基于局部特征和粒子滤波的云成像仪图像预测
|
摘要
由于云的分布变化对太阳辐照度的影响,对天空中云的分布进行预测是保证光伏电场稳定利用太阳能发电的重要环节。同时,云图的准确预测对气象分析也具有重要的应用价值。利用气象学研究成果对图像进行预测计算复杂度高,需要高性能计算机支持,因此不适合用于短时间内的云图预测。而结合计算机视觉知识对云图进行观测分析实时性高,近年来受到越来越广泛的关注。本文主要从鱼眼镜头的校正算法、云的检测、匹配、跟踪预测算法进行了系统的研究和实验。本文的具体研究工作包括：
1.确定了一种镜头校正模型,采用多项式拟合的方法逼近这一校正模型。巧妙地利用太阳天顶角与太阳在图像中的几何位置提取了一组数据集用于确定校正模型,并采用了一种迭代的方法对多项式的形式进行估计；
2.从特征选取和分类器设计的角度出发,选择了两种区分度最高的特征——红蓝分量差和颜色不变量,并设计了一种自适应混合高斯模型与基于LDA的线性分类器相级联的分类算法对云进行检测。实验结果表明该算法的准确率高于其它方法；
3.在对比各类颜色特征对噪声的抗干扰性能的基础上,设计了一种将灰度SURF和RGB颜色特征相结合的Color-SURF特征,用于对图像序列中相同的云进行匹配。该特征不仅能检测到更加丰富的特征点,并且提高了匹配的准确性；
4.提出了一种分层运动估计模型。根据实际匹配的特征点数量的大小,设计了一种由粗到精的运动模型。传统的仿射变换模型需要六对以上特征才能估计运动参数,本文中提出的运动模型可以对检测到两对以上特征的云进行运动估计。这组运动模型不仅可以有效地估计云的平移,同时可以估计云的旋转和尺度变化；
5.实现了一种采用粒子滤波的方法对云的运动参数空间进行更新。通过预测的运动参数可以得到云的预测图像。实验结果表明,将该算法用于短时间内的云图预测能够取得较高准确率。
Because of the strong impact of cloudiness on surface solar irradiance, an accurate description of the temporal development of the cloud distribution is essential for the large-scale application of solar energy. Meanwhile, the accurate prediction of all-sky image is of important value in atmosphere analysis. It is computational expensive to make study using meteorology technologies, which are not suitable for short-term prediction of cloud. On another hand, cloud image analysis with the help of computer vision technology, which shows high performance on accuracy and efficiency, are becoming a hot research topic.
In this paper, we deal with four parts:camera calibration, cloud detection, cloud matching, and cloud movement estimation. The details are as follows:
1. A camera model and calibration method for fisheye lens is proposed. To collect the training data, we make use of the relation of solar zenith angle and the position of the sun in the image innovatively, which could make up the data conveniently.
2. Two most distinctive features including red-blue difference and color invariant are extracted, and a hierarchical adaptive segmentation method which combines adaptive Mixture Gaussian Model and LDA-based linear classifier is designed, which are used in the classification of cloud and sky. Experimental results show that the good performance of our proposed method.
3. With the comparison of the robustness of some classical color features, SURF features combined with RGB color information are used in cloud matching in image sequences. The proposed Color-SURF feature not only enriches the quantity of detected keypoints, but also increases the accuracy of matching.
4. A hierarchical movement estimation model is designed. In traditional affine-transformation model, six pairs of matches at are indispensable to get the motion parameters. In the coarse to fine model, with two pairs of key points detected on the cloud, we are able to estimate the motion of it. This model could estimate not only the displacement, but also variation of scales and rotation of the cloud.
5. Particle Filtering is adopted to update the movement of cloud in order to reduce the estimation errors. Experimental results on the real captured all-sky images show the high accuracy of the proposed method.
