HUMAN DETECTION WITH IMAGING SENSORS

• US 20080159591A1
• Filed: 01/03/2007
• Published: 07/03/2008
• Est. Priority Date: 01/03/2007
• Status: Active Grant

• Current Assignee: Science Applications International Corporation
• Original Assignee: Science Applications International Corporation
• Inventors: Ruedin, Joshua C.
• Granted Patent: US 7,961,906 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06V 10/803 of input or preprocessed data
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A method and apparatus for determining human beings from terrain or man-made obstacles is provided. A long-wave infrared camera along with additional devices such as a color camera, two cameras in stereo configuration, and/or a LADAR scanner are used such that the physical scene captured in one image is the same from all of the devices. The images may be processed such that areas of interest representing characteristics of human beings are labeled likely human. The processing may include determining the physical size, range, and relative locations of the objects found in the images. The system, method and apparatus may be used in unmanned vehicles or autonomous machines, as a driving aid to a manned vehicle or system, or as part of a security system.

Claims

1. A method of detecting a human being from objects in a field of view, the method comprising:

(a) capturing an image in the field of view with an infrared camera;

(b) capturing the image in the field of view with another device;

(c) determining first areas of the image that fall within a temperature range, the range being indicative of thermal emission characteristics of the human being based on output from the infrared camera;

(d) determining second areas of the image that correspond to characteristics of the human being based on output from the other device;

(e) subtracting the second areas of the image from the first areas of the image to define third common areas; and

(f) determining that the third common areas include a human being.

2. The method of claim 1, wherein the other device comprises a stereo camera.

3. The method of claim 2, wherein output from the stereo camera includes a disparity map.

4. The method of claim 3, wherein the third common areas are included in a masked disparity map.

5. The method of claim 4, wherein step (f) further comprises determining if the surface area of the masked disparity map is consistent with the surface area of the human being.

6. The method of claim 1, further including (g) displaying a likelihood that the third common areas includes a human being.

7. The method of claim 1, wherein the other device comprises a color camera.

8. The method of claim 1, wherein the infrared camera is a long-wave infrared camera.

9. The method of claim 8, wherein the third common areas are included in a masked color map.

10. The method of claim 9, wherein step (f) further comprises determining if the common areas include a human face using a face detection algorithm.

11. The method of claim 9, wherein step (f) further comprises determining if the common area includes colors that represent human skin colors using a color matching algorithm.

12. An apparatus for detecting a human being from a field of vision, the apparatus comprising:

(a) an infrared camera;

(b) a stereo camera; and

(c) a control node for processing data from the same field of vision simultaneously recorded by both the infrared camera and the stereo camera for detecting the human being.

13. The apparatus of claim 12, wherein the infrared camera comprises a long-wave infrared camera.

14. The apparatus of claim 12, wherein the long-wave infrared camera and the stereo camera are mounted to a support structure.

15. The apparatus of claim 12, further comprising a color camera.

16. The apparatus of claim 12, further comprising a LADAR scanner.

17. A method of detecting a human being in a field of vision, the method comprising:

(a) capturing a first image in the field of view with a long-wave infrared camera;

(b) capturing a second image in the field of view with another device;

(c) overlaying the second image onto the first image to define a common area;

(d) determining if the surface area of the common area are indicative of the human being.

18. The method of claim 17, wherein the other device comprises a stereo camera.

19. The method of claim 17, wherein the other device comprises a color camera.

20. The method of claim 17, wherein the other device comprises a LADAR scanner.