A Pot of Gold: Rainbows as a Calibration Cue

Workman, Scott; Mihail, Radu Paul; Jacobs, Nathan

doi:10.1007/978-3-319-10602-1_53

Cited by 14 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent work exploited semantics for geo-localization. Shadows, direction of the sun [19,42] and even rainbows [40] have been used for very rough localization (roughly 100km error) and camera calibration. These approaches require a long video recorded with a stationary Figure 2: 2D embedding of the Sun-CNN feature space with t-SNE.…”

Section: Related Workmentioning

confidence: 99%

Find your way by observing the sun and other semantic cues

Wang

Brubaker

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

In this paper we present a robust, efficient and affordable approach to self-localization which does not require neither GPS nor knowledge about the appearance of the world. Towards this goal, we utilize freely available cartographic maps and derive a probabilistic model that exploits semantic cues in the form of sun direction, presence of an intersection, road type, speed limit as well as the ego-car trajectory in order to produce very reliable localization results. Our experimental evaluation shows that our approach can localize much faster (in terms of driving time) with less computation and more robustly than competing approaches, which ignore semantic information.

show abstract

Section: Related Workmentioning

confidence: 99%

Find your way by observing the sun and other semantic cues

Wang

Brubaker

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Other methods take advantage of the properties of vanishing points [3,22,9], which provide a strong characterization of geometric scene structure. As the need to calibrate images captured "in the wild" has grown, many more methods have been introduced which take advantage of natural cues, such as sun position [23] and solar refractive phenomena [24].…”

Section: Related Workmentioning

confidence: 99%

DEEPFOCAL: A method for direct focal length estimation

Workman

Greenwell

Zhai

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Estimating the focal length of an image is an important preprocessing step for many applications. Despite this, existing methods for single-view focal length estimation are limited in that they require particular geometric calibration objects, such as orthogonal vanishing points, co-planar circles, or a calibration grid, to occur in the field of view. In this work, we explore the application of a deep convolutional neural network, trained on natural images obtained from Internet photo collections, to directly estimate the focal length using only raw pixel intensities as input features. We present quantitative results that demonstrate the ability of our technique to estimate the focal length with comparisons against several baseline methods, including an automatic method which uses orthogonal vanishing points.

show abstract

“…Automatic vanishing point (VP) and horizon line detection are two of the most fundamental problems in geometric computer vision [6,22]. Knowledge of these quantities is the foundation for many higher level tasks, including image mensuration [10], facade detection [20], geolocalization [4,31], and camera calibration [2,12,15,17]. Recent work in this area [3,30,33] has explored novel problem formulations that significantly increase robustness to noise.…”

Section: Introductionmentioning

confidence: 99%

Detecting Vanishing Points Using Global Image Context in a Non-ManhattanWorld

Zhai

Workman

Jacobs

2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

121

View full text Add to dashboard Cite

We propose a novel method for detecting horizontal vanishing points and the zenith vanishing point in man-made environments. The dominant trend in existing methods is to first find candidate vanishing points, then remove outliers by enforcing mutual orthogonality. Our method reverses this process: we propose a set of horizon line candidates and score each based on the vanishing points it contains. A key element of our approach is the use of global image context, extracted with a deep convolutional network, to constrain the set of candidates under consideration. Our method does not make a Manhattan-world assumption and can operate effectively on scenes with only a single horizontal vanishing point. We evaluate our approach on three benchmark datasets and achieve state-ofthe-art performance on each. In addition, our approach is significantly faster than the previous best method.

show abstract

A Pot of Gold: Rainbows as a Calibration Cue

Cited by 14 publications

References 29 publications

Find your way by observing the sun and other semantic cues

Find your way by observing the sun and other semantic cues

DEEPFOCAL: A method for direct focal length estimation

Detecting Vanishing Points Using Global Image Context in a Non-ManhattanWorld

Contact Info

Product

Resources

About