备忘，记录语义SLAM的一些论文和学习资料
涉及的部分论文戳这里，免费下载

相关算法

1.AVP-SLAM
论文：Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot
代码：有基于仿真的复现版本AVP-SLAM-PLUS,参考版本AVP-SLAM-SIM
https://github.com/liuguitao/AVP-SLAM-PLUS
https://github.com/TurtleZhong/AVP-SLAM-SIM

有兴趣可以看下AVP-SLAM-PLUS的代码，思路比较简单，如果手中有拼接和分割比较好的环视数据集比较容易进行修改，基本原理就是把包含语义信息的图像转成点云再使用icp，但是在使用自己的数据时icp点云配准效果很不好，后来用特征匹配给他提供了下初值效果的到了改善。

再多说一句，秦通博士的原论文是基于惯导和轮速计提供的位姿实现的语义地图的拼接，之后又使用icp进行局部地图优化等等操作优化累计误差，如果有惯导和轮速计数据应该会得到比较好的建图和定位效果，因为在调试过程中如果惯导比较给力，在地库里面直接通过惯导和轮速计在短时间的到的位姿还是比较准确的。

2.DSP-SLAM室外车辆语义信息检测
论文：DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
代码：https://github.com/JingwenWang95/DSP-SLAM

3.Probabilistic Data Association for Semantic SLAM

4.VSO
VSO: Visual Semantic Odometry

5.DS-SLAM
论文：DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
代码：https://github.com/ivipsourcecode/DS-SLAM.git

6.Kimera
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

7.DeepLabv3+SLAM
Semantic SLAM Based on Improvement DeepLabv3+ in Dynamic Scenarios

语义SLAM用于特征选择

SalientDSO:Bringing Attention to Direct Sparse Odometry

Visual SLAM with Network Uncertainty Informed Feature Selection

毕业论文：SIVO：Semantically Informed Visual odometry and mapping
代码：https://github.com/navganti/SIVO

Utilizing Semantic Visual Landmarks for Precise Vehicle Navigation

Detect-SLAM: Making Object Detection and SLAM Mutually Beneficial_WACV2018
DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments—IROS2018
DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes—IEEE Robotics and Automation Letters, 2018
代码：https://github.com/BertaBescos/DynaSLAM
Semantic Monocular SLAM for Highly Dynamic Environments—IROS2018
Semantic segmentation–aided visual odometry for urban autonomous driving—IJARS2017
Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving—ECCV2018

Long-term Visual Localization using Semantically Segmented Images—ICRA2018