Improved wide-angle, fisheye and omnidirectional camera calibration

Urban, Steffen; Leitloff, Jens; Hinz, Stefan

doi:10.1016/j.isprsjprs.2015.06.005

Cited by 110 publications

(56 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For calibration of the MCS a generic methodology for wide-angle, fisheye and omnidirectional cameras in general has been developed using this approach. This resulted in improved accuracy with respect to previous research (Urban et al, 2015). After calibration the parameters for world to camera projection of each camera and the mutual transformations within the MCS are known.…”

Section: Augmented Reality Systemmentioning

confidence: 93%

“…The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLII-4/W4, 2017 Tehran's Joint ISPRS Conferences of GI Research, SMPR andEOEC 2017, 7-10 October 2017, Tehran, Iran of self-initialization, multi-camera modeling (Urban et al 2015), statistical modeling (Urban et al, 2016b), feature detection (Urban & Hinz, 2016), feature-based tracking, modelbased tracking as well as combined tracking (Urban 2016). Figure 15 shows three trajectories transformed to the building model for better evaluation.…”

Section: Augmented Reality Systemmentioning

confidence: 99%

See 1 more Smart Citation

Collaborative Multi-Scale 3d City and Infrastructure Modeling and Simulation

Breunig

Borrmann²,

Rank³

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Commission IV, WG IV/7KEY WORDS: Collaborative planning, integration of 3D modeling and simulation, multi-scale modelling, mobile computer vision. ABSTRACT:Computer-aided collaborative and multi-scale 3D planning are challenges for complex railway and subway track infrastructure projects in the built environment. Many legal, economic, environmental, and structural requirements have to be taken into account. The stringent use of 3D models in the different phases of the planning process facilitates communication and collaboration between the stake holders such as civil engineers, geological engineers, and decision makers. This paper presents concepts, developments, and experiences gained by an interdisciplinary research group coming from civil engineering informatics and geo-informatics banding together skills of both, the Building Information Modeling and the 3D GIS world. New approaches including the development of a collaborative platform and 3D multi-scale modelling are proposed for collaborative planning and simulation to improve the digital 3D planning of subway tracks and other infrastructures. Experiences during this research and lessons learned are presented as well as an outlook on future research focusing on Building Information Modeling and 3D GIS applications for cities of the future.

show abstract

Section: Augmented Reality Systemmentioning

confidence: 93%

Section: Augmented Reality Systemmentioning

confidence: 99%

Collaborative Multi-Scale 3d City and Infrastructure Modeling and Simulation

Breunig

Borrmann²,

Rank³

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…We use the omnidirectional camera model [27], [28], which models the lens distortion with a polynomial function. The projection function Π maps a 3D point X to a 2D point x on the normalized image plane, x = Π(X; Φ), where Φ is the fisheye intrinsic parameters.…”

Section: Omnidirectonal Stereo a Fisheye Projection Model And Ementioning

confidence: 99%

SweepNet: Wide-baseline Omnidirectional Depth Estimation

Won

Ryu

Lim

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel widebaseline omnidirectional stereo algorithm which computes the dense depth estimate from the fisheye images using a deep convolutional neural network. The capture system consists of multiple cameras mounted on a wide-baseline rig with ultrawide field of view (FOV) lenses, and we present the calibration algorithm for the extrinsic parameters based on the bundle adjustment. Instead of estimating depth maps from multiple sets of rectified images and stitching them, our approach directly generates one dense omnidirectional depth map with full 360°coverage at the rig global coordinate system. To this end, the proposed neural network is designed to output the cost volume from the warped images in the sphere sweeping method, and the final depth map is estimated by taking the minimum cost indices of the aggregated cost volume by SGM. For training the deep neural network and testing the entire system, realistic synthetic urban datasets are rendered using Blender. The experiments using the synthetic and real-world datasets show that our algorithm outperforms the conventional depth estimation methods and generate highly accurate depth maps.

show abstract

“…A unit rayp for the spherical coordinate θ, φ corresponds top(θ, φ) = (cos(φ) cos(θ), sin(φ), cos(φ) sin(θ)) . With the intrinsic and extrinsic parameters of the i-th camera (calibrated using [22,28,1]), the image pixel coordinate x i for a 3D point X can be written as a projection function Π i ; x i = Π i (X). Thus a point at θ, φ on the sphere of radius ρ is projected to Π i (ρp(θ, φ)) in the i-th fisheye image.…”

Section: Spherical Sweepingmentioning

confidence: 99%

OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching

Won

Ryu

Lim

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on an omnidirectional rig are processed by the feature extraction module, and then the deep feature maps are warped onto the concentric spheres swept through all candidate depths using the calibrated camera parameters. The 3D encoderdecoder block takes the aligned feature volume to produce the omnidirectional depth estimate with regularization on uncertain regions utilizing the global context information. In addition, we present large-scale synthetic datasets for training and testing omnidirectional multi-view stereo algorithms. Our datasets consist of 11K ground-truth depth maps and 45K fisheye images in four orthogonal directions with various objects and environments. Experimental results show that the proposed method generates excellent results in both synthetic and real-world environments, and it outperforms the prior art and the omnidirectional versions of the state-of-the-art conventional stereo algorithms.

show abstract

Improved wide-angle, fisheye and omnidirectional camera calibration

Cited by 110 publications

References 7 publications

Collaborative Multi-Scale 3d City and Infrastructure Modeling and Simulation

Collaborative Multi-Scale 3d City and Infrastructure Modeling and Simulation

SweepNet: Wide-baseline Omnidirectional Depth Estimation

OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching

Contact Info

Product

Resources

About