Event-aided Direct Sparse Odometry
arXiv:2204.07640 · doi:10.1109/CVPR52688.2022.00569
Abstract
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.
arXiv comment16 pages, 14 Figures, Page: https://rpg.ifi.uzh.ch/eds
References in corpus (10)
- ORB-SLAM: a Versatile and Accurate Monocular SLAM System
- ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
- Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
- On-Manifold Preintegration for Real-Time Visual-Inertial Odometry
- Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios
- Learning High-Speed Flight in the Wild
- A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation
- Event-based Stereo Visual Odometry
- Event-based, 6-DOF Camera Tracking from Photometric Depth Maps
- Event-based Camera Pose Tracking using a Generative Event Model
Cited by in corpus (11)
- Autonomous Drone Racing: A Survey
- Event-based Background-Oriented Schlieren
- Event-based Stereo Depth Estimation: A Survey
- A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
- Data-Driven Feature Tracking for Event Cameras With and Without Frames
- DH-PTAM: A Deep Hybrid Stereo Events-Frames Parallel Tracking And Mapping System
- An N-Point Linear Solver for Line and Motion Estimation with Event Cameras
- ES-PTAM: Event-based Stereo Parallel Tracking and Mapping
- MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice
- Event-based Photometric Bundle Adjustment
- Event-based Mosaicing Bundle Adjustment