Event-based 3D SLAM with a depth-augmented dynamic vision sensor

We present the D-eDVS- a combined event-based 3D sensor — and a novel event-based full-3D simultaneous localization and mapping algorithm which works exclusively with the sparse stream of visual data provided by the D-eDVS. The D-eDVS is a combination of the established PrimeSense RGB-D sensor and a biologically inspired embedded dynamic vision sensor. Dynamic vision sensors only react to dynamic contrast changes and output data in form of a sparse stream of events which represent individual pixel locations. We demonstrate how an event-based dynamic vision sensor can be fused with a classic frame-based RGB-D sensor to produce a sparse stream of depth-augmented 3D points. The advantages of a sparse, event-based stream are a much smaller amount of generated data, thus more efficient resource usage, and a continuous representation of motion allowing lag-free tracking. Our event-based SLAM algorithm is highly efficient and runs 20 times faster than realtime, provides localization updates at several hundred Hertz, and produces excellent results. We compare our method against ground truth from an external tracking system and two state-of-the-art algorithms on a new dataset which we release in combination with this paper.

Authors

• David Weikersdorfer
• David B. Adrian
• Daniel Cremers
• Jörg Conradt

Keywords

• Three-dimensional displays
• Simultaneous localization and mapping
• Cameras
• Runtime
• Current measurement
• Heuristic algorithms
• Dynamic Vision Sensor
• Event-based 3D
• Dynamic Changes
• Pixel Location
• Motor Representations
• Event Stream
• RGB-D Sensor
• Root Mean Square Error
• Color Images
• Transformation Matrix
• Pixel Resolution
• Depth Images
• Low Latency
• Depth Information
• Motion Model
• Image Point
• Depth Camera
• Particle Filter
• Depth Values
• Dynamic Bayesian Network
• Power In Watts
• High Power Consumption
• Markov Property
• Voxel Grid
• Nearest Integer
• Exponential Decay Model
• Sparse Grid
• Power Consumption