1030 Open source projects that are alternatives of or similar to rt-mrcnn

Can rewind and save YouTube live stream

Implementation of the paper "YOLACT Real-time Instance Segmentation" in Tensorflow 2

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Reference implementation of "Faster Training of Mask R-CNN by Focusing on Instance Boundaries"

Real-time Anchor-Free Instance Segmentation, in CVPR 2020

Get images from a network camera stream or webcam

JavaScript/WebGL real-time face tracking and expression detection library. Build your own emoticons animated in real time in the browser! SVG and THREE.js integration demos are provided.

Train a Mask R-CNN model with the Tensorflow Object Detection API

Python script to download Instagram livestreams and replays.

Tensorflow 2.x implementation YOLACT

Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available

Deeplab for semantic segmentation tasks

Download live streams from YouTube

📚 A collection of papers about Referring Image Segmentation.

Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

Real-time Detectron using webcam.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

State of the art object detection in real-time using YOLOV3 algorithm. Augmented with a process that allows easy training of the classifier as a plug & play solution . Provides alert if an item in an alert list is detected.

JavaScript/WebGL lib: detect if the user is looking at the screen or not from the webcam video feed. Lightweight and robust to all lighting conditions. Great for play/pause videos if the user is looking or not, or for person detection. Link to live demo.

A simple Angular webcam component / pure & minimal, no flash-fallback

Real-time pupillometry in the web browser using a 4K webcam video feed processed by this WebGL/Javascript library. 2 demo experiments are included.

A cross-platform network media aggregation application.

We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).

No description or website provided.

A simple, fully convolutional model for real-time instance segmentation.

Real-time face swap for PC streaming or video calls

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

A sample project to build a custom Mask RCNN model using Tensorflow object detection API

OpenMMLab Detection Toolbox and Benchmark

InstantDL: An easy and convenient deep learning pipeline for image segmentation and classification

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

Cell Detection with PyTorch.

Live Hidden Camera is a library which record live video and audio from Android device without displaying a preview.

In this project, we will use a webcam with Raspberry Pi to live stream wirelessly.

Smart India Hackathon 2019 project given by the Department of Atomic Energy

Just another simple, fast, and resilient open-source WebSockets server. 📣

Open solution to the Google AI Object Detection Challenge 🍁

AcFun直播通用后端

Measure characteristics of a looped back signal.

A compact Unscented Kalman Filter (UKF) library for Teensy4/Arduino system (or any real time embedded system in general)

A 24/7 live video broadcast with automatic content selection and overlays using FFMPEG and Python!

MemStream: Memory-Based Streaming Anomaly Detection

Implementation of ECCV20 paper: the devil is in classification: a simple framework for long-tail object detection and instance segmentation

Pipelined implementation of Sobel Edge Detection on OV7670 camera and on still images

React Native live video streaming demo app using Open-Tok

Simple shared surface streaming application

A multiplayer capture the flag game made in Godot with love and blood. Running live at www.superctf.com

PyTorch re-implementation of ''Real-time Scene Text Detection with Differentiable Binarization'' (AAAI 2020)

Archived: Now bundled in https://github.com/cloudfoundry/loggregator-release

2021年计算机视觉技术综述分类汇总

the moving objects tracking system via two axis camera motion (and as optionally n joint robotic arm) for raspberry pi distributions

How to create custom COCO data set for instance segmentation

声网agora.io React-Native模块封装 支持iOS / Android

💵 View your favorite coins' ticker prices with i3blocks.

【基于JAVA开发的在线直播平台】Ant Live；腾讯云直播服务；直播鉴黄；礼物；支付宝充值提现；弹幕聊天室；前端后分离；SpringBoot；直播平台开发；

NodeJS live stream server with HLS ABR support

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

Phoenix LiveView multiplayer card game