Showing 141 open source projects for "video frames"

View related business solutions
  • Veeam Data Platform v13.1 - Get Your Free Trial Icon
    Veeam Data Platform v13.1 - Get Your Free Trial

    Secure by design, portable by default. Recover clean, fast, anywhere. Start a free trial.

    Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
    Try it Free
  • Ship Agents Faster Icon
    Ship Agents Faster

    Transform your applications and workflows into powerful agentic systems at global scale.

    Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
    Start Free
  • 1
    VideoPlayerDemo

    VideoPlayerDemo

    Encapsulate ijkplay player, self-implementing bottom-streaming

    VideoPlayerDemo is a multimedia demonstration project that showcases video playback capabilities within a mobile or desktop application environment. It focuses on integrating FFmpeg-based decoding with a custom rendering pipeline to display video content efficiently. The project demonstrates how to handle media streams, synchronize audio and video, and manage playback controls. It serves as a learning resource for developers exploring media frameworks and playback architectures. The...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 2
    XIVO

    XIVO

    X Inertial-aided Visual Odometry

    ...XIVO runs at 140FPS on stored data (here from a RealSense D435i sensor) or on live streams with a latency of around 1-7ms, depending on the hardware. It takes as input video frames from a calibrated camera and inertial measurements from an IMU and outputs a sparse point cloud with attribute features and 6 DOF pose of the camera. It performs auto-calibration of the relative pose between the camera and the IMU as well as the time-stamp alignment.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 3
    VoTT

    VoTT

    Visual Object Tagging Tool, an electron app for building models

    Visual Object Tagging Tool: An electron app for building end-to-end Object Detection Models from Images and Videos. An open source annotation and labeling tool for image and video assets. VoTT is a React + Redux Web application, written in TypeScript. This project was bootstrapped with Create React App. VoTT can be installed as a native application or run from source. VoTT is also available as a stand-alone Web application and can be used in any modern Web browser. VoTT is available for...
    Downloads: 5 This Week
    Last Update:
    See Project
  • 4
    I3D models trained on Kinetics

    I3D models trained on Kinetics

    Convolutional neural network model for video classification

    ...The project provides TensorFlow and Sonnet-based implementations, pretrained checkpoints, and example scripts for evaluating or fine-tuning models. It also offers sample data, including preprocessed video frames and optical flow arrays, to demonstrate how to run inference and visualize outputs.
    Downloads: 0 This Week
    Last Update:
    See Project
  • Train ML Models With SQL You Already Know Icon
    Train ML Models With SQL You Already Know

    BigQuery automates data prep, analysis, and predictions with built-in AI assistance.

    Build and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
    Start Free
  • 5
    vid2vid

    vid2vid

    Pytorch implementation of our method for high-resolution

    vid2vid is a deep learning framework for high-resolution video-to-video translation that generates photorealistic videos from structured inputs such as semantic maps, pose sequences, or edge maps. Built on top of image-to-image translation techniques like pix2pixHD, it extends these ideas into the temporal domain by ensuring consistency across video frames. The system can synthesize complex outputs such as realistic talking faces, human motion animations, or dynamic street scenes by learning temporal relationships between frames.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 6
    GIF for CLI

    GIF for CLI

    Takes in a GIF, short video, or a query to the Tenor GIF API

    gif-for-cli is a small, playful utility that brings animated GIFs to the command line by rendering frames directly in a terminal. It takes an input GIF (or a URL) and converts each frame into a terminal-friendly representation, timing updates to approximate the original animation. Depending on terminal capabilities, it can use ANSI color blocks or image protocols to achieve surprisingly faithful playback. The tool includes conveniences such as looping control, scaling to fit your terminal,...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 7

    Kino

    NO LONGER MAINTAINED

    Kino is a non-linear DV editor for GNU/Linux. It features excellent integration with IEEE-1394 for capture, VTR control, and recording back to the camera. Kino supports a number of formats: Raw DV, DV AVI, still frames, WAV, MP3, Ogg Vorbis, MPEG, DivX.
    Downloads: 10 This Week
    Last Update:
    See Project
  • 8
    Video Nonlocal Net

