Methods, functional data, and systems for image feature translation

• US 7,551,783 B2
• Filed: 05/30/2007
• Issued: 06/23/2009
• Est. Priority Date: 01/23/2002
• Status: Expired due to Fees

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Johnson, Michael, Henderson, Thomas A., Hamza, Rida M., Kwong, Au W.
• Primary Examiner(s): Strege; John B
• Application Number:
  US11/807,742
• Publication Number:
  US 20070237397A1
• Time in Patent Office: 755 Days
• Field of Search: 382/209, 382/217, 382/218, 348/160
• US Class Current: 382/209
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 2201/02 Recognising information on displays, dials, clocks

Abstract

Methods, functional data, and systems are provided for image feature translation. An image is decomposed into sub images, each sub image having its features identified by feature attributes. The feature attributes are used to identify a particular feature within each sub image. The orientation of the particular feature within the sub image is then mapped or calculated to a value. One or more of the mapped or calculated values are translated into a reading associated with an instrument. The reading is then optionally recorded or transmitted.

Claims

1. A method of processing an image, comprising:

using a computer to carry out the method of identifying one or more sub images which are associated with an image of one or more instrument panels of one or more devices;

identifying values represented by one or more located features within each sub image by using one or more templates, wherein each template includes one or more rules to assist in identifying the values and each template associated with a feature vector and the feature vector representing a shape of a particular sub image and coverage area of the particular sub image and angular position of the particular sub image within the image, and wherein each feature vector is represented as a collection of three pixel coordinates; and

using the values to generate one or more readings for one or more of the instrument panels of one or more of the devices, wherein the values are used to determine locations of the features within each of the sub images, each location for each feature is then calculated using an initial calibration coordinate points and the angular position to resolve the one or more readings.

2. The method of claim 1, wherein identifying values further includes representing the three pixel coordinates as a first pixel coordinate for a center of a particular sub image to which it relates, a second pixel coordinate for an edge coordinate along an x-axis extending eastward or westward from the center, and a third pixel coordinate for a different edge coordinate along a y-axis extending northward or southward from the center.

3. The method of claim 1 further comprising, deriving the shapes of each particular sub image from the corresponding three pixel coordinates associated with each feature vector.

4. The method of claim 1, wherein identifying the one or more sub images further includes capturing the one or more sub images as pictures taken from the instrument panels that are included in one or more of the following:

an aircraft, a marine vehicle, and a land vehicle.

5. The method of claim 1, wherein using further includes generating the one or more readings by performing calculations on the values in response to each sub image'"'"'s feature vector.

6. The method of claim 1, wherein identifying the one or more sub images further includes using a camera to periodically take digital pictures of the instrument panel to capture the one or more sub images.

7. The method of claim 1 further comprising, reporting the one or more readings to control the one or more devices.

8. The method of claim 1 further comprising, storing the one or more readings in a data store that is subsequently mined to produce historical trends.

9. A machine-implemented system for capturing and processing images, comprising:

a camera to capture an image within a machine-readable medium;

a template embodied in a machine-readable medium that is uniquely associated with a sub image of the image;

a feature vector embodied in a machine-readable medium for defining a feature within the sub image, wherein the feature vector identifies three coordinate points within the sub image for the feature of the sub image and the sub image representing a graphical symbol, and a shape for the graphical symbol also reflected in the feature vector along with its coverage area attributes within the image, and wherein a first pixel coordinate defines a center of the sub image, a second pixel coordinate defines an eastward or westward extension of the feature from the center of the sub image, and a third pixel coordinate defines a northward or southward extension of the feature from the center of the sub image; and

a processing set of executable instructions to process on a machine and to extract a location of the feature within the sub image by using the template and the feature vector, and wherein the template includes one or more rules for the feature, and wherein the location is used along with initial calibration coordinates and a calculated angular orientation to generate a reading for the feature.

10. The system of claim 9 further comprising, a mapping set of executable instructions to process on the machine and to map the location to a value.

11. The system of claim 10 wherein the value is associated with the reading on an instrument panel.

12. The system of claim 11 further comprising, a recording set of executable instructions to process on the machine and to record the value.

13. The system of claim 9 further comprising, a camera controlling set of executable instructions to process on the machine and to capture one or more additional images at configurable periods.

14. The system of claim 9 further comprising, one or more additional cameras capturing one or more additional images.

15. The system of claim 9 further comprising, an image enhancing set of executable instructions to process on the machine and to enhance a quality associated with the image before the image is processed by the processing set of executable instructions on the machine.

16. The system of claim 9 further comprising, a calibration set of executable instructions to process on the machine and to calibrate the captured image.

17. A machine-implemented system for capturing and processing images, comprising:

an image capturing device that processes on a machine and that records a picture of an image in a machine-readable format accessible to the machine; and

instructions that process on the machine that uses the image and a feature vector associated with the image to produce a reading for an instrument panel associated with the image, wherein the feature vector defines a feature of the reading via three pixel coordinates, one pixel coordinate defines a center for the instrument panel, a second pixel coordinate defines an eastward or westward extension of the feature, and a third pixel coordinate defines a northward or southward extension of the feature, and wherein the feature via the feature vector has its location resolved within the image via a template and after the location is known, initial calibration coordinate points and a calculated angular orientation are used to determine the reading.

18. The system of claim 17, wherein the instructions periodically interact with the image capturing device at configurable intervals to capture new images of the instrument panel to produce new readings.

19. The system of claim 17, wherein the instructions automatically report the reading to other instructions for subsequent automated processing in response to the reading.

20. The system of claim 17, wherein the instructions use the template in connection with the feature vector to derive the location of the feature within the image.