Object detection system and method

• US 20070230943A1
• Filed: 03/29/2006
• Published: 10/04/2007
• Est. Priority Date: 03/29/2006
• Status: Active Grant

• Current Assignee: Sunvision Scientific Incorporated
• Original Assignee: Sunvision Scientific Incorporated
• Inventors: Chang, Chao-Hung, Chang, Chow-Ing, Chang, Tain-Tzu
• Granted Patent: US 7,574,131 B2
• Time in Patent Office: Days
• US Class Current: 396/322
• CPC Class Codes: G03B 37/00 Panoramic or wide-screen photography; Photographing extended surfaces, e.g. for surveying; Photographing internal surfaces, e.g. of pipe

Abstract

An object detection system and method is applied to an active surveillance system for detecting at least one target object appeared in an area of interest. The object detection system includes a processor for defining the area of interest into at least a first and a second zone; a controller for assigning a first and a second weight to the first and the second zone, respectively, wherein the first weight is higher than the second weight; and a first image capturing device for capturing an image of the target object appeared in the first zone prior to capturing an image of the target object appeared in the second zone. With these arrangements, the detection of at least one target object appeared in more than one zone having a specific weight assigned thereto may be implemented with improved efficiency and accuracy in object selection and reduced interferences from environmental variables.

Claims

1. An object detection system for detecting at least one target object present in an area of interest, the system comprising:

a processor for defining the area of interest into at least a first region and a second region;

a controller for assigning a first priority to the first region and assigning a second priority to the second region, wherein the first priority is higher than the second priority; and

a first image capturing member for capturing image of the target object present in the first region prior to capturing image of the target object present in the second region.

2. The object detection system as claimed in claim 1, further comprising a second image capturing member for capturing a panoramic image of the area of interest.

3. The object detection system as claimed in claim 2, wherein the first image capturing member has a smaller angle of view than the second image capturing member.

4. The object detection system as claimed in claim 1, wherein the first image capturing member doesn'"'"'t capture image of the target object present in the second region when the second priority is set to be zero.

5. The object detection system as claimed in claim 1, wherein the processor changes sizes and locations of the first region and the second region with a predetermined time period.

6. The object detection system as claimed in claim 1, wherein the controller varies the first priority and the second priority with a predetermined time period.

7. The object detection system as claimed in claim 1, wherein the controller lowers the first priority or the second priority after the first image capturing member captured the target object present in the first region or the second region over a predetermined time.

8. The object detection system as claimed in claim 1, wherein values of the first priority and the second priority are successively increased in at least one predetermined direction.

9. An object detecting method for detecting at least one target object present in an area of interest, the method comprising the steps of:

defining the area of interest into at least a first region and a second region;

assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

capturing an image of the target object in the first region prior to capturing an image of the target object in the second region with a first image capturing member.

10. The object detecting method as claimed in claim 9, further comprising the step of capturing a panoramic image of the area of interest with a second image capturing member.

11. The object detection system as claimed in claim 10, wherein the first image capturing member has a smaller angle of view than the second image capturing member.

12. The object detecting method as claimed in claim 9, wherein the first image capturing member doesn'"'"'t capture image of the target object present in the second region when the second priority is set to be zero.

13. The object detection method as claimed in claim 9, further comprising the step of:

changing sizes and locations of the first region and the second region with a predetermined time period.

14. The object detection method as claimed in claim 9, further comprising the step of:

varying the first priority and the second priority with a predetermined time period.

15. The object detection method as claimed in claim 9, further comprising the step of:

lowering the first priority or the second priority after the first image capturing member captured the target object present in the first region or the second region over a predetermined time.

16. The object detection method as claimed in claim 9, wherein values of the first priority and the second priority are successively increased in at least one predetermined direction.

17. A surveillance system comprising:

an image capturing device for acquiring a first panoramic image data with a first resolution from a predetermined surveillance area;

a first data saving member for receiving the first panoramic image data captured by the image capturing device such that the first panoramic image data can be stored in the first data saving member and then transferred to the data identifying member;

a data identifying member connected to the first data saving member for receiving the first panoramic image data transferred from the first data saving member and for identifying image data of at least one target object from the first panoramic image data and dividing the first panoramic image data into target object image data and background image data;

the data identifying member comprising an object detection system for detecting at least one target object present in the panoramic image data, and the object detection system comprising;

a processor for defining the first panoramic image data into at least a first region and a second region;

a controller for assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

an image capturing member for capturing an image of the target object present in the first region prior to capturing an image of the target object present in the second region;

a data converting member for receiving the background image data from the data identifying member and converting the background image data from the first resolution into a second resolution, wherein the second resolution is lower than the first resolution; and

an image synthesizer for receiving the background image data with the second resolution and the target object image data with the first resolution, and forming a second panoramic image data with the background image data with the second resolution and the target image data with the first resolution.

18. A surveillance method comprising the steps of:

acquiring a first panoramic image data with a first resolution from a predetermined surveillance area by an image capturing device;

saving the first panoramic image data in a first data saving member;

transferring the first panoramic image data from the first data saving member to a data identifying member;

identifying image data of at least one interested target object from the first panoramic image data and dividing the first panoramic image data into target object image data and background image data by the data identifying member, wherein the data identifying member comprises an object detection system for detecting at least one target object present in the first panoramic image data, the object detection system comprising;

defining the first panoramic image data into at least a first region and a second region;

assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

capturing an image of the target object present in the first region prior to capturing an image of the target object present in the second region with an image capturing member;

receiving the background image data from the data identifying member and converting the background image data from the first resolution into a second resolution by a data converting member, wherein the second resolution is lower than the first resolution; and

receiving the background image data with the second resolution and the target image data with the first resolution and forming a second panoramic image data with the background image data with the second resolution and the target image data with the first resolution by an image synthesizer.

19. A surveillance system comprising:

an image capturing device for acquiring a panoramic image data from a predetermined surveillance area;

a first data saving member for receiving the first panoramic image data captured by the image capturing device such that the panoramic image data can be stored in the first data saving member and then transferred to the data identifying member;

a data identifying member connected to the first data saving member for receiving the first panoramic image data transferred from the first data saving member and for identifying image data of at least one target object from the panoramic image data and dividing the panoramic image data into target object image data and background image data;

wherein the data identifying member comprises an object detection system for detecting at least one target object present in the panoramic image data, and the object detection system comprising;

a processor for defining the panoramic image data into at least a first region and a second region;

a controller for assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority;

an image capturing member for capturing image of the target object present in the first region prior to capturing image of the target object present in the second region; and

a second data saving member for receiving the target object image data; and

wherein the background image data in the first data saving member are deleted after the target image data are in the second data saving member.

20. A surveillance method, comprising the steps of:

acquiring a panoramic image data from a predetermined surveillance area by an image capturing device;

saving the first panoramic image data in a first data saving member;

transferring the panoramic image data from the first data saving member to a data identifying member;

identifying image data of at least one target object from the panoramic image data and dividing the panoramic image data into target image data and background image data by the data identifying member connected to the image capturing device, wherein the data identifying member comprises an object detection system for detecting at least one target object present in the panoramic image data, and the object detection system comprising;

defining the panoramic image data into at least a first region and a second region;

assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

capturing an image of the target object present in the first region prior to capturing an image of the target object present in the second region with an image capturing member;

transferring the target image data in a second data saving member;

deleting the background image data in the first data saving member after transferring the target image data in the second data saving member.

21. A surveillance system comprising:

a first image capturing device having a first resolution for acquiring a panoramic image data from a predetermined surveillance area;

a second image capturing device having a second resolution for tracking and acquiring at least one target object present in the predetermined surveillance area, wherein the second resolution is higher than the first resolution; and

an object detection system for controlling the tracking of the second image capturing device, the object detection system comprising;

a processor for receiving the panoramic image data from the first image capturing device and defining the panoramic image data into at least a first region and a second region;

a controller for assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

a locating member for locating an image of the target object present in the first region of the area of interest prior to locating an image of the target object present in the second region of the area of interest; and

wherein the second image capturing device tracks the target object by following the location of the target object provided by the object detection system.

22. The surveillance system as claimed in claim 21, wherein the second image capturing device is movable.

23. The surveillance system as claimed in claim 21, wherein the second image capturing device is not movable and further includes a movable mirror to reflect the image of the target object to the second image capturing device.

24. A surveillance method, comprising the steps of:

acquiring a panoramic image data from a predetermined surveillance area by a first image capturing device with a first angle of view;

detecting the movement of at least one target object present in the predetermined surveillance area, wherein the detecting step comprises the steps of;

receiving the panoramic image data from the first image capturing device and defining the panoramic image data into at least a first region and a second region;

assigning a first priority to the first region and a second priority to the second region, wherein the first priority is higher than the second priority; and

locating an image of the target object present in the first region prior to locating an image of the target object present in the second region; and

tracking the target object by following the location of the target object provided by the object detecting step with a second image capturing device, wherein the second image capturing device having a second angle of view smaller than the first angle of view.

25. The surveillance method as claimed in claim 24, wherein the second image capturing device is movable.

26. The surveillance method as claimed in claim 24, wherein the step of tracking the target object is performed by a movable mirror such that the image of the target object can be reflected to the second image capturing device when the second image capturing device is not movable.