CVApr 15, 2022

Event-aided Direct Sparse Odometry

arXiv:2204.07640v2136 citationsh-index: 115
Originality Incremental advance
AI Analysis

This enables low-power motion-tracking applications where frames are triggered sparingly, addressing a domain-specific need in robotics and autonomous systems.

The paper tackles the problem of visual odometry by introducing EDS, a direct monocular method using events and frames to track camera motion between frames, achieving lower frame rates than state-of-the-art frame-based solutions for a target error performance.

We introduce EDS, a direct monocular visual odometry using events and frames. Our algorithm leverages the event generation model to track the camera motion in the blind time between frames. The method formulates a direct probabilistic approach of observed brightness increments. Per-pixel brightness increments are predicted using a sparse number of selected 3D points and are compared to the events via the brightness increment error to estimate camera motion. The method recovers a semi-dense 3D map using photometric bundle adjustment. EDS is the first method to perform 6-DOF VO using events and frames with a direct approach. By design, it overcomes the problem of changing appearance in indirect methods. We also show that, for a target error performance, EDS can work at lower frame rates than state-of-the-art frame-based VO solutions. This opens the door to low-power motion-tracking applications where frames are sparingly triggered "on demand" and our method tracks the motion in between. We release code and datasets to the public.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes