Depth-based image target region area extraction method
A technology of target area and extraction method, which is applied in image analysis, image data processing, instruments, etc., can solve the problems that the measurement surface is not parallel to the camera, the actual camera perspective projection model is not considered, and the area measurement result is inaccurate, etc.
Pending Publication Date: 2019-10-22
YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] The existing image area calculation method is to calculate the pixel area of the image area, and use the single depth of the object and camera parameters to obtain the proportional relationship between the actual scale and the pixel scale to obtain the real area area. This method does not take into account the perspective projection of the actual camera model, which simply assumes that the measurement surface is parallel to the camera
In fact, the measurement surface is often not parallel to the camera. Through single-point perspective projection mapping, the effect of near-large and far-small will be produced, which will lead to inaccurate area measurement results.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] see figure 1 , is a step diagram of a method for extracting the area of an image target area based on depth in the present application;
[0037] Depend on figure 1 It can be seen that the present application provides a method for extracting the area of an image target area based on depth, including:
[0038] S10: Calculate the number c of pixels in the target area; first, it is necessary to determine the total number of all pixels contained in the set target area through calculation, that is, the number c of pixels in the target area. Specifically, by figure 2 As shown, in a feasible embodiment, step S10 is specifically: in the entire image range, set the set of pixels belonging to the target area as T, at this time, assign a label to each pixel p located in the target area, and assign The entire image is traversed pixel by pixel. When a pixel with a mark is traversed, the pixel is recorded. Finally, the total number of marked pixels is c, that is, the number of...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a depth-based image target region area extraction method. The method comprises the steps of calculating a pixel number c of a target region; calculating the depth Z of the target area; calculating the real area S of the target area; the invention aims to provide a depth-based image target region area extraction method, the gravity center of a target region is calculated, the depth value of gravity center pixels is used to approximately represent the depth of the whole target region, and the area measurement error caused by a single-point perspective projection model ofan actual camera can be effectively reduced.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for extracting the area of an image target region based on depth. Background technique [0002] The existing image area calculation method is to calculate the pixel area of the image area, and use the single depth of the object and camera parameters to obtain the proportional relationship between the actual scale and the pixel scale to obtain the real area area. This method does not take into account the perspective projection of the actual camera The model simply assumes that the measurement surface is parallel to the camera. In fact, the measurement surface is often not parallel to the camera, and the single-point perspective projection mapping produces the effect that the near side is large and the far side is small, which will lead to inaccurate area measurement results. If the center of gravity of the target area is calculated and the depth value of the...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/62G06T7/66G06T7/50G06T7/80G01B11/28
CPCG06T7/62G06T7/66G06T7/50G06T7/80G01B11/28
Inventor 颜冰张恭源王山钱国超邹德旭彭兆裕马御棠代维菊洪志湖文刚龚泽威一
Owner YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST