Population density determination from multi-camera sourced imagery

1. A method for redistributing a population according to a determined population density of a defined space from multi-camera sourced imagery comprising:

loading into memory of a computer data processing system, a set of images each acquired from a different one of a set of multiple different cameras positioned about the defined space;

identifying the defined space and retrieving a rule for acting upon a determined population density in the identified defined space;

locating different individuals within each of the images and computing a population distribution of the located different individuals in respect to different locations of the defined space;

submitting each of the images to a convolutional neural network as training data, each in association with a correspondingly computed population distribution;

subsequent to the submission of the images to the neural network as training data, acquiring in real-time, contemporaneous imagery from the different cameras, submitting each of the contemporaneous imagery to the neural network, and receiving in response from the neural network, a predicted population distribution for the defined space; and,

applying the retrieved rule to determine an action for the defined space and transmitting a message to a mobile computing device with the action.

2. The method of claim 1 , wherein the message includes a heat map of the defined space in respect to the population distribution received from the neural network.

3. The method of claim 1 , wherein the correlating includes an indication of a threshold density of individuals at the specific location.

4. The method of claim 3 , wherein the threshold density is a density that falls below threshold maximum number of individuals at the specific location.

5. The method of claim 3 , wherein the threshold density is a density that surpasses threshold minimum number of individuals at the specific location.

6. The method of claim 1 , further comprising:

repeatedly acquiring in real-time, newer contemporaneous imagery from the different cameras, submitting each of the newer contemporaneous imagery to the neural network, and receiving in response to each submission from the neural network, a predicted population distribution for the defined space;

computing a rate of change of the predicted population distribution in connection with the specific location based upon the receipt of a multiplicity of predicted population distributions for the defined space; and,

displaying an alert in the display responsive to the rate of change exceeding a threshold value.

7. An image acquisition computer data processing system configured to redistributing a population according to a determined population density of a defined space from multi-camera sourced imagery, the system comprising:

a host computing system comprising one or more computers, each with at least one processor and memory;

a multiplicity of different cameras positioned about a defined space and communicatively coupled to the host computing system;

a data store of previously acquired imagery of the defined space by the different cameras; and,

a population density determination module comprising program instructions enabled during execution in the memory of the host computing system to perform:

identifying the defined space and retrieving a rule for acting upon a determined population density in the identified defined space;

locating different individuals within each of the images and computing a population distribution of the located different individuals in respect to different locations of the defined space;

submitting each of the images to a convolutional neural network as training data, each in association with a correspondingly computed population distribution;

subsequent to the submission of the images to the neural network as training data, acquiring in real-time, contemporaneous imagery from the different cameras, submitting each of the contemporaneous imagery to the neural network, and receiving in response from the neural network, a predicted population distribution for the defined space; and,

applying the retrieved rule to determine an action for the defined space and transmitting a message to a mobile computing device with the action.

8. The system of claim 7 , wherein the message includes a heat map of the defined space in respect to the population distribution received from the neural network.

9. The system of claim 7 , wherein the correlating includes an indication of a threshold density of individuals at the specific location.

10. The system of claim 9 , wherein the threshold density is a density that falls below threshold maximum number of individuals at the specific location.

11. The system of claim 9 , wherein the threshold density is a density that surpasses threshold minimum number of individuals at the specific location.

12. The system of claim 7 , wherein the program instructions are further enabled to perform:

repeatedly acquiring in real-time, newer contemporaneous imagery from the different cameras, submitting each of the newer contemporaneous imagery to the neural network, and receiving in response to each submission from the neural network, a predicted population distribution for the defined space;

computing a rate of change of the predicted population distribution in connection with the specific location based upon the receipt of a multiplicity of predicted population distributions for the defined space; and,

displaying an alert in the display responsive to the rate of change exceeding a threshold value.

13. A computer program product for redistributing a population according to a determined population density of a defined space from multi-camera sourced imagery, the computer program product including a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to perform a method including:

identifying the defined space and retrieving a rule for acting upon a determined population density in the identified defined space;

locating different individuals within each of the images and computing a population distribution of the located different individuals in respect to different locations of the defined space;

submitting each of the images to a convolutional neural network as training data, each in association with a correspondingly computed population distribution;

subsequent to the submission of the images to the neural network as training data, acquiring in real-time, contemporaneous imagery from the different cameras, submitting each of the contemporaneous imagery to the neural network, and receiving in response from the neural network, a predicted population distribution for the defined space; and,

applying the retrieved rule to determine an action for the defined space and transmitting a message to a mobile computing device with the action.

14. The computer program product of claim 13 , wherein the message includes a heat map of the defined space in respect to the population distribution received from the neural network.

15. The computer program product of claim 13 , wherein the correlating includes an indication of a threshold density of individuals at the specific location.

16. The computer program product of claim 15 , wherein the threshold density is a density that falls below threshold maximum number of individuals at the specific location.

17. The computer program product of claim 15 , wherein the threshold density is a density that surpasses threshold minimum number of individuals at the specific location.

18. The computer program product of claim 13 , wherein the method further comprises:

repeatedly acquiring in real-time, newer contemporaneous imagery from the different cameras, submitting each of the newer contemporaneous imagery to the neural network, and receiving in response to each submission from the neural network, a predicted population distribution for the defined space;

computing a rate of change of the predicted population distribution in connection with the specific location based upon the receipt of a multiplicity of predicted population distributions for the defined space; and,

displaying an alert in the display responsive to the rate of change exceeding a threshold value.