Image super-resolution method and device based on rotation of depth camera
A depth camera and super-resolution technology, applied in the field of image processing, can solve the problems of sub-pixel displacement image super-resolution effect is not very ideal, difficult to realize accurately, backhaul error, etc., to achieve a simple solution, improve the effect, and not easy to data virtual scene Effect
Inactive Publication Date: 2019-10-18
TSINGHUA UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The lateral sub-pixel displacement scheme requires continuous fine translation, which is difficult to achieve accurately in actual application scenarios, and mechanical errors such as backhaul errors are unavoidable in mechanical components, resulting in the current sub-pixel displacement image super-resolution effect is not very good ideal
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
[0015] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the present invention Examples, not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0016] In one embodiment of the present invention, refer to figure 1 , provide an image super-resolution method based on depth camera rotation, including: S11, rotate the depth camera, obtain a low-resolution image sequence based on the rotation of the depth camera; S12, perform super-resolution on the low-resolution image, and obtain super-resolution High-resolution images, and super-re...
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 an image super-resolution method and an image super-resolution device based on the rotation of a depth camera. The method comprises the steps of acquiring a low-resolution imagesequence based on the rotation of the depth camera, and performing super-resolution on the low-resolution image sequence by adopting an image degradation model or a convolutional neural network modelto acquire a super-resolution image, namely, a high-resolution image with the resolution improved after super-resolution. In the super-resolution process, a low-resolution image sequence is obtainedin a rotating mode. The translation is not needed in the rotating process. Rotating actions are not cross-linked, return errors are not generated, data virtual scenes are not likely to be generated, the rotating scheme is simple, a complex translation device does not need to be designed, and the ideal super-resolution effect can be achieved in a simple rotating mode.
Description
technical field [0001] The present invention relates to the technical field of image processing, and more particularly, to an image super-resolution method and device based on depth camera rotation. Background technique [0002] 3D imaging technology is the process of reproducing the objective world through sensors, and has been widely used in various fields such as remote sensing mapping, unmanned driving, automated workshops, and medicine. Among them, the depth image is an important three-dimensional image. Applications in human-computer interaction, robot vision and three-dimensional scene reconstruction all rely on high-quality depth images. [0003] Existing methods for acquiring 3D images include binocular vision systems, structured light systems, or depth cameras based on time of flight (Ttime of Flight, TOF) technology. Among them, the binocular vision system has the disadvantages of low long-distance imaging accuracy, needing calibration points for imaging, and bei...
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 IPC IPC(8): G06T3/40
CPCG06T3/4053
Inventor 王飞巩马理
Owner TSINGHUA UNIV