Adaptive resolution system and method for providing efficient low bit rate transmission of image data for distributed applications

• US 6,829,391 B2
• Filed: 08/31/2001
• Issued: 12/07/2004
• Est. Priority Date: 09/08/2000
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG)
• Inventors: Ramesh, Visvanathan, Comaniciu, Dorin, Berton, Fabio
• Primary Examiner(s): Do, Anh Hong
• Application Number:
  US09/944,316
• Publication Number:
  US 20020064314A1
• Time in Patent Office: 1,194 Days
• Field of Search: 382/243, 382/232, 348/400.1, 345/427
• US Class Current: 382/243
• CPC Class Codes: G06T 9/001 Model-based coding, e.g. wire frame
• CPC Class Codes: G08B 13/19667 Details realated to data compression, encryption or encoding, e.g. resolution modes for reducing data volume to lower transmission bandwidth or memory requirements
• CPC Class Codes: G08B 13/19691 Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound

Abstract

A client-server system and method that enables efficient, low bit rate transmission of image data over a network from an image server (e.g., active cameras) to a client for, e.g., distributed surveillance. A detection and tracking module detects a human presence within an observation area and provides 2-dimensional face coordinates and its estimated scale to a video transmission module. The captured video is then efficiently encoded in log-polar coordinates using an adaptive log-polar mapping, with a foveation point centered on the face. A fovea region, which covers the target object (face), is uniformly sampled and transmitted at full resolution to the client. The periphery region (background) is sampled according to a log-polar grid. To compensate for bit rate variations due to the changes in the scale of the target object and/or bandwidth of the communication channel, the resolution of the periphery region is modified through an adaptive log-polar mapping process, so as to maintain a virtually constant transmission rate from the server to the client. The high resolution of the data in the fovea region enables efficient recognition and/or identification of the transmitted video.

Claims

1. A method for encoding image data for transmission over a communication channel, comprising the steps of:

receiving image data;

encoding the image data using an adaptive log-polar mapping protocol that generates a log-polar representation of the image data comprising a fovea region and periphery region, wherein the encoding comprises selecting encoding parameters for the log-polar mapping based on either the size of the fovea region, the channel bandwidth, or both, to modify the resolution of the image data within the periphery region; and

transmitting the image data within the fovea region at full resolution and the image data within the periphery region at the modified resolution.

2. The method of claim 1, wherein the step of encoding comprises dynamically modifying the transmission resolution of the image data within the periphery region, if necessary, to compensate for a bit rate variation due to either a change in the size of the fovea region, the bandwidth of the communication channel or both.

3. The method of claim 2, wherein the step of dynamically modifying comprises maintaining the transmission bandwidth of the encoded image data at a substantially constant rate.

4. The method of claim 1, wherein the encoding step utilizes a sampling grid comprising a hexagonal lattice framework.

5. The method of claim 1, wherein the step of selecting encoding parameters comprises accessing predetermined encoding parameters stored in a LUT (look-up table) based on a radius measure of the fovea region.

6. The method of claim 1, comprising the step of detecting and tracking a target image within the image data, wherein the target image is tracked within the fovea region of the image data.

7. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for encoding image data for transmission over a communication channel, the method steps comprising:

receiving image data;

encoding the image data using an adaptive log-polar mapping protocol that generates a log-polar representation of the image data comprising a fovea region and periphery region, wherein the encoding comprises selecting encoding parameters for the log-polar mapping based on either the size of the fovea region, the channel bandwidth, or both, to modify the resolution of the image data within the periphery region; and

transmitting the image data within the fovea region at full resolution and the image data within the periphery region at the modified resolution.

8. The program storage device of claim 7, wherein the instructions for encoding comprise instructions for dynamically modifying the transmission resolution of the image data within the periphery region, if necessary, to compensate for a bit rate variation due to either a change in the size of the fovea region, the bandwidth of the communication channel or both.

9. The program storage device of claim 8, wherein the instructions for dynamically modifying comprise instructions for maintaining the transmission bandwidth of the encoded image data at a substantially constant rate.

10. The program storage device of claim 7, wherein the encoding utilizes a sampling grid comprising a hexagonal lattice framework.

11. The program storage device of claim 7, wherein the instructions for selecting encoding parameters comprise instructions for accessing predetermined encoding parameters stored in a LUT (look-up table) based on a radius measure of the fovea region.

12. The program storage device of claim 7, comprising instructions for detecting and tracking a target image within the image data, wherein the target image is tracked within the fovea region of the image data.

13. A method for providing distributed surveillance over a communications network, comprising the steps of:

detecting the presence of an individual in a predetermined field of view;

tracking the face of the individual within the field of view;

generating image data, the image data comprising two-dimensional coordinates and estimated scale of the individual'"'"'s face being tracked;

filtering and sampling the image data using a log-polar mapping to generate encoded image data comprising a fovea region and periphery region, the fovea region being centered on the face of the individual; and

transmitting the encoded image data over a communication channel at a predetermined transmission bit rate, the fovea region being transmitted at full resolution;

wherein the log-polar mapping of the periphery region is adapted based on scale and locations changes of the fovea region to substantially maintain the predetermined transmission bit rate.

14. The method of claim 13, wherein the method steps are executed by an image server.

15. The method of claim 14, wherein the step of transmitting comprises transmitting the encoded image data to a client at a central location.

16. The method of claim 15, further comprising the steps of:

reconstructing an image from the encoded image data by applying an inverse log-polar mapping; and

performing biometric identification using the reconstructed image to identify the individual.

17. A client/server system, comprising:

an image sever, operatively interfaced to a camera, the image server comprising

an encoder for filtering and sampling image data received from the camera using a log-polar mapping to generate encoded image data comprising a fovea region and periphery region, the fovea region being centered on a target of interest in the image; and

a communication stack for transmitting the encoded image data over a communication channel at a predetermined bit rate, wherein the fovea region is transmitted at full resolution, and wherein the log-polar mapping of the periphery region is adapted based on scale and locations changes of the fovea region to substantially maintain the predetermined transmission bit rate; and

a client for receiving the encoded image data transmitted from the image server and decoding the encoded image data for identification of the target of interest.

18. The system of claim 17, wherein the system is employed for distributed surveillance over a network.

19. The system of claim 17, wherein the system is employed for videoconferencing over a network.

20. The system of claim 17, wherein the system is employed for industrial inspection.