A method for determining population density of a defined space from multi-camera sourced imagery includes loading a set of images acquired from multiple different cameras positioned about the 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. The method additionally includes 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, contemporaneous imagery from the different cameras is acquired in real time and submitted to the neural network, in response to which, a predicted population distribution for the defined space is received from the neural network. Finally, a message is displayed that includes information correlating at least a portion of the population distribution with a specific location of the defined space.