"Particle Swarm Optimization (PSO) is a relatively recent heuristic search method whose
mechanics are inspired by the swarming or collaborative behavior of biological populations.
PSO is similar to the Genetic Algorithm (GA) in the sense that these two evolutionary
heuristics are population-based search methods. In other words, PSO and the GA move
from a set of points (population) to another set of points in a single iteration with likely
improvement using a combination of deterministic and probabilistic rules. The GA and its
many versions have been popular in academia and the industry mainly because of its
intuitiveness, ease of implementation, and the ability to effectively solve highly nonlinear,
mixed integer optimization problems that are typical of complex engineering systems. The
drawback of the GA is its expensive computational cost." queted from "A COMPARISON OF PARTICLE SWARM OPTIMIZATION AND THE GENETIC ALGORITHM"
_____
The pseudo code of PSO procedure is as follows
For each particle
Initialize particle
END
Do
For each particle
Calculate fitness value
If the fitness value is better than the best fitness value (pBest) in history
set current value as the new pBest
End
Choose the particle with the best fitness value of all the particles as the gBest
For each particle
Calculate particle velocity according equation (a)
Update particle position according equation (b)
End
While maximum iterations or minimum error criteria is not attained
_____
Most of evolutionary techniques have the following procedure:
1. Random generation of an initial population
2. Evaluate the fitness value for each subject.
3. Reproduction of the population based on fitness values, add random solution to explore the space of solution.
4. If requirements are met, then stop. Otherwise go back to 2.
_____
Using evolutionary algorithm or PSO are nice formulation for some complex problem but visualizing the evolutionary process is fun.
You could take a look to : Yong-Hyuk Kim, Kang Hoon Lee and Yourim Yoon, Visualizing the Search Process of Particle Swarm Optimization, Proceedings of the 11th Annual conference on Genetic and evolutionary computation (GECCO 2009), 49-56, July 2009. (videos)
If you want play:
PSO: http://code.google.com/p/particle-swarm-optimization/
Genetic Algorithm: Evolving Objects (EO): an Evolutionary Computation Framework
A bunch of news about Computer vision, Computer Graphics, GPGPU or the mix of the three....
Monday, December 19, 2011
A short but simple GDB tutorial
Quoted from Geeks3D "Here is a short tutorial about GBD for beginners. GDB is the powerful command line based debugger available with Linux. If you usually use a visual debugger like the one integrated in Visual Studio, a command line debugger like GDB can be a bit… frightening. But actually it’s quite easy to step into your code with it. Few commands are necessary to quickly start using GDB for basic debugging tasks."
Tutorial
Here it starts: > gdb your_program
Tutorial
Here it starts: > gdb your_program
Tuesday, December 13, 2011
Wednesday, November 23, 2011
DOOM3 Source code is available
"Doom 3 GPL source release
=========================
This file contains the following sections:
GENERAL NOTES
LICENSE
GENERAL NOTES
=============
Game data and patching:
-----------------------
This source release does not contain any game data, the game data is still
covered by the original EULA and must be obeyed as usual."
GitHub
=========================
This file contains the following sections:
GENERAL NOTES
LICENSE
GENERAL NOTES
=============
Game data and patching:
-----------------------
This source release does not contain any game data, the game data is still
covered by the original EULA and must be obeyed as usual."
GitHub
Microsoft Kinect for PC
Kinect for PC will be improved for closed range application.
Microsoft have created an investment program to help some start up (Kinect Accelerator)
Source Microsoft
Kinect Accelerator
Microsoft have created an investment program to help some start up (Kinect Accelerator)
Source Microsoft
Kinect Accelerator
Wednesday, November 9, 2011
Good bye PhotoSceneEditor, Hi 123D Catch
PhotoSceneEditor is now used in Autodesk software as 123D Catch.
"Catching Reality"
http://labs.autodesk.com/utilities/photo_scene_editor/ => http://www.123dapp.com/catch
To know more :
http://www.123dapp.com/catch
"Catching Reality"
http://labs.autodesk.com/utilities/photo_scene_editor/ => http://www.123dapp.com/catch
To know more :
http://www.123dapp.com/catch
Libellés :
Computer Graphics,
computer vision,
reconstruction
Monday, October 24, 2011
Monday, October 17, 2011
Marvelous designer
Marvelous designer allow to create nice and realistic clothes !
Source : 3dvf
Libellés :
Computer Graphics,
reconstruction
Thursday, October 13, 2011
Thursday, October 6, 2011
Rendering Synthetic Objects into Legacy Photographs
An interesting paper of SIGGRAPH ASIA 2011.
Rendering Synthetic Objects into Legacy Photographs
Kevin Karsch, Varsha Hedau, David Forsyth, Derek Hoiem
To be presented at SIGGRAPH Asia 2011
A method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements.
