RGB-D-SLAM

My take on a SLAM, based on shape primitive recognition with a RGB-D camera. The system uses depth informations as a connected 2D graph to extract primitive shapes, and use them with 3D points and lines to estimate it's position in space. A map is created with those points, lines and primitive shapes.

The primitive detection is based on Fast Cylinder and Plane Extraction from Depth Cameras for Visua Odometry. See the Doxygen documentation on GitHub Pages.

For now, we are at the state of visual odometry with local mapping.

Process

feature detection & matching

The system starts by splitting the depth image as a 2D connected graph, and run a primitive analysis on it. This analysis extract local planar features, that are merged into bigger planes. Using an iterative RANSAC algorithm, those planar features are fitted to cylinders if possible, providing two kind of high level features. Those high level features are matched on one frame to another by comparing their normals and Inter-Over-Union score.

The system also extract points and lines, to improve reliability of pose extraction. The lines are extracted using LSD. The feature points are tracked by optical flow and matched by their BRIEF descriptors when needed, and every N frames to prevent optical flow drift.

local map

Every features are maintained in a local map, that keep tracks of the reliable local features. Those features parameters (positions, uncertainties, speed, ...) is updated if a map feature is matched, using an individual Kalman filter per feature (no bundle adjustment yet).

New features are maintained in a staged feature container, that behaves exactly like the local map, but as a lesser priority during the matching step.

pose optimization

The final pose for the frame is computed using the local map to detected feature matches. Outliers are filtered out using a simple RANSAC, and the final pose is computed using Levenberg Marquardt algorithm, with custom weighting functions.

The optimized pose is used to update the local map and motion model, in case the features are lost for a moment.

The complete systems runs in real time, between 30FPS and 60FPS for images of 640x480 pixels (depth and RGB images).

To be implemented soon

• Advanced camera parameter model
• Point descriptors based on custom neural network
• Usage of keyframe to separate local maps
• Loop closing based on multiscale neural network
• Use a graph between keyframe to represent the trajectory, and close the loop easily (using bundle adjustment)
• Create a new separate trajectory when loosing track of features, and merge it to the main trajectory when possible

packages

opencv
Eigen
g2o
pugixml

How to build Build

mkdir build && cd build
cmake ..
make

How to use

./slam_freiburg1 desk

Parameters

-h Display the help
-d displays the staged features (not yet in local map)
-f path to the file containing the data (depth, rgb, cam parameters)
-c use cylinder detection 
-j Drop j frames between slam process
-i index of starting frame (> 0)
-l compute line features
-s Save the trajectory in an output file

Check mem errors

valgrind --suppressions=/usr/share/opencv4/valgrind.supp --suppressions=/usr/share/opencv4/valgrind_3rdparty.supp ./slam_freiburg1 desk

References:

Primitive extraction

• Fast Cylinder and Plane Extraction from Depth Cameras for Visual Odometry
• Fast Sampling Plane Filtering, Polygon Construction and Merging from Depth Images
• Fast Plane Extraction in Organized Point Clouds Using Agglomerative HierarchicalClustering
• Depth image-based plane detection

Pose Optimization

• Using Quaternions for Parametrizing 3D Rotations in Unconstrained Nonlinear Optimization - 2001
• At All Costs: A Comparison of Robust Cost Functions for Camera Correspondence Outliers - 2015
• An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference Direction - 2019
• A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
• A General and Adaptive Robust Loss Function - 2019

Visual odometry

• LVT: Lightweight Visual Odometry for Autonomous Mobile Robots
• Dense RGB-D visual odometry using inverse depth
• SPLODE: Semi-Probabilistic Point and Line Odometry with Depth Estimation from RGB-D Camera Motion
• PL-SVO: Semi-Direct Monocular Visual Odometry byCombining Points and Line Segments
• Probabilistic Combination of Noisy Points andPlanes for RGB-D Odometry and Probabilistic RGB-D Odometry based on Points, Linesand Planes Under Depth Uncertainty - 2017
• Robust Stereo Visual Inertial Navigation System Based on Multi-Stage Outlier Removal in Dynamic Environments
• RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments - 2021

SLAM

• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• 3D SLAM in texture-less environments using rank order statistics
• 3D Mapping with an RGB-D Camera
• Online 3D SLAM by Registration of Large PlanarSurface Segments and Closed Form Pose-GraphRelaxation
• LIPS: LiDAR-Inertial 3D Plane SLAM
• Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments
• Monocular Object and Plane SLAM in Structured Environments
• Point-Plane SLAM Using Supposed Planes for Indoor Environments
• Stereo Plane SLAM Based on Intersecting Lines - 2020