microsoft/Cognitive-Samples-VideoFrameAnalysis

A library with sample apps for continuous analysis of live video, using the Microsoft Cognitive Services Vision APIs.

What it solves

This project provides a way to analyze video frames from a webcam in near-real-time. It simplifies the process of integrating Microsoft Cognitive Services Vision APIs (specifically the Computer Vision and Face APIs) to perform automated image analysis on a live video stream.

How it works

The project consists of a C# library called VideoFrameAnalyzer and two sample applications. It uses the OpenCvSharp package to capture frames from a webcam. The library allows developers to set a specific analysis function (such as calling the Face API) and a trigger interval (e.g., every 3 seconds) to automatically process frames and return analysis results.

Who it’s for

Developers using C# and Visual Studio who want to implement real-time video analysis using Microsoft's cloud-based vision services.

Highlights

  • Integrated support for Microsoft Computer Vision and Face APIs.
  • Near-real-time processing of webcam feeds.
  • Flexible analysis triggers based on time intervals.
  • Includes both a console application and a live camera application for demonstration.

Related

  • Project
    PozzettiAndrea/ComfyUI-SAM3DBody

    A ComfyUI wrapper for Meta's SAM 3D Body that enables full-body 3D human mesh recovery from a single image.

  • Project
    naver/must3r

    MUSt3R is a research‑grade Python library for multi‑view 3‑D reconstruction. It extends the DUSt3R model with symmetric processing, a multi‑layer memory, and online pose estimation, enabling both offline reconstruction of unordered image sets and live SLAM‑style mapping from video or webcam streams. The repo provides installation scripts, several pre‑trained ViT‑based checkpoints (224 px and 512 px), Gradio/viser and Open3D demo interfaces, and a full training pipeline. It is released under a non‑commercial license with restrictive dataset terms.

  • Project
    luicfrr/react-native-vision-camera-face-detector

    A React Native library that integrates Google MLKit with Vision Camera to provide real-time and static image face detection.

  • Project
    ucam-eo/geotessera

    A Python library for reading, exporting, and visualizing geospatial embeddings from the Tessera Earth foundation model, supporting both cloud-native streaming and local tile downloads.