1.确定了一种镜头校正模型,采用多项式拟合的方法逼近这一校正模型。巧妙地利用太阳天顶角与太阳在图像中的几何位置提取了一组数据集用于确定校正模型,并采用了一种迭代的方法对多项式的形式进行估计；
2.从特征选取和分类器设计的角度出发,选择了两种区分度最高的特征——红蓝分量差和颜色不变量,并设计了一种自适应混合高斯模型与基于LDA的线性分类器相级联的分类算法对云进行检测。实验结果表明该算法的准确率高于其它方法；
3.在对比各类颜色特征对噪声的抗干扰性能的基础上,设计了一种将灰度SURF和RGB颜色特征相结合的Color-SURF特征,用于对图像序列中相同的云进行匹配。该特征不仅能检测到更加丰富的特征点,并且提高了匹配的准确性；
4.提出了一种分层运动估计模型。根据实际匹配的特征点数量的大小,设计了一种由粗到精的运动模型。传统的仿射变换模型需要六对以上特征才能估计运动参数,本文中提出的运动模型可以对检测到两对以上特征的云进行运动估计。这组运动模型不仅可以有效地估计云的平移,同时可以估计云的旋转和尺度变化；
5.实现了一种采用粒子滤波的方法对云的运动参数空间进行更新。通过预测的运动参数可以得到云的预测图像。实验结果表明,将该算法用于短时间内的云图预测能够取得较高准确率。
Because of the strong impact of cloudiness on surface solar irradiance, an accurate description of the temporal development of the cloud distribution is essential for the large-scale application of solar energy. Meanwhile, the accurate prediction of all-sky image is of important value in atmosphere analysis. It is computational expensive to make study using meteorology technologies, which are not suitable for short-term prediction of cloud. On another hand, cloud image analysis with the help of computer vision technology, which shows high performance on accuracy and efficiency, are becoming a hot research topic.
In this paper, we deal with four parts:camera calibration, cloud detection, cloud matching, and cloud movement estimation. The details are as follows:
1. A camera model and calibration method for fisheye lens is proposed. To collect the training data, we make use of the relation of solar zenith angle and the position of the sun in the image innovatively, which could make up the data conveniently.
2. Two most distinctive features including red-blue difference and color invariant are extracted, and a hierarchical adaptive segmentation method which combines adaptive Mixture Gaussian Model and LDA-based linear classifier is designed, which are used in the classification of cloud and sky. Experimental results show that the good performance of our proposed method.
3. With the comparison of the robustness of some classical color features, SURF features combined with RGB color information are used in cloud matching in image sequences. The proposed Color-SURF feature not only enriches the quantity of detected keypoints, but also increases the accuracy of matching.
4. A hierarchical movement estimation model is designed. In traditional affine-transformation model, six pairs of matches at are indispensable to get the motion parameters. In the coarse to fine model, with two pairs of key points detected on the cloud, we are able to estimate the motion of it. This model could estimate not only the displacement, but also variation of scales and rotation of the cloud.
5. Particle Filtering is adopted to update the movement of cloud in order to reduce the estimation errors. Experimental results on the real captured all-sky images show the high accuracy of the proposed method.
引文
[1]Klein L. J, Rodrigues S. B, Nitta S, et al. Optimization of photovoltaic power generation using a Measurement and Management Technology (MMT) platform. 43rd International Symposium on Microelectronics, Raleigh,2010.
[2]‘国家发展和改革委员会,可再生能源中长期发展规划,2007.
[3]Chow CW, Urquhart B, Lave M, et al. Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed, Solar Energy,2011.85(11): 2881-2893
[4]Hammer A, Heinemann D and Lorenz E. Short-term forecasting of solar radiation: a statistical approach using satellite data. Solar energy,1999.67(1-3):139-150
[5]Cazorla A, Olmo F J, Alados-Arboledas L. Development of a sky imager for cloud cover assessment. Journal of the Optical Society of America,2008.25(1): 29--39
[6]Mukherjee DP, Acton S T. Cloud tracking by scale space classification. IEEE Transactions on Geosience and Remote Sensing,2002.40(2):405-415
[7]Heinle A, Macke A, Srivastav A. Automatic cloud classification of whole sky images. Atmospheric Measurement Techniques,2010.3:557-567
[8]Calbo J, Sabburg J. Feature extraction from whole-sky ground-based images for cloud-type recognition. Journal of Atmospheric and Oceanic Techniques,2008.
