Method and system for video object range sensing

• US 20020071036A1
• Filed: 12/13/2000
• Published: 06/13/2002
• Est. Priority Date: 12/13/2000
• Status: Active Grant

• Current Assignee: International Business Machines Incorporated (International Business Machines Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Liu, Lurng-Kuo, Gonzales, Cesar Augusto
• Granted Patent: US 6,933,979 B2
• Time in Patent Office: Days
• US Class Current: 348/207.99
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0421 by interrupting or reflecting a light beam, e.g. optical touch-screen

Abstract

The invention relates to a method for sensing the range of objects captured by an image or video camera using active illumination from a computer display. This method can be used to aid in vision based segmentation of objects.

In the preferred embodiment of this invention, we compute the difference between two consecutive digital images of a scene captured using a single camera located next to a display, and using the display'"'"'s brightness as an active source of lighting. For example, the first image could be captured with the display set to a white background, whereas the second image could have the display set to a black background. The display'"'"'s light reflected back to the camera and, consequently, the two consecutive images'"'"' difference, will depend on the intensity of the display illumination, the ambient room light, the reflectivity of objects in the scene, and the distance of these objects from the display and the camera. Assuming that the reflectivity of objects in the scene is approximately constant, the objects which are closer to the display and the camera will reflect larger light differences between the two consecutive images. After thresholding, this difference can be used to segment candidates for the object in the scene closest to the camera. Additional processing is required to eliminate false candidates resulting from differences in object reflectivity or from the motion of objects between the two images.

Claims

1. A system for video object range sensing comprising

a computer having a display;

and

a video camera for receiving or capturing images of objects in an environment, the video camera being connected to the computer wherein the computer display'"'"'s brightness is operable as an active source of lighting.

2. The system according to claim 1, further including means for flashing the display at different brightness levels, means for capturing images synchronized and corresponding to these different levels, and computer means for processing the difference between these images to extract range information.

3. The system in claim 2, including means for displaying color information.

4. A method for extracting range information from the digital data obtained from capturing images using a display and a still or moving image capture device, wherein the display'"'"'s brightness is used as an active source of lighting.

5. The method according to claim 4, wherein the difference between two images captured at two different levels of display brightness is used to select candidates for the objects closest to the camera.

6. The method according to claims 5, further including selecting objects from among the candidates thereby compensating for differences in reflectivity and motion.

7. The method according to claim 5, further including performing image integration to remove camera noise.

8. The method according to claim 5, further including performing morphological operations to filter out noise from the segmentation image.

9. A memory medium for a computer comprising:

means for controlling the computer operation to perform the following steps;

(a) flashing the computer display at different brightness leves;

(b) capturing images of objects in the environment with a video camera at each of the different brightness levels;

(c) selecting objects from among the candidates, and

(d) performing image integration to remove camera noise