Methods and systems for detecting and recognizing an object based on 3D image data

• US 7,174,033 B2
• Filed: 04/01/2003
• Issued: 02/06/2007
• Est. Priority Date: 05/22/2002
• Status: Active Grant

• Current Assignee: Bioscrypt, Inc. (Advent International Corporation)
• Original Assignee: A4VISION
• Inventors: Yukhin, Artiom, Klimov, Andrei
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US10/405,412
• Publication Number:
  US 20030231788A1
• Time in Patent Office: 1,407 Days
• Field of Search: 382/103, 382/115, 382/118, 382/124, 382/154, 382/190, 382/209, 382/218, 340/5.2, 340/5.3
• US Class Current: 382/115
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

Methods and systems are described herein for high-speed observation and recognition of an object which is within or passes through a designated area using 3D image data and tomography, stereo-photogrammetry, range finding and/or structured illumination. Such a security system may comprise multiple pairs of 3D sensors surrounding the designated area such as a portal or doorway. Alternatively, it may comprise a 3D sensor which is capable of acquiring 3D image data of an object that is situated in front of it. Using at least one 3D sensor and a 3D data collection technique such as structured illumination and/or stereo-photogrammetry, 3D image data of the object is acquired. 3D image data representing the object'"'"'s surface may be determined based on the acquired data and may be compared to data representing known objects to identify the object. Methods for fast processing of 3D data and recognition of objects are also described.

Claims

1. A method of identifying an object which is within or passes through a designated area, the method comprising:

passively acquiring by at least one 3D sensor without affirmative cooperation from the object a first 3D image data representing the object while the object is within or passes through the designated area, wherein the object can be modeled by the 3D sensor when the object is at least six inches from the 3D sensor;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

comparing the second 3D image data to data representing known objects; and

identifying the object based on the second 3D image data.

2. The method of claim 1, wherein the designated area consists of at least one of a portal, a gate or a doorway.

3. The method of claim 1, wherein passively acquiring by at least one 3D sensor without affirmative cooperation from the object a first 3D image data of the object while the object is within or passes through the designated area includes utilizing at least one of stereo-photogrammetry and structured illumination.

4. The method of claim 1, further comprising:

processing the first or second 3D image data to filter out noise.

5. The method of claim 1, wherein checking the quality of the first or second 3D image data includes utilizing a rejection algorithm.

6. The method of claim 5, wherein the rejection algorithm includes at least one of the steps of:

determining if the first, second, or third 3D image data is good; and

determining if the first, second, or third 3D image data comprises enough data for recognition.

7. A method of identifying an object which is within or passes through a designated area, the method comprising:

acquiring first 3D image data representing the object while the object is within or passes through the designated area;

checking the quality of the second 3D image data;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

generating a feature vector based on the second 3D image data, the feature vector representing features of the object; and

constructing a filter vector based on the feature vector;

determining a subset of data representing known objects based on the filter vector; and

comparing the second 3D image data to the subset of data representing features of known objects; and

identifying the object based on the second 3D image data.

8. The method of claim 7, wherein the feature vector include measurements of anthropological metrics.

9. The method of claim 7, further comprising:

generating assumptions about the identity of the object based on the feature vector.

10. A system for identifying an object while the object is within or passes through a designated area, the system comprising:

at least one 3D sensor comprising at least one illumination unit configured for illuminating the object and at least one 3D data collecting unit configured for passively acquiring without affirmative cooperation from the object a 3D image data representing the object while the object is within or passes through a designated area, wherein the object can be modeled by the 3D sensor when the object is at least six inches from the 3D sensor; and

a processing unit configured for;

receiving from the at least one 3D sensor the first 3D image data representing the object

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

comparing the second 3D image data to data representing known objects; and

identifying the object based on the second 3D image data.

11. The system of claim 10, wherein the at least one illumination unit includes at least one of a laser, light-emitting diode (“

LED”

), inert gas lamp, incandescent lamp or other lamp working in visible, ultraviolet or infrared range.

12. The system of claim 10, wherein the at least one 3D data collecting unit includes at least one of a camera, a photodetector array, and a CCD sensor.

13. The system of claim 10, further comprising:

a central processing unit; and

a memory unit.

14. A computer readable medium containing instructions for controlling a computer system to perform a method of identifying an object which is within or passes through a designated area, the method comprising:

passively acquiring by at least one 3D sensor without affirmative cooperation from the object a first 3D image data representing the object while the object is within or passes through the designated area wherein the object can be modeled by the 3D sensor when the object is at least six inches from the 3D sensor;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

comparing the second 3D image data to data representing known objects; and

identifying the object based on the second 3D image data.

15. A computer readable medium containing instructions for controlling a computer system to perform a method of identifying an object which is within or passes through a designated area, the method comprising:

acquiring first 3D image data representing the object while the object is within or passes through the designated area;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

generating a feature vector based on the second 3D image data, the feature vector representing features of the object; and

constructing a filter vector based on the feature vector;

determining a subset of data representing known objects based on the filter vector; and

comparing the second 3D image data to the subset of data representing features of known objects; and

identifying the object based on the second 3D image data.

16. An apparatus for identifying an object comprising:

at least one 3D sensor configured to passively acquire without affirmative cooperation from an object, a first 3D image data representing the object while the object is within or passes through a designated area, wherein the object can be modeled by the 3D sensor when the object is at least six inches from the 3D sensor;

a processing unit configured for receiving from the at least one 3D sensor the first 3D image data representing the object;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

comparing the second 3D image data to data representing known objects; and

identifying the object based on the second 3D image data; and

a memory unit capable of storing 3D image data.

17. An apparatus for identifying an object comprising:

a processing unit configured for acquiring first 3D image data representing the object while the object is within or passes through a designated area;

determining second 3D image data representing the object'"'"'s surface based on the first 3D image data;

checking the quality of the second 3D image data;

comparing the second 3D image data to data representing known objects;

generating a feature vector based on the second 3D image data, the feature vector representing features of the object; and

constructing a filter vector based on the feature vector;

determining a subset of data representing known objects based on the filter vector;

comparing the second 3D image data to the subset of data representing features of known objects; and

identifying the object based on the second 3D image data; and

a memory unit capable of storing 3D image data.