Automatic correction of perspective and optical distortions

Santana-Cedrés, Daniel; Gómez, Luis; Alemán‐Flores, Miguel; Salgado, Agustín; Esclarín, Julio; Mazorra, Luis; Álvarez, Luis

doi:10.1016/j.cviu.2017.05.016

Cited by 29 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section presents a Vanishing Point based Mapping method (VPM) for the calculation of the rotation matrix from three vanishing points. To ensure an accurate localization of the vanishing points, a manual procedure rather than automatical vanishing points detection algorithms [8,17] is adopted.…”

Section: Vanishing Point Based Mapping Methodsmentioning

confidence: 99%

“…Later, Chaudhury et al [16] proposed a Ransac based approach to estimate two vanishing points and aligned the closer vanishing point with the Y-axis of the image via a post-multiplication operation. Santana et al [17] utilized several long lines in the image to locate the vanishing points and performed image rectification based on a camera motion simulation. Lee et al [6,9] proposed an optimization framework which can simultaneously estimate the vanishing lines, vanishing points, and the camera parameters.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Assembling Convolution Neural Networks for Automatic Viewing Transformation

Cai

Jiang

Liu

et al. 2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Images taken under different camera poses are rotated or distorted, which leads to poor perception experiences. This paper proposes a new framework to automatically transform the images to the conformable view setting by assembling different convolution neural networks. Specifically, a referential 3D ground plane is firstly derived from the RGB image and a novel projection mapping algorithm is developed to achieve automatic viewing transformation. Extensive experimental results demonstrate that the proposed method outperforms the state-ofthe-art vanishing points based methods by a large margin in terms of accuracy and robustness.

show abstract

Section: Vanishing Point Based Mapping Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Assembling Convolution Neural Networks for Automatic Viewing Transformation

Cai

Jiang

Liu

et al. 2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…Single-View Camera Self-Calibration: Single-view methods rely on extracted line/curve features in the input image to remove radial distortion [28], [29] and/or compute camera intrinsics [30], [31], [32], [33]. Moreover, some of them assume special scene structures, e.g., Manhattan world [33].…”

Section: Geometric Degeneracy With Unknown Radial Distortionmentioning

confidence: 99%

“…We can see in (a)-(b) that 'HandCrafted+OVP' and 'HandCrafted' are able to produce reasonable results because the scenes in (a)-(b) contain many structures with line/curve features. However, when the scenes become more cluttered or structure-less as in (c)-(d), such traditional methods cannot work well, especially, the hand-crafted method [32] (i.e., 'HandCrafted') produces significantly distorted result in (d). In contrast, 'DeepSup' and 'MultiTask' achieve good performance, even in the challenging cases of cluttered or structure-less scenes in (c)-(d).…”

Section: A Geometric Approach Vs Learning Approachmentioning

confidence: 99%

Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM

Zhuang

Tran²,

Lee

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper, we revisit the geometric approach to this problem, and provide a theoretical proof that explicitly shows the ambiguity between radial distortion and scene depth when twoview geometry is used to self-calibrate the radial distortion.In view of such geometric degeneracy, we propose a learning approach that trains a convolutional neural network (CNN) on a large amount of synthetic data. We demonstrate the utility of our proposed method by applying it as a checkerboard-free calibration tool for SLAM, achieving comparable or superior performance to previous learning and hand-crafted methods.

show abstract

“…There-fore, accurate line detection is a very important aspect for the robustness and flexibility of these methods. Correction methods for other distortions [13,24,7,31] also rely on the detection of special low-level features such as vanishing points, repeated textures, and co-planar circles. But these special low-level features are not always frequent enough for distortion estimation in some images, which greatly restrict the versatility of the methods.…”

Section: Introductionmentioning

confidence: 99%

Blind Geometric Distortion Correction on Images Through Deep Learning

Zhang

Sander³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction. Multi-model distortion estimationThe GeoNetS network is only able to capture a specific distortion type with a distortion model at a time. For a new type, the entire network has to be retrained. Furthermore, the distortion type and model can be unknown in some cases. In view of these limitations, we designed a second network for multi-model distortion estimation. However, since the distortion model and the parameters ρ β can vary drastically across types, it is impossible to train a multimodel network with the model constraints. We train a network to regress the distortion flow without model constraints and at the same time classify the distortion type. The network is illustrated in Figure 3. The multi-model network N parameterized by θ is jointly trained for two tasks. The first task estimates the distortion flow, learning the mapping from the image domain I to the flow domain F. The second task classifies the distortion type, learning the mapping from image domain I to type domain T .Architecture The entire network adopts an encoderdecoder structure, which includes an encoder part, a decoder part, and a classification part. The input image is fed

show abstract

Automatic correction of perspective and optical distortions

Cited by 29 publications

References 27 publications

Assembling Convolution Neural Networks for Automatic Viewing Transformation

Assembling Convolution Neural Networks for Automatic Viewing Transformation

Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM

Blind Geometric Distortion Correction on Images Through Deep Learning

Contact Info

Product

Resources

About