Wan Youwen

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

MVision is a Chinese-language study guide covering machine vision and robotics. It collects tutorials, code links, and research paper references for topics like object detection, SLAM, and autonomous driving, no runnable code, just organized learning resources.

学习C & C++ & python&汇编语言 LLVM编译器 数据结构 算法 操作系统 单片机 linux 面试

动态语义SLAM 目标检测+VSLAM+光流/多视角几何动态物体检测+octomap地图+目标数据库

机器人操作系统ROS 语音识别 语义理解 视觉控制 gazebo仿真 雷达建图导航

数学知识点滴积累 矩阵 数值优化 神经网络反向传播 图优化 概率论 随机过程 卡尔曼滤波 粒子滤波 数学函数拟合

自我进化，个人、家庭、工作三位一体 爱 健康 财富 是人生值得追求的东西！人生不过是一段体验。我们都是时间的囚徒，活在当下。有趣！有料！

行业内领先的报告集合 行业 员工 金融 个税 福利薪酬 领导力 财富 会议 报告&工具

有代码的论文 Papers with code. Sorted by stars. Updated weekly.

中国大学MOOC《机器人操作系统入门》课程代码示例

CNN (PSPNet) + ORB_SLAM2 语义SLAM Real time semantic slam in ROS with a hand held RGB-D camera

ORB_SLAM with Octomap

基于ORB-SLAM2修改 动态环境建模 dynamic environments for monocular, stereo and RGB-D setups

rgb-slam + 语义分割mask-rcnn MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects

An open autonomous driving platform 百度自动驾驶开源框架

深度学习 YOLO-V3 结合 orb-slam2 语义地图

ORB SLAM2 + 拓扑地图 路径规划导航

一门由AlphaGo项目负责人David Sliver，在UCL(伦敦大学)主讲的强化学习经典课程

学习 TensorFLow 线性&逻辑回归 多层感知机 神经网络 自编码 循环神经网络 优化记录

免费的计算机编程类中文书籍，欢迎投稿

全栈工程师进阶加油站

第十四届全国大学生智能汽车竞赛室外光电竞速创意赛,ART-Racecar

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

Codes of my MOOC Course <Play with Linear Algebra>. Updated contents and practices are also included. 我在慕课网上的课程《玩转线性代数》示例代码，使用Python语言。课程的更多更新内容及辅助练习也将逐步添加进这个代码仓。

LeetCode Online Judge 算法刷题

A Detailed Cplusplus Concurrency Tutorial 《C++ 并发编程指南》

RNN语义分割+KinectFusion=3 d Semantic Scene

《机器学习》（西瓜书）公式推导解析，在线阅读地址：https://datawhalechina.github.io/pumpkin-book

卷积-反卷积语义分割cnn(基于caffe) + ElasticFusion(稠密SLAM) + CRF融合

GPS INS Integrated Navigation

所有基础数据结构和算法的纯C语言实现，如各自排序、链表、栈、队列、各种树以及应用、图算法、字符串匹配算法、回溯、并查集等，献丑了

基于3D卷积C3D，利用Faster-RCNN思路，使用时间段建议网络Temporal Proposal 检测视频行为

模型量化工程 Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

激光slam 完整答案解析 和 个人笔记

基于滤波器的松耦合 SSF 单IMU数据融合

北邮的PangFuming去掉ROS后的ROVIO

单目标长时间（long term tracking）跟踪算法 TLD：tracking-learning-detection 跟踪算法

单目MSCKF视觉惯性里程计 Monocular MSCKF ROS Node

ROS源代码分析、笔记和注释

kaggle 比赛 使用sklearn进行kaggle数据竞赛基础及实践

利用LLVM，Clang制作自己的编译器 UNMAINTAINED: Examples of using the LLVM and Clang compilation libraries and tools

程序员资料免费分享，欢迎关注个人微信公众号：程序员编程指南

利用光流和语义分割来进行 动态环境建模

多传感器卡尔曼融合框架 基于滤波器的松耦合举例-msf http://www.cnblogs.com/ilekoaiq/p/9311357.html http://www.cnblogs.com/yhlx125/p/8504396.html http://www.cnblogs.com/ilekoaiq/p/9311357.html

ristretto 量化ssd

图解算法 Code for the book Grokking Algorithms (https://amzn.to/29rVyHf)

Cross-Scale Cost Aggregation for Stereo Matching (CVPR 2014)

LeetCode LintCode 题解， 剑指offer题目，互联网公司面试，BAT外企等面试题目

半直接视觉里程计

Parallel Tracking And Mapping fast特征点块匹配 Track Mapping线程

Co-Fusion CRF图像分割　+ ElasticFusion(RGBD-SLAM)

作为对《C++17 STL cookbook》英文版的中文翻译。

LearnVIORB by using Runge Kutta 4th Order Integration On Manifold

:open_book: book note,读书笔记

《21个项目玩转深度学习———基于TensorFlow的实践详解》配套代码

工具，开源框架

路径跟踪 A simple pathtracer in C++.

SLAM 开发学习资源与经验分享

linux下编程代码实验 CMake/Make/Shell/Multi-thread' usage

Octomap建图参考

自身学习的安全数据科学和算法的学习资料

No description.

