Object-based SLAM Using Superquadrics

Visual SLAM uses visual information, typically point features, to localise a camera and, at the same time, map the environment. In recent years, there has been interest in using scene-understanding capabilities to enhance the mapping process and object-level SLAM systems have appeared in response. However, most of the previous work is limited to prestored object models or pre-trained networks to represent the objects, which limits working scenarios or uses representations with limited scope, such as cubes or quadrics. To address this, we propose to use superquadrics as the object representation and, in this paper, present a proof of principle SLAM system in which object-based mapping is fully integrated with camera tracking via keyframe optimisation. The system was tested on simulated and real datasets, and the results show that the system can achieve lightweight and comparatively good object representation whilst also giving good camera trajectories estimates under certain scenarios.

Authors

• Yifan Xing
• Noe Samano
• Wen Fan 0001
• Andrew Calway

Keywords

• Bundle adjustment
• Visualization
• Simultaneous localization and mapping
• Shape
• Cameras
• Rendering (computer graphics)
• Probabilistic logic
• Trajectory
• Optimization
• Intelligent robots
• Simulated Datasets
• Feature Points
• Quadric
• Ellipsoid
• Point Cloud
• Bounding Box
• Class I
• Depth Images
• Object Shape
• Camera Position
• Current Frame
• Objects In The Scene
• Complex Objects
• Map Representation
• Final Error
• Camera Pose
• Detailed Reconstruction
• Dense Surface
• 3D Pose
• 3D Bounding Box
• Perfect Shape
• Ground Truth Trajectory
• Pose Parameters
• Shampoo