A weakly supervised video object segmentation method and device
A technology for object segmentation and weak supervision, applied in image analysis, image enhancement, instruments, etc., to avoid incompleteness, reduce manual calibration costs, and improve performance
Active Publication Date: 2021-09-24
SHANGHAI JIAOTONG UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to reduce the cost of manual calibration, how to avoid the introduction of irrelevant objects, and improve the performance of video object segmentation
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
[0046] The following describes several preferred embodiments of the present invention with reference to the accompanying drawings, so as to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned herein.
[0047] figure 1 It is a schematic flow chart of a weakly supervised video object segmentation method in a preferred embodiment of the present invention, including the following steps:
[0048] S01 constructs a video object segmentation model, and after inputting the first frame of the test video and the test object bounding box in the first frame, pre-trains the video object segmentation model based on an iterative algorithm;
[0049] In this embodiment, manual calibration is used to give the bounding box of the test object instead of a complete image mask, which significantly reduces the required ma...
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 discloses a weakly supervised video object segmentation method, which includes constructing a video object segmentation model, and after inputting the first frame of the test video and the bounding box of the test object, pre-training the video object segmentation model based on an iterative algorithm; The bounding box of the test object in each frame after the first frame is tracked; the pixel-level prediction is performed on each frame after the first frame of the test video, and the image mask containing the front and back background information of the current frame is generated; based on the tracking result, the image mask The code is optimized to obtain the final object segmentation calculation result of the current frame. The invention also discloses a weakly supervised video object segmentation device, which includes a weakly supervised video object segmentation pre-training module, a video object tracking module, a video object segmentation test module and a video object segmentation optimization module. The invention reduces the labor cost required for video object segmentation and improves the performance of video object segmentation.
Description
technical field [0001] The invention relates to the field of video processing in the direction of computer vision, in particular to a weakly supervised video object segmentation method and device. Background technique [0002] Video Object Segmentation (VOS) is one of the hot research issues in the field of computer video processing. Video object segmentation can generate an image mask containing the foreground and background information of the object for each frame in the video. The masks generated by the video object segmentation framework have a wide range of applications, such as video editing, autonomous driving, video surveillance, and video coding applications based on video content. At present, mainstream methods in this field include supervised (Supervised VOS), unsupervised (Unsupervised VOS), and semi-supervised (Semi-supervised VOS) video object segmentation frameworks. [0003] The supervised video object segmentation framework assumes human-labeled prior know...
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): G06T7/246G06T7/11
CPCG06T2207/20104G06T7/11G06T7/251
Inventor 张宗璞马汝辉华扬宋涛管海兵
Owner SHANGHAI JIAOTONG UNIV