VISION-BASED MULTI-CAMERA FACTORY MONITORING WITH DYNAMIC INTEGRITY SCORING

摘要

A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and determine an integrity score for each respective image frame. The processor may then isolate a foreground section from two or more of the views, determine a principle body axis for each respective foreground section, and determine a location point according to a weighted least squares function amongst the various principle body axes.

主权项

1. A method of identifying a location of an object within a workspace, the method comprising:
obtaining a plurality of 2D images of the workspace, each respective 2D image being acquired from a camera disposed at a different location within the workspace; determining an integrity score for each respective 2D image, the integrity score relating to at least one of an absolute pixel difference, a global or a local histogram difference, and an absolute edge difference between the respective 2D image, and a prior 2D image from the same camera; identifying a foreground portion within at least three of the plurality of 2D images; determining a principle body axis for each identified foreground portion, the principle body axis being a mean centerline of the respective foreground portion and aligned with a vanishing point of the respective image; mapping the determined principle body axis from each respective 2D image into a common ground plane that is coincident with a floor of the workspace; determining a location point within the ground plane, wherein the location point minimizes a least squares function among each mapped principle body axis, and wherein the least squares function is weighted according to the integrity score for each of the respective 2D images; and wherein the location point represents a point location of the object within the workspace.