University of Southern California

Chevron U.s.a. Inc.

Ulrich Neumann

Suya You

Jing Huang

Guan Pang

Christopher Lee Fisher

Amir Anvar

Luciano Nocera

Michael Brandon Casey

Lu Wang

Sang Yun Lee

Bolan Jiang

Rongqi Qiu

A method of detecting objects in three-dimensional (3D) point clouds and detecting differences between 3D point clouds and the objects therein is disclosed. A method includes receiving a first scene 3D point cloud and a second scene 3D point cloud, wherein the first scene 3D point cloud and the second scene 3D point cloud include first and second target objects, respectively; aligning the first scene 3D point cloud and the second scene 3D point cloud; detecting the first and second target objects from the first scene 3D point cloud and the second scene 3D point cloud, respectively; comparing the detected first target object with the detected second target object; and identifying, based on the comparison, one or more differences between the detected first target object and the detected second target object. Further aspects relate to detecting changes of target objects within scenes of multiple 3D point clouds.

Multi-view 3D object recognition from a point cloud and change detection

A scene point cloud is processed and a solution to an inverse-function is determined to determine its source objects. A primitive extraction process and a part matching process are used to compute the inverse function solution. The extraction process estimates models and parameters based on evidence of cylinder and planar geometry in the scene. The matching process matches clusters of 3D points to models of parts from a library. A selected part and its associated polygon model is used to represent the point cluster. Iterations of the extraction and matching processes complete a 3D model for a complex scene made up of planes, cylinders, and complex parts from the parts library. Connecting regions between primitives and/or parts are processed to determine their existence and type. Constraints may be used to ensure a connected model and alignment of its components.

Three-dimensional point processing and model generation

A method and system of matching features in a pair of images using line signatures. The method includes determining a first similarity measure between a first line signature in a first image in the pair of images and a second line signature in a second image in the pair of images; determining a second similarity measure between the first line signature in the first image and a third line signature in the second image; comparing the first similarity measure with a first threshold value; comparing a difference between the first similarity and the second similarity with a second threshold value; and if the first similarity measure is greater than the first threshold value and the difference between the first similarity and the second similarity is greater than the second threshold value, the first line signature and the second line signature produce a match.

Image matching using line signature

A data visualization system may allow an untrained user to easily, rapidly, and unambiguously specify the content and format of a report about information. A user interface may present to a user and receive from the user a selection of a plurality of selectable visualization types, selectable data objects, and selectable data specifications. The user interface may display all of the selections which the user makes as a single composite phrase.

Phrase-driven grammar for data visualization

Systems and techniques to implement augmented virtual environments. In one implementation, the technique includes: generating a three dimensional (3D) model of an environment from range sensor information representing a height field for the environment, tracking orientation information of image sensors in the environment with respect to the 3D model in real-time, projecting real-time video from the image sensors onto the 3D model based on the tracked orientation information, and visualizing the 3D model with the projected real-time video. Generating the 3D model can involve parametric fitting of geometric primitives to the range sensor information. The technique can also include: identifying in real time a region in motion with respect to a background image in real-time video, the background image being a single distribution background dynamically modeled from a time average of the real-time video, and placing a surface that corresponds to the moving region in the 3D model.

Modeling and video projection for augmented virtual environments

Methods and systems for tracking camera pose using dynamically calibrated line features for augmented reality applications are disclosed. The dynamic calibration of the line features affords an expanded tracking range within the real environment and into adjacent, un-calibrated areas. Line features within a real environment are modeled with a minimal representation, such that they can be efficiently dynamically calibrated as a camera pose changes within the environment. A known camera pose is used to initialize line feature calibration within the real environment. Parameters of dynamically calibrated line features are also used to calculate camera pose. The tracking of camera pose through a real environment allows insertion of virtual objects into the real environment without dependencies on pre-calibrated landmarks.

Extendable tracking by line auto-calibration

An augmented reality tool makes use of autocalibrated features for rendering annotations into images of a scene as a camera moves about relative to the scene. The autocalibrated features are used for positioning the annotations and for recovery of tracking, correspondences and camera pose. An improved method of autocalibration for autocalibrating structured sets of point features together is also described. The augmented reality tool makes use of manual, semi-automatic and automatic methods employing autocalibrated features.

Growing community of inventors

Manhattan Beach, CA, United States of America

Ulrich Neumann