Determination of interactions with predefined volumes of space based on automated analysis of volumetric video
View Patent ↗One or more image and/or depth cameras capture images and/or depths of a physical environment over time. A computer system processes the images to create a static 3-dimensional (3D) model representing stationary structure and a dynamic 3D model representing moving or moveable objects within the environment. The system visually overlays the dynamic 3D model over the static 3D model in a user interface. Through the user interface, a user can create virtual spatial interaction sensors, each of which is defined by a volume of space within the environment. A virtual spatial interaction sensor can be triggered, based on analysis of the dynamic 3D model by the computer system, whenever a moveable object within the environment intersects the defined volume of the sensor. Times and durations of intersections can be logged and used for process refinement.
1. A method performed by one or more computers, each computer having at least one processor and a memory, the method comprising:
receiving image data comprising multiple images of a physical industrial environment captured over one or more periods of time by one or more cameras;
processing the image data to create a static 3D model representing stationary structure in the environment;
processing the image data to create a dynamic 3D model representing one or more moveable objects in the environment over time;
providing a user interface through which a user can view and control a visual perspective of a replay of the dynamic 3D model over time visually superimposed on the static 3D model;
receiving from the user through the user interface a specification of one or more virtual spatial interaction sensors, wherein each virtual spatial interaction sensor is defined by a point or volume of space within the environment;
displaying to the user in the user interface a visual depiction of each point or volume of space within the environment defining the one or more virtual spatial interaction sensors superimposed on a visual depiction of the static 3D model in a visual perspective; and
analyzing a portion of the dynamic 3D model to identify intersections between the one or more moveable objects and the one or more virtual spatial interaction sensors over time.
2. The method of claim 1 , wherein the static 3D model comprises a colored point cloud or a textured polygon mesh.
3. The method of claim 1 , wherein each moveable object is represented in the dynamic 3D model by one or more of moveable points, lines, polygons, volumes, point clouds and polygon meshes in space.
4. The method of claim 1 , wherein the visual perspective of the replay of the dynamic 3D model over time visually superimposed on the static 3D model comprises one or more of moveable points, lines, polygons, volumes, point clouds and polygon meshes representing the moveable objects superimposed over a point cloud or polygon mesh representation of the stationary structure.
5. The method of claim 1 , wherein at least one virtual spatial interaction sensor is defined by a shape and a pose.
6. The method of claim 5 , wherein the shape is a geometric shape, a polygon mesh or a point cloud.
7. The method of claim 5 , wherein the pose is specified relative to an aspect of the environment.
8. The method of claim 7 , wherein the aspect of the environment is a stationary coordinate system fixed relative to the environment.
9. The method of claim 7 , wherein the aspect of the environment is one of the one or more moveable objects.
10. The method of claim 1 , further comprising:
storing identifications of the intersections in a log file.
11. The method of claim 1 , further comprising:
visually representing the identified intersections on a time-based graph in the user interface.
12. The method of claim 1 , further comprising:
performing an analysis of the identified intersections to identify operational inefficiencies in the industrial environment.
13. The method of claim 1 , further comprising:
triggering an action in the industrial environment based on an identified intersection.
14. The method of claim 13 , wherein the action comprises starting a process or stopping a process.
15. The method of claim 1 , wherein the one or more moveable objects comprise one or more of: a human, an industrial machine, a robot, a workpiece, a tool, and a vehicle.
16. The method of claim 1 , wherein each of the one or more cameras is a depth camera configured to capture color data registered with depth data.
17. The method of claim 1 , wherein one of the one or more cameras comprises a 3D LIDAR sensor.
18. The method of claim 1 , wherein the one or more cameras number at least two, and wherein the user can freely navigate a six dimensional pose of the visual perspective about the static and dynamic 3D models through the user interface.
19. A system comprising the one or more computers of the method of claim 1 , wherein the one or more computers perform the method of claim 1 .
20. One or more non-transitory computer-readable media encoded with computer code that is executed by the one or more computers of the method of claim 1 to cause the one or more computers to perform the method of claim 1 .