1. |
- Valtonen Örnhag, Marcus, et al.
(författare)
-
Enforcing the General Planar Motion Model : Bundle Adjustment for Planar Scenes
- 2020
-
Ingår i: Pattern Recognition Applications and Methods - 8th International Conference, ICPRAM 2019, Revised Selected Papers. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030400132 ; 11996 LNCS, s. 119-135
-
Konferensbidrag (refereegranskat)abstract
- In this paper we consider the case of planar motion, where a mobile platform equipped with two cameras moves freely on a planar surface. The cameras are assumed to be directed towards the floor, as well as being connected by a rigid body motion, which constrains the relative motion of the cameras and introduces new geometric constraints. In the existing literature, there are several algorithms available to obtain planar motion compatible homographies. These methods, however, do not minimise a physically meaningful quantity, which may lead to issues when tracking the mobile platform globally. As a remedy, we propose a bundle adjustment algorithm tailored for the specific problem geometry. Due to the new constrained model, general bundle adjustment frameworks, compatible with the standard six degree of freedom model, are not directly applicable, and we propose an efficient method to reduce the computational complexity, by utilising the sparse structure of the problem. We explore the impact of different polynomial solvers on synthetic data, and highlight various trade-offs between speed and accuracy. Furthermore, on real data, the proposed method shows an improvement compared to generic methods not enforcing the general planar motion model.
|
|
2. |
- Örnhag, Marcus Valtonen, et al.
(författare)
-
Efficient Radial Distortion Correction for Planar Motion
- 2020
-
Ingår i: Pattern Recognition Applications and Methods - 9th International Conference, ICPRAM 2020, Revised Selected Papers. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030661243 ; 12594 LNCS, s. 46-63
-
Konferensbidrag (refereegranskat)abstract
- In this paper we investigate simultaneous radial distortion calibration and motion estimation for vehicles travelling parallel to planar surfaces. This is done by estimating the inter-image homography between two poses, as well as the distortion parameter. Radial distortion correction is often performed as a pre-calibration step; however, accurately estimating the distortion profile without special scene requirements may make such procedures obsolete. As many modern day consumer cameras are affected by radial distortion to some degree, there is a great potential to reduce production time, if properly implemented. We devise two polynomial solvers, for radially distorted homographies compatible with different models of planar motion. We show that the algorithms are numerically stable, and sufficiently fast to be incorporated in a real-time frameworks. Furthermore, we show on both synthetic and real data, that the proposed solvers perform well compared to competing methods.
|
|
3. |
- Örnhag, Marcus Valtonen, et al.
(författare)
-
Radially distorted planar motion compatible homographies
- 2020
-
Ingår i: Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods : ICPRAM 2020 - ICPRAM 2020. - : SCITEPRESS - Science and Technology Publications. - 9789897583971 ; 1, s. 280-288
-
Konferensbidrag (refereegranskat)abstract
- Fast and accurate homography estimation is essential to many computer vision applications, including scene degenerate cases and planarity detection. Such cases arise naturally in man-made environments, and failure to handle them will result in poor positioning estimates. Most modern day consumer cameras are affected by some level of radial distortion, which must be compensated for in order to get accurate estimates. This often demands calibration procedures, with specific scene requirements, and off-line processing. In this paper a novel polynomial solver for radially distorted planar motion compatible homographies is presented. The proposed algorithm is fast and numerically stable, and is proven on both synthetic and real data to work well inside a RANSAC loop.
|
|