Relative Depth Estimation Method of Underwater Image Based on Semantic Information Constraint
An underwater image and depth estimation technology, which is applied in the field of computer vision, can solve the problems of unobvious edge contours and low accuracy of underwater image estimation, so as to enhance the ability to perceive details, improve the ability to perceive underwater stereoscopically, and optimize the local gradient relationship Effect
Active Publication Date: 2022-02-25
OCEAN UNIV OF CHINA
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problems of low relative depth estimation accuracy of existing underwater images and unclear edge contours, the present invention proposes a method for estimating relative depth of underwater images based on semantic information constraints , the method includes:
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
[0060] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0061] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should be noted that, in the case of no conflict, the embodime...
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 field of computer vision, and specifically relates to a method, system, and device for estimating relative depth of underwater images based on semantic information constraints, aiming to solve the problems of low relative depth estimation accuracy and unclear edge contours of existing underwater images. The method of the present invention includes: obtaining a monocular underwater image to be estimated as an input image; obtaining a predicted depth map corresponding to the input image through a trained relative depth map prediction model, and then obtaining the relative depth relationship of the underwater scene ; The relative depth map prediction model is constructed based on a deep convolutional neural network of encoding-decoding structure. The invention improves the estimation accuracy of the relative depth of the underwater image, and enhances the edge effect of the depth estimation.
Description
technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method, system and equipment for estimating the relative depth of an underwater image based on semantic information constraints. Background technique [0002] In recent years, due to the shortage of terrestrial resources, the exploration and development of marine resources has become increasingly important. Intelligent underwater robots have very high efficiency in underwater operations and play an indispensable role in the development and utilization of marine resources. Among them, for robot-based underwater monitoring, underwater operations, and underwater visual navigation tasks, it is very important to achieve visual depth estimation based on monocular underwater images, and it is also a prerequisite to ensure the safe execution of various tasks. [0003] Because the underwater environment has the characteristics of low visibility and geometric distortion, it is...
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): G06T7/50G06N3/04G06K9/62
CPCG06T7/50G06T2207/20081G06T2207/20084G06N3/045G06F18/214
Inventor 李坤乾王西亚宋大雷刘文杰
Owner OCEAN UNIV OF CHINA