Method for constructing object three-dimensional contour based on vehicle-mounted monocular focusing sequence image
A technology of sequential images and three-dimensional contours, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as low efficiency, difficulty in achieving high precision, and laborious
Pending Publication Date: 2019-10-08
TAIYUAN UNIV OF TECH
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006]
The technical problem to be solved by the present invention is: how to change and solve the shortcomings of time-consuming, laborious, low-efficiency, and difficult to achieve high-precision three-dimensional reconstruction of objects in the existing intelligent driving field, so as to provide a method that can realize fast and high-precision reconstruction A system of three-dimensional contours of objects
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
[0020] The present invention designs a method for measuring the surface profile of an object based on image processing. The steps of the method include: the vehicle carries a photographing unit that moves along the extending direction of the object, and takes an image of the object every Δt time, so that Acquire a sequence of images of the target object within a period of time; perform image processing on all the sequence images captured by the shooting unit, and perform cropping and transformation on the image to remove some irrelevant background areas outside the measurement area of the target object in the sequence image, and obtain preprocessing Sequence image; extract the clear pixels of each frame of the pre-processing sequence image, calculate the focus factor of each pixel of the pre-processing sequence image, and calculate the corresponding image sequence number when all the pixels in the all-focus image reach the maximum focus factor, The depth distance Δz between a...
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 technical field of automatic driving and object recognition in vehicle engineering, and solves the technical problems of time consumption, labor consumption, low efficiency and difficulty in achieving high precision of three-dimensional reconstruction of an object in the existing intelligent driving field. The method acquires sequence images of a target object througha shooting unit, processes the sequence images to obtain a preprocessed image sequence, extracts clear pixel points of each frame of the preprocessed sequence image, calculates a focusing factor of each pixel point of the preprocessed sequence image, obtains corresponding image serial numbers when all pixels in the full-focus image reach the maximum focusing factor, calculates the depth distance [Delta]z between the adjacent sequence images according to the product of the real-time vehicle speed v and [Delta]t, takes [Delta]z as a depth value of a corresponding pixel point, and calculates coordinates of a corresponding point on a pixel coordinate system and a world coordinate system according to a result calibrated by a Zhang Zhengyou calibration method, thereby performing three-dimensional reconstruction through a two-dimensional image sequence, and reconstructing a three-dimensional contour of the target object.
Description
technical field [0001] The invention belongs to the field of automatic driving and object recognition technology in vehicle engineering, in particular to an automatic three-dimensional model building system for vehicle-mounted objects that builds three-dimensional contours of objects based on image processing. Background technique [0002] At present, the main solutions for realizing 3D reconstruction of objects in the field of intelligent driving include vision and lidar. Among them, vision is to use the camera to obtain the surface information of the object. According to the number of cameras, it can be divided into monocular vision and binocular vision. Monocular vision is to use structured light to emit a known pattern. After the camera receives the pattern reflected by the surface of the object, it calculates the difference from the original pattern through image processing, thereby realizing three-dimensional reconstruction. Binocular vision is based on the parallax p...
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): G06T17/20G06T7/45G06T7/579G06T7/571
CPCG06T17/20G06T7/45G06T7/579G06T7/571G06T2207/10016
Inventor 董志国武肖搏刘建成张宇超
Owner TAIYUAN UNIV OF TECH