[TOC] Overview in ~/.bashrc(or /etc/profile or /etc/environment) 1234567891011export JAVA_HOME=/home/cg/tools/android_tools/jdk1.8.0_251export JRE_HOME=$JAVA_HOME/jreexport CLASSPATH=.:$JAVA_HOME/lib

[TOC] http://stackoverflow.com/questions/8744994/android-camera-set-resolution http://stackoverflow.com/questions/10913181/camera-preview-is-not-restarting http://stackoverflow.com/questions/1091368

[TOC] NDK Build Generate .so or .a files using NDK tools: Edit .java file; Generate header file for the java file using JDK tools javac and javah; 123# 在 `src` 目录下javac com/ndk/test/OpenCVTest.javaja

Overview 旋转转换 Maths - Rotation conversions ptam_cg/src/Tools.cc 旋转表示 旋转矩阵 (Rotation Matrix) \[ \mathbf{R} = \begin{bmatrix} r_{11} & r_{12} & r_{13} \\ r_{21} & r_{22} & r_{23}

[TOC] Overview What Is Camera Calibration? Camera Calibration Matlab Calibrating the VI Sensor 张氏法相机标定 Multi-Camera Self-Calibration LIBCBDETECT: Corner and Checkerboard Detection: MATLAB code for fu

[TOC] Overview 插值：求过已知有限个数据点的近似函数。 拟合：已知有限个数据点，求近似函数，不要求过已知数据点，只要求在某种意义下它在这些点上的总偏差最小。 插值和拟合都是要根据一组数据构造一个函数作为近似，由于近似的要求不同，二者的数学方法上是完全不同的。而面对一个实际问题，究竟应该用插值还是拟合，有时容易确定，有时则并不明显。 插值 Comparison of 1D and

Overview [1] 图片的解析度即每英寸图像所包含的像素数量（1 英寸=2.54厘米）， 一般以PPP（法语：points par pouce)或者DPI （英语：dots per inch）为单位。像素（或者点）越多，图像包含的信息越多（越精确）。例如，300dpi的解析度代表图片在其宽度和高度上各有300像素，因此一共有90 000 像素（300x300 dpi）。 根据这个公式，很容易

mikeferguson/robot_calibration: Generic calibration for robots pangfumin/odom_extrinsic_calibrate: Odom intrinsic and odom-sensors extrinsic calibration on SE2 using batch optimization Spatial Hand-

[TOC] Overview 服务机器人究竟是如何实现自主定位导航的？ 在实现自主导航之前，移动机器人都有哪些避障方法？ 机器人自主移动的四大核心功能： 环境构建 自主导航（室内定位、智能避障、路径规划等） 智能跟随 自主回充 SLAM & 自主导航 自主导航，从大的方面来讲包括局域导航和全局导航两部分。 局域导航是指通过视觉、雷达、超声波等传感器实时获取当前环境信

[TOC] IMU测量模型（离散时间） IMU测量模型： \[ \begin{aligned} {\omega}_m &= \omega + b_{gd} + n_{gd} \\ a_m &= a + b_{ad} + n_{ad} \end{aligned} \] 其中， 离散时间的 Bias： \[ \begin{aligned} b_{gd}[k] &= b_{gd}

[TOC] Overview HKUST-Aerial-Robotics/VINS-kidnap: VINS-Fusion with Cerebro vins kidnap安装使用 Install Nvidia Drive and CUDA ubuntu上安装NVIDIA驱动和cuda9.0，及NVIDIA-Docker Install Docker and Nvidia-Docker

[TOC] Overview ethz-asl/maplab: An open visual-inertial mapping framework. Maplab Framework Typical workflow Online ROVIOLI frontend Offline maplab console a convenient console user interf

[TOC] Overview Alg. PDF: Formula Derivation and Code Analysis of S-MSCKF Code: 本文 1. ImageProcessor initialize loadParameters create FastFeatureDetector imuCallback imu_msg_buffer.push_back(*msg)

[TOC] Overview 代码：lidar_radar_ekf_fusion System State Vector \[ x = [p_x, p_y, v_x, v_y]^T \in \mathbb{R}^{4 \times 1} \] State Transition & Measurement Function State transition function: \[ x^

[TOC] Overview 代码：imu_x_fusion System State Vector the nominal-state \(\mathbf{x}\) and the error-state \(\delta \mathbf{x}\) \[ \mathbf{x} = \begin{bmatrix} \mathbf{p} \\ \mathbf{v} \\ \math

[TOC] 最小二乘问题 最小二乘问题（Least Squares Problem），即 \[ \min_{\mathbf{x}} \mathbf{F}(\mathbf{x}) = \frac{1}{2} {\|\mathbf{f}(\mathbf{x})\|}^2_2 \] 其中，\(\mathbf{F}(\mathbf{x})\) 为 目标函数，\(\mathbf{f}(\mathbf{x})

version: 0.11.13-kinetic RTAB-Map (Real-Time Appearance-Based Mapping) is a RGB-D, Stereo and Lidar Graph-Based SLAM approach based on an incremental appearance-based loop closure detector. RTAB-Map

[TOC] Overview Deepdrive is an open simulation platform built to accelerate progress and increase transparency in self-driving AI. BerkeleyDeepDrive: We seek to merge deep learning with automotiv

[TOC] Overview the note is from Apollo Self-Driving Car Lesson Self-Driving Overview why need self-driving car 5 driving levels self-driving car history how self-driving car work hardware