[9]Mundhenk T N, Rivett M J, Liao X. Techniques for Fisheye Lens Calibration using a Minimal Number of Measurements. Proceedings of the SPIE Intelligent Robotics and Computer Vision Conference,2000.40:405-415
[10]Qingyong Li, Weitao Lu, Keypoint based moment invariants descriptor for ground-based cloud image retrieval, IEEE International Symposium on Industrial Electronics,2009.763-768
[11]A.Yilmaz, O.Javed and M.Shah, Object tracking, a survey. ACM Computing Surveys,2006
[12]Monnet, Antoine, Anurag Mittal et al. Background modeling and subtraction of dynamic scenes. Proceedings of Ninth IEEE International Conference on Computer Vision,2003.2:1305-1312
[13]Chittajallu, D.R., Brunner, G., Kurkure, U.et al. Fuzzy-Cuts:A knowledge-driven graph-based method for medical image segmentation, IEEE International Conference on Computer Vision and Pattern Recognition,2009.715-722
[14]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models. International Journal of Computer Vision,1,321-332
[15]Pfister G, Mckenzie R L, Liley, Cloud coverage based on all-sky imaging and its impact on surface solar irradiance, Journal of Applied Meteorology,2003.42, 1421-143
[16]Sabburg J, Calbo J, Pages D. Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky Images. Journal of Atmospheric and Oceanic Techniques,2006.110:633--652
[17]M. P. Souza-Echer, E. B. Pereira, and L. S. Bins, "A simple method for the assessment of the cloud cover state in high-latitude regions by a ground-based digital camera," J. Atmos. Ocean. Technol,2006.
[18]J. Yang, L. Weitao, and M. Ying, "An automatic ground-based cloud detection method based on adaptive threshold," J. Appl. Meteorol,2009.
[19]S. L. M. Neto, A. V. Wangenheim, E. B. Pereira, and E. Comunello, "The use of Euclidean geometric distance on RGB color space for the classification of sky and cloud patterns," J. Atmos. Ocean. Techno 1,2010.
[20]Qingyong Li, Weitao Lu, Jun Yang Wang, et al. Thin Cloud Detection of All-Sky Images Using Markov Random Fields, IEEE Geoscience and Remote Sensing Letters,2012.9(3):417-421
[21]Chen Y, Rui Y, Huang T. Jpdaf based hmm for real-time contour tracking. IEEE Conference on Computer Vision and Pattern Recognition.2001,543-550.
[22]姚剑敏,粒子滤波跟踪方法研究[学位论文],长春：中国科学院长春光学精密机械与物理研究所,2004
[23]Heinemann D, Lorenz E, Girodo M, Forecasting of solar radiation, Proceedings of the International Workshop on Solar Resource,2004.
