MATE: Machine Learning for Adaptive Calibration Template Detection
Abstract
:1. Introduction
Existing Methods
2. Proposed Approach
2.1. Computational Complexity
2.2. Mapping Existing Approaches on the Proposed Network
3. Experiments and Results
3.1. Training the Network
3.2. Datasets
3.3. Evaluation
3.4. Impact of the Training Set Size
3.5. Impact of the Spatial Support of the First Layer
3.6. Application to a CMYK Hexboard
4. Discussion and Conclusions
Acknowledgments
Author Contributions
Conflicts of Interest
References
- Sturm, P.; Ramalingam, S.; Tardif, J.P.; Gasparini, S.; Barreto, J. Camera models and fundamental concepts used in geometric computer vision. Found. Trends Comput. Graph. Vis. 2011, 6, 1–183. [Google Scholar] [CrossRef]
- Brown, D.C. Decentering distortion of lenses. Photom. Eng. 1966, 32, 444–462. [Google Scholar]
- Bouguet, J.Y. Camera Calibration Toolbox for Matlab. Available online: http://www.vision.caltech.edu/bouguetj/calib_doc/ (accessed on 22 January 2016).
- Zhang, Z. A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 2000, 22, 1330–1334. [Google Scholar] [CrossRef]
- Zhang, Z. Flexible camera calibration by viewing a plane from unknown orientations. In Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 20–27 September 1999; pp. 666–673.
- Sturm, P.F.; Maybank, S.J. On plane-based camera calibration: A general algorithm, singularities, applications. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, 23–25 June 1999.
- Tsai, R. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE J. Robot. Autom. 1987, 3, 323–344. [Google Scholar] [CrossRef]
- Harris, C.; Stephens, M. A combined corner and edge detector. In Proceedings of the Alvey Vision Conference, Manchester, UK, 31 August–2 September 1988; p. 50.
- Smith, S.M.; Brady, J.M. SUSAN—A new approach to low level image processing. Int. J. Comput. Vis. 1997, 23, 45–78. [Google Scholar] [CrossRef]
- Zhu, W.; Ma, C.; Xia, L.; Li, X. A fast and accurate algorithm for chessboard corner detection. In Proceedings of the IEEE 2nd International Congress on Image and Signal Processing, 2009 (CISP’09), Tianjin, China, 17–19 October 2009; pp. 1–5.
- Moravec, H.P. Towards Automatic Visual Obstacle Avoidance. In Proceedings of the 5th International Joint Conference on Artificial Intelligence, Cambridge, MA, USA, 22–25 August 1977.
- Arca, S.; Casiraghi, E.; Lombardi, G. Corner localization in chessboards for camera calibration. In Proceedings of the International Conference on Multimedia, Image Processing and Computer Vision (IADAT-MICV2005), Madrid, Spain, 30 March–1 April 2005.
- Su, J.; Duan, X.; Xiao, J. Fast detection method of checkerboard corners based on the combination of template matching and Harris Operator. In Proceedings of the IEEE 2013 International Conference on Information Science and Technology (ICIST), Yangzhou, China, 27–28 March 2013; pp. 858–861.
- Placht, S.; Fürsattel, P.; Mengue, E.A.; Hofmann, H.; Schaller, C.; Balda, M.; Angelopoulou, E. Rochade: Robust checkerboard advanced detection for camera calibration. In Proceedings of the 2014 European Conference on Computer Vision (ECCV), Zurich, Switzerland, 6–12 September 2014; pp. 766–779.
- Vezhnevets, V. OpenCV Calibration Object Detection, Part of the Free Open-Source OpenCV Image Processing Library. Available online: http://opencv.org/ (accessed on 2 September 2016).
- Scaramuzza, D. OCamCalib: Omnidirectional Camera Calibration Toolbox for Matlab. Free Open-Source Toolbox, Version 3.0 (November 16, 2013). Available online: https://sites.google.com/site/scarabotix/ocamcalib-toolbox (accessed on 6 July 2016).
- Rufli, M.; Scaramuzza, D.; Siegwart, R. Automatic detection of checkerboards on blurred and distorted images. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France, 22–26 September 2008; pp. 3121–3126.
