Search Results for "2-plan"

Segmentation models with pre trained backbones. High-level API (just two lines to create a neural network) 9 models architectures for binary and multi class segmentation (including legendary Unet) 124 available encoders (and 500+ encoders from timm) All encoders have pre-trained weights for faster and better convergence. Popular metrics and losses for training routines. All encoders have pretrained weights.

GLMixer performs real time graphical blending of several movie clips and of computer generated graphics. Drop video files in the mixing workspace and place them in a circular area to change their opacity ; if you selects two videos, moving them together performs a fading transition. This principle generalizes to a large number of videos. Direct interaction with the video allows to be fast and reactive, and to move and deform them on screen. The output of your operations is shown in the output window, typically displayed in full-screen on an external monitor or a projector. ...

This is a .Net framework windows tool developed to deal with the dvd Vob File's operations including cleaning .vob files, joining .vob files, splitting .vob files , converting .vob files and authoring .vob files to VIDEO_TS

Scene is a computer vision framework that performs background subtraction and object tracking, using two traditional algorithms and three more recent algorithms based on neural networks and fuzzy classification rules. For each detected object, Scene sends TUIO messages to one or several client applications. The present release features GPU accelerated versions of all the background subtraction methods and morphological post processing of the object blobs with dilation and erosion filters, implemented in OpenCL. ...

A comprehensive software suite for reading barcodes. Supports EAN/UPC, Code 128, Code 39, Interleaved 2 of 5 and QR Code. Includes libraries and applications for decoding captured barcode images and using a video device (eg, webcam) as a barcode scanner.

The tools in this project are used by the Virtual Reality lab at University of Texas at Austin to record the stream of rendered images (OpenGL) and combine them with eye tracking data (if eyes are being tracked) and user defined metadata. The project is split into two parts. DVR is used to record the data stream as a QuickTime movie. The RVD is used to read the movie recorded by the DVR. Acknowledgements: John Stone - created most of the code base Gabriel Diaz and Joseph Cooper - QA Dmitry Kit - Maintainer/QA Dr. Mary Hayhoe and Dr. Dana Ballard Virtual Reality Laboratory at University of Texas in Austin

A paint program where the canvas is the visual cortex of a simple kind of artificial intelligence. You paint with the mouse into its dreams and it responds by changing what you painted gradually. There will also be an API for using it with other programs as a general high-dimensional space. Each pixel's brightness is its own dimension. Bayesian nodes have exactly 3 childs because that is all thats needed to do NAND in a fuzzy way as Bayes' Rule which is NAND at certain extremes. NAND can be...

Tapeless video and audio ingest and transcoding server for television studios and professional environments. Uncompressed SD or HDTV, is captured and real-time encoded into MXF wrapped online & offline editing and review formats e.g. DV50, JPEG 2:1,

...We propose an approach which treats the detection of changes in behavior detected with a sensor/video fusion, which occur at radically different time-scales, through a CBR in two levels: low and high level. The system is always updating the database with the daily data.

...Wonsang You, M.S. Houari Sabirin, and Munchurl Kim, "Moving object tracking in H.264/AVC bitstream," Lecture Notes in Computer Science, vol. 4577, 2007, pp. 483-492. 2. Wonsang You, M.S. Houari Sabirin, and Munchurl Kim, "Real-time detection and tracking of multiple objects with partial decoding in H.264/AVC bitstream domain," Proceedings of SPIE, vol. 7244, 72440D (February 2009).

Читает позиции прямо с гобана (с помощью камеры), контролирует и записывает партии Го. This application watches your goban (using a camera), controls and logs the Go game.

EStereo is a computer vision C++ library for real-time disparity estimation. It computes dense stereo matching from 2 or 3 images as well as 3D scene reconstruction. The library also comes with a GUI-based application (StereoPlus).

Video Recognition Toolkit is a software for visual video processing algorithms modeling. It supports algorithm execution and result display in real-time. There are several new algorithms and some algorithms from OpenCV and LTIlib libraries.

The project aims to provide a Java library that enables OpenGL animation and rendering of mandelbrot fractals using LWJGL.

We have moved! Please go to https://launchpad.net/fr0st

Money$hot (M$) is a realtime video special effects/switcher program for people with more than one webcam. M$ uses DirectShow on WinXP/Vista as a compositing engine. M$ can capture, composite, transform (using FreeFrame, etc.), and stream.

An OS/hardware vendor independent GPU accelerated image and video processing library written in C. Interface allows easy combination and manipulation of customizable filters. Works with an active OpenGL context.

Flamey Framey - This Software aim to make new Video Enjoyable Environment.This software can editing video and attatching intaractivity useing easy XML.especally easy to make Picture in Picture movie. This software baed on Quicktime for java and java.

This project is a community project of the Visualjockey [VJo] community. We will develop a package of plugins for the Visualjockey VJ-Software. By sharing the sources of the plugin we can faster and better develop realtime plugins for VJo.

A landscape viewable outside of a window invites users to participate with the outside environment by actively changing it. A familiar space becomes disorienting when interaction with a familiar setup responds contradictorily to users expectations. This

Genjutsu-vision is a networked computer vision framework for OpenGL. Based upon GLFW and IPP for optimization, networked computer vision development technologies enable vision analysis of data from multiple sources.

Flipbook is made to flip a sequence of images and allow you to study the resulting animation frame by frame. That's it, pure and simple. I will use Flipbook as the glue between my digital stills camera and a final animation. It will import JPEGs or PNGs

Sensors to MIDI management system. This is a project that allows for creating MIDI output from sensors input. This output can then be used in MIDI processors, like GarageBand, Resolum and other real-time multimedia software. The input can be taken from d

Creation of three dimensional synthetic images and movies from two pictures or channels (cams). On the long run several features for 3D F/X are intended.