Natural scene-based vehicle body look-around camera self-calibration method and system based on a natural scene

A natural scene, self-calibration technology, applied in image data processing, instruments, 3D modeling, etc., can solve problems such as wrong results, long time consumption, and easy to find image feature points, and achieve high-precision results

Pending Publication Date: 2020-01-10
的卢技术有限公司
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the self-calibration method based on a specific calibration object needs to use a specific calibration object, usually a checkerboard, and requires the cooperation of specific personnel. The calibration steps are complicated and take a long time; When , the image feature points are easy to find, and due to the small number of matching points, the accuracy of the camera transformation result is not high; the self-calibration method based on the lane line is too dependent on the lane line on the road. will produce wrong results

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Natural scene-based vehicle body look-around camera self-calibration method and system based on a natural scene
  • Natural scene-based vehicle body look-around camera self-calibration method and system based on a natural scene
  • Natural scene-based vehicle body look-around camera self-calibration method and system based on a natural scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] refer to Figure 1~3 The schematic diagram shows that this embodiment proposes a self-calibration method for the car body surround-view camera based on natural scenes. This method is based on the natural scene-based self-calibration method for the car body surround-view camera. It is mainly based on SLAM real-time positioning and mapping technology. Point information, combined with tools such as wheel odometer or GPS odometer, determines the trajectory of the camera movement, builds a global consistency map, and calculates the transformation matrix between adjacent cameras to complete the calibration of the surround-view camera. SLAM is the abbreviation of Synchronous Localization and Map Construction. SLAM is not so much an algorithm as it is a concept more appropriate. It is defined as solving the problem of "a robot starts from an unknown location in an unknown environment and passes repeated observations during the movement. Map features (such as wall corners, pilla...

Embodiment 2

[0101] refer to Figure 4~6 A self-calibration system for a car body surround-view camera based on a natural scene, characterized in that it includes an initial module 100, a camera odometer calibration module 200, a scene recovery module 300, a loopback detection module 400, a pose graph optimization module 500, and scene merging Module 600; where the initial module 100 is used to collect camera images and odometer data at each moment when the body is moving, and to obtain the initial pose and image internal feature point data of a single camera; the machine odometer calibration module 200 is used to calculate a single camera and the transformation matrix of the odometer; after the scene restoration module 300 is used to restore the coordinates of the scene point, the input loop detection module 400 is used to judge whether the vehicle has passed the historical position, that is, whether a loop occurs; the pose graph optimization module 500 is used to detect As a result, came...

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

No PUM Login to View More

Abstract

The invention discloses a vehicle body look-around camera self-calibration method and system based on a natural scene. The method comprises the following steps: a vehicle carrying a look-around cameraruns in a calibration scene; the initial module is used for carrying out initial pose estimation and data acquisition on the look-around camera arranged on the vehicle body; a camera odometer calibration module calculates a transformation matrix of a single camera and an odometer in combination with the initial pose estimated by the initial module and the acquired odometer data; and the scene merging module merges scene points of different cameras, completes the construction of a map, and calculates a transformation matrix between adjacent cameras. The vehicle body look-around camera self-calibration method based on the natural scene provided by the invention has the beneficial effects that firstly, the vehicle body look-around camera self-calibration method based on the natural scene does not depend on any other calibration object, and only one area needs to be randomly selected as a calibration area before calibration;

Description

technical field [0001] The present invention relates to the technical field of multi-camera calibration technology, in particular to a self-calibration method and system for a car body surround-view camera based on natural scenes. Background technique [0002] In recent years, the existing calibration methods are mainly divided into three types: the self-calibration method based on a specific calibration object, generally a checkerboard; the self-calibration method based on feature points, which finds the corresponding feature points between adjacent images to calculate the transformation matrix between cameras; The self-calibration method of lane lines calculates the transformation matrix between cameras. However, the self-calibration method based on a specific calibration object needs to use a specific calibration object, usually a checkerboard, and requires the cooperation of specific personnel. The calibration steps are complicated and take a long time; When , the image...

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
no application Login to View More
IPC IPC(8): G06T7/80G06T17/00
CPCG06T7/80G06T17/00G06T2207/30252G06T2207/10004Y02T10/40
Inventor赵杰
Owner的卢技术有限公司