Link : http://kevinkarsch.com/publications/sa11.html
Rendering Synthetic Objects into Legacy Photographs
Kevin Karsch, Varsha Hedau, David Forsyth, Derek Hoiem
To be presented at SIGGRAPH Asia 2011
A method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements.
Friday, September 16, 2011
3d camera mapping.
3d camera mapping (modelling, texturing, compositing) was done with Blender 2.49
ARCHIVE PHOTO INSERTS FROM MOTALKO from Miklós Falvay on Vimeo.
ARCHIVE PHOTO INSERTS FROM MOTALKO from Miklós Falvay on Vimeo.
Wednesday, August 31, 2011
Kinect Mocap
Ipisoft purpose solution to perform Mocap from "standard" webcam or Kinect devices.
To know more product, Kinect HowTo
To know more product, Kinect HowTo
Libellés :
Computer Graphics,
computer vision,
Kinect
Autodesk real time point cloud reconstruction with Kinect
This is the result of the Benjamin Butin student Project in the Autodesk Photofly team
Libellés :
Computer Graphics,
computer vision,
Kinect,
Tech demo
Tuesday, August 23, 2011
Wind simulation from Autodesk
Autodesk are happy to announce another technology preview on Autodesk Labs.
Project Falcon for Alias software on Autodesk Labs
Project Falcon for Alias software is a wind tunnel simulator that allows designers to interactively investigate the aerodynamic performance of their designs. Flow and wind pressure results update almost in real-time in response to changes in wind-direction and speed.
Project Falcon for Alias software on Autodesk Labs
Project Falcon for Alias software is a wind tunnel simulator that allows designers to interactively investigate the aerodynamic performance of their designs. Flow and wind pressure results update almost in real-time in response to changes in wind-direction and speed.
Friday, August 5, 2011
Spark: Modular, Composable Shaders for Graphics Hardware
Spark: Modular, Composable Shaders for Graphics Hardware
By Tim Foley (Intel Corporation and Stanford University), Pat Hanrahan (Stanford University)
In creating complex real-time shaders, programmers should be able to decompose code into independent, localized modules of their choosing. Current real-time shading languages, however, enforce a fixed decomposition into per-pipeline-stage procedures. Program concerns at other scales - including those that cross-cut multiple pipeline stages - cannot be expressed as reusable modules.
We present a shading language, Spark, and its implementation for modern graphics hardware that improves support for separation of concerns into modules. A Spark shader class can encapsulate code that maps to more than one pipeline stage, and can be extended and composed using object-oriented inheritance. In our tests, shaders written in Spark achieve performance within 2% of HLSL.
.
Read the Siggraph paper: Spark: Modular, Composable Shaders for Graphics Hardware [PDF 3.1 MB]
Download the source code: spark-0.1.zip* [ZIP 36.3 MB];
Presented at: ACM SIGGRAPH 2011, Vancouver, B.C. Canada
Source INTEL
By Tim Foley (Intel Corporation and Stanford University), Pat Hanrahan (Stanford University)
In creating complex real-time shaders, programmers should be able to decompose code into independent, localized modules of their choosing. Current real-time shading languages, however, enforce a fixed decomposition into per-pipeline-stage procedures. Program concerns at other scales - including those that cross-cut multiple pipeline stages - cannot be expressed as reusable modules.
We present a shading language, Spark, and its implementation for modern graphics hardware that improves support for separation of concerns into modules. A Spark shader class can encapsulate code that maps to more than one pipeline stage, and can be extended and composed using object-oriented inheritance. In our tests, shaders written in Spark achieve performance within 2% of HLSL.
.
Read the Siggraph paper: Spark: Modular, Composable Shaders for Graphics Hardware [PDF 3.1 MB]
Download the source code: spark-0.1.zip* [ZIP 36.3 MB];
Presented at: ACM SIGGRAPH 2011, Vancouver, B.C. Canada
Source INTEL
AMD APP KernelAnalyzer 1.9 (OpenCL)
"AMD has published an update of its tool for OpenCL developers. AMD’s APP KernelAnalyzer is a tool to compile, analyze and disassemble OpenCL, Brook+ or IL (Intermediate Language) kernels for Radeon GPUs. APP SDK v2.5 or greater is required for OpenCL support and ATI Stream 1.4 for Brook+.
AMD APP KernelAnalyzer main features
Compile, analyze and disassemble the OpenCL kernel for multiple Catalyst driver versions and GPU device targets.
View any kernel compilation errors and warnings generated by the OpenCL runtime.
View the AMD Intermediate Language (IL) code generated by the OpenCL run-time.
View the ISA code generated by the AMD Shader Compiler.
View various statistics generated by analyzing the ISA code.
View General Purpose Registers and spill registers allocated for the kernel.
Official page and download: APP KernelAnalyzer @ AMD."
Source Geeks3D
Wednesday, August 3, 2011
Wednesday, July 20, 2011
Wednesday, June 29, 2011
Many faces to create new ones
AKB48 is a japonese Idol group. They have made a buzz about a new member of the group... But this new member was entirely made from face of the existing member !
