Direct Pose Estimation and Refinement

Hatem Said Alismail
doctoral dissertation, tech. report CMU-RI-TR-16-50, Robotics Institute, Carnegie Mellon University, August, 2016


Download
  • Adobe portable document format (pdf) (34MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
We study a fundamental question in pose estimation from vision-only video data: should the pose of a camera be determined from fixed and known correspondences? Or should correspondences be simultaneously estimated alongside the pose?

Determining pose from fixed correspondences is known as feature-based, where well-established tools from projective geometry are utilized to formulate and solve a plethora of pose estimation problems. Nonetheless, in degraded imaging conditions such as low light and blur, reliably detecting and precisely localizing interest points becomes challenging.

Conversely, estimating correspondences alongside motion is known as the direct approach, where image data are used directly to determine geometric quantities without relying on sparse interest points as an intermediate representation. The approach is in general more precise by virtue of redundancy as many measurements are used to estimate a few degrees-of-freedom. However, direct methods are more sensitive to changes in illumination.

In this work, we combine the best of the feature-based approaches with the precision of direct methods. Namely, we make use of densely and sparsely evaluated local feature descriptors in a direct image alignment framework to address pose estimation in challenging conditions. Applications include tracking planar targets under sudden and drastic changes in illumination as well as visual odometry in poorly-lit subterranean mines.

Motivated by the success of the proposed approach, we introduce a novel formulation for the joint refinement of pose and structure across multiple views akin to feature-based bundle adjustment (BA). In contrast to minimizing the reprojection error using BA, initial estimates are refined such that the photometric consistency of their image projections is maximized without the need for correspondences. The fundamentally different technique is evaluated on a range of datasets and is shown to improve upon the accuracy of the state-of-the-art in vision-based simultaneous localization and mapping (VSLAM).

Keywords
pose estimation, direct methods, visual SLAM, visual odometry, Lucas and Kanade, tracking, robust pose estimation, mine mapping, low light vision, bit-planes

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center

Text Reference
Hatem Said Alismail, "Direct Pose Estimation and Refinement," doctoral dissertation, tech. report CMU-RI-TR-16-50, Robotics Institute, Carnegie Mellon University, August, 2016

BibTeX Reference
@phdthesis{Alismail_2016_8198,
   author = "Hatem Said Alismail",
   title = "Direct Pose Estimation and Refinement",
   booktitle = "",
   school = "Robotics Institute, Carnegie Mellon University",
   month = "August",
   year = "2016",
   number= "CMU-RI-TR-16-50",
   address= "Pittsburgh, PA",
}