Mechanical pan, tilt and zoom in a webcam

• US 7,917,935 B2
• Filed: 10/01/2004
• Issued: 03/29/2011
• Est. Priority Date: 10/01/2004
• Status: Active Grant

• Current Assignee: Logitech Europe S A (Logitech International SA)
• Original Assignee: Logitech Europe S A (Logitech International SA)
• Inventors: Krishnan, Venkatesh Tumati, McAlpine, Paul, Lechnenne, Olivier, Chang, Yuh-Lin, Miauton, Patrick, Zimmermann, Remy
• Primary Examiner(s): DIEP, NHON THANH
• Application Number:
  US10/956,737
• Publication Number:
  US 20060075448A1
• Time in Patent Office: 2,370 Days
• Field of Search: None
• US Class Current: 725/105
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display

Abstract

A system and method for mechanically panning, tilting, and/or zooming a webcam to track a user'"'"'s face. In one embodiment, such movement is controlled by kernel software in a host to which the webcam sends video data. In this way, a driver in the host kernel handles the face tracking, transparent to the application programs that would access the video. In an alternate embodiment, such movement is controlled by firmware in the webcam itself. The video and control signals are sent over the same standard cable, such as a USB bus. In one embodiment, the video is supplied to an instant messaging application. The use of a standard bus (e.g., USB) and the offloading of the face tracking to the webcam and driver allows easy use by the instant messaging application.

Claims

1. A system for mechanically moving an optical module in a webcam by tracking a user'"'"'s face, the system comprising:

an optical module in said webcam for capturing image data;

a computer coupled via a bus to said webcam, with video data sent to the computer, and control signals sent from the computer to the webcam being both sent over the bus;

computer readable media in said computer having computer readable instructions providing a driver, said driver including

a machine vision module for;

identifying the location of the user'"'"'s face based on the captured image data,

generating a boundary region within the field of view of the optical module, wherein the boundary region represents the location of a user'"'"'s face, and wherein the boundary region is generated based on the location of the user'"'"'s face identified in the identifying step,

identifying a field of view of the optical module, and

identifying a predetermined-threshold field of view smaller than the field of view of the optical module and larger than the boundary region; and

a movement controlling module for;

deciding to move the optical module to place the center of the boundary region inside the predetermined-threshold field of view if a center of the boundary region is outside of the predetermined-threshold field of view, and

deciding not to move the optical module if the center of the boundary region is inside the predetermined-threshold field of view;

a mechanical module in said webcam, communicatively coupled over said bus to the movement controlling module, for moving the optical module based on the decision of the movement controlling module; and

computer readable media in said computer having computer readable instructions providing an application using said video data from said webcam, said application being independent of said driver.

2. The system of claim 1, wherein the image data from the webcam is provided to an instant messaging application.

3. The system of claim 1, wherein the machine vision module comprises:

a face detector for detecting a user'"'"'s face based on pre-specified parameters;

a flesh tracker for tracking movement of a user'"'"'s flesh based on flesh tone; and

a motion detector coupled to the face detector and the flesh tracker for detecting motion of a user'"'"'s face.

4. The system of claim 3, wherein the machine vision module further comprises:

a flesh sampler coupled to the face detector, for extracting a sample of the user'"'"'s flesh, and for providing this sample to the flesh tracker.

5. The system of claim 1 wherein said webcam is moved based on positive localization of facial features.

6. A system for mechanically moving an optical module in a webcam by tracking a user'"'"'s face, the system comprising:

a webcam comprising;

an optical module for capturing video data; and

a mechanical module coupled to the optical module, for moving the optical module;

a standard bus connected to the webcam; and

a computer coupled to the standard bus, the computer having a driver module comprising;

a machine vision module coupled to the optical module, for;

identifying the location of the user'"'"'s face based on the captured video data;

generating a boundary region within the field of view of the optical module, wherein the boundary region represents the location of a user'"'"'s face, and wherein the boundary region is generated based on the location of the user'"'"'s face identified in the identifying step,

identifying a field of view of the optical module, and

identifying a predetermined-threshold field of view smaller than the field of view of the optical module and larger than the boundary region; and

a movement controlling module coupled to the machine vision module for;

deciding to move the optical module to place the center of the boundary region inside the predetermined-threshold field of view if a center of the boundary region is outside of the predetermined-threshold field of view;

deciding not to move the optical module if the center of the boundary region is inside the predetermined-threshold field of view, and providing the decision to the mechanical module,

the computer also having an application module for a user to interact with the webcam via the computer, wherein the diver module is independent of the application module.