All about computer vision processing and learning
4.0K views | +2 today
Follow
All about computer vision processing and learning
Image processing, Visual learning, Augmented reality, etc
Curated by Maxime Cottret
Your new post is loading...
Your new post is loading...
Scooped by Maxime Cottret
Scoop.it!

New algorithms locate where a video was shot from its images and sounds | KurzweilAI

New algorithms locate where a video was shot from its images and sounds | KurzweilAI | All about computer vision processing and learning | Scoop.it
Eight randomly chosen keyframes of videos contained in the video/sound geotagged database used in this research (credit: Xavier Sevillano et al./Information
more...
No comment yet.
Rescooped by Maxime Cottret from IT Books Free Share
Scoop.it!

A Practical Introduction to Computer Vision with OpenCV - PDF Free Download - Fox eBook

A Practical Introduction to Computer Vision with OpenCV - PDF Free Download - Fox eBook | All about computer vision processing and learning | Scoop.it
“ A Practical Introduction to Computer Vision with OpenCV PDF Free Download, Reviews, Read Online, ISBN: 1118848454, By Kenneth Dawson-Howe”
Via Fox eBook
more...
Fox eBook's curator insight, May 20, 2014 5:05 AM

Chapter 1 Introduction
Chapter 2 Images
Chapter 3 Histograms
Chapter 4 Binary Vision
Chapter 5 Geometric Transformations
Chapter 6 Edges
Chapter 7 Features
Chapter 8 Recognition
Chapter 9 Video
Chapter 10 Vision Problems

Scooped by Maxime Cottret
Scoop.it!

Google’s Tango smartphone uses a Kinect-like sensor to create 3D maps of the entire world | ExtremeTech

Google’s Tango smartphone uses a Kinect-like sensor to create 3D maps of the entire world | ExtremeTech | All about computer vision processing and learning | Scoop.it
Google has just unveiled Project Tango, a smartphone with built-in 3D computer vision technology. Think of it as a smartphone with built-in Kinect functionality -- but rather than enable Leap-like gesture control, the computer vision tech is used to create a full 3D map of your current environment. At its most basic, you might use Tango to create a map of your house, or a 3D model of your favorite antique vase or your motorbike. Its advanced uses, though, are what make me truly dizzy with excitement. We are looking at a device that could, in one fell swoop, revolutionize indoor navigation, DIY, shopping, gaming, and more. How? Read on.
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Un match de tennis filmé sous tous les angles

Un match de tennis filmé sous tous les angles | All about computer vision processing and learning | Scoop.it
Les captations d'événements sportifs, de cinéma et d'émissions TV vont sans doute connaître une transformation des angles de vue grâce au développement d'une technique de caméras virtuelles permettant de se...
Maxime Cottret's insight:

Impressionnant !!!

more...
No comment yet.
Rescooped by Maxime Cottret from Computer Vision Highlights
Scoop.it!

Volumetric 3D Mapping in Real-Time on a CPU

This video shows a volumetric multi-resolution mapping system for RGB-D images that runs on a standard CPU. ICRA 2014
Via CVScoops
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

A smart-object recognition algorithm that doesn’t need humans | KurzweilAI

A smart-object recognition algorithm that doesn’t need humans | KurzweilAI | All about computer vision processing and learning | Scoop.it
(Credit: BYU Photo) BYU engineer Dah-Jye Lee has created an algorithm that can accurately identify objects in images or video sequences --- without human
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Integrated GPUs: how useful are they in HPC?

Integrated GPUs: how useful are they in HPC? | All about computer vision processing and learning | Scoop.it
Due to their potential computation power, GPUs are often used for high performance computing. However, discrete GPUs are connected to the CPU via the PCIe bus, which can cause bottlenecks due to hi...
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Computing OpenSURF on OpenCL and General Purpose GPU

Computing OpenSURF on OpenCL and General Purpose GPU | All about computer vision processing and learning | Scoop.it
Speeded-Up Robust Feature (SURF) algorithm is widely used for image feature detecting and matching in computer vision area. Open Computing Language (OpenCL) is a framework for writing programs that...
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Accelerating Sequential Computer Vision Algorithms Using Commodity Parallel Hardware

Since 2004, the clock frequency of CPUs has not increased significantly. Computer Vision applications have an increasing demand for more processing power and are limited by the performance capabili...
more...
No comment yet.
Rescooped by Maxime Cottret from Computer Vision Highlights
Scoop.it!

Variational Methods for Computer Vision - (Prof. Daniel Cremers)

The first of a serie of lectures from Prof. Dr. Daniel Cremers (TU München) on variational methods.
Via CVScoops
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Seene, futur Instagram de la photo 3D ?

Seene, futur Instagram de la photo 3D ? | All about computer vision processing and learning | Scoop.it
Une startup londonienne propose une application mobile étonnante pour réaliser ses propres clichés 3D en un clic.
more...
No comment yet.
Rescooped by Maxime Cottret from WIT
Scoop.it!