Python Machine Learning 机器学习

开源ICP库，trimesh2，实测下来应该是开源ICP算法中效果最好的，谁用谁知道 C++ library and set of utilities for input, output, and basic manipulation of 3D triangle meshes

深度强化学习 Deep Reinforcement Learning Lab, a platform designed to make DRL technology and fun for everyone

VINS-Mono 是香港科技大学开源的一个VIO 单目视觉惯性里程计 Monocular Visual-Inertial State Estimator https://www.cnblogs.com/ilekoaiq/p/8836970.html

YOLOv1 ZCU102 SoC x86 / ARM NEON优化加速

研究生数学建模，数学建模竞赛优秀论文，数学建模算法，LaTeX论文模板，算法思维导图，参考书籍，Matlab软件教程，PPT

高性能高集成度飞控代码 HappyMoon Open source project

信息学竞赛，国内官方网站为：

一些经典且高质量的电子书分享

相机雷达位姿校准 This package is used to calculate the translation and rotation matrix between camera and laser,then draw the point cloud of laser with image color.

集体智慧编程 代码&笔记 https://www.cnblogs.com/xiaoYu3328/p/5173854.html

基于YOLO的3D目标检测：YOLO-6D This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).

Everything about Transfer Learning and Domain Adaptation--迁移学习

A collection of LLVM passes (with tests and build scripts)

a simple thread pool coding by C++98 on Linux

《把时间当作朋友》

一个关于数字隐私搜集、保护、清理集一体的方案,外加开源信息收集(OSINT)对抗 (长期更新)

动态场景建图 Scene Flow Propagation for Semantic Mapping and Object Discovery in Dynamic Street Scenes

是基于RGB图像去学得到的6维的位姿，基于SSD做的 类似YOLO-6D Inference code and trained networks for SSD-6D

Learn OpenCV : C++ and Python Examples

AI学习之路

在线书籍编写模板 Modern documentation format and toolchain using Git and Markdown

知识付费套利（Knowledge payment arbitrage）

A simple logging library implemented in C99

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

paper implement

自由钢琴 AutoPiano，喜欢可以star ( http://crystalworld.gitee.io/qpiano/#/ )

深度图补全 https://zhuanlan.zhihu.com/p/42084058

A Chinese Translation of Stanford CS229 notes 斯坦福机器学习CS229课程讲义的中文翻译

高性能编程 笔记

Lipo Battery Charger with USB C Power Delivery Based on the STM32G0

Open Neural Network Compiler

微软开源 Quantum Katas，领先的量子编程解决方案 Programming exercises for learning Q# and quantum computing

学习python，关于与孩子一起学编程的代码

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org. http://www.cs.cmu.edu/afs/cs.cmu.edu/academic/class/15745-s14/public/lectures/

Efficient Large-scale Stereo Matching.

Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

c++代码实验 C++/C++11's usage

EKF-SLAM 算法实现，以ArUco码为路标，《概率机器人》第10章

C++ 网络库 https://blog.csdn.net/solstice/article/category/779646

Go编程时光，一个零基础入门 Golang 的教程

个人维护的安全知识框架,内容包括不仅限于 web安全、工控安全、取证、应急、蓝队设施部署、后渗透、Linux安全、各类靶机writup

通用视觉SLAM框架 A General Simultaneous Localization and Mapping Framework which supports feature based or direct method and different sensors including monocular camera, RGB-D sensors or any other input types can be handled.论文链接 http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhao_GSLAM_A_General_SLAM_Framework_and_Benchmark_ICCV_2019_paper.pdf

双目MSCKF视觉惯性里程计 Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight

Generate 3D dense point cloud based on ORB-SLAM, and build indoor navigation map using OctoMap.

TNN 训练时激活量三值化，参数全精度 –> infernce时，激活量，参数都三值化（不使用任何乘法）。用FPGA和ASIC设计了硬件

这篇文章主要是基于2D的检测框去拟合3D检测框，预测量主要有三个：1.三维框的大小（在x,y,z轴上的大小），2.旋转角，3.置信度。 3D Bounding Box Estimation Using Deep Learning and Geometry (MultiBin)

deeplearningbook学习笔记，来自于 http://www.deeplearningbook.org

A reliable, high-performance, thread safe, flexsible, clear-model, pure C logging library.

