gitqinxinyu Goto Github PK
Name: qinxinyu
Type: User
Name: qinxinyu
Type: User
基于计算机视觉的交通场景智能应用(目标检测与目标追踪)
123
Portfolio for 3D Point Cloud Processing from www.shenlanxueyuan.com China
🏆The 1st place solution of track3 (City-Scale Multi-Camera Vehicle Tracking) in the NVIDIA AI City Challenge at CVPR 2021 Workshop.
(ICRA) Anytime Stereo Image Depth Estimation on Mobile Devices
百度人体分析Demo:人体关键点、人体属性、手势识别、人像分割、人流量统计、驾驶行为分析(邀测)、人流量统计动态版(邀测)
Cascade-RCNN+DeepSort MOTDT Trackor++
A small 2-day prototype of cctv camera tracking cars and humans
CGI-Stereo Python Inference Demo
**多车牌检测、车牌角度矫正、车牌文本识别、车牌颜色识别、危险品车辆识别,ncnn车牌识别
yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌
Linux环境安装配置Clash工具,以实现代理上网效果。包含下载、安装、配置、运行、测试以及开机自启动、定期自动更新订阅功能的操作文档,希望对你有所帮助
Non-official Pytorch implementation of the CREStereo(CVPR 2022 Oral).
CVPR 2020 论文开源项目合集
收集 CVPR 最新的成果,包括论文、代码和demo视频等,欢迎大家推荐!
Classification and Segmentation of the MNIST dataset given as a point set input. Classification: the program classifies hand written digits, given as a sample of 100 points in a 2 dimensional field. the architecture is based on a Stanford article of a PointNet which is especially efficient for 3D image classification. the PointNet classification accuracy is 92.86% Segmentation: this is an extension to the classification net which can later define segments within the pointset. the program receives an input of a handwritten digit, given as a sample of 200 points in a 2 dimensional field, where 100 of the points are a sample of the digit itself, and the rest of the points are "background" points which are not part of the digit. the program classifies each point into one of the 2 segments and returns if it is part of the digit or part of the background. the PointNet segmentation accuracy is 97.65%
Methods and Implements of Deep Clustering
这是一个deeplabv3-plus-pytorch的源码,可以用于训练自己的模型。
deepsort yolov5
DeepSORT + YOLOv5
Depth Estimation using Stereo images using deep learning based architecture for disparity measurement.The architectures used for disparity estimation are BgNet,CreStereo, Raft-Stereo, HitNet,GwcNet etc.
Experimental projects we've done with DepthAI.
Data Labeling, Tracking and Annotation with AI
A real time, webcam based, driver attention state monitoring system in Python3 using OpenCV and Dlib
[ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
使用Tensoflow构建电影推荐系统
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.