Method for processing images in a stereo vision system and apparatus for same

1. An apparatus for extracting a three-dimensional information of a subject by processing images in a stereovision system, the apparatus comprising:

an image capture unit comprising a first camera for capturing first images of the subject, a second camera for capturing second images of the subject, the first and the second images having a different view of the subject, and a lighting unit for flashing light for the first and the second cameras to capture the first and second images;

a camera controller configured to control the first and the second cameras by alternatively capturing the first and the second images of the same subject in order at a predetermined time interval without time synchronization;

an image estimator configured

to estimate first estimated intermediate images between two consecutive first images, wherein each of the first estimated intermediate images is correspondent to each of the camera controller captured images of the second camera, and

to estimate second estimated intermediate images between two consecutive second images, wherein each of the second estimated intermediate images is correspondent to each of the camera controller captured images of the first camera;

an image processor configured to extract the three-dimensional information of the subject by using the first images and the first estimated intermediate images at the same time, or using the second images and the second estimated intermediate images at the same time; and

a mode switching unit for switching a shooting mode of the image capture unit from a first mode to a second mode upon determining that the subject stays still,

wherein the first and second cameras obtain the image information by grabbing images of the subject in time synchronization in the first mode by the image capture unit, and obtain the image information by alternately grabbing images of the subject with a certain time interval in the second mode by the camera controller, the image estimator, and the image processor.

2. The apparatus according to claim 1 , further comprising a lighting controller for controlling the lighting unit to operate in time synchronization with the grabbing of the images by the first and second cameras.

3. The apparatus according to claim 1 , further comprising:

an image analyzer for determining whether the subject stays still, based on the obtained image information.

4. The apparatus according to claim 3 , wherein the first and second cameras obtain the image information in the second mode according to a signal transmitted from the camera controller.

5. The apparatus according to claim 4 , wherein the first and second cameras grab images at a low speed in the first mode and grab images at a high speed in the second mode.

6. The apparatus according to claim 4 , wherein the image analyzer comprises a hit sensor for sensing whether the subject is hit by a user, based on the image information obtained in the second mode.

7. The apparatus according to claim 6 , further comprising a database for storing the image information obtained in the second mode by the first and second cameras.

8. The apparatus according to claim 7 , wherein the image estimator is configured to check a point of impact upon sensing that the subject is hit by the user, extract images from the first and the second images before and after the point of impact from the database, and obtain predicted images as the first and the second estimated intermediate images based on the extracted images.

9. The apparatus according to claim 8 , wherein the image estimator is configured to obtain each predicted image by using the two consecutive first images and one of the second images which is taken between the two consecutive first images.

10. The apparatus according to claim 9 , wherein the two consecutive first images correspond to sequential frame images received from the first camera, and the one of the second images corresponds to a frame image received from the second camera, which is taken between the two consecutive first images.

11. The apparatus according to claim 8 , wherein the image processor is configured to obtain physical characteristics of the subject based on the first and the second images before and after the point of impact and the predicted images.

12. A method for extracting a three-dimensional information of a subject by processing images in a stereovision system, the method comprising:

obtaining image information of the subject in a first mode using an image capture unit comprising a first camera for capturing first images of the subject, a second camera for capturing second images of the subject, the first and the second images having a different view of the subject, and a lighting unit for flashing light for the first and the second cameras to capture the first and second images;

determining whether the subject stays still, based on the obtained image information;

switching a shooting mode of the image capture unit to a second mode by using a camera controller, an image estimator, and an image processor;

controlling, by the camera controller, the first and the second cameras by alternatively capturing the first and the second images of the same subject in order at a predetermined time interval without time synchronization;

estimating, by the image estimator,

first estimated intermediate images between two consecutive first images, wherein each of the first estimated intermediate images is correspondent to each of the camera controller captured images of the second camera, and

second estimated intermediate images between two consecutive second images, wherein each of the second estimated intermediate images is correspondent to each of the camera controller captured images of the first camera; and

extracting, by the image processor, the three-dimensional information of the subject by using the first images and the first estimated intermediate images at the same time, or using the second images and the second estimated intermediate images at the same time.

13. The method according to claim 12 , further comprising obtaining the image information in the switched second mode by the first and second cameras.

14. The method according to claim 13 , further comprising sensing whether the subject is hit by a user, based on the image information obtained in the second mode.

15. The method according to claim 14 , further comprising storing the image information obtained in the second mode in a database.

16. The method according to claim 15 , further comprising, upon sensing that the subject is hit by the user, checking a point of impact, extracting the image information before and after the point of impact from the database, and obtaining predicted image information based on the extracted image information before and after the point of impact.

17. The method according to claim 16 , wherein the predicted image information is obtained using the two consecutive first images and one of the second images which is taken between the two consecutive first images.

18. The method according to claim 17 , wherein the two consecutive first images correspond to sequential frame images received from the first camera, and the one of the second images corresponds to a frame image received from the second camera, which is taken between the two consecutive first images.

19. The method according to claim 16 , further comprising, by the image processor, obtaining physical characteristics of the subject based on the image information before and after the point of impact and the predicted image information.

20. The method according to claim 12 , wherein the first and second cameras grab images at a low speed in the first mode and grab images at a high speed in the second mode.