[24]Evans A N. Cloud Motion Analysis Using Multichannel Correlation-Relaxation Labeling. IEEE Geoscience and Remote Sensing Letters,2006.3(3):392-396
[25]廖训佚,鱼眼图像全景拼接系统[学位论文].重庆：重庆大学,2009
[26]刘丽群,基于鱼眼镜头的全方位机器视觉应用研究[学位论文],天津：天津理工大学,2009
[27]Kannala J, Brandt SS, A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses, IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(8):1335-1340
[28]Shah, S, Aggarwal, J.K, A simple calibration procedure for fish-eye (high distortion) lens camera," IEEE International Conference on Robotics and Automation,1994.4:3422-3427
[29]Heikkila J, Geometric camera calibration using circular control points, IEEE Transactions on Pattern Analysis and Machine Intelligence,22(10):1066-1077
[30]李航,统计学习方法.北京：清华大学出版社,2012
[31]Green Robin M, Spherical Astronomy, Cambridge Cambridge University Press, 1985
[32]Geusebroek J M, Boomgaard R, Smeulders AWM. Color Invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001.23(12): 1338-1350
[33]Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels, Proceedings of the 1999 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing IX,1999.41-48
[34]Richard O D, Peter E H, David G S.模式分类(第二版),北京：机械工业出版社,2003
[35]Sung K, Poggio T. Example-based learning for view based human face detection. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998. 20(1)39-51
[36]Christopher M. Bishop. Pattern Recognition and Machine Learning. Berlin:Springer.2006
[37]Simon J.D. Prince. Computer Vision:Models, Learning, and Inference. Cambridge:Cambridge University Press,2012
[38]McLachlan G, Krishnan T. The EM Algorithm and Extension. New York:John Wiley & Sons,1996
[39]Tuytelaars T, Mikolajczyk K. Local Invariant Feature Detectors:A Survey. Foundations and Trends(?) in Computer Graphics and Vision,2008.3(3):177-280
[40]Richard Szeliski, Computer Vision:Algorithms and Applications, Springer,2010
[41]C. Harris and M. Stephens, A combined corner and edge detector. Proceedings of the 4th Alvey Vision Conference.1988.147-151
[42]Bay H, Ess A, Tuytelaars T. Speeded Up Robust Features (SURF).9th European Conference on Computer Vision,2008.110(3):346-359
[43]Juan L, Gwon O. A comparison of SIFT, PCA-SIFT and SURF. International Journal of Image Processing,2010.3(4):143-152
[44]Bauer J, Sunderhauf N, Protzel P. Comparing several implementations of two recently published feature detectors. Proceedings of the International Conference on Intelligent and Autonomous Systems,2007.6(1):143-148
[45]Lowe DG. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision,2004.61(2):91-110
[46]van de Sande K.E.A, Gevers T, Snoek CGM, Evaluating Color Descriptors for Object and Scene Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence,32(9):1582-1596.
[47]Schwarz MW, Cowan WB and Beatty JC. An Experimental Comparison of RGB, YIQ, LAB, HSV, and Opponent Co for Models. ACM Transaction on Graphics, 1987.6(2):123-158
[48]Fuh C, Maragos P. Motion displacement estimation using an affine model for image matching. Optical Engineering,1991.30(7):881-887
[49]Gordon NJ, Salmond DJ, Smith AFM. Novel approach to nonlinear/nonGaussian Bayesian state estimation, IEE Proceedings F Radar and Signal Processing,1993, 140(2):107-113
[50]杨宜,智能视频监控中异常事件监测方法研究[学位论文],北京：北京邮电大学,2012
[51]C. Fuh and P. Maragos, "Motion displacement estimation using an affine model for image matching", Optical Engineering,1991.
[52]G. Bishop, and G. Welch, "An Introduction to the Kalman Filter," TR 95-041, Department of Computer Science, University of North Carolina at Chapel Hill,. NC, USA.2004.
[53]Kalman, R. E.,"A New Approach to Linear Filtering and Prediction Problems," Transaction of the ASME-Journal of Basic Engineering,1960
[54]Michael Isard, Andrew Blake. Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision,1998,29(1):5-28
[55]P. Del Moral. Measure valued processes and interacting particle systems. Application to nonlinear filtering problems. The Annals of Applied Probability, 1998.8(2):438-495
[56]Jun S Liu, Rong Chen, Sequential Monte Carlo methods for dynamic systems, Journal of the American Statistical Association,1998.93(443):1032-1044
[2]‘国家发展和改革委员会,可再生能源中长期发展规划,2007.
