Method and device for image depth estimation
An image depth and image technology, applied in the field of image depth estimation methods and devices, can solve the problems of large labor cost, time cost, time-consuming and labor-intensive, etc., and achieve the effect of cost saving
Active Publication Date: 2021-07-02
BEIJING SHENRUI BOLIAN TECH CO LTD +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The above method requires a large number of images with depth labels for training. Therefore, whether it is collected by radar or infrared equipment or manually labeled, it will consume a lot of labor and time costs, making the existing image depth estimation methods Time-consuming and labor-intensive
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
[0043] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0044] In order to solve the problem in the existing technology, a large number of images with depth labels are required for training, and whether it is collected by radar or infrared equipment or manually marked, it will consume a lot of labor and time costs, making the existing Image depth estimation method is time-consuming and labor-intensive.
[0045] The present applicat...
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 present application discloses an image depth estimation method. The method extracts information from the image to be estimated and the corresponding current depth map, uses the extracted information as current image reconstruction information, and uses the target image reconstruction model and the current image reconstruction information to estimate Reconstruct the image, obtain the reconstructed image and the corrected depth map, use the corrected depth map as the current depth map, return to the step of extracting information from the image to be estimated and the current depth map, until the preset number of iterations is reached, when the preset number of iterations is reached The obtained corrected depth map is used as the result of image depth estimation for the image to be estimated. In the technical solution of this application, only one image to be estimated is needed to estimate the depth of the image, and there is no need to train a large number of images with depth labels to obtain the depth estimation model and then estimate the depth of the image, which greatly saves data. The cost of collection and manual labeling saves time and effort.
Description
technical field [0001] The present application relates to the technical field of image depth estimation, and in particular to an image depth estimation method and device. Background technique [0002] At present, the image depth estimation method of monocular vision adopts a supervised method, for example: using radar or infrared equipment to collect images with depth labels or artificially marking images to obtain images with depth labels, and then using traditional machine learning Or the deep learning method is used to train images with depth labels to obtain a depth estimation model, and then use the depth estimation model to predict the depth of the image. The above method requires a large number of images with depth labels for training. Therefore, whether it is collected by radar or infrared equipment or manually labeled, it will consume a lot of labor and time costs, making the existing image depth estimation methods Time-consuming and labor-intensive. Contents 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 Patents(China)
IPC IPC(8): G06T7/50G06T11/00
CPCG06T11/005G06T7/50
Inventor 周振俞益洲李一鸣乔昕
Owner BEIJING SHENRUI BOLIAN TECH CO LTD