Here the synthetized face :
Ok it's look almost planar... but it give a nice result.
Here the Making Of :
If you want make your own Idol :
http://www.icenomi.com/oshimen/index.html
Source : 3DVF Icenomi
Here the synthetized face :
Ok it's look almost planar... but it give a nice result.
Here the Making Of :
If you want make your own Idol :
http://www.icenomi.com/oshimen/index.html
Source : 3DVF Icenomi
Libellés :
Computer Graphics,
computer vision,
Tech demo
Wednesday, June 22, 2011
Monday, June 20, 2011
Friday, June 17, 2011
Official Microsoft Kinect SDK is out
"The Kinect for Windows SDK beta is a starter kit for applications developers that includes APIs, sample code, and drivers. This SDK enables the academic research and enthusiast communities to create rich experiences by using Microsoft Xbox 360 Kinect sensor technology on computers running Windows 7."
Source : Microsoft
They have put focus on skeletal recognition and tracking. As sample you will have a game... and more
Official samples:
"Skeletal Viewer—Capturing Data with the NUI API (C++ and C#)
The Kinect sensor includes two cameras: one delivers depth information and the other delivers color data. The NUI API enables applications to access and manipulate this data. The SkeletalViewer sample uses the NUI API to render data from the Kinect sensor’s cameras as images on the screen. The managed sample uses WPF to render captured images, and the native application uses DirectX.
ShapeGame—Creating a Game with Audio and Skeletal Tracking
Displays the tracked skeletons of two players together with shapes falling from the sky. Players can control the shapes by moving and speaking commands.
Audio Capture Raw (C++)
The Kinect sensor’s audio component is a four-element microphone array. The AudioCaptureRaw sample uses the Windows Audio Session API (WASAPI) to capture the raw audio stream from the Kinect sensor’s microphone array and write it to a .wav file.
MicArrayEchoCancellation—Acoustic Echo Cancellation, Beam Forming, and Source Localization (C++)
The primary way for C++ applications to access the Kinect sensor’s microphone array is through the MSRKinectAudio DirectX Media Object (DMO). The MSRKinectAudio DMO supports all standard microphone array functionality, and adds support for beamforming and source localization. The MicArrayEchoCancellation sample shows how to use the KinectAudio DMO as a DirectShow® source to access the Kinect sensor’s microphone array. This sample uses acoustic echo cancellation to record a high-quality audio stream and beamforming and source localization to determine the selected beam and the direction of the sound source.
MFAudioFilter—Media Foundation Audio Filter (C++)
Shows how to capture an audio stream from the Kinect sensor’s microphone array by using the MSRKinectAudio DMO in filter mode in a Windows Media Foundation topology.
RecordAudio—Recording an Audio Stream and Monitoring Direction (C#)
Demonstrates how to capture an audio stream from the Kinect sensor’s microphone array and monitor the currently selected beam and sound source direction.
Speech—Recognizing Voice Commands (C#)
Demonstrates how to use the Kinect sensor’s microphone array with the Microsoft.Speech API to recognize voice commands."
An example made by a user.
Source : Microsoft
They have put focus on skeletal recognition and tracking. As sample you will have a game... and more
Official samples:
"Skeletal Viewer—Capturing Data with the NUI API (C++ and C#)
The Kinect sensor includes two cameras: one delivers depth information and the other delivers color data. The NUI API enables applications to access and manipulate this data. The SkeletalViewer sample uses the NUI API to render data from the Kinect sensor’s cameras as images on the screen. The managed sample uses WPF to render captured images, and the native application uses DirectX.
ShapeGame—Creating a Game with Audio and Skeletal Tracking
Displays the tracked skeletons of two players together with shapes falling from the sky. Players can control the shapes by moving and speaking commands.
Audio Capture Raw (C++)
The Kinect sensor’s audio component is a four-element microphone array. The AudioCaptureRaw sample uses the Windows Audio Session API (WASAPI) to capture the raw audio stream from the Kinect sensor’s microphone array and write it to a .wav file.
MicArrayEchoCancellation—Acoustic Echo Cancellation, Beam Forming, and Source Localization (C++)
The primary way for C++ applications to access the Kinect sensor’s microphone array is through the MSRKinectAudio DirectX Media Object (DMO). The MSRKinectAudio DMO supports all standard microphone array functionality, and adds support for beamforming and source localization. The MicArrayEchoCancellation sample shows how to use the KinectAudio DMO as a DirectShow® source to access the Kinect sensor’s microphone array. This sample uses acoustic echo cancellation to record a high-quality audio stream and beamforming and source localization to determine the selected beam and the direction of the sound source.
MFAudioFilter—Media Foundation Audio Filter (C++)
Shows how to capture an audio stream from the Kinect sensor’s microphone array by using the MSRKinectAudio DMO in filter mode in a Windows Media Foundation topology.