    Video Nonlocal Net

    Non-local Neural Networks for Video Classification

    video-nonlocal-net implements Non-local Neural Networks for video understanding, adding long-range dependency modeling to 2D/3D ConvNet backbones. Non-local blocks compute attention-like responses across all positions in space-time, allowing a feature at one frame and location to aggregate information from distant frames and regions. This formulation improves action recognition and spatiotemporal reasoning, especially for classes requiring context beyond short temporal windows. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 9
    DetectAndTrack

    DetectAndTrack

    The implementation of an algorithm presented in the CVPR18 paper

    DetectAndTrack is the reference implementation for the CVPR 2018 paper “Detect-and-Track: Efficient Pose Estimation in Videos,” focusing on human keypoint detection and tracking across video frames. The system combines per-frame pose detection with a tracking mechanism to maintain identities over time, enabling efficient multi-person pose estimation in video. Code and instructions are organized to replicate paper results and to serve as a starting point for researchers working on pose in video. Although the repo has been archived and is now read-only, its issue tracker and artifacts remain useful for understanding implementation details and experimental settings. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • Build Securely on Azure with Proven Frameworks Icon
    Build Securely on Azure with Proven Frameworks

    Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

    Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
    Download Now
  • 10
    Whammy

    Whammy

    A real time javascript webm encoder based on a canvas hack

    Whammy is a lightweight JavaScript encoder for generating WebM video directly in the browser. It exploits the relationship between WebP image frames and the VP8 codec used by WebM. Developers can add canvas elements, canvas contexts, or encoded image data as individual video frames. Frame rate can be defined globally, while individual frame durations can also be specified. Encoding happens when the collected frames are compiled, producing a Blob that can be displayed or saved as WebM content. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 11
    twitchslam

    twitchslam

    A toy implementation of monocular SLAM written while livestreaming

    twitchslam is a small educational implementation of monocular simultaneous localization and mapping created during a livestream. It processes ordinary video while estimating camera motion and building a map of observed 3D points. Frames contain extracted visual features, while map points retain their 2D correspondences across frames. OpenCV handles feature extraction, SDL2 provides a 2D view, and Pangolin renders the reconstructed map in 3D. The project includes pose optimization, projection-based point recovery, a kinematic model, and map loading and saving. ...
    Downloads: 2 This Week
    Last Update:
    See Project
  • 12

    urmusic5

    The Free and Open Source Music Visualizer Tool

    urmusic is a free and open-source software that allows you to easily create your own music visualizer and create a music video for it! It makes use of hardware acceleration to render frames as fast as possible. Donations: Support me on ko-fi: https://ko-fi.com/nasso
    Downloads: 2 This Week
    Last Update:
    See Project
  • 13

    hranol

    Multiplatform image batch processing

    Hranol is lightweight command line utility that takes image folders and filtering parameters as input and applies these filters to all images. It was designed for batch processing grayscale video frames of high-speed camera.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 14
    Five video classification methods

    Five video classification methods

    Code that accompanies my blog post outlining five video classification

    ...This reduces model complexity, training time, and a whole whack load of hyperparameters we don’t have to worry about. Every video will be subsampled down to 40 frames. So a 41-frame video and a 500-frame video will both be reduced to 40 frames, with the 500-frame video essentially being fast-forwarded. We won’t do much preprocessing. A common preprocessing step for video classification is subtracting the mean, but we’ll keep the frames pretty raw from start to finish.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 15

    SGA Conversion and Analysis Tool

    Convert SGA format multimedia files to PNG and AVI format

    This program is a utility for viewing, analyzing, and converting the data in SGA format multimedia files used by Digital Pictures in their games for the Sega Mega CD, Sega Super 32X, Sega Saturn, 3DO video game systems, and Windows PCs into formats that can be read by media player software on modern PCs.
    Downloads: 18 This Week
    Last Update:
    See Project
  • 16
    High Speed Parallel Imaging (HSPI)

    High Speed Parallel Imaging (HSPI)

    HSPI does parallel capture and sky surveys.

