IEEE Transactions on Pattern Analysis and Machine Intelligence· 2017Q1
Direct Sparse Odometry
- 2,928citations
- Q1SCImago
- 2017year
Short summary
Direct Sparse Odometry (DSO) introduces a novel formulation for visual odometry that jointly optimizes camera motion and 3D structure using a direct, sparse, and probabilistic model, achieving real-time performance.
AI-generated from the title and abstract; the full text is not read.
Key points
- DSO uses a direct, sparse, probabilistic model to minimize photometric error for joint optimization of motion and structure.
- It achieves real-time performance by sampling pixels evenly and omitting smoothness priors.
- The method naturally handles edges and featureless surfaces without relying on keypoint detectors.
- DSO integrates full photometric calibration, including exposure and lens effects.
AI-generated from the title and abstract; the full text is not read.
Abstract
Direct Sparse Odometry (DSO) is a visual odometry method based on a novel, highly accurate sparse and direct structure and motion formulation. It combines a fully direct probabilistic model (minimizing a photometric error) with consistent, joint optimization of all model parameters, including geometry-represented as inverse depth in a reference frame-and camera motion. This is achieved in real time by omitting the smoothness prior used in other direct methods and instead sampling pixels evenly throughout the images. Since our method does not depend on keypoint detectors or descriptors, it can naturally sample pixels from across all image regions that have intensity gradient, including edges or smooth intensity variations on essentially featureless walls. The proposed model integrates a full photometric calibration, accounting for exposure time, lens vignetting, and non-linear response functions. We thoroughly evaluate our method on three different datasets comprising several hours of video. The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness.
The authors' abstract, as published at the source. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Aerospace Engineering
Aerospace EngineeringEngineering