RecordAudio—Recording an Audio Stream and Monitoring Direction (C#)
Demonstrates how to capture an audio stream from the Kinect sensor’s microphone array and monitor the currently selected beam and sound source direction.
Speech—Recognizing Voice Commands (C#)
Demonstrates how to use the Kinect sensor’s microphone array with the Microsoft.Speech API to recognize voice commands."
An example made by a user.
Libellés :
Computer Graphics,
computer vision,
Kinect,
Tech demo
Thursday, June 16, 2011
Google Search by image
Google launch a service to perform web image search by similarity. It's a service like http://www.tineye.com/.
http://images.google.com/ A camera have appear in the text label. Drag and Drop an image on the text field or click on the camera.
http://images.google.com/ A camera have appear in the text label. Drag and Drop an image on the text field or click on the camera.
Libellés :
Google,
Image processing,
Tech demo
Wednesday, June 15, 2011
AMD gDEBugger, an advanced OpenGL and OpenCL debugger
AMD have released an integrated debugger for OpenGL and OpenCL to Visual Studio.
AMD gDEBugger is an advanced OpenGL and OpenCL debugger, profiler and memory analyzer. Actually AMD gDEBugger is based on the well known gDEBugger by Graphic Remedy. This new debugger is a plugin for Visual Studio and supports all capabilities of the original gDEBugger as well as new features.
"gDEBugger takes the mystery out of debugging OpenCL and OpenGL, allowing developers to peer into computer and graphic memory objects such as OpenCL images to view their contents as they change from write, copy, and kernel operations. Allocated OpenCL and OpenGL objects are monitored to allow detecting memory leaks and the scenarios that caused the leaking objects to be created, API function call logs can be viewed and saved and unrecommended and deprecated functions and behaviors are marked, with best-practice alternatives offered. "
AMD gDEBugger download should be available shortly.
More information on the official homepage: AMD gDEBugger @ AMD.
Source : Geeks3D
AMD gDEBugger is an advanced OpenGL and OpenCL debugger, profiler and memory analyzer. Actually AMD gDEBugger is based on the well known gDEBugger by Graphic Remedy. This new debugger is a plugin for Visual Studio and supports all capabilities of the original gDEBugger as well as new features.
"gDEBugger takes the mystery out of debugging OpenCL and OpenGL, allowing developers to peer into computer and graphic memory objects such as OpenCL images to view their contents as they change from write, copy, and kernel operations. Allocated OpenCL and OpenGL objects are monitored to allow detecting memory leaks and the scenarios that caused the leaking objects to be created, API function call logs can be viewed and saved and unrecommended and deprecated functions and behaviors are marked, with best-practice alternatives offered. "
AMD gDEBugger download should be available shortly.
More information on the official homepage: AMD gDEBugger @ AMD.
Source : Geeks3D
Libellés :
Computer Graphics,
Opencl,
Visual Studio
Monday, June 13, 2011
What's new in Computer Vision System Toolbox in R2011a
Matlab have updated is Computer Vision System Toolbox.
Here's the documentation.
Here’s a list of what’s new:
Here's the documentation.
Here’s a list of what’s new:
- extractFeatures function for creating an array of feature vectors (descriptors) based on interest points within an image
- matchFeatures function for finding the best matches between two arrays of feature vectors (descriptors)
- Visualization of epipolar geometry for stereo images using epipolarLine, isEpipoleInImage, and lineToBorderPoints functions
- estimateUncalibratedRectification function for calculating projective transformations to rectify stereo images
- Video segmentation based on Gaussian Mixture Models using ForegroundDetector System object YCbCr video format support for ToVideoDisplay block and DeployableVideoPlayer System object
- vision.BlockMatcher
- vision.Deinterlacer
- vision.GeometricTransformEstimator
- vision.OpticalFlow
- vision.TemplateMatcher
Matlab Visual Sudoku Solver
After the Google Goggles Sudoku Demo Matlab have released near the same demo.
Not purely real time. But a working one with explanation. (Basis bricks are a sudoku solver, some image processing (morphological operations) and number recognition).
http://www.mathworks.com/videos/matlab/sudoku.html
The source code is accessible on the same webpage.
Not purely real time. But a working one with explanation. (Basis bricks are a sudoku solver, some image processing (morphological operations) and number recognition).
http://www.mathworks.com/videos/matlab/sudoku.html
The source code is accessible on the same webpage.
Thursday, June 9, 2011
Kinect Graffiti
A nice initiative to make Temporary art !
Kinect Graffiti™ from Jean-Christophe Naour on Vimeo.
Thanks to Dlpnet.
Kinect Graffiti™ from Jean-Christophe Naour on Vimeo.
Thanks to Dlpnet.
Libellés :
Computer Graphics,
computer vision,
Kinect,
processing
Monday, May 30, 2011
SVG GIRL
An incredible SVG demo :
http://jsdo.it/event/svggirl
You could edit SVG slides an reload the animation.
http://jsdo.it/event/svggirl
You could edit SVG slides an reload the animation.
Friday, May 27, 2011
New AR game from Dassault System
Following the last Rio game. Dassault System will release the King Fu Panda 2 game.
Here the preview :
Source 3DVF
Here the preview :
Source 3DVF
Thursday, May 26, 2011
Hello Read/Write World!
The Read/Write the world project have innovative ideas :
Quoted from http://readwriteworld.cloudapp.net/?p=35
Quoted from http://readwriteworld.cloudapp.net/?p=35
"Today we’re unveiling a major new project in Bing. Technically it’s an indexing, unification, and connection of the world’s geo-linked media. Informally, it’s the magic of:
- Seeing your photos automatically connected to others;
- Being able to simply create immersive experiences from your or your friends photos, videos, and panoramas;
- “Fixing” the world, when the official imagery of your street is out of date;
- Visually mapping your business, your favorite park, or your real estate for everyone to see;
- Understanding the emergent information from the density and tagging of media.
The Read/Write World has 3 pillars: Clear Content Rights; Uniform Access and Open Source Viewers; and Real-Time Geo-Services."
Swimming through the Read/Write World from Read/Write World on Vimeo. Another interesting talk :
Libellés :
Computer Graphics,
computer vision,
Tech demo
Wednesday, May 25, 2011
123d A free Nurbs Autodesk 3D modeler
123D is a public beta software from Autodesk that allow you to perform Nurbs based modeling.
TO know more and see video : http://www.123dapp.com/support
I seems have function dedicated for 3D printing :
TO know more and see video : http://www.123dapp.com/support
I seems have function dedicated for 3D printing :
Monday, May 23, 2011
Sony "smartAR"
New video about "smartAR" the Augmented Reality work in progress of Sony
Libellés :
Computer Graphics,
computer vision,
Tech demo
Thursday, May 19, 2011
Wednesday, May 18, 2011
SIGGRAPH 2011 Technical Papers Video Preview
The technical Papers video preview of SIGGRAPH 2011 :
Interesting or fun ->
Microgeometry from an elastomeric sensor
Exploring photobios
Passive Facial capture
Garment modeling
Interesting or fun ->
Microgeometry from an elastomeric sensor
Exploring photobios
Passive Facial capture
Garment modeling
Libellés :
Computer Graphics,
computer vision,
siggraph,
Tech demo,
tech paper
Wednesday, May 11, 2011
From tiny to large Icons
This siggraph 2011 paper "describe a novel algorithm for extracting a resolution-independent vector representation from pixel art images, which enables magnifying the results by an arbitrary amount without image degradation."
To know more : Here
I'm curious to see the result on large images.
One more paper from Johannes Kopf (Microsoft)
To know more : Here
I'm curious to see the result on large images.
One more paper from Johannes Kopf (Microsoft)
Libellés :
Computer Graphics,
computer vision,
siggraph,
Tech demo
Intel OpenCL 1.1 SDK (beta version)
From ozone3d.net.
"Intel has published a new version of its OpenCL SDK. This new SDK, targeting Intel CPUs, supports the OpenCL 1.1 specification and brings a preview support for Linux (64-bit only).
Intel OpenCL SDK version 1.1 new features:
SDK is fully conformant with OpenCL 1.1 specification for the CPU
Beta support for Microsoft* Windows* operating systems (32 and 64 bit)
Preview support for Linux* operating systems
OpenCL Installable Client Driver (ICD) Compliant
Unique Implicit CPU Vectorization Module for best utilization of the CPU hardware vector units (SIMD) across work items
Optional OpenCL 1.1 Core Features: Out-of-order execution model, Execution of native kernels, Image support and Optimization options through OpenCL complier flags (cl-fast-relaxed-math)
Double precision floating point extension (cl_khr_fp64)
OpenGL*/OpenCL Sharing (cl_khr_gl_sharing)
Preview: Device Fission Extension Support (cl_ext_device_fission)
Code samples
Debug and Analyze with the Intel OpenCL SDK Tools: Debug kernels using printf (cl_intel_printf), Intel OpenCL SDK Offline Complier and Code
Analyzer, Intel Graphics Performance Analyzers support, OpenCL kernel analyzing using Intel VTune Amplifier XE 2011 Integration
Detailed release notes are available HERE."
"Intel has published a new version of its OpenCL SDK. This new SDK, targeting Intel CPUs, supports the OpenCL 1.1 specification and brings a preview support for Linux (64-bit only).
