Unlock instant, AI-driven research and patent intelligence for your innovation.
Video target segmentation method and system based on full duplex strategy
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A target segmentation and full-duplex technology, applied in the field of video processing and computer vision, can solve the problem of limiting the interaction ability of intra-frame and inter-frame features, and achieve the effect of improving prediction performance and high robustness
Active Publication Date: 2021-11-02
NANKAI UNIV
View PDF8 Cites 0 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
In the video target segmentation task, the apparent information within the frame and the motion information between frames are two very important information sources. The early methods mainly use the solution based on the simplex strategy (that is, only use the apparent information or the motion information). schemes, but such methods limit the maximum ability of intra-frame and inter-frame feature interaction capabilities
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
Embodiment 1
[0052] Such as figure 1 As shown, this embodiment provides a video object segmentation method based on a full-duplex strategy. This embodiment uses this method as an example to illustrate the server. It can be understood that this method can also be applied to terminals, and can also be applied to It includes terminals, servers and systems, and is realized through the interaction between terminals and servers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can provide cloud services, cloud database, cloud computing, cloud function, cloud storage, network server, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security service CDN, and big data and artificial intelligence platforms. The terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, ...
Embodiment 2
[0101] This embodiment provides a video object segmentation system based on a full-duplex strategy.
[0102] A video object segmentation system based on a full-duplex strategy, including:
[0103] A preprocessing module, which is configured to: pass the video to be divided through an optical flow generator to obtain an optical flow graph;
[0104] A segmentation module configured to: input the appearance map and the optical flow map matched with the appearance map into the trained video target segmentation model to obtain a segmentation prediction map;
[0105] The model construction module is configured as follows: the video target segmentation model includes: sequentially connected ResNet50 skeleton network, cross-attention relationship module, bidirectional purification module and decoder in full-duplex mode.
[0106] The examples and application scenarios implemented by the above modules are the same as those in the first embodiment, but are not limited to the content dis...
Embodiment 3
[0108] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps in the video object segmentation method based on a full-duplex strategy as described in the first embodiment above are implemented.
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 belongs to the technical field of video processing and computer vision, and provides a video target segmentation method and system based on a full duplex strategy. The method comprises the following steps: enabling a to-be-segmented video to pass through an optical flow generator to obtain an optical flow graph; and inputting the apparent image and the optical flow image matched with the apparent image into a trained video target segmentation model to obtain a segmentation prediction image, wherein the video target segmentation model comprises a ResNet50 skeleton network, a cross attention relation module, a bidirectional purification module in a full duplex mode and a decoder which are connected in sequence. According to the method, the cross attention relation module is used for realizing bidirectional information transmission in a feature embedding space, and the bidirectional purification module in the bidirectional full duplex mode is used for updating the inconsistency in spatial-temporal feature embedding, so that the segmentation prediction performance of the model is effectively improved.
Description
technical field [0001] The invention belongs to the technical field of video processing and computer vision, and in particular relates to a video object segmentation method and system based on a full-duplex strategy. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Video object segmentation (Video Object Segmentation, VOS) is a basic field of video content understanding and intelligent analysis. Its task goal is to describe the moving foreground object in the video frame at the pixel level. This task has been widely used in many fields such as autonomous driving and human-computer interaction. In the video target segmentation task, the apparent information within the frame and the motion information between frames are two very important information sources. The early methods mainly use the solution based on the simplex strategy (that is, o...
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