Image processing system for augmented reality and method thereof
View Patent ↗An image processing system including a camera, a positioning device, a processor and a display is provided. The camera captures a real view image. The positioning device detects a camera position of the camera. The processor receives a high-precision map and a virtual object, calculates a camera posture of the camera according to the camera position by using a simultaneous localization and mapping (SLAM), projects a depth image according to the camera posture and a three-dimensional information of the high-precision map, superimposes the depth image and the real view image to generate a stack image, and superimposes the virtual object to the stack image according to a virtual coordinate of the virtual object to produce a rendered image. The display displays the rendered image.
1. An image processing system, comprising:
a camera used for capturing a real view image of a large outdoor object;
a positioning device used for detecting a camera position of the camera;
a processor coupled to the camera and the positioning device, calculating a camera posture of the camera according to the camera position by using a simultaneous localization and mapping (SLAM) algorithm, projecting a depth image according to the camera posture and a three-dimensional information of a high-precision map, superimposing the depth image and the real view image to generate a stack image, and superimposing a virtual object to the stack image according to a virtual coordinate of the virtual object to produce a rendered image; and
a display coupled to the processor for displaying the rendered image;
wherein the three-dimensional information of the high-precision map comprises a three-dimensional composition of the real view image or a height information of the large outdoor object in the real view image.
2. The image processing system according to claim 1 , wherein the depth image is a grayscale block, and the processor compares an edge information of the grayscale block with an edge information of the real view image and superimposes the depth image and the real view image by rotating or translating one of the grayscale block and the real view image.
3. The image processing system according to claim 1 , wherein the stack image comprises coordinate information of each coordinate point in the real view image, and the processor superimposes the virtual object to the stack image according to the coordinate information and the virtual coordinate of the virtual object.
4. The image processing system according to claim 1 , wherein the processor, by using a coordinate transformation function, maps coordinate of each coordinate point in the high-precision map to a camera coordinate for displaying on the display.
5. The image processing system according to claim 1 , wherein the depth image is a grayscale block, and the processor compares an edge information of the grayscale block with an edge information of the real view image and superimposes the depth image and the real view image by translating one of the grayscale block and the real view image.
6. The image processing system according to claim 5 , wherein the processor-further superimposes the depth image and the real view image by rotating one of the grayscale block and the real view image.
7. The image processing system according to claim 6 , wherein the stack image comprises coordinate information of each coordinate point in the real view image, and the processor superimposes the virtual object to the stack image according to the coordinate information and the virtual coordinate of the virtual object.
8. The image processing system according to claim 6 , wherein the processor, by using a coordinate transformation function, maps coordinate of each coordinate point in the high-precision map to a camera coordinate for displaying on the display.
9. An image processing method, comprising:
capturing a real view image of a large outdoor object by a camera;
detecting a camera position of the camera by a positioning device;
calculating a camera posture of the camera according to the camera position by a processor using an SLAM algorithm;
projecting a depth image by the processor according to the camera posture and a three-dimensional information of the high-precision map;
superimposing the depth image and the real view image by the processor to generate a stack image;
superimposing a virtual object to the stack image by the processor according to a virtual coordinate of the virtual object to produce a rendered image; and
displaying the rendered image by a display;
wherein the three-dimensional information of the high-precision map comprises a three-dimensional composition of the real view image or a height information of the large outdoor object in the real view image.
10. The image processing method according to claim 9 , wherein the depth image is a grayscale block, and the image processing method further comprises:
comparing an edge information of the grayscale block with an edge information of the real view image, and superimposing the depth image and the real view image by rotating or translating one of the grayscale block and the real view image.
11. The image processing method according to claim 9 , wherein the stack image comprises coordinate information of each coordinate point in the real view image, and the image processing method further comprises:
superimposing the virtual object to the stack image according to the coordinate information and the virtual coordinate of the virtual object.
12. The image processing method according to claim 9 , further comprising:
mapping coordinate of each coordinate point in the high-precision map to a camera coordinate for displaying on the display by using a coordinate transformation function.
13. The image processing method according to claim 9 , wherein the depth image is a grayscale block, and the image processing method further comprises:
comparing an edge information of the grayscale block with an edge information of the real view image, and superimposing the depth image and the real view image by translating one of the grayscale block and the real view image.
14. The image processing method according to claim 13 , wherein the image processing method further comprises:
superimposing the depth image and the real view image by rotating one of the grayscale block and the real view image.
15. The image processing method according to claim 14 , wherein the stack image comprises coordinate information of each coordinate point in the real view image, and the image processing method further comprises:
superimposing the virtual object to the stack image according to the coordinate information and the virtual coordinate of the virtual object.
16. The image processing method according to claim 14 , further comprising:
mapping coordinate of each coordinate point in the high-precision map to a camera coordinate for displaying on the display by using a coordinate transformation function.