Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A fractional differentiation and sparse representation technology, applied in the field of image recognition and target tracking, which can solve the problems of ignoring the influence of tracking accuracy, drift, and single feature selection.
Inactive Publication Date: 2017-03-22
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF2 Cites 11 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0002] At present, in the technical field of image recognition and target tracking, the feature selection for describing the target is relatively simple, and different features have different abilities to describe the target. The sharing and complementarity between different features can improve the performance of a single feature; and local The way of building a dictionary with overlapping blocks repeatedly calculates a l
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment 1
[0047] Specific embodiment 1, such as figure 1 As shown, a sparse representation tracking method based on fractional differentiation and multi-feature union, the specific steps are as follows:
[0048] Step 1, local block of the template image area
[0049] In order to track the target more accurately, the area of the template image is divided into 9 parts, namely sub-block 1 to sub-block 9, that is, the size of the target block is 30×30 pixels, and the size of sub-block 1 and sub-block 2 is 10×20 pixels. Sub-block 3 and sub-block 4 are 20 × 10 pixels, sub-block 5 is 10 × 10 pixels, sub-block 6, sub-block 7, sub-block 8 and sub-block 9 are 20 × 20 pixels, a total of 9 image sub-blocks are generated, and the extraction grayscale and HOG features such as figure 2 shown. The overlapping sub-blocks contain more information about the tracking target, and multiple calculations of this part of information will enhance the robustness of tracking.
[0050] Step 2, feature descri...
specific Embodiment 2
[0084] Specific embodiment 2, as another embodiment of the present invention, in step 1, the size of the target block is 30×30 pixels, and the target image area is divided into 5 blocks of equal size, that is, the size of the sub-block is 15×15 pixels , with a step size of 15 pixels, sub-block 1, sub-block 2, sub-block 3 and sub-block 4 equally divide the target block, each block has a size of 15×15 pixels, plus a sub-block with a size of 15×15 pixels in the center area , a total of 5 image sub-blocks are generated, such as Figure 5 As shown, the division method of step 2 is the same as that of step 1. The overlapping sub-blocks in the middle contain more information about the tracking target, and multiple calculations of this part of information will enhance the robustness of tracking.
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 provides a fractional differential-based multi-feature combined sparse representation tracking method. The method includes the following steps: in a frame of particle filtering, first, performing partitioning processing on a target image region, dividing the target region into 9 related and unequal subblocks according to the features of the target region, extracting the gray scale feature and HOG feature of each subblock, combining the two features to perform sparse representation on a target subblock, and also performing the same feature extraction and sparse representation on 8 adjacent regions around the target; then, adopting a nucleating accelerated neighbor gradient algorithm to jointly solve sparse coefficients of 9 candidate particles; and finally, regarding target blocks in different positions as different categories, utilizing a block of the same category as a candidate particle block and a representation coefficient in a dictionary to reconstruct the block, and building a likelihood function according to a reconstruction error to determine an optimal candidate particle, thereby realizing accurate tracking of a main target and 8 auxiliary targets.
Description
technical field [0001] The inventor relates to the technical field of image recognition and target tracking, especially a sparse representation tracking method based on fractional differentiation and multi-feature union. Background technique [0002] At present, in the technical field of image recognition and target tracking, the feature selection for describing the target is relatively simple, and different features have different abilities to describe the target. The sharing and complementarity between different features can improve the performance of a single feature; and local The way of building a dictionary with overlapping blocks repeatedly calculates a lot of background information, and the more times the background information is calculated, the greater the possibility of drift during the tracking process, which affects the real-time and robustness of the tracking; in the actual tracking target When , only the target subject is selected as the main target of trackin...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more