IMAGE ACQUISITION AND EXPLOITATION CAMERA SYSTEM AND METHODS THEREFORE

• US 20110273553A1
• Filed: 07/19/2011
• Published: 11/10/2011
• Est. Priority Date: 04/11/2005
• Status: Abandoned Application

• Current Assignee: Panayotis B. Spatharis
• Original Assignee: Panayotis B. Spatharis
• Inventors: SPATHARIS, Panayotis B.
• Application Number:
  US13/185,727
• Publication Number:
  US 20110273553A1
• Time in Patent Office: Days
• US Class Current: 348/77
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content

Abstract

A system for extracting, processing, and sending metadata associated with audio data and/or video data is described. In one embodiment, a system includes a sensor configured to acquire image data. A first electronic board with a processor is configured to control the sensor. A second electronic board that is configured to enrich the image data is operatively and removably coupled to the first electronic board.

Claims

1. A modular system for facial recognition, comprising:

a container comprising;

a visual sensor configured to acquire image data including a face; and

a first electronic board including a first processor to control the sensor;

a portable housing, operatively and removably connected to the container by a cable or wirelessly, comprising a storage subsystem including a database of metadata relating to faces;

a face recognition electronic board including a second processor used to extract and associate metadata in substantially real-time, wherein information about faces is extracted from the acquired image data and associated with the acquired image data as metadata about faces, the face recognition electronic board is in communication with the first electronic board and the storage subsystem; and

a display device directly connected to at least one of the container and the portable housing, the display device receiving data and displaying data in substantially real-time from at least one of the first electronic board and the face recognition electronic board, wherein the acquired image and results of the metadata extraction and association including face recognition are simultaneously shown in substantially real-time on the display device;

wherein the container, the portable housing and the display device are modular components with connectors.

2. The system of claim 1, further comprising:

a controller coupled to the face recognition electronic board, the controller receives an input, the controller controls the enriching of the image data by the second processor based on the input.

3. The system of claim 1, wherein the face recognition electronic board receives at least one of a collateral data or an audio signal from a microphone.

4. The system of claim 1, wherein the second processor performs in substantially real-time face recognition.

5. The system of claim 1, wherein the second processor produces a high-resolution indexed data stream and a low-resolution proxy data stream.

6. The system of claim 1, wherein the second processor generates content at multiple data rates and multiple resolutions.

7. The system of claim 1, wherein the second processor performs in substantially real-time visual properties recognition.

8. The system of claim 1, wherein the second processor performs in substantially real-time voice recognition and speaker identification.

9. The system of claim 1, wherein the second processor performs in substantially real-time words and optical character recognition.

10. The system of claim 1 wherein the second processor performs in substantially real-time speech to text conversion.

11. The system of claim 1, further comprising a second camera, wherein the second camera is attached to the housing, wherein image data from the first and second camera are processed substantially simultaneously by the second processor.

12. The system of claim 1, further comprising an audio sensor to acquire audio data, wherein the first processor receives the audio data from the audio sensor, the second processor enriches the audio data in substantially real-time.

13. A modular system for facial recognition, comprising:

a capture subsystem, housed in a container, having a sensor configured to capture visual content, the captured visual content including a face;

a portable housing, operatively and removably connected to the container by a cable or wirelessly, including a storage device wherein a database of metadata relating to face recognition is stored;

a central processing unit (CPU) subsystem wherein metadata is both extracted from the captured visual content and associated with the captured visual content in substantially real-time, the CPU subsystem communicating with the housing, and the CPU subsystem processing the associated metadata relating to face recognition and visual content using a digital asset management application; and

a display device, connected to the housing, the display device receiving and displaying metadata in substantially real-time, wherein the results of the metadata extraction and association include face recognition and are displayed in substantially real-time;

wherein the container, the portable housing and the display device are modular components with connectors.

14. The system of claim 13, further comprising:

a CPU controller which receives an input, the CPU controller controls a function associated with the CPU subsystem based on the input.

15. The system of claim 13, further comprising:

a controller which receives an input, the controller controls a function associated with the capture subsystem based on the input.

16. The system of claim 13, further comprising a second camera, wherein the second camera is attached to the housing, wherein image data from the first and second camera are processed substantially simultaneously by the CPU subsystem.

17. The system of claim 13, wherein the CPU subsystem receives at least one of a collateral data or an audio signal from a microphone.

18. The system of claim 13, wherein the CPU subsystem generates content at multiple data rates and multiple resolutions.

19. The system of claim 13, further comprising an audio sensor to acquire audio data, wherein the CPU subsystem receives the audio data from the audio sensor and enriches the audio data in substantially real-time.

20. A method of changing a camera in a modular facial recognition system comprising:

connecting a first camera system module which captures images of faces in a first format to a CPU system and a storage device using a peripheral device connection, wherein the CPU system extracts and associates metadata in substantially real-time and wherein the storage device is portable and stores metadata for facial recognition;

coupling a display device to the CPU system and storage device wherein the display device displays in substantially real-time face recognition metadata simultaneously with captured images of faces;

disconnecting the first camera system from the peripheral device connection;

connecting a second camera system which captures images of faces in a second format to the CPU system and storage device; and

enriching the audio data in substantially real-time,

wherein when the first and second camera are both connected to the system the captured images of faces from the first camera and the captured images of faces in the second format from the second camera are processed substantially simultaneously by the CPU system.

21. The method of claim 20, further comprising:

connecting a third camera to the CPU system and storage device wherein image data from the second and third camera are processed substantially simultaneously by the CPU system.

22. The method of claim 20, wherein the peripheral device connection is one of a universal serial bus, a fire wire, a category-5 cable, or wirelessly.

23. The method of claim 20, further comprising acquiring audio data using an audio sensor.