Both sides previous revision
Previous revision
Next revision
|
Previous revision
Next revision
Both sides next revision
|
research:vslam:stereo-dso [2018/08/12 01:49] Rui Wang |
research:vslam:stereo-dso [2020/05/08 17:50] Rui Wang |
===== Abstract ===== | ===== Abstract ===== |
** Stereo DSO ** is a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the active window, including the intrinsic/extrinsic camera parameters of all keyframes and the depth values of all selected pixels. In particular, it integrates constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo. Real-time optimization is realized by sampling pixels uniformly from image regions with sufficient intensity gradient. Fixed-baseline stereo resolves scale drift. It also reduces the sensitivities to large optical flow and to rolling shutter effect which are known shortcomings of direct image alignment methods. Quantitative evaluation demonstrates that the proposed Stereo DSO outperforms existing state-of-the-art visual odometry methods both in terms of tracking accuracy and robustness. Moreover, our method delivers a more precise metric 3D reconstruction than previous dense/semi-dense direct approaches while providing a higher reconstruction density than feature-based methods. | ** Stereo DSO ** is a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the active window, including the intrinsic/extrinsic camera parameters of all keyframes and the depth values of all selected pixels. In particular, it integrates constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo. Real-time optimization is realized by sampling pixels uniformly from image regions with sufficient intensity gradient. Fixed-baseline stereo resolves scale drift. It also reduces the sensitivities to large optical flow and to rolling shutter effect which are known shortcomings of direct image alignment methods. Quantitative evaluation demonstrates that the proposed Stereo DSO outperforms existing state-of-the-art visual odometry methods both in terms of tracking accuracy and robustness. Moreover, our method delivers a more precise metric 3D reconstruction than previous dense/semi-dense direct approaches while providing a higher reconstruction density than feature-based methods. |
| |
| ===== Download ===== |
| - The estimated camera trajectories of all the sequences of KITTI Odometry: {{:research:vslam:stereo-dso:KITTI_odometry_training.zip|training (00-10)}}, {{:research:vslam:stereo-dso:KITTI_odometry_testing.zip|training (11-21)}}.\\ |
| - Paper: {{:research:vslam:stereo-dso:wang2017stereodso.pdf|Paper}}, supplementary document of the paper: {{:research:vslam:stereo-dso:wang2017stereodso-supp.pdf|Supplementary Document}}. |
| |
| |
===== Results ===== | ===== Results ===== |
{{:research:vslam:dso:rs.png?350&nolink|}} | {{:research:vslam:dso:rs.png?350&nolink|}} |
| |
As qualitative results we run our method on all the sequences from the training set and compare the estimated camera trajectories to the provided ground truth. Following are the results on some example sequences. All the estimated camera trajectories can be downloaded here {{:research:vslam:stereo-dso:stereo_dso_kitti_training.zip|Camera Trajectories}}. | As qualitative results we run our method on all the sequences from the training set and compare the estimated camera trajectories to the provided ground truth. Following are the results on some example sequences. **All the estimated camera trajectories can be downloaded here {{:research:vslam:stereo-dso:camera_trajectories.zip|Camera Trajectories}}**. |
| |
{{:research:vslam:dso:00.png?350&nolink|}} | {{:research:vslam:dso:00.png?350&nolink|}} |