Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
research:vslam:vi-dso [2017/09/20 02:22] Lukas von Stumberg Added supplementary material and video. |
research:vslam:vi-dso [2018/04/17 17:22] Lukas von Stumberg |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ==== Direct Sparse Visual-Inertial Odometry | + | ====== |
- | + | **Contact:** [[members:stumberg|Lukas von Stumberg]], [[members:usenko]], | |
- | This page provides supplementary material and a video to the paper "Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization". | + | |
- | + | ||
- | The supplementary material can be downloaded at: {{ :research: | + | |
- | The video is available at: [[https:// | + | |
< | < | ||
- | <iframe width=" | + | <iframe width=" |
</ | </ | ||
+ | |||
+ | ===== Abstract ===== | ||
+ | We present **VI-DSO**, a novel approach for visual-inertial odometry, | ||
+ | which jointly estimates camera poses and sparse scene | ||
+ | geometry by minimizing photometric and IMU measurement | ||
+ | errors in a combined energy functional. The visual part of | ||
+ | the system performs a bundle-adjustment like optimization | ||
+ | on a sparse set of points, but unlike key-point based | ||
+ | systems it directly minimizes a photometric error. This | ||
+ | makes it possible for the system to track not only corners, | ||
+ | but any pixels with large enough intensity gradients. IMU | ||
+ | information is accumulated between several frames using | ||
+ | measurement preintegration, | ||
+ | optimization as an additional constraint between keyframes. | ||
+ | We explicitly include scale and gravity direction into our | ||
+ | model and jointly optimize them together with other | ||
+ | variables such as poses. As the scale is often not | ||
+ | immediately observable using IMU data this allows us to | ||
+ | initialize our visual-inertial system with an arbitrary | ||
+ | scale instead of having to delay the initialization until | ||
+ | everything is observable. We perform partial | ||
+ | marginalization of old variables so that updates can be | ||
+ | computed in a reasonable time. In order to keep the system | ||
+ | consistent we propose a novel strategy which we call | ||
+ | " | ||
+ | partial marginalization even in cases where the initial | ||
+ | scale estimate is far from the optimum. We evaluate our | ||
+ | method on the challenging EuRoC dataset, showing that VI-DSO outperforms the state of the art. | ||
+ | |||
+ | ===== Downloads ===== | ||
+ | The paper can be downloaded at: http:// | ||
+ | There is also supplementary material with additional evaluation and mathematical derivations at: {{ : | ||
+ | The video is available at: [[https:// | ||
+ | |||
+ | The project is based on [[: | ||
+ | |||
+ | < | ||
+ | < | ||
+ | </ |