GithubHelp home page GithubHelp logo

菜鸡SLAMer

Mail Badge B站

GIF

👋 关于我 | About Zeshi Lin

  • A SLAMer who loves programming and robotics. & Open Source enthusiast.
  • 🌱 Currently working in Guangzhou, China.
  • 💬 Cheat me about SLAM and my projects on [email protected]
  • ⚡ Fun fact: Algorhythms related with perception.

🛠 技术栈 | Tech Stack

  • 💻   C++ Python Linux CMake
  • 🔧   ROS OpenCV G2O GTSAM
  • 🛢   Git GitHub Markdown

⭐️ 开源项目 | Open Source Projects

Readme Card Readme Card Readme Card

  • ONNX-CPP-RUNNER：Based on ONNX API and LightGlue, a C++ inference deployment project for SuperPoint and LightGlue.
  • super-vio：Front-end of this vio algorithm is based on SuperPoint and LightGlue. Backend is based on GTSAM, IMU preintegration is also implementing with GTSAM.
  • lk-vio：Front-end of this vio algorithm is based on ORB dand LK Optical Flow. Backend is based on g20.

📹 项目效果 | Project Demo

  • 基于LIO-SAM的高动态场景SLAM，添加了重力因子和iVoX数据结构的支持。视频为在水上行驶的建图过程。 Video on Bilibili

📝 最近动态 | Recent Updates

  • Implmenting the super-vio project.
  • Reconstructing the lk-vio project with ROS to visualize the results. Integrating with g2o for IMU preintegration.

📫 工作历史 | Work Experience

  • 基于ORB-SLAM3的VR定位算法，前端匹配改为用光流法，提高算法在移动端的实时性。
  • 基于Cartographer的2D激光SLAM算法，剔除ROS依赖，改用共享内存通信；修改IMU数据的利用方式，改为IMU预积分，提高算法鲁棒性。
  • 基于LIO-SAM的3D激光SLAM算法，添加了重力因子和iVoX数据结构的支持，提高算法在高动态场景下的鲁棒性以及降低计算量。
  • 基于3D激光点云的水面点云分割
  • 基于PP-PicoDet检测移动库位以及PP-TinyPose检测关键点的定位算法，为机器在入库阶段提供更精准的定位。
  • 无人采水船的整体算法代码架构，主要负责基于摄像头的目标检测和深度估计，基于毫秒波雷达以及超声波的障碍物感知，以及栅格地图的更新。

JerseyLin's Projects

cam_lidar_calibration icon cam_lidar_calibration

(ITSC 2021) Optimising the selection of samples for robust lidar camera calibration. This package estimates the calibration parameters from camera to lidar frame.

d-liom icon d-liom

Tightly-coupled Direct LiDAR-Inertial Odometry and Mapping Based on Cartographer3D.

faster-lio icon faster-lio

Faster-LIO: Lightweight Tightly Coupled Lidar-inertial Odometry using Parallel Sparse Incremental Voxels

gf_orb_slam2 icon gf_orb_slam2

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

glue-factory icon glue-factory

Training library for local feature detection and matching

gms-feature-matcher icon gms-feature-matcher

GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence (CVPR 17 & IJCV 20)

ikd-tree-detailed icon ikd-tree-detailed

「香港大学 MaRS 实验室」开源 ikd-Tree 算法中文注释版；新增了header-only分支，便于直接嵌入工程。

lk-vio icon lk-vio

a vio based on ORB and Optical Flow

orb_slam3 icon orb_slam3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

patchwork icon patchwork

SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)

patchwork-plusplus icon patchwork-plusplus

Patchwork++: Fast and robust ground segmentation method for 3D point cloud. @ IROS'22

super-vio icon super-vio

a simple vio based on super-point, light-glue and g2o

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.