System and method for crowd counting and tracking

A crowd-counting device comprising:

• a depth stream sensor configured to capture frames of depth stream data that indicates at each pixel a depth or distance to the depth stream sensor;
• a spatial analysis module connected to receive depth stream data captured by the depth stream sensor, wherein the spatial analysis module analyzes each frame of depth stream data to identify objects corresponding with user's heads, wherein the spatial analysis module, wherein the spatial analysis module utilizes a minimum depth pixel to identify a top portion of a user's head, flood fills pixels surrounding the minimum depth pixel corresponding with the user's head, removes the portion representing the user's head from the frame, and iteratively repeats the process until all objects have been identified and removed from the frame, wherein for each identified user head the spatial analysis module creates an output vector that identifies features associated with the user's head, wherein the spatial analysis module flood fills pixels based on a threshold fill depth that identifies or fills all pixels located within a minimum depth of the minimum depth associated with the identified object;
• a temporal analysis module connected to receive the output vectors generated by the spatial analysis module, wherein the temporal analysis module compares output vectors generated with respect to a current frame with output vectors generated with respect to a previous frame in order to generate attributes of location and direction with respect to each detected user head;
• and
• an analytics module that increments and decrements a count of users based on location and direction information provided by the temporal analysis module.

A video analytic system comprising:

• a depth stream sensor that collects depth stream data;
• a spatial analysis module connected to receive and analyze the depth stream data on a frame by frame basis, wherein the spatial analysis module iteratively identifies objects of interest based on local maximum or minimum depth stream values within each frame, removes identified objects of interest, and repeats until all objects of interest have been identified;
• a temporal analysis module connected to receive objects of interest identified by the spatial analysis module in a frame, wherein the temporal analysis module associates each object of interest in the current frame with an object of interest identified in a previous frame, wherein the temporal analysis module utilizes the association between current frame objects of interest and previous frame objects of interest to generate temporal features related to each object of interest, wherein the temporal analysis module comprises:
• an association module connected to receive information about each object of interest identified by the spatial analysis module with respect to the current frame, wherein the association module compares current frame objects of interest with previous frame objects of interest and associates a current frame object of interest with a previous frame object of interest;
• a validation module connected to receive the associations made by the association module, wherein the validation module validates that the current frame object of interest and previous frame object of interest refer to the same object;
• a reliability module connected to receive the validated associations from the validation module, wherein the reliability module determines a reliability value associated with each detected object of interest based, in part, on a number of frames in which the object has been tracked and associated with previous frame objects of interest;
• and
• an output module configured to calculate attributes of each object of interest based on associations between current frame objects of interest and previous frame objects of interest;
• and
• an analytics module connected to receive the temporal features generated by the temporal analysis module, wherein the analytics module detects events based on the received temporal features.

A crowd-counting device comprising:

• a depth stream sensor configured to capture frames of depth stream data that indicates at each pixel a depth or distance to the depth stream sensor;
• a spatial analysis module connected to receive depth stream data captured by the depth stream sensor, wherein the spatial analysis module analyzes each frame of depth stream data to identify objects corresponding with user's heads, wherein the spatial analysis module, wherein the spatial analysis module utilizes a minimum depth pixel to identify a top portion of a user's head, flood fills pixels surrounding the minimum depth pixel corresponding with the user's head, removes the portion representing the user's head from the frame, and iteratively repeats the process until all objects have been identified and removed from the frame, wherein for each identified user head the spatial analysis module creates an output vector that identifies features associated with the user's head, wherein the spatial analysis module utilizes a rate of change threshold associated with pixel depth to determine those pixels to be included as part of the identified object;
• a temporal analysis module connected to receive the output vectors generated by the spatial analysis module, wherein the temporal analysis module compares output vectors generated with respect to a current frame with output vectors generated with respect to a previous frame in order to generate attributes of location and direction with respect to each detected user head;
• and
• an analytics module that increments and decrements a count of users based on location and direction information provided by the temporal analysis module.