Image capturing method for image recognition and system thereof

• US 9,373,035 B2
• Filed: 05/09/2013
• Issued: 06/21/2016
• Est. Priority Date: 06/06/2012
• Status: Active Grant

• Current Assignee: EYS3D Microelectronics, Co.
• Original Assignee: EYS3D Microelectronics, Co.
• Inventors: Wu, Ben, Ho, Ming-Che, Chen, Chih-Kao
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US13/890,267
• Publication Number:
  US 20130329947A1
• Time in Patent Office: 1,139 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

An image capturing method includes providing at least three image capturing devices arranged along a same direction and an image processor, the at least three image capturing devices capturing at least three first images, determining a target object in the at least three first images, activating a first pair of image capturing devices of the at least three image capturing devices according to shooting angles of the target object in the at least three first images in order to capture a first pair of motion images, and the image processor performing image recognition to the target object of the first pair of motion images.

Claims

1. An image capturing method for image recognition, comprising:

providing at least three image capturing devices arranged along a same direction and an image processor;

the at least three image capturing devices capturing at least three first images;

determining a target object in the at least three first images;

activating a first pair of image capturing devices of the at least three image capturing devices according to shooting angles of the target object in the at least three first images in order to capture a first pair of motion images by activating the first pair of image capturing devices with shooting centers closer to the target object; and

the image processor performing image recognition on the target object according to the first pair of motion images.

2. The image capturing method of claim 1, wherein determining the target object in the at least three first images comprises determining the target object in the at least three first images according to image sizes of a plurality of objects in the at least three first images.

3. The image capturing method of claim 1, wherein determining the target object in the at least three first images comprises determining the target object in the at least three first images by detecting human body/face images in the at least three first images.

4. The image capturing method of claim 1, wherein activating the first pair of image capturing devices of the at least three image capturing devices according to the shooting angles of the target object in the at least three first images comprises activating the first pair of image capturing devices shooting front images of the target object.

5. The image capturing method of claim 1, further comprising:

clipping images of the target object from the first pair of motion images for generating a first pair of motion clip images of the target object; and

transmitting the first pair of motion clip images to the image processor;

wherein the image processor performing image recognition on the target object according to the first pair of motion images comprises the image processor performing image recognition on the target object according to the first pair of motion clip images of the target object.

6. The image capturing method of claim 1, further comprising:

the at least three image capturing devices capturing at least three second images;

determining the target object in the at least three second images;

activating a second pair of image capturing devices of the at least three image capturing devices according to shooting angles of the target object in the at least three second images in order to capture a second pair of motion images; and

the image processor performing image recognition on the target object according to the second pair of motion images.

7. The image capturing method of claim 1, wherein the image processor performing image recognition on the target object according to the first pair of motion images comprises the image processor performing three-dimensional image recognition on the target object according to the first pair of motion images.

8. The image capturing method of claim 1 further comprising the image processor generating a command according to a result of image recognition on the target object.

9. The image capturing method of claim 1, wherein the image processor performing image recognition on the target object according to the first pair of motion images comprises the image processor performing image recognition on the target object and other objects according to the first pair of motion images.

10. An image capturing system for image recognition, comprising:

at least three image capturing devices arranged along a same direction; and

a controller coupled to the at least three image capturing devices, the controller comprising;

a sensor selection module for determining a target object in at least three first images according to the at least three first images captured by the at least three image capturing devices, and for activating a first pair of image capturing devices of the at least three image capturing devices according to shooting angles of the target object in the at least three first images in order to capture a first pair of motion images by activating the first pair of image capturing devices with shooting centers closer to the target object; and

an input/output interface for transmitting motion images of the target object to an image processor according to the first pair of motion images in order to perform image recognition on the target object.

11. The image capturing system of claim 10, wherein the sensor selection module determines the target object in the at least three first images according to image sizes of a plurality of objects in the at least three first images.

12. The image capturing system of claim 10, wherein the sensor selection module determines the target object in the at least three first images by detecting human body/face images in the at least three first images.

13. The image capturing system of claim 10, further comprising:

an image crop module for clipping the images of the target object from the first pair of motion images for generating a first pair of motion clip images of the target object,

wherein the input/output interface is for transmitting the first pair of motion clip images of the target object to the image processor for performing image recognition on the target object.