Machine vision depth estimation method, device and system
A technology of depth estimation and machine vision, applied in instrumentation, computing, image analysis, etc., can solve problems such as holes in the depth map, and achieve the effect of accurate depth value estimation results
Pending Publication Date: 2021-06-25
HANGZHOU HIKROBOT TECH CO LTD
View PDF0 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] The invention provides a machine vision depth estimation method to solve the hole problem of the depth map in binocular vision based on structured light
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
[0117] In order to make the purpose, technical means and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings.
[0118] The present invention proposes to collect light information images through multiple sets of binocular cameras, fuse multiple frames in space, and perform depth restoration, so that the depth map is more complete, accurate, and dense, and the actual field of view is increased.
[0119] see figure 1 as shown, figure 1 It is a schematic diagram of the camera layout in the trinocular vision camera system based on projecting active structured light according to the embodiment of the present invention.
[0120] In this embodiment, in order to reduce the number of cameras and the complexity of image processing as much as possible, at least three cameras are included in the visual camera system, and the first camera and the second camera form a group of first bi...
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 machine vision depth estimation method, and the method comprises the steps: obtaining at least three view images, wherein the view images are obtained by at least two groups of binocular image obtaining devices which share the same image obtaining device; carrying out image three-dimensional correction on the view image; based on the binocular images from the at least two groups of binocular image acquisition devices in the view image after stereo correction, respectively carrying out stereo matching on each group of binocular images to obtain a depth value of each pixel in each group of binocular images; and for any pixel I in each group of binocular images, fusing the depth value of the pixel I in each group of binocular images to obtain the depth estimation value of the pixel I, wherein the I is a natural number not greater than the total number of pixels in the binocular images. According to the method, device and system, more information is obtained from multiple angles and multiple directions for depth estimation of the target scene, and the defects of object shielding, texture direction discomfort and the like are overcome.
Description
technical field [0001] The present invention relates to the field of machine vision, in particular, to a machine vision depth estimation method. Background technique [0002] Structured light is an optical projector that projects a certain pattern of light information on the surface of an object, and forms a three-dimensional map of light information modulated by the surface shape of the measured object on the surface. The three-dimensional map of light information is collected by the camera, and the position and depth of the object are calculated according to the change of the light signal caused by the object, and then the entire three-dimensional space is restored. [0003] At present, the depth estimation technology based on stereo vision is mainly the way of binocular camera collecting laser speckle, which is one of the ways based on projecting active structured light. But there are still some problems in the binocular camera vision system based on laser speckle: [0...
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): G06T7/593G06T7/80
CPCG06T7/596G06T7/80
Inventor 龙学雄李建禹
Owner HANGZHOU HIKROBOT TECH CO LTD