Object detector, object detecting method and robot

• US 7,532,743 B2
• Filed: 08/12/2004
• Issued: 05/12/2009
• Est. Priority Date: 08/29/2003
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Morisada, Hidehiko
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US10/916,392
• Publication Number:
  US 20050069208A1
• Time in Patent Office: 1,734 Days
• Field of Search: 382/103, 382/106, 382116-118, 382/141, 382/153, 382/155, 382/164, 382/168, 382/172, 382190-195, 382/203, 382/209, 382/232, 382/260, 382/274, 382/276, 382291-295, 382/305, 382/318, 382/165, 250/221, 318/568.12
• US Class Current: 382/103
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

An object detector, an object detecting method and a robot can reduce diction errors of detecting wrong objects without increasing the volume of the computational operation to be performed to detect the right object. A face detector 101 comprises a face detecting section 110 that operates like a conventional face detecting section and is adapted to roughly select face candidates from an input image by template matching and detect face candidates by means of a support vector machine for face recognition, a non-face judging section 120 that detects non-face candidates that are judged to be non-faces and removes them from the face candidates selected by the face detecting section 110 and a skin tracker section 114 for tracking a face region after the non-face judgment. When the assumed distance between the face detector and the face as computed from the input image and the measured distance as measured by a distance sensor show a large difference, when the color variance of the face candidate is small, when the occupancy ratio of the skin color region is large and when the change in the size of the face region is large after the elapse of a predetermined time, the non-face judging section 120 judges such face candidates as non-faces and removes them from the face candidates.

Claims

1. An object detector for detecting an object of detection out of an input image, the detector comprising:

an object detecting unit adapted to detect object candidates judged to be the object;

a non-object detecting unit adapted to detect non-object candidates judged to be non-objects and output the object candidates less the non-object candidates;

a distance measuring unit adapted to measure a distance between the object detector and the object of detection;

the non-object detecting unit is further adapted to compute an assumed distance between the object detector and the object of detection on the basis of a size of an object candidate in the detected object candidates relative to the input image and judge the object candidate to be a non-object candidate when a difference between the assumed distance and the distance measured by the distance measuring unit is greater than a predetermined threshold value; and

the non-object detecting unit is further adapted to compute, using a processor, a variance of the object candidate in a color space and, if the variance is less than a predetermined variance threshold value, judge the object candidate to be the non-object candidate.

2. The object detector according to claim 1, wherein:

the object of detection includes a face region;

the object detecting unit is adapted to detect face candidates judged to be the face region satisfying certain face conditions; and

the non-object detecting unit includes a non-face detecting unit adapted to detect non-face candidates judged to be non-faces satisfying certain non-face conditions and output the face candidates less the non-face candidates.

3. The object detector according to claim 2, wherein the non-face detecting unit is adapted to judge the face candidate as a non-face candidate when a difference between a size of the face candidate in the input image and a size of the face candidate in an input image of a predetermined time ago is greater than a predetermined threshold value.

4. The object detector according to claim 2, wherein the non-face detecting unit is adapted to compute an occupancy ratio of a skin color region relative to the face region and judge the face candidate to be a non-face candidate when the occupancy ratio of the skin color region is higher than a predetermined threshold value.

5. The object detector according to claim 2, further comprising:

a tracking unit adapted to track the face candidates from which the non-face candidates are removed by the non-face detecting unit; and

the non-face detecting unit is further adapted to detect the non-face candidates from the face candidates that are tracked by the tracking unit at a predetermined timing.

6. The object detector according to claim 2, wherein the face detecting unit includes a matching result generating unit adapted to determine a correlated value of the input image and a template of a predetermined size showing an average face image and a discriminating unit configured to discriminate the face candidate by pattern recognition from the input image region selected on the basis of the correlated value.

7. An object detecting method for an object detector to detect an object of detection out of an input image, the method comprising:

detecting object candidates judged to be the object;

detecting non-object candidates judged to be non-objects and outputting the object candidates less the non-object candidates;

measuring a distance between the object detector and the object of detection;

computing an assumed distance between the object detector and the object of detection on the basis of a size of an object candidate relative to the input image;

judging the object candidate to be a non-object candidate when a difference between the assumed distance and the distance measured by the measuring is greater than a predetermined threshold value;

computing, using a processor, a variance of the object of detection in a color space; and

judging the object candidate to be the non-object candidate if the variance is less than a predetermined variance threshold value.

8. The method according to claim 7, wherein:

the object of detection includes a face region;

the detecting object candidates includes detecting face candidates judged to be the face region satisfying certain face conditions; and

the detecting non-object candidates includes non-face candidates judged to be non-faces satisfying certain non-face conditions and outputting the face candidates less the non-face candidates.

9. The method according to claim 8, wherein the detecting non-face candidates includes judging the face candidate as a non-face candidate when a difference between a size of the face candidate in the input image and the size of the face candidate in an input image of a predetermined time ago is greater than a predetermined threshold value.

10. The method according to claim 8, wherein the detecting non-face candidates includes computing an occupancy ratio of a skin color region relative to the face region and judging the face candidate to be a non-face candidate when an occupancy ratio of the skin color region is higher than a predetermined threshold value.

11. The method according to claim 8, further comprising:

tracking the face candidates from which the non-face candidates are removed by detecting non-face candidates; and

detecting the non-face candidates from the face candidates that are tracked by the tracking at a predetermined timing.

12. A robot equipped with an object detector for detecting an object of detection out of an input image and configured to autonomously act based on the object of detection, the object detector comprising:

an object detecting unit adapted to detect object candidates judged to be the object;

a non-object detecting unit adapted to detect non-object candidates judged to be non-objects and output the object candidates less the non-object candidates;

a distance measuring unit adapted to measure a distance between the object detector and the object of detection;

the non-object detecting unit is further adapted to compute an assumed distance between the object detector and the object of detection on the basis of a size of an object candidate in the detected object candidates relative to the input image and judge the object candidate to be a non-object candidate when a difference between the assumed distance and the distance measured by the distance measuring unit is greater than a predetermined threshold value and;

the non-object detecting unit is further adapted to compute, using a processor, a variance of the object candidate in a color space and, if the variance is less than a predetermined variance threshold value, judge the object candidate to be the non-object candidate.

13. The robot according to claim 12, wherein:

the object detector unit is adapted to detect a face region from the input image as the object of detection;

the object detecting unit is adapted to detect face candidates judged to be the face region satisfying certain face conditions; and

the non-object detecting unit includes a non-face detecting unit adapted to detect non-face candidates judged to be non-faces satisfying certain non-face conditions and output the face candidates less the non-face candidates.

14. The robot according to claim 13, wherein the non-face detecting unit is adapted to judge the face candidate as a non-face candidate when a difference between a size of the face candidate in the input image and a size of the face candidate in an input image of a predetermined time ago is greater than a predetermined threshold value.

15. The robot according to claim 13, wherein the non-face detecting unit is adapted to compute an occupancy ratio of a skin color region relative to the face region and judge the face candidate to be a non-face candidate when the occupancy ratio of the skin color region is higher than a predetermined threshold value.