Halide, un nouveau langage de programmation pour le traitement d'images, par des chercheurs du MIT

Halide, un nouveau langage de programmation pour le traitement d'images, par des chercheurs du MIT | All about computer vision processing and learning | Scoop.it
“ Des chercheurs du laboratoire d'informatique et d'intelligence artificielle (CSAIL) du MIT ont présenté, dans un article publié à la conférence SIGGRAPH 2012, un nouveau langage de programmation, appelé Halide.”
Via Walid Arouss
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013

by Tao Chen · Zhe Zhu · Ariel Shamir · Shi-Min Hu · Daniel Cohen-Or
Maxime Cottret's insight:

impressive !!!

more...
No comment yet.
Rescooped by Maxime Cottret from Post-Sapiens, les êtres technologiques
Scoop.it!

Advancing artificial intelligence: Microsoft deploys corgis to beat Google on imaging | ZDNet

Advancing artificial intelligence: Microsoft deploys corgis to beat Google on imaging | ZDNet | All about computer vision processing and learning | Scoop.it
“Microsoft says Project Adam has given it the world's best image classifier.”
Via Jean-Philippe BOCQUENET
more...
No comment yet.
Rescooped by Maxime Cottret from Computer Vision Highlights
Scoop.it!

Robust 3D Tracking with Descriptor Fields [CVPR 2014]

A. Crivellaro and V. Lepetit. "Robust 3D Tracking with Descriptor Fields". CVPR 2014
Via CVScoops
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

BradLarson/GPUImage

BradLarson/GPUImage | All about computer vision processing and learning | Scoop.it
GPUImage - An open source iOS framework for GPU-based image and video processing
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Facebook met au point une vérification faciale très fiable

Facebook met au point une vérification faciale très fiable | All about computer vision processing and learning | Scoop.it

Facebook sera à l'avenir capable de reconnaitre presque à tout coup le visage d'un utilisateur. Le réseau social a mis au point une technologie, baptisé DeepFace

more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Depth Map Based Superresolution Method in 3D Reconstruction

Depth Map Based Superresolution Method in 3D Reconstruction | All about computer vision processing and learning | Scoop.it
In this thesis a superresolution method for geometry reconstruction is presented. Superresolution methods have already been used in order to improve texture resolution and RGB images. In a lesser d...
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Le smartphone se transforme en scanner 3D grâce à une application

Le smartphone se transforme en scanner 3D grâce à une application | All about computer vision processing and learning | Scoop.it
Une équipe de chercheurs de l’École polytechnique fédérale de Zurich a mis au point une application mobile qui permet de faire de la modélisation 3D en temps réel à partir d’un smartphone. Elle utilise...
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

New algorithm finds you, even in untagged photos | KurzweilAI

New algorithm finds you, even in untagged photos | KurzweilAI | All about computer vision processing and learning | Scoop.it
The location of tags in a images tells us a story. From them, we can extract a tag relativity graph. The graph enables social search by understanding tag
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Carnegie Mellon computer searches web 24/7 to analyze images and teach itself common sense | KurzweilAI

Carnegie Mellon computer searches web 24/7 to analyze images and teach itself common sense | KurzweilAI | All about computer vision processing and learning | Scoop.it
(credit: Carnegie Mellon University) A computer program called the Never Ending Image Learner (NEIL) is now running 24 hours a day at Carnegie Mellon
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Khronos Releases OpenVX 1.0 Specification for Computer Vision Acceleration

more...
No comment yet.
Rescooped by Maxime Cottret from Computer Vision Highlights
Scoop.it!

Semi-Dense Visual Odometry for a Monocular Camera (ICCV '13)

The authors propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to ben- efit from the simplicity and accuracy of dense tracking -- which does not depend on visual features -- while running in real-time on a CPU. The key idea is to continuously esti- mate a semi-dense inverse depth map for the current frame, which in turn is used to track the motion of the camera using dense image alignment. More specifically, they estimate the depth of all pixels which have a non-negligible image gradi- ent. Each estimate is represented as a Gaussian probability distribution over the inverse depth. They propagate this in- formation over time, and update it with new measurements as new images arrive.The method runs in real-time on a CPU.
Via CVScoops
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Better robot vision | KurzweilAI

Better robot vision | KurzweilAI | All about computer vision processing and learning | Scoop.it
A statistical construct called the Bingham distribution enables a new algorithm to identify an object's orientation using far fewer data points (red and purple
more...
No comment yet.
Scooped by Maxime Cottret
Scoop.it!

Teaching computers to recognize objects better | KurzweilAI

Teaching computers to recognize objects better | KurzweilAI | All about computer vision processing and learning | Scoop.it
With each of the raw images of the photos in color, today's state-of-the-art object-detection algorithms make errors — such as identifying a car (above) —
more...
No comment yet.