[3]Chow CW, Urquhart B, Lave M, et al. Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed, Solar Energy,2011.85(11): 2881-2893
[4]Hammer A, Heinemann D and Lorenz E. Short-term forecasting of solar radiation: a statistical approach using satellite data. Solar energy,1999.67(1-3):139-150
[5]Cazorla A, Olmo F J, Alados-Arboledas L. Development of a sky imager for cloud cover assessment. Journal of the Optical Society of America,2008.25(1): 29--39
[6]Mukherjee DP, Acton S T. Cloud tracking by scale space classification. IEEE Transactions on Geosience and Remote Sensing,2002.40(2):405-415
[7]Heinle A, Macke A, Srivastav A. Automatic cloud classification of whole sky images. Atmospheric Measurement Techniques,2010.3:557-567
[8]Calbo J, Sabburg J. Feature extraction from whole-sky ground-based images for cloud-type recognition. Journal of Atmospheric and Oceanic Techniques,2008.
[9]Mundhenk T N, Rivett M J, Liao X. Techniques for Fisheye Lens Calibration using a Minimal Number of Measurements. Proceedings of the SPIE Intelligent Robotics and Computer Vision Conference,2000.40:405-415
[10]Qingyong Li, Weitao Lu, Keypoint based moment invariants descriptor for ground-based cloud image retrieval, IEEE International Symposium on Industrial Electronics,2009.763-768
[11]A.Yilmaz, O.Javed and M.Shah, Object tracking, a survey. ACM Computing Surveys,2006
[12]Monnet, Antoine, Anurag Mittal et al. Background modeling and subtraction of dynamic scenes. Proceedings of Ninth IEEE International Conference on Computer Vision,2003.2:1305-1312
[13]Chittajallu, D.R., Brunner, G., Kurkure, U.et al. Fuzzy-Cuts:A knowledge-driven graph-based method for medical image segmentation, IEEE International Conference on Computer Vision and Pattern Recognition,2009.715-722
[14]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models. International Journal of Computer Vision,1,321-332
[15]Pfister G, Mckenzie R L, Liley, Cloud coverage based on all-sky imaging and its impact on surface solar irradiance, Journal of Applied Meteorology,2003.42, 1421-143
[16]Sabburg J, Calbo J, Pages D. Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky Images. Journal of Atmospheric and Oceanic Techniques,2006.110:633--652
[17]M. P. Souza-Echer, E. B. Pereira, and L. S. Bins, "A simple method for the assessment of the cloud cover state in high-latitude regions by a ground-based digital camera," J. Atmos. Ocean. Technol,2006.
[18]J. Yang, L. Weitao, and M. Ying, "An automatic ground-based cloud detection method based on adaptive threshold," J. Appl. Meteorol,2009.
[19]S. L. M. Neto, A. V. Wangenheim, E. B. Pereira, and E. Comunello, "The use of Euclidean geometric distance on RGB color space for the classification of sky and cloud patterns," J. Atmos. Ocean. Techno 1,2010.
[20]Qingyong Li, Weitao Lu, Jun Yang Wang, et al. Thin Cloud Detection of All-Sky Images Using Markov Random Fields, IEEE Geoscience and Remote Sensing Letters,2012.9(3):417-421
[21]Chen Y, Rui Y, Huang T. Jpdaf based hmm for real-time contour tracking. IEEE Conference on Computer Vision and Pattern Recognition.2001,543-550.
[22]姚剑敏,粒子滤波跟踪方法研究[学位论文],长春：中国科学院长春光学精密机械与物理研究所,2004
[23]Heinemann D, Lorenz E, Girodo M, Forecasting of solar radiation, Proceedings of the International Workshop on Solar Resource,2004.
