Method and system for creating 3d model for digital twin from point cloud

A method for creating a computer-aided design (CAD) model from a point cloud representing a scene having one or several objects, the method comprises the steps of:

• acquiring or receiving the point cloud representing the scene having the one or several objects;
• using a segmentation algorithm (hereafter “SA”) configured for receiving as an input the point cloud, for detecting at least one of the one or several objects in the point cloud, and for outputting, for each object detected in the point cloud, an object type and a list of bounding boxes, wherein the object type is chosen among a set of one or several predefined object types that the SA has been trained to identify, wherein each bounding box of the list of bounding boxes defines a spatial location within the point cloud containing a set of points representing a detected object or a part of the detected object;
• receiving or acquiring one or several object families, wherein each object family contains a profile defined for a point cloud meshing algorithm, wherein the profile is configured for specifying a meshing technique to be used by the point cloud meshing algorithm when converting the point cloud representing the object belonging to the object family to a 3D surface, wherein each said object family contains one or several of the predefined object types so that each predefined object type be assigned to a single object family, and wherein each said object family is assigned to a different profile;
• for each said detected object, determining the object family to which its said object type belongs to, and then automatically creating the CAD model by running the point cloud meshing algorithm on the set of points assigned or associated to at least one of the bounding boxes of the list of bounding boxes, wherein the running includes using a meshing technique defined for the profile assigned to the object family to which the object type of the detected object belongs to for converting the set of points to the 3D surface of the CAD model;
• and
• automatically providing the CAD model created via an interface.

A method for providing, by a data processing system, a trained algorithm for detecting at least one object in a point cloud representing a scene and assigning, to each detected object, an object type chosen among a set of one or several predefined types and a list of bounding boxes, the method comprises the steps of:

• receiving input training data, wherein the input training data contains a plurality of point clouds, each representing a scene, each said scene having one or several objects;
• receiving output training data, wherein the output training data identifies, for each of the point clouds of the input training data, at least one object of the scene, and for each identified said object, associates to said object the object type chosen among the set of said one or several predefined types and the list of bounding boxes, wherein each bounding box of the list of bounding boxes defines a spatial location within a point cloud containing a set of points representing the object or a part of the object;
• training an algorithm based on the input training data and the output training data;
• and
• providing the trained algorithm.

A data processing system, comprising:

• a processor;
• and
• an accessible memory, the data processing system configured to:
• acquire or receive a point cloud representing a scene having one or several objects;
• use a segmentation algorithm (hereafter “SA”) configured for receiving as an input said point cloud, for detecting at least one of said one or several objects in said point cloud, and for outputting, for each detected object in the point cloud, an object type selected among a set of one or several predefined object types and a list of bounding boxes, wherein each bounding box of said list is configured for defining a spatial location within said point cloud having a set of points representing the detected object or a part of the detected object;
• define one or several object families, and for each of said object families, to define or create or store a profile defined for a point cloud meshing algorithm, wherein said profile is configured for specifying a meshing technique to be used by said point cloud meshing algorithm when converting said point cloud representing the object belonging to an object family to a 3D surface, wherein each of said object families contains one or several of said predefined object types so that each predefined object type be assigned to a single said object family, and wherein each of said object families is assigned to a different profile;
• for each said detected object, determine the object family to which its said object type belongs to, and then automatically create a computer-aided design (CAD) model by running said point cloud meshing algorithm on the set of points assigned or associated to the bounding box of said list of bounding boxes, wherein said running includes using the meshing technique defined for the profile assigned to the object family to which the object type of the detected object belongs to for converting said set of points to a 3D surface of the CAD model;
• and
• automatically provide a created said CAD model via an interface.

A non-transitory computer-readable medium encoded with executable instructions that, when executed, cause one or more data processing system to:

• acquire or receive a point cloud representing a scene containing one or several objects;
• use a segmentation algorithm (hereafter “SA”) configured for receiving as an input said point cloud, for detecting at least one of said one or several objects in said point cloud, and for outputting, for each detected object in said point cloud, an object type selected among a set of one or several predefined object types and a list of bounding boxes, wherein each bounding box of said list of bounding boxes is configured for defining a spatial location within said point cloud containing a set of points representing the detected object or a part of the detected object;
• define one or several object families, and for each object family, to define or create or store a profile defined for a point cloud meshing algorithm, wherein said profile is configured for specifying a meshing technique to be used by said point cloud meshing algorithm when converting the point cloud representing the object belonging to said object family to a 3D surface, wherein each said object family contains one or several of said predefined object types so that each predefined object type be assigned to a single said object family, and wherein each said object family is assigned to a different profile;
• for each said detected object, determine the object family to which its said object type belongs to, and then automatically create a computer-aided design (CAD) model by running the point cloud meshing algorithm on the set of points assigned or associated to the bounding box of said list of bounding boxes, wherein said running includes using the meshing technique defined for the profile assigned to the object family to which the object type of the detected object belongs to for converting said set of points to said 3D surface of the CAD model;
• and
• automatically provide a created said CAD model via an interface.