System and method for moving object selection in a handheld image capture device

• US 8,125,512 B2
• Filed: 11/16/2007
• Issued: 02/28/2012
• Est. Priority Date: 11/16/2007
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Fahn, Paul, Marti, Stefan
• Primary Examiner(s): Harrell, Robert B
• Application Number:
  US11/941,828
• Publication Number:
  US 20090128618A1
• Time in Patent Office: 1,565 Days
• Field of Search: 348/36
• US Class Current: 348/36
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: H04N 23/58 Means for changing the camera field of view without moving the camera body, e.g. nutating or panning of optics or image sensors
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/695 Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects

Abstract

A system and method for automatically selecting an object from a field of view of a handheld image capture device. The system includes sensors configured to sense features of one or more objects in the field of view and a decision unit configured to automatically select one or more objects from the field of view based on the sensed features using a decision algorithm that is based on a decision structure, wherein the decision structure receives and prioritizes inputs from the sensors. The system may also optionally include an object movement detecting module configured to detect movement of objects, and a manual selection unit configured to provide user priorities; if included, the information from these elements may also be used by the decision unit to automatically select the object or objects.

Claims

1. A system for automatically selecting an object from a field of view of an image capture device, the system comprising:

a plurality of sensors configured to sense features of objects in the field of view;

a decision unit configured to automatically select one or more objects of interest based on the sensed features using a decision algorithm that is based on a decision structure, wherein the decision structure receives and prioritizes inputs from the plurality of sensors; and

an object movement detection module configured to sense the movement of the body of the handheld image capture device and having a background subtraction unit configured to

analyze a series of captured images to calculate the motion of one or more object images relative to the frame of the captured images;

subtract background motion vectors using camera body movement data; and

produce background compensated image data,

wherein a captured image is received from the image capture device.

2. The system of claim 1, wherein the decision unit is configured to receive information from the sensors and the object movement module so as to automatically select one or more objects from the field of view.

3. The system of claim 2, wherein the information comprises at least one of:

size, location, shape, and trajectory of the one or more objects.

4. The system of claim 2, wherein the decision unit selects one or more objects based on an analysis based on one or more of an object size sensing, an object movement sensing, object thermal sensing, and object recognition sensing.

5. The system of claim 2, wherein the decision unit selects one or more objects based on priorities from a manual selection unit.

6. The system of claim 2, wherein the decision unit selects one or more objects based on one or more conditions arranged in a hierarchy.

7. The system of claim 1, wherein the object movement detection module is further configured to:

sense the movement of an actuated lens of the handheld image capture device;

calculate the motions of one or more objects by analyzing a series of captured images;

subtract background motion vector using actuated lens movement data; and

produce background compensated image data.

8. The system of claim 7, wherein the object movement detection module further comprises a moving object detection unit that determines moving objects based on the background compensated image data.

9. The system of claim 1, wherein the system outputs information about the one or more selected objects.

10. The system of claim 9, wherein the output information is at least one of:

object image size information, object shape information, and object image location information.

11. The system of claim 1, wherein the sensors include a face or human being detection sensor.

12. The system of claim 1, wherein the sensors include an object recognition sensor configured to recognize various objects whose representative templates are stored in a storage associated with the sensor.

13. The system of claim 1, wherein the sensors include at least one of:

thermal, magnetic, inductive, non-visible light, multi-spectral, radar, lidar, eye gaze detection, depth, acoustic, and smell sensors.

14. The system of claim 1, wherein the object movement detection module further comprises a moving object detection unit that determines moving objects based on the background compensated image data.

15. A computer-implemented method of automatically selecting an object of interest from a field of view of an image capture device, the method comprising:

receiving a captured image as input;

sensing features of a plurality of objects in the captured image using a plurality of sensors;

detecting movement of one or more objects in the captured image wherein said detecting comprises

detecting camera body movement;

detecting actuated lens movement;

calculating motions of one or more objects by analyzing a series of captured images;

subtracting background motions based on the camera body movement and the actuated lens movement; and

identifying one or more moving objects; and

automatically selecting one or more objects of interest based on the sensed features using a decision algorithm that is based on a decision structure, wherein the decision structure receives and prioritizes inputs from the plurality of sensors.

16. The method of claim 15, wherein at least one of the sensors is configured to sense a feature other than human face features or human beings.

17. The method of claim 15, wherein the automatically selecting one or more objects of interest comprises analyzing data based on at least one of:

object size sensing, object thermal sensing, and object recognition sensing.

18. The method of claim 15, wherein the automatically selecting one or more objects of interest comprises analyzing object movement.

19. A system for automatically selecting an object from a field of view of a handheld image capture device, the system comprising:

a plurality of sensors configured to sense features of objects in the field of view;

an object movement detection module configured to detect movement of objects in the field of view by detecting camera body movement, detecting actuated lens movement, calculating the motions of objects, subtracting the camera body movement and actuated lens movement from the motions of objects, and determining what objects are moving objects;

a manual selection unit configures to provide user priorities; and

a decision unit configured to receive information from the plurality of sensors, the object movement module and the manual selection unit and to automatically select one or more objects of interest based on object size, object movement, object temperature and the priorities.

20. The system of claim 19, additionally comprising a mechanism for outputting object image size, object image movement, and object image location information.

21. A non-transitory computer usable medium having computer readable program code embodied therein for automatically selecting an object of interest from a field of view of an image capture device, the computer readable code comprising instructions for:

receiving an image of the field of view from the image capture device;

sensing features of one or more objects in the image;

detecting movement of the one or more objects in the image wherein said detecting comprises

detecting camera body movement;

detecting actuated lens movement;

calculating motions of one or more objects by analyzing a series of captured images;

subtracting background motions based on the camera body movement and the actuated lens movement; and

identifying one or more moving objects;

automatically selecting one or more objects of interest based on the sensed features and the detected movement; and

outputting information about the selected one or more objects.