oym1994 Goto Github PK

protobuf

Protocol Buffers - Google's data interchange format

putslam

RGBD-based Simultaneous Localization and Mapping

pytorch-deeplab-xception

DeepLab v3+ model in PyTorch. Support different backbones.

pytorch_robotics_transformer

A PyTorch re-implementation of the RT-1 (Robotics Transformer)

recent_slam_research

跟踪SLAM前沿动态【周更】

refusion

ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals

rm_main_board_code_college

RM主控板官方程序college版,含自动瞄准射击

rm_main_board_code_junior

RM开发板官方源码，仅供参考学习，欢迎交流

robotics_transformer_tensorflow

RT1 with training code

ros

Core ROS packages

ros-academy-for-beginners

**大学MOOC《机器人操作系统入门》课程代码示例

rqt_timeplot

绘制相机-imu-轮速记时间戳

se2clam

SE(2)-Constrained Localization and Mapping by Fusing Odometry and Vision (IEEE Transactions on Cybernetics 2019)

se2lam

Visual-Odometric On-SE(2) Localization and Mapping (ICRA 2019)

sfnd_2d_feature_tracking

Keypoints Detector(HARRIS, FAST, BRISK, ORB, AKAZE, and SIFT), Patch Descriptor(BRIEF, ORB, FREAK, AKAZE and SIFT)，and Matching(BFmatching, FLANN matching)).

slam_framework_overview

经典slam框架论文及代码地址汇总

slambook-en

The English version of 14 lectures on visual SLAM.

slslam

Building a 3D Line-based Map Using a Stereo SLAM

superpoint

Efficient neural feature detector and descriptor

tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow-c-mnist

tensorflow-enet

TensorFlow implementation of ENet

tensorflow-fcn

An Implementation of Fully Convolutional Networks in Tensorflow.

tensorflow-learning

B站上炼数成金的公开课笔记

tensorflow-tutorial

Some tensorflow demo

tracking_sdf

Implementation of "Real-Time Camera Tracking and 3D Reconstruction Using Signed Distance Functions" by Bylow et al.

udacity-nanodegrees

:mortar_board: List of Udacity Nanodegree programs with links to the free courses in their curricula

vins-course

VINS-Mono code without Ceres or ROS

vins-fusion-annotation

对VINS-FUSION进行注释

vo-slam-review

SLAM is mainly divided into two parts: the front end and the back end. The front end is the visual odometer (VO), which roughly estimates the motion of the camera based on the information of adjacent images and provides a good initial value for the back end.The implementation methods of VO can be divided into two categories according to whether features are extracted or not: feature point-based methods, and direct methods without feature points. VO based on feature points is stable and insensitive to illumination and dynamic objects