- Wang, Z.; Wu, W.; Xu, X.; Xue, D. Recognition and location of the internal corners of planar checkerboard calibration pattern image. Appl. Math. Comput. 2007, 185, 894–906. [Google Scholar] [CrossRef]
- De la Escalera, A.; Armingol, J.M. Automatic chessboard detection for intrinsic and extrinsic camera parameter calibration. Sensors 2010, 10, 2027–2044. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Bennett, S.; Lasenby, J. ChESS—Quick and robust detection of chess-board features. Comput. Vis. Image Underst. 2014, 118, 197–210. [Google Scholar] [CrossRef]
- Bok, Y.; Ha, H.; Kweon, I.S. Automated Checkerboard Detection and Indexing using Circular Boundaries. Pattern Recognit. Lett. 2016, 71, 66–72. [Google Scholar] [CrossRef]
- Ha, J.E. Automatic detection of chessboard and its applications. Opt. Eng. 2009, 48, 067205. [Google Scholar] [CrossRef]
- Rosten, E.; Drummond, T. Machine learning for high-speed corner detection. In Proceedings of the European Conference on Computer Vision, Graz, Austria, 7–13 May 2006; pp. 430–443.
- Rosten, E.; Porter, R.; Drummond, T. Faster and better: A machine learning approach to corner detection. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 32, 105–119. [Google Scholar] [CrossRef] [PubMed]
- Roels, J.; Vylder, J.D.; Aelterman, J.; Saeys, Y.; Philips, W. Automated membrane detection in electron microscopy using convolutional neural networks. In Proceedings of the 25th Belgian-Dutch Conference on Machine Learning, Kortrijk, Belgium, 12–13 September 2016.
- Powell, S.; Magnotta, V.A.; Johnson, H.; Jammalamadaka, V.K.; Pierson, R.; Andreasen, N.C. Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures. Neuroimage 2008, 39, 238–247. [Google Scholar] [CrossRef] [PubMed]
- Donné, S.; Luong, H.; Goossens, B.; Dhondt, S.; Wuyts, N.; Inzé, D.; Philips, W. Machine learning for maize plant segmentation. In Proceedings of the 25th Belgian-Dutch Conference on Machine Learning, Kortrijk, Belgium, 12–13 September 2016.
- Dong, C.; Loy, C.C.; He, K.; Tang, X. Learning a deep convolutional network for image super-resolution. In Proceedings of the 2014 European Conference on Computer VISION (ECCV2014), Zurich, Switzerland, 12–13 September 2016; pp. 184–199.
- Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009 (CVPR 2009), Miami Beach, FL, USA, 20–25 June 2009; pp. 248–255.
- LeCun, Y.; Cortes, C.; Burges, C.J. The MNIST Database of Handwritten Digits. 1998. Available online: http://yann.lecun.com/exdb/mnist (accessed on 10 February 2016).
- Schmidhuber, J. Deep Learning in Neural Networks: An Overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [PubMed]
- Memon, Q.; Khan, S. Camera calibration and three-dimensional world reconstruction of stereo-vision using neural networks. Int. J.Syst. Sci. 2001, 32, 1155–1159. [Google Scholar] [CrossRef]
- Jun, J.; Kim, C. Robust camera calibration using neural network. In Proceedings of the IEEE Region 10 Conference (TENCON 99), Cheju Island, Korea, 15–17 September 1999; pp. 694–697.
- Ahmed, M.T.; Hemayed, E.E.; Farag, A.A. Neurocalibration: A neural network that can tell camera calibration parameters. In Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 20–27 September 1999; pp. 463–468.
- Glorot, X.; Bordes, A.; Bengio, Y. Deep sparse rectifier neural networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA, 11–13 April 2011; pp. 315–323.
- Nair, V.; Hinton, G.E. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, 21–24 June 2010; pp. 807–814.
- Lucchese, L.; Mitra, S.K. Using saddle points for subpixel feature detection in camera calibration targets. In Proceedings of the IEEE 2002 Asia-Pacific Conference on Circuits and Systems, 2002 (APCCAS’02), Bali, Indonesia, 28–31 October 2002; pp. 191–195.
- Bottou, L. Large-scale machine learning with stochastic gradient descent. In Proceedings of 19th International Conference on Computational Statistics (COMPSTAT’2010), Paris, France, 22–27 August 2010; pp. 177–186.
