A dynamic target tracking method based on medical imaging
A dynamic target and medical imaging technology, applied in the field of computer vision, can solve the problem of model deviation from the tracking target, and achieve the effects of eliminating the influence of local minimum values, facilitating judgment and segmentation, and intuitive tracking effects
Active Publication Date: 2022-07-05
TONGJI UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] There are also target tracking methods based on template matching, which can successfully detect and calibrate the target after selecting a suitable model, but if there is no specific modification adaptation, then the tracking is only reliable for a short time and without severe deformation. However, In most applications, the appearance of objects undergoes structurally significant changes over a long period of time due to viewpoint changes, deformations, or occlusions, and motion tracking-based methods can handle such appearance changes, however, the accumulated motion errors and fast The visual change of the model deviates from the tracking target
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 1
[0054] A dynamic target tracking method based on medical imaging, the target tracking scene is the movement trajectory of barium meal in the mouth and throat and the movement of tissues and organs, such as figure 1 shown, including: acquiring medical image video, manually initializing multiple tissue and organ targets and barium meal targets in the reference frame medical image or the first frame medical image; tracking the medical image video using discrete point tracking method and improved inter-frame difference method barium meal target; use the multi-target tracking method of KCF+DSST to track tissue and organ targets in medical imaging and video; the tracking results of the barium meal target and the tracking results of the tissue and organ targets are mutually corrected.
[0055] In order to facilitate subsequent processing, the dynamic target tracking method also includes image preprocessing for each frame of medical images after manually initializing multiple tissue an...
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 relates to a dynamic target tracking method based on medical imaging, comprising: acquiring medical image video, manually initializing multiple tissue and organ targets and barium meal targets in a reference frame medical image or a first frame medical image; The improved inter-frame difference method tracks barium meal targets in medical images and videos; uses KCF+DSST multi-target tracking method to track tissue and organ targets in medical images and videos; the tracking results of barium meal targets and the tracking results of tissue and organ targets are mutually corrected. Compared with the prior art, the present invention proposes discrete point tracking and an improved inter-frame difference method for the flowing barium meal; for the position calibration of tissues and organs with less deformation, the correlation filtering method of KCF+DSST and the corresponding method are proposed. Multi-target tracking; the tracking results of the barium meal target and the tissue and organ target are mutually corrected, which can further optimize the tracking accuracy, and the tracking effect is better.
Description
technical field [0001] The invention relates to the field of computer vision, in particular to a dynamic target tracking method based on medical imaging. Background technique [0002] In the field of computer vision research, moving target detection and tracking has always been the focus of scientific research. Moving target tracking on medical imaging video sequences is to determine the position and shape of the target in each frame. At present, the research on object tracking in medical images is mainly based on the results of medical image segmentation, such as segmentation methods based on threshold, region and edge. Existing studies have also proposed many object tracking methods for medical image processing and analysis. , such as point-based tracking, contour-based tracking, and kernel-based tracking techniques, which are widely used for motion tracking in medical images today. [0003] One tracking method is to select a frame as a reference image on a medical imagin...
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 Patents(China)
IPC IPC(8): G06T7/00G06T7/215G06T3/60G06T7/11
CPCG06T7/0012G06T7/215G06T3/60G06T7/11G06T2207/20104
Inventor 秦国锋
Owner TONGJI UNIV