Country
Full text data for US and EP
Status
Type
Filing Date
Publication Date
Inventor
Assignee
Click to expand
IPC
No.
Publication Number
Title
Publication/Patent Number Publication/Patent Number
Publication date Publication date
Application number Application number
Filing date Filing date
Inventor Inventor
Assignee Assignee
IPC IPC
1
US10198858B2
Publication/Patent Number: US10198858B2
Publication date: 2019-02-05
Application number: 15/470,863
Filing date: 2017-03-27
Assignee: 3Dflow Srl
Abstract: A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting the images; extracting keypoints therefrom and generating keypoint descriptors; organizing the images in a proximity graph; pairwise image matching and generating keypoints connecting tracks according maximum proximity between keypoints; performing an autocalibration between image clusters to extract internal and external parameters of the acquisition devices, wherein calibration groups are defined that contain a plurality of image clusters and wherein a clustering algorithm iteratively merges the clusters in a model expressed in a common local reference system starting from clusters belonging to the same calibration group; and performing a Euclidean reconstruction of the object as a sparse 3D point cloud based on the extracted parameters. A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting ...more ...less
2
US2018276885A1
Publication/Patent Number: US2018276885A1
Publication date: 2018-09-27
Application number: 15/470,863
Filing date: 2017-03-27
Assignee: 3Dflow Srl
Abstract: A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting the images; extracting keypoints therefrom and generating keypoint descriptors; organizing the images in a proximity graph; pairwise image matching and generating keypoints connecting tracks according maximum proximity between keypoints; performing an autocalibration between image clusters to extract internal and external parameters of the acquisition devices, wherein calibration groups are defined that contain a plurality of image clusters and wherein a clustering algorithm iteratively merges the clusters in a model expressed in a common local reference system starting from clusters belonging to the same calibration group; and performing a Euclidean reconstruction of the object as a sparse 3D point cloud based on the extracted parameters. A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting ...more ...less
3
EP3382645A2
Publication/Patent Number: EP3382645A2
Publication date: 2018-10-03
Application number: 18163990.7
Filing date: 2018-03-26
Assignee: 3Dflow srl
Abstract: Method for generating a 3D model of an object of interest (1, 404), which method comprises the following steps: Structure from Motion processing of a plurality of sparse images acquired by one or more acquisition devices (2, 402) for generating a sparse 3D point cloud and a plurality of internal and external parameters of the acquisition devices (2, 402) obtained by processing said images, obtaining, from the sparse 3D point cloud and from the internal and external parameters of the acquisition devices, by multiview stereo processing, a dense 3D point cloud for said generation of the 3D model. The method provides the reconstruction of the surface of said object of interest (1, 404) by the following steps: a) illuminating the object of interest (1, 404) from different directions (501); b) acquiring the plurality of images from a single point of view (502), each image corresponding to a different lighting direction; c) automatically recognizing the lighting direction for each acquired image; d) calculating the vector field of the surface normals; e) calculating the albedo of the observed surface; f) reconstructing the orientation of the surface. Method for generating a 3D model of an object of interest (1, 404), which method comprises the following steps: Structure from Motion processing of a plurality of sparse images acquired by one or more acquisition devices (2, 402) for generating a sparse 3D point cloud and a ...more ...less
4
EP3382644A1
Publication/Patent Number: EP3382644A1
Publication date: 2018-10-03
Application number: 18164011.1
Filing date: 2018-03-26
Assignee: 3Dflow srl
Abstract: A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting the images; extracting keypoints therefrom and generating keypoint descriptors; organizing the images in a proximity graph; pairwise image matching and generating keypoints connecting tracks according maximum proximity between keypoints; performing an autocalibration between image clusters to extract internal and external parameters of the acquisition devices, wherein calibration groups are defined that contain a plurality of image clusters and wherein a clustering algorithm iteratively merges the clusters in a model expressed in a common local reference system starting from clusters belonging to the same calibration group; and performing a Euclidean reconstruction of the object as a sparse 3D point cloud based on the extracted parameters. A method based on Structure from Motion for processing a plurality of sparse images acquired by one or more acquisition devices to generate a sparse 3D points cloud and of a plurality of internal and external parameters of the acquisition devices includes the steps of collecting ...more ...less
5
EP3382645A3
Publication/Patent Number: EP3382645A3
Publication date: 2018-12-19
Application number: 18163990.7
Filing date: 2018-03-26
Assignee: 3Dflow srl
Abstract: Method for generating a 3D model of an object of interest (1, 404), which method comprises the following steps: Structure from Motion processing of a plurality of sparse images acquired by one or more acquisition devices (2, 402) for generating a sparse 3D point cloud and a plurality of internal and external parameters of the acquisition devices (2, 402) obtained by processing said images, obtaining, from the sparse 3D point cloud and from the internal and external parameters of the acquisition devices, by multiview stereo processing, a dense 3D point cloud for said generation of the 3D model. The method provides the reconstruction of the surface of said object of interest (1, 404) by the following steps: a) illuminating the object of interest (1, 404) from different directions (501); b) acquiring the plurality of images from a single point of view (502), each image corresponding to a different lighting direction; c) automatically recognizing the lighting direction for each acquired image; d) calculating the vector field of the surface normals; e) calculating the albedo of the observed surface; f) reconstructing the orientation of the surface. Method for generating a 3D model of an object of interest (1, 404), which method comprises the following steps: Structure from Motion processing of a plurality of sparse images acquired by one or more acquisition devices (2, 402) for generating a sparse 3D point cloud and a ...more ...less
6
US9245200B2
Publication/Patent Number: US9245200B2
Publication date: 2016-01-26
Application number: 14/068,437
Filing date: 2013-10-31
Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values. An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected ...more ...less
7
US2014161359A1
Publication/Patent Number: US2014161359A1
Publication date: 2014-06-12
Application number: 14/068,437
Filing date: 2013-10-31
Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values. An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected ...more ...less
8
ITVI20120303A1
Publication/Patent Number: ITVI20120303A1
Publication date: 2014-05-10
Application number: VI20120303
Filing date: 2012-11-09
IPC: