Vehicular trailering assist system with automatic trailer recognition
US-2024157875-A1 · May 16, 2024 · US
US2016176343A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016176343-A1 |
| Application number | US-201414907852-A |
| Country | US |
| Kind code | A1 |
| Filing date | Aug 25, 2014 |
| Priority date | Aug 30, 2013 |
| Publication date | Jun 23, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Provided are a camera calibration device and a camera calibration system that can significantly reduce a burden on an operator associated with transport of calibration patterns or an operation of arranging calibration patterns in a calibration operation, and can significantly reduce the storage place for the calibration patterns. The device or system includes an image conversion unit 141 that converts an image captured by each camera based on a projection matrix for conversion into a bird's-eye viewpoint based on the initial parameters of each camera, thereby generating a converted image; an error evaluation unit 142 that calculates an error between a converted image of a reference camera selected from among the plurality of cameras and a converted image of a camera other than the reference camera; a projection matrix updating unit 143 that updates the projection matrix based on the error so that images of a common imaging area captured by the respective cameras match; and a camera parameter calculation unit 145 that calculates camera parameters including an external parameter related to the posture of each of the cameras with respect to the ground based on the updated projection matrix.
Opening claim text (preview).
1 . A camera calibration device for calibrating a plurality of cameras, which are mounted on a vehicle, configured to capture images of areas around the vehicle including a ground, and have a common imaging area, using at least three calibration patterns that are arranged in the common imaging area, the camera calibration device comprising: an image conversion unit configured to convert an image captured by each camera into an image of a bird's-eye viewpoint based on a predetermined projection matrix; an error evaluation unit configured to calculate an error between a converted image of the calibration patterns captured by a predetermined camera of the plurality of cameras and a converted image of the calibration patterns captured by another camera that shares the common imaging area with the predetermined camera; a projection matrix updating unit configured to update the predetermined projection matrix based on the error; a distance information input unit configured to receive information on a distance between two given calibration patterns of the calibration patterns; and a camera parameter calculation unit configured to decompose the projection matrix in which the error calculated by the error evaluation unit becomes zero into a normal vector to the around in each of the converted images and a relative external parameter of each camera, and calculate camera parameters including an external parameter related to a posture of each camera with respect to the ground from the normal vector to the ground, the relative external parameter of each camera, and the information on the distance received by the distance information input unit. 2 . The camera calibration device according to claim 1 , further comprising a rotation amount input unit configured to receive a relative rotation amount of the vehicle with respect to the ground, wherein the camera parameter calculation unit is configured to calculate the camera parameters by taking into consideration the rotation amount received by the rotation amount input unit. 3 . A camera calibration device for calibrating a plurality of cameras, which are mounted on a vehicle, configured to capture images of areas around the vehicle including a ground, and have a common imaging area, using feature points of an object that is present in the common imaging area, the camera calibration device comprising: an image conversion unit configured to convert an image captured by each camera into an image of a bird's-eye viewpoint based on a predetermined projection matrix; an error evaluation unit configured to calculate an error between a converted image of the object captured by a predetermined camera of the plurality of cameras and a converted image of the object captured by another camera that shares the common imaging area with the predetermined camera; a projection matrix updating unit configured to update the predetermined projection matrix based on the error; a distance information input unit configured to receive information on a distance between two given points of the object; and a camera parameter calculation unit configured to decompose the projection matrix in which the error calculated by the error evaluation unit becomes zero into a normal vector to the ground in each of the converted images and a relative external parameter of each camera, and calculate camera parameters including an external parameter related to a posture of each camera with respect to the ground from the normal vector to the ground, the relative external parameter of each camera, and the information on the distance received by the distance information input unit. 4 . The camera calibration device according to claim 3 , further comprising a rotation amount input unit configured to receive a relative rotation amount of the vehicle with respect to the ground, wherein the camera parameter calculation unit is configured to calculate the camera parameters by taking into consideration the rotation amount received by the rotation amount input unit. 5 . A camera calibration method for calibrating a plurality of cameras, which are mounted on a vehicle, configured to capture images of areas around the vehicle including a ground, and have a common imaging area, using at least three calibration patterns that are arranged in the common imaging area, the camera calibration method comprising: converting an image captured by each camera into an image of a bird's-eye viewpoint based on a predetermined projection matrix; calculating an error between a converted image of the calibration patterns captured by a predetermined camera of the plurality of cameras and a converted image of the calibration patterns captured by another camera that shares the common imaging area with the predetermined camera; updating the predetermined projection matrix based on the error; and decomposing the projection matrix in which the error becomes zero into a normal vector to the ground in each of the converted images and a relative external parameter of each camera, and calculating camera parameters including an external parameter related to a posture of each camera with respect to the ground from the normal vector to the ground, the relative external parameter of each camera, and information on a distance between two given calibration patterns of the calibration patterns. 6 . A camera calibration method for calibrating a plurality of cameras, which are mounted on a vehicle, configured to capture images of areas around the vehicle including a ground, and have a common imaging area, using a feature object that is present in the common imaging area, the camera calibration method comprising: converting an image captured by each camera into an image of a bird's-eye viewpoint based on a predetermined projection matrix; calculating an error between a converted image of the feature object captured by a predetermined camera of the plurality of cameras and a converted image of the feature object captured by another camera that shares the common imaging area with the predetermined camera; updating the predetermined projection matrix based on the error; and decomposing the projection matrix in which the error becomes zero into a normal vector to the ground in each of the converted images and a relative external parameter of each camera, and calculating camera parameters including an external parameter related to a posture of each camera with respect to the ground from the normal vector to the ground, the relative external parameter of each camera, and information on a distance between two given points of the feature object.
Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title
Linear translation of whole images or parts thereof, e.g. panning · CPC title
Vehicle exterior; Vicinity of vehicle · CPC title
Image quality inspection · CPC title
Physics · mapped topic
Related publications grouped by family.
Answers are generated from the same data shown on this page.