Useful CMake Examples

cpp implementation of robotics algorithms including localization, mapping, SLAM, path planning and control

A Python subset for a better MLIR programming experience

3D目标检测 Frustum PointNets for 3D Object Detection from RGB-D Data

Development repository for the Triton language and compiler

雷达点云数据障碍物检测 Obstacle detection with laser data

对BNN的简单扩展，量化激活函数，有线性量化与log量化两种，其1-bit量化即为BinaryNet。在正向传播过程中加入了均值为0的噪音。

人人都能用英语

锂电池快充充电器 Lipo Battery Charger with USB C Power Delivery Based on the STM32G0 https://zhuanlan.zhihu.com/p/143096853

LeetCode, HackRank, 剑指offer, classic algorithm implementation

【国赛】【美赛】数学建模相关算法 MATLAB实现

Linux内核与设备驱动程序学习笔记

A trivial gnuplot interface for c++

Point Cloud Library (PCL)

Linux平台下C++(C++98、C++03、C++11)实现的线程池

C++ headers(hpp) with Python style. 常用头文件 实现源文件函数

stb single-file public domain libraries for C/C++ https://www.jianshu.com/p/5e4b99586282

A lightweight tar library written in ANSI C

是一个静态代码分析工具，通过该工具，我们可以检查出代码中的一些潜在问题，同时也就实现了自动化的code review。 A static source code analysis tool to improve quality and reduce defects for C, C++ and Objective-C https://blog.csdn.net/TuGeLe/article/details/83349714

A C++ library for python-like list

C++ Insights - 用编译器的眼睛看你的源代码 C++ Insights - See your source code with the eyes of a compiler

A type-safe hash map implementation for C

Interactive & Asynchronous 3D Visualization Tool

A beautiful stack trace pretty printer for C++

Hands-On Design Patterns with C++, published by Packt

PX4 Autopilot Software

A repository containing C++11/14/17 concepts and code snippets 新特征

yolov3 :by using libdarknet.so; python3 and opencv3 ; video/img detect and save results

算法精粹--举一反三，抛弃题海战术

chhzh123's personal blog https://chhzh123.github.io

my blog

🍦 蓝桥杯竞赛练习题的题解(C/C++/Java)-努力成为萌萌的程序媛～

Gitbook based Blog, Android, Linux, Deep Learning, Computer Vision

darknet深度学习框架源码分析：详细中文注释，涵盖框架原理与实现语法分析

Commonly used image filters. :earth_americas: 包罗常见的图像滤波器。

Complete set of Chinese History E-books. :books: 完整全套的中国历史电子版

自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 关键词提取 新词发现 短语提取 自动摘要 文本分类 拼音简繁

学习caffe 书籍 http://pan.baidu.com/s/1slffF69 pd: 6688

基于3D卷积C3D做帧分类，然后预测存在行为的视频段并分类

简单直接可用博客模板

轻量级的--计算机视觉库

高性能分布式计算平台 A Flexible and Powerful Parameter Server for large-scale machine learning

用python做计算机视觉，人工智能，机器学习，深度学习等

fitlog是一款在深度学习训练中用于辅助用户记录日志和管理代码的工具

Models and examples built with TensorFlow

Deep Learning System core principles introduction.

High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.

An unofficial cuda assembler, for all generations of SASS, hopefully ：）

Applied AI experiments and examples for PyTorch

周知集锦 :sunglasses: Curated list of awesome lists

Production First and Production Ready End-to-End Speech Recognition Toolkit

Accessible large language models via k-bit quantization for PyTorch.

Older python debugger (please use python-trepan2 instead)

深度增强学习 训练 机械臂推开抓取 Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

What are learned in tiktoken?

参加华为AscendC算子编程比赛的代码

No description.

No description.

Several simple examples for popular neural network toolkits calling custom CUDA operators.

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

No description.

学习安全运营的记录 | The knowledge base of security operation

基于C++开发的视频行为分析系统v4系统，可以在不用考虑音视频开发，编解码开发，界面开发等情况下， 只需要训练自己的模型，开发自己的算法插件，就可以轻松实现出任何想要的视频行为检测，比如周界入侵，烟火检测，打架，斗殴，跌倒，人群聚集，电动车，垃圾箱，抽烟，攀爬，离岗睡岗，安全帽，充电桩，工作服， 疲劳检测，交通拥堵等等。

ESJZone 的小說備份

A minimal GPU design in Verilog to learn how GPUs work from the ground up

属于每个人的公众号”查特查特“上线啦！新问题、新方法、新发现，欢迎提PR！

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Image Signal Processor

camera pipeline

A place to record memories, knowledge and ideas | 记录回忆，知识和畅想的地方

Inference code for LLaMA models

My Blog WebSite

一个逗比写的各种逗比脚本~

opencv-mobile 通过调整编译参数，删减部分opencv源码，来最小化编译的 opencv 库提供了 opencv 常用的功能，如读写图片，处理，矩阵操作等等 版本与上游同步，无第三方依赖在绝大多数情况下，以 1/10 的体积无痛替换官方 opencv，尤其适合对体积有特殊要求的移动端和嵌入式环境

💩State-of-the-art shitcode principles your project should follow to call it a proper shitcode

Hackable and optimized Transformers building blocks, supporting a composable construction.

A parser, editor and profiler tool for ONNX models.

fast log and exp functions for x86/x64 SSE

code for fun

真AI人工智能

[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning

Makes ARM NEON documentation accessible (with examples)

Google's Next Gen Pose Estimation in PyTorch

User Guides For those new to the LLVM system.(LLVM系统的新用户指南,中文翻译版)

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

daily programming gemm https://zhuanlan.zhihu.com/p/95497033

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Skeleton-based action recognition models in PyTorch, including Two-Stream CNN, HCN, HCN-Baseline, Ta-CNN and Dynamic GCN