Semi-supervised single-target video segmentation method

A video segmentation and single-target technology, applied in neural learning methods, image analysis, image data processing, etc., can solve problems such as robustness, insufficient use of spatio-temporal information, etc., and achieve the effect of improving processing performance

Active Publication Date: 2021-09-03
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF26 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This idea is to match the current frame with the first frame target every time, there will be no cumulative error propagated frame by frame, and it will have better robustness, and the impact of occlusion will be reduced, even if the segmentation of the middle frame fails , and will not interfere with other frames, the disadvantage is that the spatio-temporal information is not fully utilized

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
  • Semi-supervised single-target video segmentation method
  • Semi-supervised single-target video segmentation method
  • Semi-supervised single-target video segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0037] The purpose of the present invention is for semi-supervised VOS, combined with the advantages of deep neural network in feature extraction, using the layer-by-layer nonlinear transformation of the network structure, training network weights, performing convolution pooling down-sampling through the improved U-net network and then Upsampling (encoder-decoder), returning to the shape of the original image, giving the prediction of each pixel, applying the segmentation result to the target tracking, and realizing the tracking of the target. And use the stochastic gradient descent algorithm (SGD) to optimize the loss. Based on the advantages of the adopted U-net network, by inputting the target image into the network for downsampling...

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

No PUM Login to view more

Abstract

The invention discloses a semi-supervised single-target video segmentation method, and belongs to the technical field of video target segmentation. According to the invention, the method comprises the steps: training the network weight based on layer-by-layer nonlinear transformation of a network structure, carrying out convolution pooling down-sampling through an improved U-net network, carrying out up-sampling, obtaining the shape of an original image, obtaining a target identification prediction value of each pixel, and obtaining a single-target video segmentation result of a search image of a corresponding template target object; and applying the obtained segmentation result to target tracking, so accurate positioning of the tracking target can be realized, and the target tracking processing performance is improved.

Description

technical field [0001] The invention relates to the technical field of video object segmentation, in particular to a semi-supervised single-object video segmentation method. Background technique [0002] With the rapid development of hardware, software and artificial intelligence, semantic segmentation has become one of the hot spots in the field of computer vision research and has been widely used. At present, image-based semantic segmentation can be done very well, but the effect is not good in the case of poor single-frame observation, occlusion, motion blur, poor lighting, etc., and the actual robot can continuously monitor the environment for a long time in the environment The observations have a lot of information redundancy in time. From the perspective of data fusion, a large amount of data redundancy can offset the noise in the observations. Therefore, in theory, using video for image or visual tasks should be better than a single frame. At present, this research d...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/10G06N3/04G06N3/08
CPCG06T7/10G06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/20132G06N3/048G06N3/045
Inventor 饶云波程奕茗薛俊民
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap