Multi-Sensor Fusion: IMU and 6DoF Odometry Loosely-Coupled Fusion based on ESKF
[TOC]
code: cggos/imu_x_fusion
Infrared(IR) Light of Depth Camera
[TOC]
Overview
The infrared light recording of the devices we tested. The iPad LiDAR and the iPhone LiDAR emit point grids. The sensor of the Note10+ ToF flashes scattered light. The Pixel uses only its cameras.
Realsense ZR300 (Structure Light)
Realsense D435i (Structure Light)
Oppo R11s (ToF)
Huawei P...
基于ARKit的AR尺子Demo代码分析
Code: https://github.com/levantAJ/Measure
UIViewController
final class ViewController: UIViewController {
override func touchesBegan(_ touches: Set<UITouch>, with event: UIEvent?) {
resetValues()
isMeasuring = true
targetImageView.image = UIImage(named: "targetGreen")
}
override func to...
Multi-Sensor Fusion: Vehicle Localization based on Particle Filter
[TOC]
Overview
code: cggos/carnd_p3_kidnapped_vehicle
粒子滤波(Particle Filter) 没有线性高斯分布的假设;相对于直方图滤波,粒子滤波(Particle Filter)不需要对状态空间进行区间划分。粒子滤波算法采用很多粒子对置信度进行近似,每个粒子都是对t时刻机器人实际状态的一个猜测。
越接近t时刻的Ground Truth状态描述的粒子,权重越高。
粒子更新的过程类似于达尔文的自然选择(Natural Selection)机制,与当前Sensor测量状态越匹配的粒子,有更大的机会生存下来,与Sensor测量结果不符的粒子会被淘汰掉,最终粒子都会集中在正确的状态附近。
粒子滤波(Particle F...
Multi-Sensor Fusion: LiDAR and Radar fusion based on UKF
[TOC]
Overview
code: cggos/lidar_radar_fusion_ekf_ukf
EKF v.s. UKF v.s. PF
EKF: 通过 泰勒分解将模型线性化 求出预测模型的概率均值和方差
线性、高斯
对于非线性问题, EKF除了计算量大,还有线性误差的影响
UKF: 通过 不敏变换 来求出预测模型的均值和方差
非线性、高斯
UKF生成了一些点,来近似非线性,由这些点来决定实际x和P的取值范围
跟 粒子滤波器(PF) 不同的是,UKF里Sigma点的生成并没有概率的问题
...
(Paper Reading) A Novel Feedback Mechanism-Based Stereo Visual-Inertial SLAM
Overview
the filtering-based frontend VIO
the optimization-based backend with loop closure
the state feedback
Inspired by the idea of [38], we feed the optimized state produced by the backend back to the frontend to correct the state estimation
The frontend is used for pose estimation and map construction, whereas the bac...
Zero Velocity Update (ZUPT) in OpenVINS
[TOC]
Overview
The key idea of the zero velocity update (ZUPT) is to allow for the system to reduce its uncertainty leveraging motion knowledge (i.e. leverage the fact that the system is stationary).
This is of particular importance in cases where we have a monocular system without any temporal SLAM features. In this case, if we are stationar...
Photometric Calibration
[TOC]
Overview
https://github.com/tum-vision/mono_dataset_code
https://blog.csdn.net/KYJL888/article/details/104893357
https://github.com/tum-vision/online_photometric_calibration
Install
安装aruco marker dection,用来标定渐晕
cd mono_dataset_code/thirdparty
tar -zxvf aruco-1.3.0.tar.gz
cd aruco-1.3.0/
mkdir build
cd build
cmake ..
make
sudo...
100 post articles, 13 pages.