Indoor Reality Inc.

University of California

Other

Videopression LLC

Signetron Inc.

Avideh Zakhor

Minghua Chen

Andrew R Neureuther

Philippe Schmid

Joseph Menke

Damian Mrowca

Zixian Zang

Peiran Gao

James Wong

Plamen Levchev

Soren Hein

Aaron Hallquist

Yong Liu

Richard Wang

Allan Gu

Eric Lee Turner

Ralph Neff

Phillippe Schmid

Methods for defining a building internal framework from external imagery are presented, the method including: receiving a number of raw images of a building; processing the number of raw images of the building to establish a number of facades; and determining the building internal framework for each of the number of facades. In some embodiments, the processing the number of raw images includes: for each of the number of façades, selecting a façade; selecting all IR thermography images corresponding with the selected façade; removing distortion from the selected IR thermography images; stitching the selected IR thermography images corresponding with the selected façade together to form a single façade image corresponding with the selected facade; correcting perspective distortion of the single facade image; cropping the single façade image; and receiving dimensions of an actual façade corresponding with the single façade image.

Methods and systems for determining building internal framework from external imagery

Methods for processing a 3D point cloud of a building into polygons using an electronic computing device are presented, the methods including: causing the electronic computing device to receive the 3D point cloud; causing the electronic computing device to segment the 3D point cloud into a number of facades; and causing the electronic computing device to generate a number of polygons representing the number of facades. In some embodiments, the causing the electronic computing device to segment the 3D point cloud into a number of facades includes: performing voxel downsampling operation on the 3D point cloud; calculating a point normal for every point in the voxel downsampled 3D point cloud; and performing region growing to find each of the number of facades.

3D point cloud processing

Methods for generating a floor plan from a building scan of a building using an electronic computing device are presented, the method including: causing the electronic computing device to receive the building scan; converting the building scan to a floor plan; and refining the floor plan to approximate the building. In some embodiments, the causing the electronic computing device to receive the building scan further includes: extracting information from an input file to obtain a representation of a number of rooms and walls corresponding with the building scan, where the information is selected from the group consisting of: a set of vertices, a set of triangles, and a set of rooms.

Methods for generating a floor plan from a building scan

Methods for detecting a windows in a building utilizing a building scan using an electronic computing device are presented, the methods including: causing the electronic computing device to receive the building scan; processing the building scan; detecting the windows based on no return transparency of portions of the building scan; and incorporating the detected windows into a 3D model corresponding with the building scan. In some embodiments, processing the building scan generates at least the following: a colored point cloud; a 2D floor plan of the building; and a walked path. In some embodiments, detecting the windows based on transparency of a portions of the building scan further includes: decomposing the colored point cloud into walls; rotating and pixilating the walls; extracting transparent features corresponding with the windows; and classifying and smoothing the transparent features corresponding with the windows.

Building scan window detection

Methods for indoor 3D surface reconstruction and 2D floor plan recovery by segmenting a number of objects and building structure elements from a building scan using an electronic computing device are presented, the methods including: causing the electronic computing device to capture the building scan, where the building scan includes a number of scan points; pre-processing scan data from the building scan; generating an octree and a 2.5D model from the pre-processed scan data; extracting interior and exterior volumes from the octree model and the 2.5D model; and meshing the extracted volumes to generate a 3D object geometry and a 3D building geometry, where the 3D object geometry corresponds with the number of objects and the 3D building geometry corresponds with the indoor 3D surface reconstruction of building structure elements.

Methods for indoor 3D surface reconstruction and 2D floor plan recovery utilizing segmentation of building and object elements

Methods for interior climate control of a building utilizing multimodal sensor positioning using an electronic mobile device are presented, the method including: causing the electronic mobile device to receive a building floor plan; generating a number of fingerprint databases corresponding with the building floor plan; determining positions of users each having a mobile electronic device in the building; receiving occupancy climate parameters; and adjusting interior climate control for a zone corresponding with users in the zone and occupation climate parameters. In some embodiments, generating a number of fingerprint databases further includes: performing a single walkthrough of the building with the mobile electronic device; gathering spatial sensor data corresponding with the mobile electronic device during the single walkthrough, where the spatial sensor data corresponds with any of images WiFi signal strength, Bluetooth signal strength, and/or magnetic vector fingerprint captured along a path traversed during the walkthrough.

