Method for fusing local shape feature structure and global shape feature structure of video image
A global feature and video image technology, applied to computer parts, instruments, characters and pattern recognition, etc., can solve problems such as inability to integrate structures, insufficient representation of a single feature, and inability to characterize shape and contour features more accurately.
Active Publication Date: 2012-07-25
广东和邦网络科技有限公司
View PDF2 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the insufficient representation of a single feature, the representation of the shape is diverse, and the unique discriminant characteristics of the shape can be mined from multiple perspectives, while the multi-feature is difficult to integrate from the structure, resulting in inaccurate feature representation.
In this case, the current method cannot carry out the structural fusion of features, and thus cannot characterize the shape and contour features more accurately.
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
[0037] The method for fusing local and global feature structures of shapes in a video image of the present invention includes the following steps:
[0038] Step 1. Use the shape contour context to describe the local features of the shape, and use the contour point distribution histogram to describe the global features of the shape. There are many methods for local and global feature representation. The features that can fully express the point distribution of the contour space are the shape context description local point feature and the contour point distribution histogram, because it not only considers the relative distance, but also considers the relative angle when describing the feature. .
[0039] The specific method is:
[0040] Let I be the shape contour image, I(x, y) is the pixel value of I at the coordinates (x, y), x and y represent the horizontal and vertical coordinates of the point, c(x, y) is the center of gravity of I, x c And y c These are the horizontal and vertic...
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 method for fusing a local shape feature structure and a global shape feature structure of a video image. The method comprises the following steps: describing a local shape feature by adopting a shape contour context, describing a global shape feature by adopting a contour point distribution histogram, measuring a local shape feature structure and a global shape feature structure by adopting the x<2> measure, fusing and mapping the local shape feature structure and the global shape feature structure by adopting the matrix spectrum optimization and solution method, and obtaining the feature representation. The method fills the blank of the prior art and can obtain the feature representation having strong classifying and distinguishing capacity and no unsupervised clustering.
Description
Technical field [0001] The invention belongs to the field of video surveillance image processing, and specifically relates to a method for fusing local and global feature structures of shapes in a video image. Background technique [0002] In recent years, there have been more and more applications of intelligent video surveillance systems based on content analysis. To achieve intelligent analysis and recognition of video surveillance images, shape representation and cognition are important issues that need to be resolved. Insufficient characterization of a single feature makes the characterization of shapes diversified. Multi-features can mine the unique discriminative characteristics of shapes from multiple perspectives, but it is difficult to merge multiple features from the structure, resulting in inaccurate characterization of features. In this case, the current method cannot perform feature structure fusion, and thus cannot more accurately characterize the shape and contour...
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): G06K9/62
Inventor 蔺广逢朱虹范引娣范彩霞张二虎
Owner 广东和邦网络科技有限公司