 2210/12 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An imaging system comprising:
an image sensor; and
an electronic processor in communication with the image sensor, the electronic processor configured to:
obtain video data, captured using the image sensor, of a scene including a region of interest, the video data including a plurality of frames;
determine a total number of detected humans in the region of interest of a current frame of the plurality of frames;
determine a velocity of each detected human in the region of interest the current frame;
determine a number of running humans in the region of interest of the current frame by determining a number of detected humans in the region of interest of the current frame having a velocity greater than a velocity threshold;
determine a probability associated with the number of running humans in the region of interest of the current frame and the total number of detected humans in the region of interest of the current frame based on accumulated statistics for the region of interest, the accumulated statistics including average numbers of running humans out of total numbers of detected humans; and
in response to determining that the probability is less than a threshold probability, generate an alert indicating a stampede is detected in the region of interest.