视觉惯性里程计Visual–Inertial Odometry(VIO)概述
周围很多朋友开始做vio了，之前在知乎上也和胖爷讨论过这个问题，本文主要来自于知乎的讨论。 来自https://www.zhihu.com/question/53571648/answer/137726592 个人理解错误的地方还请不吝赐教，转载请标明出处，内容如有改动更新，请看原博：http ...
原文：VIO概述 On-Manifold Preintegration for Real-Time Visual--Inertial Odometry
目前的研究方向可以总结为在滤波算法中实现高精度，在优化算法中追求实时性 当加入IMU后，研究方向分为松耦合和紧耦合，松耦合分别单独计算出IMU测量得到的状态和视觉里程计得到的状态然后融合，紧耦合则将IMU测量和视觉约束信息放在一个非线性优化函数中去优化 紧耦合的框架使得IMU数据可以对视觉里程计进行矫正，同时视觉里程计信息也可以矫正IMU的零偏，因此一般认为紧耦合的定位精度较高 个人认为松耦合和滤 ...
2017-04-28 15:04 0 3287 推荐指数：
相关推荐
译文：PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features 摘要：为了解决基于惯性测量和视觉观测的相机轨迹估计和构建结构三维（3D）地图的问题，本文提出了点线视觉惯性里程计 ...
Real-Time MDNet
Real-Time MDNet ECCV 2018 2018-10-22 15:52:01 Paper：http://openaccess.thecvf.com/content_ECCV_2018/papers ...
论文笔记：Deeper and Wider Siamese Networks for Real-Time Visual Tracking
Deeper and Wider Siamese Networks for Real-Time Visual TrackingUpdated on 2019-04-01 16:10:37 Paper (arXiv V3)：https://arxiv.org/pdf/1901.01660.pdf ...
论文阅读之：Deep Meta Learning for Real-Time Visual Tracking based on Target-Specific Feature Space
Deep Meta Learning for Real-Time Visual Tracking based on Target-Specific Feature Space 2018-01-04 15:58:15 Paper: https://arxiv.org/pdf ...
论文笔记：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking 本文目标在于 tracking performance 和 efficiency 之间达到一种平衡 ...
论文笔记：Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking 2019-03-20 16:45:23 Paper：https://arxiv.org/pdf/1812.06148.pdf Project ...
YOLACT: Real-Time Instance Segmentation
论文： YOLACT: Real-Time Instance Segmentation 目录 0.简介 1.YOLACT结构 2.Prototypes 3.Coefficients 4. InstanceMasks组装 loss ...