MATE: Machine Learning for Adaptive Calibration Template Detection
The problem of camera calibration is two-fold. On the one hand, the parameters are estimated from known correspondences between the captured image and the real world. On the other, these correspondences themselves—typically in the form of chessboard corners—need to be found. Many distinct approaches...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/11/1858 |
| _version_ | 1798041882069041152 |
|---|---|
| author | Simon Donné Jonas De Vylder Bart Goossens Wilfried Philips |
| author_facet | Simon Donné Jonas De Vylder Bart Goossens Wilfried Philips |
| author_sort | Simon Donné |
| collection | DOAJ |
| description | The problem of camera calibration is two-fold. On the one hand, the parameters are estimated from known correspondences between the captured image and the real world. On the other, these correspondences themselves—typically in the form of chessboard corners—need to be found. Many distinct approaches for this feature template extraction are available, often of large computational and/or implementational complexity. We exploit the generalized nature of deep learning networks to detect checkerboard corners: our proposed method is a convolutional neural network (CNN) trained on a large set of example chessboard images, which generalizes several existing solutions. The network is trained explicitly against noisy inputs, as well as inputs with large degrees of lens distortion. The trained network that we evaluate is as accurate as existing techniques while offering improved execution time and increased adaptability to specific situations with little effort. The proposed method is not only robust against the types of degradation present in the training set (lens distortions, and large amounts of sensor noise), but also to perspective deformations, e.g., resulting from multi-camera set-ups. |
| first_indexed | 2024-04-11T22:27:45Z |
| format | Article |
| id | doaj.art-aef32dcf87e04f8a945d1e606ac0629e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:27:45Z |
| publishDate | 2016-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-aef32dcf87e04f8a945d1e606ac0629e2022-12-22T03:59:36ZengMDPI AGSensors1424-82202016-11-011611185810.3390/s16111858s16111858MATE: Machine Learning for Adaptive Calibration Template DetectionSimon Donné0Jonas De Vylder1Bart Goossens2Wilfried Philips3iMinds - IPI, Ghent University, Ghent B-9000, BelgiumiMinds - IPI, Ghent University, Ghent B-9000, BelgiumiMinds - IPI, Ghent University, Ghent B-9000, BelgiumiMinds - IPI, Ghent University, Ghent B-9000, BelgiumThe problem of camera calibration is two-fold. On the one hand, the parameters are estimated from known correspondences between the captured image and the real world. On the other, these correspondences themselves—typically in the form of chessboard corners—need to be found. Many distinct approaches for this feature template extraction are available, often of large computational and/or implementational complexity. We exploit the generalized nature of deep learning networks to detect checkerboard corners: our proposed method is a convolutional neural network (CNN) trained on a large set of example chessboard images, which generalizes several existing solutions. The network is trained explicitly against noisy inputs, as well as inputs with large degrees of lens distortion. The trained network that we evaluate is as accurate as existing techniques while offering improved execution time and increased adaptability to specific situations with little effort. The proposed method is not only robust against the types of degradation present in the training set (lens distortions, and large amounts of sensor noise), but also to perspective deformations, e.g., resulting from multi-camera set-ups.http://www.mdpi.com/1424-8220/16/11/1858computer visioncamera calibrationcheckerboard detectiondeep learning |
| spellingShingle | Simon Donné Jonas De Vylder Bart Goossens Wilfried Philips MATE: Machine Learning for Adaptive Calibration Template Detection Sensors computer vision camera calibration checkerboard detection deep learning |
| title | MATE: Machine Learning for Adaptive Calibration Template Detection |
| title_full | MATE: Machine Learning for Adaptive Calibration Template Detection |
| title_fullStr | MATE: Machine Learning for Adaptive Calibration Template Detection |
| title_full_unstemmed | MATE: Machine Learning for Adaptive Calibration Template Detection |
| title_short | MATE: Machine Learning for Adaptive Calibration Template Detection |
| title_sort | mate machine learning for adaptive calibration template detection |
| topic | computer vision camera calibration checkerboard detection deep learning |
| url | http://www.mdpi.com/1424-8220/16/11/1858 |
| work_keys_str_mv | AT simondonne matemachinelearningforadaptivecalibrationtemplatedetection AT jonasdevylder matemachinelearningforadaptivecalibrationtemplatedetection AT bartgoossens matemachinelearningforadaptivecalibrationtemplatedetection AT wilfriedphilips matemachinelearningforadaptivecalibrationtemplatedetection |