System and method for ranking and extracting salient contours for target recognition

• US 5,210,799 A
• Filed: 03/28/1991
• Issued: 05/11/1993
• Est. Priority Date: 03/28/1991
• Status: Expired due to Term

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Rao, Kashi
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Fox, David
• Application Number:
  US07/676,650
• Time in Patent Office: 775 Days
• Field of Search: 382/22, 382/16, 382/19, 358/96, 358/125
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30212 Military
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/181 involving edge growing; involving edge linking
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]

Abstract

A system and method for obtaining salient contours from two-dimensional images acquired by a sensor is disclosed which process the two-dimensional images with an edge detector to produce edgels from each of the images, link the edgels into lists known as contours, compute a saliency value for each of the contours, rank the contours in decreasing order of saliency, and select certain ones of the ranked contours based on the requirements of a particular vision application.

Claims

1. A method for obtaining salient contours from two-dimensional images acquired by a sensor, comprising the steps of:

processing said two-dimensional images with an edge detector to produce edgels from each of said images;

linking said edgels into lists known as contours;

computing a saliency value for each of said contours;

ranking said contours in decreasing order of saliency; and

selecting predetermined ones from said ranked contours.

2. The method of claim 1, wherein said edge detector is a Canny edge detector.

3. The method of claim 1, after said step of selecting, further comprising the step of discarding any ranked contours not selected.

4. The method of claim 1, wherein said step of computing a saliency value for each of said contours further comprises the steps of:

ascertaining each of a plurality of saliency measures;

applying a predetermined weight to each saliency measure; and

determining a saliency value based on said weighted saliency measures.

5. The method of claim 4, wherein said saliency value, S, is determined as follows:

##EQU5## where ω

₁ is the weight for the length saliency measure, ω

_s is the weight for the smoothness saliency measure, and ω

_c is the weight for the contrast saliency measure.

6. The method of claim 4, wherein said step of ascertaining a plurality of saliency measures is performed in parallel.

7. The method of claim 4, wherein at least one of said plurality of saliency measures includes a smoothness saliency measure, S_s, calculated as:

##EQU6## where Δ

K is the average change of curvature of the contour, Δ

K_min is the smallest average change of curvature for all contours, and Δ

K_max is the largest average change of curvature for all contours.

8. The method of claim 7, wherein said average change of curvature, Δ

K, is calculated with the steps of;

computing curvature at each edgel within said contour;

determining any change of curvature; and

computing an average of said any change of curvature.

9. The method of claim 8, wherein said step of computing curvature employs a B-spline fitting.

10. The method of claim 8, wherein said step of determining any change of curvature is accomplished by convolving said computed curvature for each edgel using a difference operator.

11. The method of claim 4, wherein at least one of said plurality of saliency measures includes a contrast saliency measure, S_c, calculated as:

##EQU7## where C is the average contrast of the contour, C_min is the smallest average contrast for all contours, and C_max is the largest average contrast for all contours.

12. The method of claim 4, wherein at least one of said plurality of saliency measures includes a length saliency measure, S₁, calculated as:

##EQU8## where L, the length of the contour, is defined as the number of edgels in that contour, L_min is the length of the shortest contour, and L_max is the length of the longest contour.

13. A system for object recognition, comprising:

a sensor for generating an image of a scene;

an edge detector connected to said sensor to detect edgels within said image;

a salient contour extractor connected to receive and process said detected edgels into contours, said extractor including a processing unit for determining a saliency value for each of said contours and ranking said contours in decreasing order of saliency; and

an object matching system connected to receive preselected ones of said process contours and match them to known contours of predetermined objects.

14. The system of claim 13. wherein said salient contour extractor further comprises a linker which links said edgels into lists known as contours.

15. The system of claim 13, wherein said salient contour extractor comprises a plurality of contour extractors operating in parallel.

16. The system of claim 13, wherein said sensor is a FLIR.

17. The system of claim 13, wherein said sensor is a television camera.

18. The system of claim 13, wherein said edge detector is a Canny edge detector.

19. The system of claim 13, wherein said processing unit further comprises a computing unit for establishing a saliency value for each of said contours and determining a plurality of saliency measures for each saliency value.

20. The system of claim 19, wherein said plurality of saliency measures are preselectively weighted.