Interior climate control utilizing multimodal sensor positioning

Methods for detecting a number of luminary fixtures in an indoor environment using an electronic image capture device and electronic computing device are presented, the methods including: capturing a ceiling scan of the indoor environment with at least the electronic image capture device; analyzing a synthetic ceiling image corresponding with the ceiling scan using the electronic computing device to identify a number of luminary candidates; and converting the number of luminary candidates to define the number of luminary fixtures. In some embodiments, the capturing the ceiling scan further includes: moving the electronic image capture device through the indoor environment; capturing the indoor environment; generating a point cloud of the indoor environment; colorizing the point cloud; extracting the colored point cloud of a ceiling; dividing the extracted point cloud into a number of rooms; and generating the synthetic ceiling image for each of the number of rooms.

Methods for detecting luminary fixtures

Methods for image based localization using an electronic computing device are presented, the methods including: capturing a local image with an image capture device; associating metadata with the local image; causing the electronic computing device to receive the local image; causing the electronic computing device to match the local image with a database image, where the database image is three-dimensional (3D); and calculating a pose of the image capture device based on a pose of the database image and metadata associated with the local image. In some embodiments, the metadata includes at least pitch and roll data corresponding with the image capture device at a time of image capture.

Single image pose estimation of image capture devices

Multiple TRFC connections transport streaming data through a wireless channel, and the difference between measured round trip times of packets and minimum round trip time is used to adjust the number of TFRC connections to fully utilize bandwidth through the wireless channel.

Optimization of streaming data throughput in unreliable networks

Optical proximity correction (OPC) is a technique used to compensate for optical distortions, process effects, or both, by modifying a pattern that is used during lithography. A reference OPC model is used to create an OPC design layout pattern based on pre-distorting a desired design layout pattern associated with an integrated circuit (IC). The OPC design layout pattern is used when the IC is produced, such that the fabricated IC ideally matches the desired design layout pattern. The present invention relates to using a regression OPC model to create estimated fragment movements of the desired design layout pattern. The estimated fragment movements are then provided as initial fragment movements to the reference OPC model, which then creates the OPC design layout pattern. The initial fragment movements provided by the regression OPC model may reduce the number of iterations needed by the reference OPC model, thereby reducing computation time.

Optical proximity correction using regression

This invention relates to the creation of dictionary functions for the encoding of video signals using matching pursuit compression techniques. After an initial set of reference dictionary images is chosen, training video sequences are selected, and motion residuals are calculated. High energy portions of the residual images are extracted and stored when they match selection criteria with the reference dictionary. An energy threshold is used to limit the number of video signal 'atoms' encoded for each frame, thus avoiding the encoding of noise. A new dictionary is then synthesized from the stored portions of the image residuals and the original reference dictionary. The process can then be repeated using the synthesized dictionary as the new reference dictionary. This achieves low bit rate signals with a higher signal-to-noise ratio than have been previously achieved.

Dictionary generation method for video and image compression

An apparatus and method to compress a video signal uses a motion compensated DCT (Discrete Cosine Transform) type approach. However, instead of relying upon a DCT coder to process a motion residual signal, the motion residual signal is processed by a pattern marcher. The pattern marcher identifies regions in the motion residual signal that have not been accurately reproduced on account of image motion. Each of these regions is compared to a set of library patterns in a pattern library. The pattern marcher links each region with a selected library pattern, which accurately characterizes the region. The pattern matcher forms an atom parameter signal characterizing each selected library pattern. The atom parameter signal is transmitted as a compressed version of the video signal. After transmission, the video signal is reconstructed from the atom parameter signal. In particular, a pattern fetcher is used to interpret the atom parameter signal to identify the selected library patterns used to characterize the motion residual signal. The selected library patterns are combined with other information to reconstruct the video signal.

Method and apparatus for compression of low bit rate video signals

A method for making a mask for optical lithography or other projection printing, wherein the mask is represented by a mask pattern, is disclosed herein. The mask provides a substantially binary output image on the surface of a wafer as light is applied to the mask. Light passes through the mask and onto a wafer at varying intensities, such intensities represented by output intensity values, the threshold values of which produce output images within predetermined constraints. The method includes the steps of defining sampling points which are representative of the binary output image. These sampling points are used in defining local objective functions, which are combined to give a total objective function. The present invention further includes the steps of adjusting the mask pattern to provide for minimization by optimization of the objective function, transferring the mask pattern to a mask generating machine to generate a mask, and generating a mask. Moreover, the present invention includes the step of providing an output image which is focused on a plurality of optical planes. Furthermore, the present invention includes the step isolating three of the plurality of optical planes so that their output intensity is optimized at these planes, thereby producing a focusing plane shift at the center focal plane as well as producing an extended depth of focus.

Growing community of inventors

Berkeley, CA, United States of America

Avideh Zakhor