satchelwu

ImageAnnotation

ImageAnnotation(Qt + Opencv) Tool makes tagging object easier, faster and more effective. Hope it can help you a lot. There are also some useful tools in the "Components" folders, maybe just for you. Please enjoy it !

Human-Falling-Detect-Tracks

AlphaPose + ST-GCN + SORT.

yolov5-tensorrt

yolov5 tensorrt inference

ALPR

基于4种轻量级深度卷积网络的无场景约束全自动车牌识别，轻量级车牌检测，轻量级车牌识别，pyqt5可视化界面

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

CTracker

DBFace

DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

DeepFaceLab

DeepFaceLab is a tool that utilizes machine learning to replace faces in videos. Includes prebuilt ready to work standalone Windows 7,8,10 binary (look readme.md).

facerecognize-for-mobile-phone

适用于移动端的人脸识别模型，计算量与mobilefacenet相同，但megaface上提升了2%+

fast-reid

SOTA ReID Methods and Toolbox

HyperLandmark

Deep Learning Based Free Mobile Real-Time Face Landmark Detector.

ImageMosaicing

Source code for Mosaicking of unmanned aerial vehicle imagery in the absence of camera poses, Remote Sensing 2016

libtorch-yolov3-deepsort

mobile-lpr

Mobile-LPR 是一个面向移动端的准商业级车牌识别库，以NCNN作为推理后端，使用DNN作为算法核心，支持多种车牌检测算法，支持车牌识别和车牌颜色识别。

MobileFace

A face recognition solution on mobile device.

Multitarget-tracker

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

ncnn_android_face_vehicle

ncnn在Android的一个测试，包含了人脸检测(face detection)，人脸属性(face attributes)，人脸识别(face recognition)。车辆检测(Vehicle detection)，车牌检测(plate detection)，车牌识别(plate recognition)；人头检测(head detection)的流程

open_ptrack_v2

OPT v2 "Gnocchi" - adding object tracking and pose recognition

retinaface

Reimplement RetinaFace use C++ and TensorRT

retinanet-examples

Fast and accurate object detection with end-to-end GPU optimization

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

tensorRTIntegrate

TensorRT ONNX Plugin、Inference、Compile

thingsboard

Open-source IoT Platform - Device management, data collection, processing and visualization.

tracking-by-detection

Multiple object tracking (MOT) algorithm implemented in C++

trt_pose

Real-time pose estimation accelerated with NVIDIA TensorRT

Ultra-Light-Fast-Generic-Face-Detector-1MB

一款超轻量级通用人脸检测模型（模型文件大小仅1MB，320x240输入下计算量仅90MFlops）适用于边缘计算设备、低算力设备以及PC

Violence-Recognition-Dataset

some video with fighting and normal

vod-converter

Convert between visual object detection datasets

yolact

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

yolov4-triton-tensorrt

This repository deploys YOLOv4 as an optimized TensorRT engine to Triton Inference Server