Open Source Linux Realtime Processing Software - Page 4

Argo-Panoptes is a distributed surveillance system that allows video remote control using a smartphone or web browser as user interface. The system is able to alert the user about failures or motion detection by email, SMS or MMS.

an experimentation page for art made with Processing

PyMesh is a codebase developed by Qingnan Zhou for his PhD research at New York University. It is a rapid prototyping platform focused on geometry processing. PyMesh is written with both C++ and Python, where computational intensive functionalities are realized in C++, and Python is used for creating minimalistic and easy-to-use interfaces. PyMesh is a rapid prototyping platform focused on geometry processing. It provides a set of common mesh processing functionalities and interfaces with a number of state-of-the-art open-source packages to combine their power seamlessly under a single developing environment. Mesh process should be simple in python. PyMesh promotes human-readable, minimalistic interface and works with native python data structures such as numpy.ndarray.

PyTorch-NLP is a library for Natural Language Processing (NLP) in Python. It’s built with the very latest research in mind, and was designed from day one to support rapid prototyping. PyTorch-NLP comes with pre-trained embeddings, samplers, dataset loaders, metrics, neural network modules and text encoders. It’s open-source software, released under the BSD3 license. With your batch in hand, you can use PyTorch to develop and train your model using gradient descent. For example, check out this example code for training on the Stanford Natural Language Inference (SNLI) Corpus. Now you've setup your pipeline, you may want to ensure that some functions run deterministically. Wrap any code that's random, with fork_rng and you'll be good to go. Now that you've computed your vocabulary, you may want to make use of pre-trained word vectors to set your embeddings.

Real time face tracking and recognition refers to the task of locating human faces in a video stream and identifying the faces by matching them against the database of known faces.

SSBRenderer is a plugin for frameservers on Windows & Unix platforms to render 2D graphics by SSB (Substation Beta) data on frames of video streams.

Real-time SVC streaming with a MP4 container in Standard Legacy Streaming Server and SVC Clients

Sabbia acquires a video stream from a webcam and transforms the movements detected into MIDI messages. This way it is possible to control a MIDI device or a MIDI software by hand movements.

A VHDL - Verilog SAD256 module

This is an object recognition library written on top of OpenCV. Scalable Multimodal Object Recognition (SMORs) is designed for real time highly accurate object detection.

SeeHawk is a cross-platform, cross-device video/image capturing, viewing, and editing application.

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. Preparing your data the same way as during weights pre-training may give you better results (higher metric score and faster convergence). It is not necessary in case you train the whole model, not only the decoder. Pytorch Image Models (a.k.a. timm) has a lot of pretrained models and interface which allows using these models as encoders in smp, however, not all models are supported. Input channels parameter allows you to create models, which process tensors with an arbitrary number of channels.

A software package designed for controlling an AEG-based sentry turret with optical target recognition through a USB webcam

Il vise à faire suivre un objet rouge par un webcam. Qui enverra les informations nécessaires à un microcontrolleur qui dirigera un servomoteur en fonction des informations reçues. Nous travaillons en deux groupes de deux car la réalisation de ce projet étant assez courte nous n’orrions pu tout faire. Nous nous occupons donc seulement de la partie détection et envoie des informations sous forme analogique par une sortie son en stéréo.

A front-end to use the dvgrab, ffmpeg2theora and oggfwd commands.It helps to stream media files from Firewire, DV, IP cameras, webcams or files.

TV_ENCODE! is a textual front end for MEncoder which allows the user to record live TV from NTSC, PAL, ATSC (or any future form) to industry standard MPEG-4 Video with MP3 Audio (DivX Compatible). Support for multiple capture sources.

A graphical toolkit to use the GPU (Graphical Processor) to perform general purpose operations.

The UHAPI4Linux project is working on an open source implementation of UHAPI: 1. Provide development platform on PC for application and middleware 2. Demonstrate UHAPI concepts 3. Bootstrap developers with UHAPI

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! IMPORTANT !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! This UltraGrid repository at SourceForge has moved to GitHub address: https://github.com/CESNET/UltraGrid Releases can be found here: https://github.com/CESNET/UltraGrid/releases The SourceForge repository is no longer maintained. !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! UltraGrid from Laboratory of Advanced Networking Technologies (www.sitola.cz) is a software for real-time transmissions of high-defintion (HD), 2K, 2160p/Quad Full HD/SuperHD, and 4K video.

This software uses computer vision algorithms for mining sequence data from telemonitoring data with CBRs. 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.

Videod efficiently provides live or recorded video streams to one or multiple local clients for processing. It is released under the CeCILL-C license (see http://www.cecill.info/index.en.html), a French equivalent of the GNU LGPL.

ViewMAX is a feature enhanced branch of ZoneMinder. It includes a new look and feel, and attempts to maintain compatibility with it's original ZM parent code tree. This project is no longer being extended or supported.

The goal of this project is to create a fast generator of a volumetric fire animation. The generator uses a short precomputed sequence to produce an endless animation. Packages real-time-fire2.0 and higher contain additionally a heat haze.

The webcam computer vision (WCCV) project focuses on computer vision algorithms and systems that follow the web cam paradigm: cheap, robust and efficient. The project comprises designs, patterns, code, tutorials and examples.

Wechselspieler is an interactive motion tracking tool to transform movement information coming from a file or video into sound in realtime using the MIDI or OSC protocol. It features an easy to use GUI for defining/editing the image trigger regions.