Video concerning object segmenting method and device for hierarchical time domain segmentation
A technology that focuses on objects and layering, applied in the field of image processing, can solve problems such as segmentation processing that cannot be automated
Active Publication Date: 2018-08-28
BEIHANG UNIV
View PDF5 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the existing attention object segmentation methods require manual participation, and the segmentation parameters are designed according to each research goal and the obtained target characteristics, so as to divide the image to be processed into different levels of superpixel blocks or image blocks. Segmentation methods are not yet capable of fully automated segmentation processing
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
[0056] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0057] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects and not necessarily Describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances ...
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 video concerning object segmenting method and device for hierarchical time domain segmentation. A Frame image sequence can be obtained through videos to be processed. Iteration N times parity dividing is conducted on the frame image sequence, obtaining 2N sub-frame sequences, wherein the parity dividing means that the frame image of odd number sequence in each parent sequence to be divided is determined as an odd number frame sequence, and the frame image of even number sequence can be determined as an even number frame sequence, and 2N sub-frame sequence is an odd number frame sequence and an even number frame sequence, obtained from the iteration Nth parity dividing (N is an integer, more than or equal to 1). Based on the 2N sub-frame sequences, co-dividing sequence pairs in the number of 2N-1 can be obtained, and each co-dividing sequence pair includes two sub-frame sequences. Based on the preset co-dividing model and the co-dividing sequence pair, dividingimages of each frame image aiming at the concerning object can be obtained. Accordingly, the automatic video hierarchical dividing can be realized, and the concerning objects can be rapidly segmented.
Description
technical field [0001] The present invention relates to image processing technology, in particular to a video attention object segmentation method and device for hierarchical time domain segmentation. Background technique [0002] In the technology related to video content understanding, in order to simulate the visual attention characteristics of human beings and realize the machine's object tracking, scene reconstruction and video retrieval operations on the attention objects in the video, it is necessary to automatically detect and segment the attention objects in the video. [0003] Since videos and images are similar to a certain extent, the analysis of video content in the prior art is usually converted into the understanding of single frame image content and coupled with the constraints of temporal and spatial continuity between frames. The existing attention object segmentation method usually divides the image to be processed into superpixel blocks or image blocks of...
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): G06T7/10
CPCG06T7/10G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20221
Inventor 李甲苑鹏程谷大鑫赵沁平
Owner BEIHANG UNIV