[24]Evans A N. Cloud Motion Analysis Using Multichannel Correlation-Relaxation Labeling. IEEE Geoscience and Remote Sensing Letters,2006.3(3):392-396
[25]廖训佚,鱼眼图像全景拼接系统[学位论文].重庆：重庆大学,2009
[26]刘丽群,基于鱼眼镜头的全方位机器视觉应用研究[学位论文],天津：天津理工大学,2009
[27]Kannala J, Brandt SS, A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses, IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(8):1335-1340
[28]Shah, S, Aggarwal, J.K, A simple calibration procedure for fish-eye (high distortion) lens camera," IEEE International Conference on Robotics and Automation,1994.4:3422-3427
[29]Heikkila J, Geometric camera calibration using circular control points, IEEE Transactions on Pattern Analysis and Machine Intelligence,22(10):1066-1077
[30]李航,统计学习方法.北京：清华大学出版社,2012
[31]Green Robin M, Spherical Astronomy, Cambridge Cambridge University Press, 1985
[32]Geusebroek J M, Boomgaard R, Smeulders AWM. Color Invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001.23(12): 1338-1350
[33]Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels, Proceedings of the 1999 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing IX,1999.41-48
[34]Richard O D, Peter E H, David G S.模式分类(第二版),北京：机械工业出版社,2003
[35]Sung K, Poggio T. Example-based learning for view based human face detection. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998. 20(1)39-51
[36]Christopher M. Bishop. Pattern Recognition and Machine Learning. Berlin:Springer.2006
[37]Simon J.D. Prince. Computer Vision:Models, Learning, and Inference. Cambridge:Cambridge University Press,2012
[38]McLachlan G, Krishnan T. The EM Algorithm and Extension. New York:John Wiley & Sons,1996
[39]Tuytelaars T, Mikolajczyk K. Local Invariant Feature Detectors:A Survey. Foundations and Trends(?) in Computer Graphics and Vision,2008.3(3):177-280
[40]Richard Szeliski, Computer Vision:Algorithms and Applications, Springer,2010
[41]C. Harris and M. Stephens, A combined corner and edge detector. Proceedings of the 4th Alvey Vision Conference.1988.147-151
[42]Bay H, Ess A, Tuytelaars T. Speeded Up Robust Features (SURF).9th European Conference on Computer Vision,2008.110(3):346-359
[43]Juan L, Gwon O. A comparison of SIFT, PCA-SIFT and SURF. International Journal of Image Processing,2010.3(4):143-152
[44]Bauer J, Sunderhauf N, Protzel P. Comparing several implementations of two recently published feature detectors. Proceedings of the International Conference on Intelligent and Autonomous Systems,2007.6(1):143-148
[45]Lowe DG. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision,2004.61(2):91-110
[46]van de Sande K.E.A, Gevers T, Snoek CGM, Evaluating Color Descriptors for Object and Scene Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence,32(9):1582-1596.
[47]Schwarz MW, Cowan WB and Beatty JC. An Experimental Comparison of RGB, YIQ, LAB, HSV, and Opponent Co for Models. ACM Transaction on Graphics, 1987.6(2):123-158
[48]Fuh C, Maragos P. Motion displacement estimation using an affine model for image matching. Optical Engineering,1991.30(7):881-887
[49]Gordon NJ, Salmond DJ, Smith AFM. Novel approach to nonlinear/nonGaussian Bayesian state estimation, IEE Proceedings F Radar and Signal Processing,1993, 140(2):107-113
[50]杨宜,智能视频监控中异常事件监测方法研究[学位论文],北京：北京邮电大学,2012
[51]C. Fuh and P. Maragos, "Motion displacement estimation using an affine model for image matching", Optical Engineering,1991.
[52]G. Bishop, and G. Welch, "An Introduction to the Kalman Filter," TR 95-041, Department of Computer Science, University of North Carolina at Chapel Hill,. NC, USA.2004.
[53]Kalman, R. E.,"A New Approach to Linear Filtering and Prediction Problems," Transaction of the ASME-Journal of Basic Engineering,1960
[54]Michael Isard, Andrew Blake. Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision,1998,29(1):5-28
[55]P. Del Moral. Measure valued processes and interacting particle systems. Application to nonlinear filtering problems. The Annals of Applied Probability, 1998.8(2):438-495
[56]Jun S Liu, Rong Chen, Sequential Monte Carlo methods for dynamic systems, Journal of the American Statistical Association,1998.93(443):1032-1044