Intel OpenCL SDK version 1.1 new features:
SDK is fully conformant with OpenCL 1.1 specification for the CPU
Beta support for Microsoft* Windows* operating systems (32 and 64 bit)
Preview support for Linux* operating systems
OpenCL Installable Client Driver (ICD) Compliant
Unique Implicit CPU Vectorization Module for best utilization of the CPU hardware vector units (SIMD) across work items
Optional OpenCL 1.1 Core Features: Out-of-order execution model, Execution of native kernels, Image support and Optimization options through OpenCL complier flags (cl-fast-relaxed-math)
Double precision floating point extension (cl_khr_fp64)
OpenGL*/OpenCL Sharing (cl_khr_gl_sharing)
Preview: Device Fission Extension Support (cl_ext_device_fission)
Code samples
Debug and Analyze with the Intel OpenCL SDK Tools: Debug kernels using printf (cl_intel_printf), Intel OpenCL SDK Offline Complier and Code
Analyzer, Intel Graphics Performance Analyzers support, OpenCL kernel analyzing using Intel VTune Amplifier XE 2011 Integration
Detailed release notes are available HERE."
Monday, May 9, 2011
Kinect facial capture
Quoted from Youtube
"
This video shows an example of how 3D facial motion performance can be captured without markers using a Microsoft Kinect camera (data shown in green). The resulting facial animation is shown in purple. The color video is just shown for reference and not used in the process.
This is work by M. Breidthttp://www.kyb.tuebingen.mpg.de/nc/employee/details/mbreidt.html , H. H. Bülthoff and C. Curiohttp://www.kyb.tuebingen.mpg.de/research/dep/bu/ce.html at the department for Human Perception, Action and Cognition of the Max Planck Institute for Biological Cybernetics, Tübingen, Germanyhttp://www.kyb.tuebingen.mpg.de/?id=43
Thanks to Joachim Tesch and Johannes Lächele for their help in recording raw data from the Kinect!"
Saturday, May 7, 2011
Tuesday, May 3, 2011
41 GigaPixels panorama
Here a panorama of 41 Gigapixel of the french city Saint Raphael.
The making of
PS : It's not perfect (there is some ghost from the blending step):
PS : 111 GigaPixel Sevilla
The making of
PS : It's not perfect (there is some ghost from the blending step):
PS : 111 GigaPixel Sevilla
Libellés :
Computer Graphics,
computer vision,
Panoramic images
Monday, May 2, 2011
Panasonic VIERA AR Setup Simulator
Let see what a TV could render in your room.
It's Augmented Reality and they use marker.
Only limited to Iphones....
It's cool that they show the case that do not work. (Pattern is not detected in those condition)
It's Augmented Reality and they use marker.
Only limited to Iphones....
It's cool that they show the case that do not work. (Pattern is not detected in those condition)
Libellés :
Computer Graphics,
computer vision,
Tech demo
Wednesday, April 20, 2011
Real Time Spherical panorama on Iphone
"Today, we're introducing the official Photosynth app which lets you capture amazing panoramas of your favorite places to share with your friends and even the world with Bing Maps. (The app is currently available via iTunes and will be available on iOS devices later today.) Photosynth’s interactive panoramas allow you to look left, right, up and down, letting you capture and view more of the places you visit.
Using the latest computer vision technology, the Photosynth app makes capturing panoramas fun and engaging, while creating sharp, high-resolution results. With the app, you can process, view, and store your panoramas directly on your device. Then, share them in a variety of ways, including to Facebook as images or as interactive panoramas (hosted for free) on Photosynth.net.
"
http://www.bing.com/community/site_blogs/b/search/archive/2011/04/18/capture-panoramas-anywhere-you-go-with-the-photosynth-app-and-share-on-bing.aspx
Using the latest computer vision technology, the Photosynth app makes capturing panoramas fun and engaging, while creating sharp, high-resolution results. With the app, you can process, view, and store your panoramas directly on your device. Then, share them in a variety of ways, including to Facebook as images or as interactive panoramas (hosted for free) on Photosynth.net.
"
http://www.bing.com/community/site_blogs/b/search/archive/2011/04/18/capture-panoramas-anywhere-you-go-with-the-photosynth-app-and-share-on-bing.aspx
Libellés :
Computer Graphics,
computer vision,
iphone,
Panoramic images,
photosynth,
Tech demo
Thursday, April 14, 2011
Kinect pose recognition Details !
Here some details about the tech used to recognize the pose of the players with Kinect !
The CVPR paper : http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf
Here a video and some details : http://www.istartedsomething.com/20110319/microsoft-research-reveals-guts-of-kinect-technology/
The CVPR paper : http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf
Here a video and some details : http://www.istartedsomething.com/20110319/microsoft-research-reveals-guts-of-kinect-technology/
Kinect Official SDK ... official website
http://research.microsoft.com/en-us/um/redmond/projects/kinectsdk/
The SDK will be available for VB, C# et C++. It will cover all the hardware of the Kinect (color camera, depth, micro network, echo suppresion, acoustic localization, skeletal animation).
The SDK will be available for VB, C# et C++. It will cover all the hardware of the Kinect (color camera, depth, micro network, echo suppresion, acoustic localization, skeletal animation).
