Uncertainty Based Camera Model Selection

Abstract

The quality and speed of Structure from Motion (SfM) methods depend significantly on the camera model chosen for the reconstruction. In most of the SfM pipelines, the camera model is manually chosen by the user. In this paper, we present a new automatic method for camera model selection in large scale SfM that is based on efficient uncertainty evaluation. We first perform an extensive comparison of classical model selection based on known Information Criteria and show that they do not provide sufficiently accurate results when applied to camera model selection. Then we propose a new Accuracy-based Criterion, which evaluates an efficient approximation of the uncertainty of the estimated parameters in tested models. Using the new criterion, we design a camera model selection method and fine-tune it by machine learning. Our simulated and real experiments demonstrate a significant increase in reconstruction quality as well as a considerable speedup of the SfM process.

Integrity of Visual Navigation—Developments, Challenges, and Prospects

“…The projection model is dependent on the applied lens. A review of different camera models and selection methods can be found in the works by Polic et al (2020) and Sturm et al (2011). Most systems can be well approximated using the classic pinhole model (fisheye lenses are the only common optical system that may significantly depart from that).…”

Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty

“…The uncertainty so obtained has been extensively studied in photometric computer vision [11]. It has also found applicability in a wide variety of tasks, such as RGB-D SLAM [10], radial distortion model selection [42] in SFM, skeletal images selection for efficient SFM [51], height map fusion [79], 3D reconstruction [17], and camera calibration [39]. Polic et al recently make efforts [41,40] towards efficient uncertainty computation in large-scale 3D reconstruction.…”

“…where J includes the index to the remaining parameters in θ. This step is also called S-transformation [2] that specifies the gauge of covariance matrix [11,42]. From the probabilistic point of view, it is in essence the inverse variance of a conditional Gaussian on θ i given all the other parameters [23].…”

Camera Self-Calibration with GNSS Constrained Bundle Adjustment for Weakly Structured Long Corridor UAV Images

“…For the camera self-calibration with a long corridor structure, the related research can be divided into three categories: the research on the theoretic analysis [23,24], the research on the strategies of self-calibration [25,26], and the accuracy verification with such structures [27][28][29][30][31][32]. Wu et al [23] analyzed the motion field of images with radial distortion and proved the ambiguous reconstruction with the "bowl effect" of camera self-calibration under weak structures and configuration through mathematical theory.…”

“…Although this method can alleviate the "bowl effect", it relied on more than three GCPs for absolute image orientation. Polic et al [26] proposed an uncertainty-based camera model selection method to reduce the "bowl effect", but this method did not consider the newest mathematical-based distortion models and high-precision GNSS observations. Griffiths et al [27] analyzed the accuracy of 3D reconstruction from long corridor structure UAV images in detail, and experiments show that the more complex distortion model can improve the accuracy of camera self-calibration.…”