SUSPICIOUS BEHAVIOR DETECTION SYSTEM AND METHOD

• US 20090131836A1
• Filed: 01/23/2009
• Published: 05/21/2009
• Est. Priority Date: 03/06/2007
• Status: Abandoned Application

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Takahashi, Yusuke, Baba, Kenji, Suzuki, Yoshihiko, Toyoshima, Ichiro, ENOHARA, Takaaki, Itakura, Toyokazu
• Application Number:
  US12/358,555
• Publication Number:
  US 20090131836A1
• Time in Patent Office: Days
• US Class Current: 600/595
• 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 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Abstract

There is provided a suspicious behavior detection system capable of specifying and identifying a suspicious person exhibiting abnormal behavior. A suspicious behavior detection system is a system to detect suspicious behavior of a monitored subject, by using images captured by a stereo camera. The suspicious behavior detection system has an ambulatory path acquisition unit which acquires ambulatory path information of the monitored subject, and a behavioral identification unit which identifies behavior of the monitored subject based on the ambulatory path information, and automatically determines suspicious behavior of the monitored subject.

Claims

1. A suspicious behavior detection system comprising:

a sensor means for detecting movement of a monitored subject;

an ambulatory path acquisition means which acquires information about an ambulatory path of the monitored subject, based on the output of the sensor means;

a behavioral identification means which identifies behavior of the monitored subject, based on the ambulatory path information acquired by the ambulatory path acquisition means, by using learned information obtained by learning behavior along the ambulatory path; and

a determination means which automatically determines suspicious behavior of the monitored subject in real time, based on the behavior identified by the behavioral identification means.

2. The suspicious behavior detection system according to claim 1, wherein the sensor means includes a stereo camera, a single-lens camera, or other optical sensor.

3. The suspicious behavior detection system according to claim 1, wherein the sensor means has a stereo camera for imaging the monitored subject;

and

an image processing means for processing image signals output from the stereo camera.

4. The suspicious behavior detection system according to claim 1, wherein the ambulatory path acquisition means has a sensor means which has cameras, and detect movement of the monitored subject in monitored areas corresponding to the imaging areas of the cameras;

and

a generation means which integrates the output of the sensor means, and generates integrated ambulatory path information indicating an ambulatory path of the monitored subject extending over the monitored areas.

5. The suspicious behavior detection system according to claim 4, wherein the sensor means includes any one of stereo camera, single-lens camera, and other optical sensor, as cameras.

6. The suspicious behavior detection system according to claim 4, wherein the ambulatory path acquisition means has a completion means which executes a completion process to connect ambulatory paths of the monitored subject based on the output of the sensor means, and generates the ambulatory path information including the unmonitored area.

7. The suspicious behavior detection system according to claim 6, wherein the completion means is configured to execute the completion process based on attributive information including characteristic quantities such as height and behavioral pattern of the monitored subject.

8. The suspicious behavior detection system according to claim 1, wherein the behavioral identification means adopts a pattern recognition method, and is configured to mathematically analyze characteristics of the ambulatory path information of a monitored subject, and output information to determine suspicious behavior by teaching one of or both of normal and abnormal patterns as learned information.

9. The suspicious behavior detection system according to claim 1, wherein the behavioral identification means has a means to execute sequential learning, which periodically and automatically selects information from a data group of stored ambulatory path information, based on optional conditions (duration, place, human nature, etc.), as a method of acquiring the learned information.

10. The suspicious behavior detection system according to claim 1, wherein the behavioral identification means includes different kinds of behavioral identification means for identifying behavior with different characteristics, by using learned information with different characteristics as the learned information, based on the ambulatory path information acquired by the ambulatory path acquisition means.

11. The suspicious behavior detection system according to claim 1, further comprising a means to zoom in on a monitored subject determined to exhibit suspicious behavior by the determination means, by controlling tracking and zooming functions of a camera included in the sensor means.

12. A suspicious behavior detection method adapted to a suspicious behavior detection system using a sensor means for detecting movement of a monitored subject, the suspicious behavior detection method comprising:

a step of acquiring information about an ambulatory path of the monitored subject, based on the output of the sensor means;

a step of identifying behavior of the monitored subject, based on the ambulatory path information, by using learned information acquired by learning behavior along the ambulatory path; and

a step of automatically determining suspicious behavior of the monitored subject in real time, based on the behavior identified by the behavioral identification means.