Virtual visite
Here a French initiative to make a virtual visit of local cultural inheritance.
Source 3Dvf.com
Présentation circuit touristique avec réalité augmentée from Dominomenuvideo on Vimeo.
Source 3Dvf.com
Libellés :
Computer Graphics,
computer vision,
Tech demo
Monday, April 11, 2011
3D clip again
Krause Follow Me from OPTIX Digital Pictures on Vimeo.
Source : http://www.optixdigital.de/followme/
Libellés :
Computer Graphics,
computer vision,
Tech demo
Friday, April 8, 2011
360° pano mirror for Iphone
The obvious default is that all the 360° pano is limited to the resolution of the sensor size.
Tuesday, April 5, 2011
Programmer level matrix ?
http://www.indiangeek.net/wp-content/uploads/Programmer%20competency%20matrix.htm
It shows skills per level and it's not bad !
I.E.:
It shows skills per level and it's not bad !
I.E.:
Computer Science | |||||
---|---|---|---|---|---|
2n (Level 0) | n2 (Level 1) | n (Level 2) | log(n) (Level 3) | ||
data structures | Doesn't know the difference between Array and LinkedList | Able to explain and use Arrays, LinkedLists, Dictionaries etc in practical programming tasks | Knows space and time tradeoffs of the basic data structures, Arrays vs LinkedLists, Able to explain how hashtables can be implemented and can handle collisions, Priority queues and ways to implement them etc. | Knowledge of advanced data structures like B-trees, binomial and fibonacci heaps, AVL/Red Black trees, Splay Trees, Skip Lists, tries etc. |
Tuesday, March 29, 2011
Total Immersion Receives USD $5,5M in Funding Led by Intel Capital
Posted on March 24, 2011 by Total Immersion
Press Release : Total Immersion, global leader in augmented reality, announced today that it has secured USD $5,5M in a funding round led by Intel Capital joined by existing investors Partech, iSource and Elaia Partners. The new funding will be used towards further development of the D’Fusion platform and to drive new usage of augmented reality (AR) for end-users. Specifically, the team will be focusing on expanding operations in Asia and in the US, developing a large community of developers and exploring new consumer markets.
“Augmented reality is one of the key technologies enabling contextual computing on the mobile phone, tablets and PC through interactive experience for exploration, suggestion and direction. At Total Immersion, we’re constantly looking for developing usage of augmented reality experiences for our customers and for end-users and this investment is another big step towards that objective,” said Bruno Uzzan, CEO and co-founder of Total Immersion.
“Total Immersion provides a unique and immersive user experience,” said Christian Morales, General Manager, Europe, Middle East, Africa of Intel Corporation. “Augmented reality is changing the way how people perceive and interact with their environment. It offers new opportunities for both developers and users. We look forward to working with Total Immersion to develop new usage experiences for Intel platforms”
“Augmented reality is a disruptive technology blending real life with digital information which will enable new and exciting businesses” said Marcos Battisti, Intel Capital’s Managing Director for Western Europe and Israel. “Total Immersion is bringing this ground breaking new technology into everyday life and our investment will enable the company to accelerate its growth and adoption. We are truly excited by Total Immersion’s capabilities and their contribution to future evolutions in this field.”
BatteryTech - high-performance mobile platform abstraction framework
BatteryTech™ is a high-performance mobile platform abstraction framework. Boiled down, it is a way for you to write native C++ code for Android™ and iPhone® while developing on a Mac® or in Windows®.
BatteryTech allows you to:
- Deploy on both Android™ and iPhone® with very little extra time invested
- Skip having to mess around with clunky platform APIs
- Have the highest-performing code possible
- Build your own custom game engine using libraries like Chipmunk Physics, Box2D, Bullet, Lua and others
- Develop more in less time by testing most builds on a fast PC or Mac
- Port existing titles only once to get multiple platform support
- Develop multiplayer games that work across all platforms (iPhone vs Android in real-time)
- Enjoy native coding without the worry about getting it to work on another platform
Features
- OpenGL ES 1.0, 1.1 and 2.0 (Shader) support
- Lightweight, High-performance Audio Mixer
- Lightweight GLES UI Library
- OGG, PNG, JPG, GIF and TTF decoding
- Asset-based File IO
- Standard Networking
- Cross-platform demo app using Box2D with projects for every OS
Supported Targets
- Windows native
- OSX native
- iPhone/iPod Touch 2nd gen+
- iPad / iPad 2
- Nearly all Android phones and tablets (1.5+)
Supported IDEs
- Eclipse CDT (Win32 / Android NDK)
- Eclipse ADT (Android / NDK)
- Xcode (iOS / OSX)
- Visual Studio 2010 (Win32)
What's in the demo:
- A basic game framework using GameObject creation and management
- Menus, sounds and music examples
- Box2D integration
- Support for both Fixed-Function and Shader rendering depending on device
- Examples of loading, changing and saving settings to file in a game
AMD OpenCL Emu Documentation
Quote
OpenCL Emu is a set of effective tools for the OpenCL software development designed for AMD GPUs
without the explicit need of GPU hardware. It allows developing and debugging an OpenCL kernel as a
C++ procedure inside your MS Visual Studio application while providing an easy switch between CPU,
GPU or GPU-emulator at the backend.
