Busyness defection and notification method and system
First Claim
1. A computer-implemented image based method of determining and communicating a busyness metric associated with a number of people within an area captured by one or more image capturing devices, the method comprising:
- a) acquiring one or more images of the area from the one or more image capturing devices;
b) calculating a representation of the number of people within the area from the acquired one or more images of the area, the representation of the number of people calculated using a regression model trained with a training set of images, the regression model configured to receive an input feature vector associated with an acquired image and output a number of distinct people associated with the input feature vector associated with the acquired image;
c) calculating the busyness metric as a function of the representation of the number of people within the area, the busyness metric related to the calculated representation of people within the area during a sequence of acquired images representative of a predetermined time period; and
d) communicating the busyness metric to one or more of an electronic device associated with a user, a data storage device and a post processing device,wherein step b) includes;
b1) dividing each of the one or more acquired images into a plurality of windows;
b2) extracting feature vectors from each of the plurality of windows;
b3) concatenating the extracted feature vectors to form a single feature vector representation of the number of people within the area covered by the plurality of windows; and
b4) inputting the single feature vector to the regression model to determine the number of people within the area covered by the plurality of windows.
4 Assignments
0 Petitions
Accused Products
Abstract
This disclosure provides a video-based method and system for busyness detection and notification. Specifically, according to an exemplary embodiment, multiple overhead image capturing devices are used to acquire video including multiple non-overlapping ROIs (regions of interest) and the video is processed to count the number of people included within the ROIs. A busyness metric is calculated based on the number of people counted and notification of the busyness metric or changes in the busyness metric is communicated to appropriate personnel, e.g., a manager of a retail store.
-
Citations
18 Claims
-
1. A computer-implemented image based method of determining and communicating a busyness metric associated with a number of people within an area captured by one or more image capturing devices, the method comprising:
-
a) acquiring one or more images of the area from the one or more image capturing devices; b) calculating a representation of the number of people within the area from the acquired one or more images of the area, the representation of the number of people calculated using a regression model trained with a training set of images, the regression model configured to receive an input feature vector associated with an acquired image and output a number of distinct people associated with the input feature vector associated with the acquired image; c) calculating the busyness metric as a function of the representation of the number of people within the area, the busyness metric related to the calculated representation of people within the area during a sequence of acquired images representative of a predetermined time period; and d) communicating the busyness metric to one or more of an electronic device associated with a user, a data storage device and a post processing device, wherein step b) includes; b1) dividing each of the one or more acquired images into a plurality of windows; b2) extracting feature vectors from each of the plurality of windows; b3) concatenating the extracted feature vectors to form a single feature vector representation of the number of people within the area covered by the plurality of windows; and b4) inputting the single feature vector to the regression model to determine the number of people within the area covered by the plurality of windows. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An image processing system comprising:
-
a memory and a processor in communication with the processor, the memory and processor configured to receive digital images from one or more image capturing devices directed on an area, and execute instructions to perform an image based method of determining and communicating a busyness metric associated with a number of people within the area, the method comprising; a) acquiring video of the area from the one or more of image capturing devices; b) calculating a representation of the number of people within the area from the acquired one or more images of the area, the representation of the number of people calculated using a regression model trained with a training set of images, the regression model configured to receive an input feature vector associated with an acquired image and output a number of distinct people associated with the input feature vector associated with the acquired image; c) calculating the busyness metric as a function of the representation of the number of people within the area, the busyness metric related to the calculated representation of people within the area during a sequence of acquired images representative of a predetermined time period; and d) communicating the busyness metric to one or more of an electronic device associated with a user, a data storage device and a post processing device, wherein step b) includes; b1) dividing each of the one or more acquired images into a plurality of windows; b2) extracting feature vectors from each of the plurality of windows; b3) concatenating the extracted feature vectors to form a single feature vector representation of the number of people within the area covered by the plurality of windows; and b4) inputting the single feature vector to the regression model to determine the number of people within the area covered by the plurality of windows. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A computer-implemented image based method of determining and communicating a busyness metric associated with a number of people within an area captured by one or more image capturing devices, the method comprising:
-
a) acquiring one or more images of the area from the one or more image capturing devices; b) calculating a representation of the number of people within the area from the acquired one or more images of the area, the representation of the number of people calculated using a regression model trained with a training set of images, the regression model configured to receive an input feature vector associated with an acquired image and output a number of distinct people associated with the input feature vector associated with the acquired image; c) calculating the busyness metric as a function of the representation of the number of people within the area, the busyness metric related to the calculated representation of people within the area during a sequence of acquired images representative of a predetermined time period; and d) communicating the busyness metric to one or more of an electronic device associated with a user, a data storage device and a post processing device, wherein step b) comprises; b1 ) performing background image subtraction on the one or more acquired images to generate one or more respective foreground images associated with the one or more acquired images; b2 ) counting foreground pixels, blobs, and/or edge pixels associated with the one or more foreground images; and b3 ) inputting the counted foreground pixels, blobs, and/or edge pixels, represented as a feature vector, to the regression model to determine the number of people within the area.
-
-
18. An image processing system comprising:
-
a memory and a processor in communication with the processor, the memory and processor configured to receive digital images from one or more image capturing devices directed on an area, and execute instructions to perform an image based method of determining and communicating a busyness metric associated with a number of people within the area, the method comprising; a) acquiring video of the area from the one or more of image capturing devices; b) calculating a representation of the number of people within the area from the acquired one or more images of the area, the representation of the number of people calculated using a regression model trained with a training set of images, the regression model configured to receive an input feature vector associated with an acquired image and output a number of distinct people associated with the input feature vector associated with the acquired image; c) calculating the busyness metric as a function of the representation of the number of people within the area, the busyness metric related to the calculated representation of people within the area during a sequence of acquired images representative of a predetermined time period; and d) communicating the busyness metric to one or more of an electronic device associated with a user, a data storage device and a post processing device, wherein step b) comprises; b1 ) performing background image subtraction on the one or more acquired images to generate one or more respective foreground images associated with the one or more acquired images; b2 ) counting foreground pixels, blobs, and/or edge pixels associated with the one or more foreground images; and b3 ) inputting the counted foreground pixels, blobs, and/or edge pixels, represented as a feature vector, to the regression model to determine the number of people within the area.
-
Specification