    HSPI offers to the astronomer the possibility to capture pictures from the CCD camera in a fast and intuitive way, keeping under control all the instrumentation in posses. HSPI can control the CCD camera, the mount, the focuser, the filter wheel and the dome from a single interface, and not only this: these features can be added on as many observatories and instrumentations you want. HSPI is ASCOM and INDI compatible, so if you want to use particular setups like Linux computers connected...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 17
    OSMF HLS Plugin

    OSMF HLS Plugin

    OSMF HLS Plugin

    The OSMF HLS Plugin is a plugin extension for OSMF (Open Source Media Framework) version 2.0 that enables playback of Apple’s HTTP Live Streaming (HLS) streams within Flash/OSMF-based video players. It supports various use cases (live, video-on-demand, DVR style) and handles HLS protocol tags, bitrate switching, discontinuities, etc., to allow AS3/Flash / AIR apps/players to use HLS as a streaming protocol. HLS playback in OSMF 2.0-based video players. Multi-bitrate streaming. VOD/Live/DVR...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 18

    JAABA

    The Janelia Automated Animal Behavior Annotator

    The Janelia Automatic Animal Behavior Annotator (JAABA) is a machine learning-based system that enables researchers to automatically compute interpretable, quantitative statistics describing video of behaving animals. Through our system, users encode their intuition about the structure of behavior by labeling the behavior of the animal, e.g. walking, grooming, or following, in a small set of video frames. JAABA uses machine learning techniques to convert these manual labels into behavior detectors that can then be used to automatically classify the behaviors of animals in large data sets with high throughput. ...
    Leader badge
    Downloads: 12 This Week
    Last Update:
    See Project
  • 19
    This is na attempt to identify objects in real time video processing. Uses a Sample Grabber filter to get frames from webcam feed. I mannaged to group pixels with similar color and that have topologic continuity. In another processing layer the objective is to relate these groups by their apparent velocity and constant borders, so that an object with different colors or patterns could be identified as the same object.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 20
    cvastroalign

    cvastroalign

    video align tool for astrophotography

    cvastroalign is a program that loads a video sequence, aligns and stacks the selected frames obtaining an image as result of this process..
    Downloads: 4 This Week
    Last Update:
    See Project
  • 21
    purpleelephant

    purpleelephant

    Development has moved to github

    Purple Elephant is a free and open source cross-platform 2D traditional animation editor, tester, player and compositor. Part of Purple Animation Tools by O. Bahri Gordebak See Wiki for details. Note that Sourceforge project page doesn't always show the latest download. Please click Files above and browse files before download. Latest version is 1.4 right now.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 22
    purplechameleon

    purplechameleon

    Development has moved to github

    Free and open source cross-platform stop-motion animation and pencil testing software. Part of Purple Animation Tools by O. Bahri Gordebak See Wiki for details. Note that Sourceforge project page doesn't always show the latest download. Please click Files above and browse files before download. Latest version is 1.4.2 right now.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 23
    purpleowl

    purpleowl

    Development has moved to github

    Purple Owl is a free and open source cross-platform frame-by-frame cut-out animation software. Part of Purple Animation Tools by O. Bahri Gordebak (purplehuman). See Wiki for details. Note that Sourceforge project page doesn't always show the latest download. Please click Files above and browse files before download. Latest version is 1.2.1 right now.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 24

    MediaCoder Agent

    The encoding agent for MediaCoder distributed transcoding

    MediaCoder Agent is used to form a distributed transcoder with MediaCoder. It is light-weight, portable and open-source. It receives video frames sent by MediaCoder via TCP, encodes them with the requested video encoder and sends encoded elementary stream back to MediaCoder. There is no disk I/O in this procedure.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 25
    OpenTLD

    OpenTLD

    OpenTLD is an open source library for real-time 2D tracking

    OpenTLD is an open source implementation of the TLD (Tracking-Learning-Detection) framework, designed for real-time 2D tracking of a single object in video sequences. Because it fuses tracking and detection, TLD can recover from occlusions, drift, or failures by using its detection mechanism to reacquire the object. In terms of usage, one typically initializes the tracker by providing a bounding box on the first frame, then calls a function like run_TLD to process a video and obtain bounding boxes over time. ...
    Downloads: 0 This Week
    Last Update:
    See Project