Home

概述 Ceres Solver is an open source C++ library for modeling and solving large, complicated optimization problems. 使用 Ceres Solver 求解非线性优化问题，主要包括以下几部分： 构建代价函数(cost function) 或 残差(residual) 构建损失函数(loss function) 构建优化问题(ceres::Problem)：通过 AddResidualBlock 添加代价函数(cost function)、损失函数(loss function) 和 待优化状态量 Los...

[TOC] 概述 Monocular visual-inertial odometry with relocalization achieved via nonlinear graph optimization-based, tightly-coupled, sliding window, visual-inertial bundle adjustment. 代码（注释版）：cggos/vins_mono_cg PDF文档：https://github.com/cggos/vins_mono_cg/blob/master/docs/vinsmono_note_cg.pdf （持续更新中） 1. 测量预处理 1.1 前端视觉处理 Simple f...

[TOC] Overview 本文介绍在 Ubuntu 16.04（ROS Kinetic）的PC平台上使用 RealSense ZR300 的 fisheye camera (FOV: 100x133) + IMU 运行 我对VINS-Mono的改版 cggos/vins_mono_cg。 安装&运行 ZR300驱动 RealSense ZR300 的加速度计和陀螺仪的时间戳不是完全相同的（加速度计的频率为250Hz而陀螺仪的频率为200Hz），但是由于RealSense ZR300的时间戳是在硬件上打的，不是操作系统接收到到图像和IMU的时间戳，所以可以通过 插值 的方式使它们的时间戳对齐。 这里使用 maplab 推荐的驱动：ethz-asl 的 maplab_...

[TOC] 极线搜索 If we are using only the left camera, we can’t find the 3D point corresponding to the point $x$ in image because every point on the line $OX$ projects to the same point on the image plane. But consider the right image also. Now different points on the line $OX$ projects to different points ( $x^{\prime}$) in right plane. So wi...

Overview The gray region is the epipolar plane The orange line is the baseline the two blue lines are the epipolar lines Basic Epipolar Geometry entities for pinhole cameras and panoramic camera sensors Fundamental Matrix $F$ maps a point in one image to a line (epiline) in the other image Calculated f...

[TOC] Overview Lens Projections About the various projections of the photographic objective lenses Models for the various classical lens projections 鱼眼相机成像、校准和拼接(笔记) Computer Generated Angular Fisheye Projections Perspective and fisheye imaging process Optics: Terminology Diop...

[TOC] Overview This code rubengooj/pl-slam contains an algorithm to compute stereo visual SLAM by using both point and line segment features. Related Publication @article{gomez2017pl, title = {PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments}, author = {Gomez-Ojeda, Ruben and Zuñiga-Noël, D...

[TOC] Overview Types of Image Feature: Edges Corners (also known as interest points) Blobs (also known as regions of interest ) Image Corners/Keypoints Keypoints Structure (from OpenCV): pt: x & y coordinates of the keypoint size: keypoint diameter angle: keypoint orientation response: keypoint detector response ...