[DeepLearning]结合目标检测、语义分割的语义SLAM总结。

简要记录自己学习过程中一些经典SLAM框架结合经典目标检测语义分割框架 的语义SLAM程序。

1. Semantc SLAM

Semantc SLAM
特点:

• ORB_SLAM2, used as our SLAM backend.
• pytorch-semseg, used as our semantic segmantation library.
• octomap, used as our map representation.
• pcl library, used for point cloud processing.
  

2. orb-slam2_with_semantic_label

Qi X, Yang S, Yan Y. Deep Learning Based Semantic Labelling of 3D Point Cloud in Visual SLAM[C]//IOP Conference Series: Materials Science and Engineering. IOP Publishing, 2018, 428(1): 012023.
国防科技大学高性能计算国家重点实验室

ORB-SLAM2+YOLO3

3.Meaningful maps with object-oriented semantic mapping

Sünderhauf N, Pham T T, Latif Y, et al. Meaningful maps with object-oriented semantic mapping[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017: 5079-5085.

ORB-SLAM2+SSD

4. DynaSLAM: Tracking, mapping, and inpainting in dynamic scenes

DynaSLAM

Bescos B, Fácil J M, Civera J, et al. DynaSLAM: Tracking, mapping, and inpainting in dynamic scenes[J]. IEEE Robotics and Automation Letters, 2018, 3(4): 4076-4083.

ORB-SLAM2 + Mask R-CNN

5. DA-RNN: Semantic mapping with data associated recurrent neural networks

DA-RNN

Xiang Y, Fox D. DA-RNN: Semantic mapping with data associated recurrent neural networks[J]. arXiv preprint arXiv:1703.03098, 2017.

RNN+CNN 语义分割

6. Ds-slam: A semantic visual slam towards dynamic environments

Ds-SLAM

Yu C, Liu Z, Liu X J, et al. Ds-slam: A semantic visual slam towards dynamic environments[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 1168-1174.

SegNet+ORB SLAM2

7. Maskfusion: Real-time recognition, tracking and reconstruction of multiple moving objects

MaskFusion

Runz M, Buffier M, Agapito L. Maskfusion: Real-time recognition, tracking and reconstruction of multiple moving objects[C]//2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). IEEE, 2018: 10-20.

MaskFusion + ElasticFusion