3D
Apple buys C3 Technologies
According to GPS Business News, Apple is buying C3 Technologies for $267 million. C3 Technologies is a Swedish company that provides 3D images of cities. It has vision technology to create 3D models from oblique camera systems without LIDAR.
3D modeling of royal burial sites by drone
Researcher Marijn Hendrickx of the University of Ghent uses a drone to build 3D models of archaeological sites. The 1 kg, 70 cm quadrocopter drone was able to map Scythian burial mounds in the area where Russia, China, Kazakhstan, and Mongolia meet; 3D models of the site were constructed from the images. More information is available at livescience.com.
Computer Vision Cinema
Computer Vision Cinema is a project at the Politecnic University of Valencia, Spain, on "research using computer vision tools and techniques to generate new audiovisual languages." The website has a blog reporting the progress of the project, which uses the Kinect, OpenCV, OpenNI, and Nite. The video below shows an automated camera turret.
Related articles:
3D facial analysis tracks each pixel
Researchers from Bath University, UK, have developed a method to build models of human faces without using physical markers. These models can be used to create more realistic facial animations. Computer vision algorithms track individual pixels in each frame of video with depth information. The 3D image is projected onto a cylinder, and then unwrapped similarly to the way world maps are drawn. This method allows subtle facial movements to be captured and replicated. There are applications in film, gaming, and security. More information is available in an article in The Engineer.
Yale University awarded grant for a neural theory of 3D shape perception
The U.S. National Science Foundation is awarding a two-year, $300,000 grant to Professor Steven Zucker of Yale University to investigate a neural theory of 3D shape perception. The grant is part of a U.S.-German collaboration. The abstract of the research is included below.
Abstract
How the brain estimates the 3D shape of objects in our surroundings remains one of the most significant challenges in visual neuroscience. The information provided by the retina is fundamentally ambiguous, because many different combinations of 3D shape, illumination and surface reflectance are consistent with any given image. Despite this ambiguity, the visual system is extremely adept at estimating 3D shape across a wide range of viewing conditions, something that no extant machine vision system can do. The long-term goal of the project is to develop a computational model in neural terms to explain how 3D shape is estimated in the primate visual system. It will build upon the responses of cells early in visual cortex (V1) and develop models of how they can be organized into mid-level configurations that specify 3D shape properties. Importantly, the project will also measure human perception of 3D shape in a series of psychophysical experiments designed to test specific predictions, bringing together the complementary expertise of Roland W. Fleming (Giessen University: human perception, psychophysics) and Steven W. Zucker (Yale University: computational vision, computational neuroscience). The results should provide a deeper understanding of visual circuit properties in the ventral processing stream; they should provide models for 3D computer vision and graphics; and they may pave the way for the development of rehabilitation strategies for patients with visual deficits.
3D eye tracking technology could boost augmented reality
SensoMotoric Instruments' (SMI) binocular eye-tracking glasses provide 3D eye-tracking data superimposed on high-definition (HD) scene camera video. SMI is promoting these glasses primarily for design of package displays, automobile cockpits, printed materials, and user interfaces; however, the eye-tracking technology holds potential for enabling truly immersive augmented reality (AR) applications. More information is available from SMI's press release.
NSF funds research on filling occlusions in point clouds
ClearEdge3D announced that is has been awarded a grant by the U.S. National Science Foundation (NSF) to investigate methods for improving the generation of 3D point clouds. According to the company, "due to the 'line of sight' limitations in laser scanning technology, there are always occluded regions of point cloud data that must be manually modeled. The core goal of the research grant is to devise algorithms that will automatically populate these occluded regions based on the feature pattern in the surrounding area."
OpenNI launches developer Arena for gesture-based apps and games
OpenNI.org, an industry organization of gesture-based and other advanced interfaces that use vision and audio sensors, has launched the OpenNI Arena at http://arena.openni.org/. The Arena allows developers to showcase apps and games based on natural interaction. OpenNI was founded by PrimeSense, the developer of the 3D sensor used in the Microsoft Kinect; WillowGarage, currently leading OpenCV development; Side-Kick; and Asus. OpenNI makes available an open-source framework with APIs to low-level vision and audio sensors and to high-level computer vision software (e.g., for tracking).
Related articles:
ClearEdge3D Ships EdgeWise Plant 2.0
Now supports large projects with ability to process up to 1,000 laser scans and unlimited points
Herndon, Virginia — September 6, 2011 — ClearEdge3D today released EdgeWise™ Plant 2.0, software that automates the extraction of complex CAD pipe geometry from 3D laser scanned data, dramatically reducing time to create accurate as-built 3D industrial plant models.
Daimler nominated for Future Prize for computer vision technology
A team from automotive manufacturer Daimler is one of three nominees for Germany's Future Prize. Daimler was nominated for its "6D Vision" system for collision avoidance. It uses a pair of cameras to produce stereo video, and is able to assess a dangerous situation two and half times faster than a human, with effective stereo vision about four times further. The final winner will be announced in December and win a 250,000 Euro prize. More information is available from Optics.org.