- Ngiam, J.; Coates, A.; Lahiri, A.; Prochnow, B.; Le, Q.V.; Ng, A.Y. On optimization methods for deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), Bellevue, WA, USA, 28 June–2 July 2011; pp. 265–272.
- Sutskever, I.; Martens, J.; Dahl, G.; Hinton, G. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th international conference on machine learning (ICML-13), Atlanta, GA, USA, 16–21 June 2013; pp. 1139–1147.
- Heikkila, J.; Silvén, O. A four-step camera calibration procedure with implicit image correction. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, 17–19 June 1997; pp. 1106–1112.
- Kannala, J.; Brandt, S.S. A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Trans. Pattern Anal. Mach. Intell. 2006, 28, 1335–1340. [Google Scholar] [CrossRef] [PubMed]
- Goossens, B.; Vylder, J.D.; Philips, W. Quasar: A new heterogeneous programming framework for image and video processing algorithms on CPU and GPU. In Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October 2014; pp. 2183–2185.
Method | Accuracy (px) | Complete Checkerboards | Missed Corners (%) | Double Detections (%) | False Positives | Time (ms) |
---|---|---|---|---|---|---|
MATE | 1.009 | 104/104 | 0.000 | 0.000 | 0 | 246 |
MATE | 1.160 | 103/104 | 0.020 | 2.444 | 40 | 264 |
ChESS | 1.094 | 104/104 | 0.000 | 0.280 | 10 | 212 |
ROCHADE | 1.130 | 104/104 | 0.000 | 0.000 | 0 | 6458 |
OCamCalib | 0.758 | 52/52 | 1.202 | 0.000 | 0 | 160 |
Method | Accuracy (px) | Complete Checkerboards | Missed Corners (%) | Double Detections (%) | False Positives | Time (ms) |
---|---|---|---|---|---|---|
MATE | 0.810 | 66/104 | 1.162 | 0.020 | 0 | 242 |
MATE | 0.999 | 81/104 | 0.62 | 4.147 | 40 | 246 |
ChESS | 1.042 | 73/104 | 0.842 | 0.902 | 15 | 209 |
ROCHADE | 0.423 | 38/104 | 54.899 | 0.000 | 0 | 6642 |
OCamCalib | 1.084 | 52/52 | 30.967 | 0.000 | 1 | 243 |
Method | Accuracy (px) | Complete Checkerboards | Missed Corners (%) | Double Detections (%) | False Positives | Time (ms) |
---|---|---|---|---|---|---|
MATE | 0.886 | 181/206 | 3.497 | 0.009 | 12 | 531 |
MATE | 1.009 | 186/206 | 3.065 | 0.809 | 492 | 529 |
ChESS | 0.946 | 175/206 | 3.398 | 0.000 | 11 | 473 |
ROCHADE | 1.510 | 186/206 | 2.895 | 0.000 | 1 | 6753 |
OCamCalib | 0.319 | 206/206 | 0.000 | 0.000 | 0 | 261 |
Method | Accuracy (px) | Complete Checkerboards | Missed Corners (%) | Double Detections (%) | False Positives | Time (ms) |
---|---|---|---|---|---|---|
MATE | 1.323 | 81/100 | 10.556 | 0.000 | 12 | 1209 |
MATE | 0.835 | 86/100 | 4.556 | 4.556 | 389 | 1205 |
ChESS | 1.389 | 80/100 | 5.481 | 0.222 | 56 | 1080 |
ROCHADE | 1.807 | 80/100 | 5.593 | 0.000 | 3 | 6688 |
OCamCalib | 0.458 | 100/100 | 0.537 | 0.000 | 0 | 533 |
© 2016 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Donné, S.; De Vylder, J.; Goossens, B.; Philips, W. MATE: Machine Learning for Adaptive Calibration Template Detection. Sensors 2016, 16, 1858. https://doi.org/10.3390/s16111858
Donné S, De Vylder J, Goossens B, Philips W. MATE: Machine Learning for Adaptive Calibration Template Detection. Sensors. 2016; 16(11):1858. https://doi.org/10.3390/s16111858
Chicago/Turabian StyleDonné, Simon, Jonas De Vylder, Bart Goossens, and Wilfried Philips. 2016. "MATE: Machine Learning for Adaptive Calibration Template Detection" Sensors 16, no. 11: 1858. https://doi.org/10.3390/s16111858