This tool would enable programmers to start developing using OpenCL language instantly without having
to learn the intricacies of the OpenCL run-time, saving them time to concentrate more on developing
parallel algorithms and making the shift to OpenCL a step easier.
Source : http://www.geeks3d.com/forums/index.php/topic,2065.0.html
Monday, March 28, 2011
Crysis 2 & CryENGINE 3 Key Rendering Features
Here an article about the Key rendering Features of Crysis 2 & CryENGINE 3.
I think they have made a very bad choice for the comparison.... of each key features... They always show in game screenshot and difference are often very hard to see. It's better to choose synthetic scene to show clearly the typical difference.
Source : Crytek.
I think they have made a very bad choice for the comparison.... of each key features... They always show in game screenshot and difference are often very hard to see. It's better to choose synthetic scene to show clearly the typical difference.
Source : Crytek.
Wednesday, March 23, 2011
Homemade Touch screen
With a few of electronics and captors !!!
A Line CDD, a few LED ... and a program
A Line CDD, a few LED ... and a program
Libellés :
Image processing,
Multitouch,
Tech demo
Monday, March 21, 2011
Kinect Hack : Help blind people
NAVI -- Navigational Aids for the Visually Impaired
Source : http://hci.uni-konstanz.de/blog/2011/03/15/navi/?lang=en
Source : http://hci.uni-konstanz.de/blog/2011/03/15/navi/?lang=en
Libellés :
computer vision,
Kinect,
Tech demo
iFace3D
After iScan3D http://www.digiteyezer.com/Digiteyezer/index.html
digiteyezer have launch the same service for Faces :
digiteyezer have launch the same service for Faces :
Libellés :
Computer Graphics,
computer vision,
Tech demo
Friday, March 18, 2011
Configure Matlab to use Visual 2010 C/C++ compiler
By default Matlab 2009 have only a C compiler (mex file compiler).
It could detects the Visual compiler for the 2005/2008 version but not for the 2010 version.
Hopefully MathWorks have released a patch ;)
Link : VS2010MEXSupport.zip
1. Download the patch attached to this Solution. The patch includes files needed to support these combinations of MATLAB and Visual C++ 2010:
• Visual C++ 2010 Professional and 64-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Professional and 32-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Express (Windows SDK 7.1 also required) and 64-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Express and 32-bit MATLAB 7.10 (R2010a)
2. Confirm that you are running MATLAB 7.10 (R2010a). You can check this using the About box available at Help->About MATLAB.
3. Unzip the contents of the patch into your MATLAB installation. This can be done from within MATLAB itself with the command:
unzip( path_to_zip_file, matlabroot);
4. Set up MEX to use Visual C++ 2010 with the command:
Note that this patch will only work with MATLAB 7.10 (R2010a). Using this patch with any version of MATLAB is not supported.
Other MathWorks products such as Real-Time Workshop do not support Visual C++ 2010.
Source : MathWorks
It could detects the Visual compiler for the 2005/2008 version but not for the 2010 version.
Hopefully MathWorks have released a patch ;)
Link : VS2010MEXSupport.zip
Subject:
How can I use Microsoft Visual C++ 2010 to create MEX files with MATLAB 7.10 (R2010a)?Problem Description:
I would like to use Visual C++ 2010 to create MEX files for use in MATLAB.Solution:
The Microsoft Visual C++ 2010 compiler is not supported on the released version of MATLAB 7.10 (R2010a), but support can be added by installing a patch. To install the patch:1. Download the patch attached to this Solution. The patch includes files needed to support these combinations of MATLAB and Visual C++ 2010:
• Visual C++ 2010 Professional and 64-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Professional and 32-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Express (Windows SDK 7.1 also required) and 64-bit MATLAB 7.10 (R2010a)
• Visual C++ 2010 Express and 32-bit MATLAB 7.10 (R2010a)
2. Confirm that you are running MATLAB 7.10 (R2010a). You can check this using the About box available at Help->About MATLAB.
3. Unzip the contents of the patch into your MATLAB installation. This can be done from within MATLAB itself with the command:
unzip( path_to_zip_file, matlabroot);
4. Set up MEX to use Visual C++ 2010 with the command:
mex –setup
Visual C++ 2010 should now be among the listed options.Note that this patch will only work with MATLAB 7.10 (R2010a). Using this patch with any version of MATLAB is not supported.
Other MathWorks products such as Real-Time Workshop do not support Visual C++ 2010.
Source : MathWorks
Subscribe to:
Posts (Atom)