Building texture extracting apparatus and method thereof

• US 9,098,746 B2
• Filed: 06/20/2011
• Issued: 08/04/2015
• Est. Priority Date: 04/28/2011
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Wu, Yi-Ju, Chang, Jiun-Wei, Tsai, Augustine, Huang, Fay, Tsai, Jui-Yang, Liu, Wen-Kai
• Primary Examiner(s): Vu, Kim
• Assistant Examiner(s): VANCHY JR, MICHAEL J
• Application Number:
  US13/164,485
• Publication Number:
  US 20120275709A1
• Time in Patent Office: 1,506 Days
• Field of Search: 382/199, 382/154, 382/286, 382/293, 345/419, 345/420, 348/144, 703/1
• US Class Current: 1/1
• CPC Class Codes: G06V 20/176 Urban or other man-made structures

Abstract

A building texture extracting apparatus and a method thereof are provided, wherein the building texture extracting apparatus comprises a storage unit and a processor. The storage unit is configured to store an aerial image and a panoramic image of a building. There is a coordinate correlation between the aerial image and the panoramic image. The processor defines an edge segment of a building in the aerial image, calculates an edge function according to the edge segment, projects the edge function onto the panoramic image according to the coordinate correlation to derive an edge curve function, decides an edge curve segment according to the edge curve function, captures an image area under the edge curve segment to be a building texture of the building, and stores the building texture in the storage unit.

Claims

1. A building texture extracting apparatus, comprising:

a non-transitory storage unit, being configured to store an aerial image and a panoramic image of a building, there being a coordinate correlation between the aerial image and the panoramic image; and

a processor, being electrically connected to the non-transitory storage unit and configured to perform the following operations;

defining an edge line segment of the building in the aerial image, the edge line segment having a starting point of three-dimensional coordinates and an end point of three-dimensional coordinates,

defining a vector according to the starting point and the end point,

calculating an edge line function corresponding to the edge line segment according to the vector,

calculating an edge curve function by projecting the edge line function onto the panoramic image according to the coordinate correlation,

defining an edge curve segment of the building in the panoramic image according to the edge curve function,

capturing a sub-image of the panoramic image to be a building texture of the building, the sub-image being under the edge curve segment, and

storing the building texture in the non-transitory storage unit.

2. The building texture extracting apparatus as claimed in claim 1, wherein the processor performs the following operations to define the edge curve segment of the building in the panoramic image:

defining a plurality of edge curve segment candidates of the building that are projected onto the panoramic image according a plurality of preset height values of the building and the edge curve function;

deriving an edge image by applying edge detection to the panoramic image;

calculating an approximation between each of the edge curve segment candidates and the edge image; and

choosing one of the edge curve segment candidates that has the largest approximation as the edge curve segment of the building in the panoramic image.

3. The building texture extracting apparatus as claimed in claim 2, wherein the edge detection is utilized to obtain a plurality of edge segments of the building in the panoramic image.

4. The building texture extracting apparatus as claimed in claim 3, wherein the edge detection comprises a binarization process so that each of a plurality of pixels comprised in the edge segments of the building is a binary value.

5. The building texture extracting apparatus as claimed in claim 1, wherein the aerial image has a first Global Positioning System (GPS) coordinate, the panoramic image has a second GPS coordinate, and the first GPS coordinate and the second GPS coordinate define the coordinate correlation.

6. A building texture extracting method for use in an electronic apparatus, the electronic apparatus comprising a non-transitory storage unit and a processor electrically connected to the non-transitory storage unit, the non-transitory storage unit being configured to store an aerial image and a panoramic image of a building, there being a coordinate correlation between the aerial image and the panoramic image, the building texture extracting method comprising the following steps of:

(a) enabling the processor to define an edge line segment of the building in the aerial image, the edge line segment having a starting point of three-dimensional coordinates and an end point of three-dimensional coordinates;

(a1) enabling the processor to define a vector according to the starting point and the end point;

(b) enabling the processor to calculate an edge line function corresponding to the edge line segment according to the vector;

(c) enabling the processor to calculate an edge curve function by projecting the edge line function onto the panoramic image according to the coordinate correlation;

(d) enabling the processor to define an edge curve segment of the building in the panoramic image according to the edge curve function;

(e) enabling the processor to capture a sub-image of the panoramic image to be a building texture of the building, the sub-image being under the edge curve segment; and

(f) enabling the processor to store the building texture in the non-transitory storage unit.

7. The building texture extracting method as claimed in claim 6, wherein the step (d) further comprises the following sub-steps of:

(d1) enabling the processor to define a plurality of edge curve segment candidates of the building that are projected onto the panoramic image according a plurality of preset height values of the building and the edge curve function;

(d2) enabling the processor to derive an edge image by applying edge detection to the panoramic image;

(d3) enabling the processor to calculate an approximation between each of the edge curve segment candidates and the edge image; and

(d4) enabling the processor to choose one of the edge curve segment candidates that has the largest approximation as the edge curve segment of the building in the panoramic image.

8. The building texture extracting method as claimed in claim 7, wherein the edge detection is utilized to obtain a plurality of edge segments of the building in the panoramic image.

9. The building texture extracting method as claimed in claim 8, wherein the edge detection comprises a binarization process so that each of a plurality of pixels comprised in the edge segments of the building is a binary value.

10. The building texture extracting method as claimed in claim 6, wherein the aerial image has a first GPS coordinate, the panoramic image has a second GPS coordinate, and the first GPS coordinate and the second GPS coordinate define the coordinate correlation.