Skip to main content

State of the Art SLAM techniques

Best Stereo SLAMs in 2017 are reviewed.

Namely, (in arbitrary order)

  • EKF-SLAM based, 
  • Keyframe based, 
  • Joint BA optimization based, 
  • RSLAM, 
  • S-PTAM, 
  • LSD-SLAM,  


Best RGB-D SLAMs in 2017 are also reviewed.

  • KinectFusion, 
  • Kintinuouns, 
  • DVO-SLAM, 
  • ElasticFusion, 
  • RGB-D SLAM,  


See my keypoints of the best Stereo SLAMs.


Stereo SLAM

Conditionally Independent Divide and Conquer EKF-SLAM [5] 

  • operate in large environments than other approaches at that time
  • uses both  close and far points
  • far points whose depth cannot be reliably estimated due to little disparity in the stereo camera 
  • uses an inverse depth parametrization [6]
  • shows empirically points can be triangulated reliably, if their depth is less than about 40 times the stereo baseline.

   
- Keyframe-based  Stereo SLAM
  - uses BA optimization in a local area to archive scalability.
  - [8]: joint optimization of BA (point-pose constraints) in a inner window
     -  pose-graph (pose-pose constraints) in an outer window of keyframes
     - achieves the constant time complexity by limiting the size of these windows
     - at the expense of not guaranteeing global consistency.

  - [9]: RSLAM uses a relative representation of landmarks and poses
    - performs relative BA in an active area, constrained by constant-time
    - able to close loops
    - allows to expand active areas at both sides of a loop
    - not enforcing global consistency

  - [10]:S-PTAM 
    - performs local BA
    - lacks large loop closing


 - [11]: LSD-SLAM
   - a semi-dense direct approach
   - minimizes photometric error in image regions with high gradient.
   - More robust than feature-based to 
     -  motion blur
     - low textured environments
   - severely degraded performance by unmodeled effects
     - rolling shutter
     - non-lambertian reflectance.


RGB-D SLAM

- KinectFusion [4]
   - fused all depth data from the sensor into a volumetric dense model
   - uses ICP with the model to track the camera pose.
   - limited to small workspace due to volumetric representation
   - lack of loop closing


- Kintinuous [12]:
  - operate in large environments
  - uses a rolling cyclical buffer
  - does loop closing with place recognition and pose graph optimization

- RGB-D SLAM [13]:
  - feature-based system
  - front-end computes frame-to-frame motion by feature matching and ICP.
  - back-end performs pose-graph optimization with loop closure constraints from a heuristic search.

- DVO-SLAM [14]:
  - optimizes a pose-graph
  - computes keyframe-to-keyframe constraints from a visual odometry
  - a visual odometry minimizes both photometric and depth error.
  - searches for loop candidates in a heuristic manner over all previous frames
  - not relying on place recognition.

- ElasticFusion [15]:
  - builds a surfel-based map of the environment.
  - a map-centric approach that doe do poses
  - performs loop closing with a non-rigid deformation to the map
  - not using the standard pose-graph optimization
  - impressive detail reconstruction
  - impressive localization accuracy
  - implementation limited to a room-size map due to the complexity scales with the number of surfels in the map.




Reference
[5] L. M. Paz, P. Pinie ́s, J. D. Tardo ́s, and J. Neira, “Large-scale 6-DOF SLAM with stereo-in-hand,” IEEE Trans. Robot., vol. 24, no. 5, pp. 946–957, 2008.


[6] J. Civera, A. J. Davison, and J. M. M. Montiel, “Inverse depth parametrization for monocular SLAM,” IEEE Trans. Robot., vol. 24, no. 5, pp. 932–945, 2008.


[7] H. Strasdat, J. M. M. Montiel, and A. J. Davison, “Visual SLAM: Why filter?” Image and Vision Computing, vol. 30, no. 2, pp. 65–77, 2012.


[8] H. Strasdat, A. J. Davison, J. M. M. Montiel, and K. Konolige, “Double window optimisation for constant time visual SLAM,” in IEEE Int. Conf. Comput. Vision (ICCV), 2011, pp. 2352–2359.


[9] C. Mei, G. Sibley, M. Cummins, P. Newman, and I. Reid, “RSLAM: A system for large-scale mapping in constant-time using stereo,” Int. J. Comput. Vision, vol. 94, no. 2, pp. 198–214, 2011.


[10] T. Pire, T. Fischer, J. Civera, P. De Cristo ́foris, and J. J. Berlles, “Stereo parallel tracking and mapping for robot localization,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2015, pp. 1373–1378.


[11] J. Engel, J. Stueckler, and D. Cremers, “Large-scale direct SLAM with stereo cameras,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2015.


[12] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard, and J. McDonald, “Real-time large-scale dense RGB-D SLAM with volu- metric fusion,” Int. J. Robot. Res., vol. 34, no. 4-5, pp. 598–626, 2015.

[13] F.Endres,J.Hess,J.Sturm,D.Cremers,andW.Burgard,“3-Dmapping with an RGB-D camera,” IEEE Trans. Robot., vol. 30, no. 1, pp. 177– 187, 2014.

[14] C. Kerl, J. Sturm, and D. Cremers, “Dense visual SLAM for RGB-D cameras,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2013. [15] T. Whelan, R. F. Salas-Moreno, B. Glocker, A. J. Davison, and S. Leutenegger, “ElasticFusion: Real-time dense SLAM and light source

estimation,” Int. J. Robot. Res., vol. 35, no. 14, pp. 1697–1716, 2016.

Comments

Post a Comment

Popular posts from this blog

How to project a camera plane A to a camera plane B

How to Create a holographic display and camcorder In the last part of the series "How to Create a Holographic Display and Camcorder", I talked about what the interest points, descriptors, and features to find the same object in two photos. In this part of the series, I'll talk about how to extract the depth of the object in two photos by calculating the disparity between the photos. In order to that, we need to construct a triangle mesh between correspondences. To construct a mesh, we will use Delaunnay triagulation.  Delaunnay Triagulation - It minimizes angles of all triangles, while the sigma of triangles is maximized. The reason for the triangulation is to do a piece wise affine transformation for each triangle mapped from a projective plane A to a projective plane B. A projective plane A is of a camera projective view at time t, while a projective plane B is of a camera projective view at time t+1. (or, at t-1.  It really doesn't matter)...
27 comments
Read more

How to train a neural network to retrieve 3D maps from videos

This blog is about how to train a neural network to extract depth maps from videos of moving people captured with a monocular camera. Note: With a monocular camera, extracting the depth map of moving people is difficult.  Difficulty is due to the motion blur and the rolling shutter of an image.  However, we can overcome these limitations by predicting the depth maps by the model trained with a generated dataset using SfM and MVS from the normalized videos. This normalized dataset can be the basis of the training set for the neural network to automatically extract the accurate depth maps from a typical video footage, without any further assistance from a MVS. To start this project with a SfM and a MVS, we will use TUM Dataset. So, the basic idea is to use SfM and Multiview Stereo to estimate depth, while serves as supervision during training. The RGB-D SLAM reference implementation from these papers are used: - RGB-D Slam (Robotics OS) - Real-time 3D Visual SLAM ...
Post a Comment
Read more