无人机遥感影像快速无缝拼接
|
摘要
由于无人机低空遥感数据具有高分辨率、高灵活性、高效率和低成本的优势,无人机被广泛应用于战场侦察、森林火灾监控、自然灾害区域评估等方面。然而由于无人机图像具有相幅小、数量多、影像的倾斜度大、重叠不规则等特点,致使现有的图像拼接算法难以获得很好的拼接效果。因此,能否根据无人机图像特点研究出有效的图像拼接算法成为成功应用无人机的关键。
本文针对因无人机图像的特点而造成的拼接工作量大、精度低等问题对基于特征的图像拼接算法进行了改进,对其流程进行了优化,使该算法在速度以及精度上都有一定的提高。
首先,实现了用于计算参考图像和待配准图像之间重叠度的相位相关法;并提出只在重叠区域中进行特征提取和特征匹配的方法,从而使得计算量成倍减少,并有效地防止了图像非重叠区域中的信息对算法的干扰,提高了拼接算法的精度。
其次,采用改进的Harris角点检测算法在参考图像和待配准图像的重叠区域里进行特征点提取,并根据由重叠度算出的待配准图像相对于参考图像移动的距离,剔除两个特征点集里明显不匹配的特征点,再通过相似度函数找出匹配的特征点集。相对常规的先匹配再剔除特征点的方法,这种方法在保证了较小计算量的同时可以大幅度地减少误匹配点对。
然后,利用匹配的特征点集对待配准图像进行模型变换,实现了图像的配准;并采用一种渐入渐出的融合算法对配准后的图像进行融合,消除了图像拼接中产生的明显缝隙,改善了图像的视觉效果。
最后,利用无人机在灾害地区获取的大量遥感数据,对该算法中图像配准、图像融合的效果进行了质量评价。各项实验数据均表明改进的图像拼接算法能得到良好的拼接效果,且具有高准确率、强鲁棒性等特点,有较高的使用价值。
Unmanned Aerial Vehicle(UAV) has been applied widely in battle field scouts, forest fire disaster monitoring, evaluations of natural disaster region, etc, due to four advantages of the low altitude remote sensing data from UAV: high resolution, good flexibility, high efficiency and low cost. However, UAV images possess features like small range, large amount, heavy shooting slope, irregularity overlap, which lead to bad image mosaic results based on the traditional image mosaic algorithm. So it becomes the key of successful UAV application to develop an effective image mosaic algorithm according to UAV images features.
To aim at solving problems in image mosaic such as heavy work burden and low accuracy resulted from various UAV images features, the image mosaic algorithm based on features is improved, and the process is optimized, which enhance the speed and accuracy of the image mosaic algorithm.
First, a phase correlation method used to calculate the overlap degree between reference images and registering images is realized. And a new method to carry out feature extraction and match only within the overlap region is proposed, which reduces the computational complexity dramatically, prevents non-overlap image region’s data from interfering the algorithm and increases the accuracy of the mosaic algorithm.
Second, feature points are extracted within the overlap regions between reference images and registering images by adopting the improved Harris angle point detection algorithm. And obvious unmatched points are deleted from the two feature points groups, according to the distance between reference images and registering images calculated from overlap degree. The matched feature points group can be certified finally through the similarity function. Comparing with the conventional method to match feature points before deleting, this method can reduce incorrect match points in a large amount while guarantee low computational complexity.
Third, the images registration is implemented by using the matched feature points group to perform model transformation for matching images. Moreover, a gradated in-and-out amalgamation algorithm is adopted to fuse the registered images, which makes images linking together smoothly and seamlessly and improve the visual effect of the final matched image.
Finally, based on a great amount of remote sensing data acquired from disaster region by UAV, the quality appraisements of the image registration, image fusion in the improved algorithm are conducted. Various kinds of experimental data demonstrate the improved image mosaic algorithm can obtain good mosaic result, possesses features such as high accuracy rate, good robustness, and has great application value.
本文针对因无人机图像的特点而造成的拼接工作量大、精度低等问题对基于特征的图像拼接算法进行了改进,对其流程进行了优化,使该算法在速度以及精度上都有一定的提高。
首先,实现了用于计算参考图像和待配准图像之间重叠度的相位相关法;并提出只在重叠区域中进行特征提取和特征匹配的方法,从而使得计算量成倍减少,并有效地防止了图像非重叠区域中的信息对算法的干扰,提高了拼接算法的精度。
其次,采用改进的Harris角点检测算法在参考图像和待配准图像的重叠区域里进行特征点提取,并根据由重叠度算出的待配准图像相对于参考图像移动的距离,剔除两个特征点集里明显不匹配的特征点,再通过相似度函数找出匹配的特征点集。相对常规的先匹配再剔除特征点的方法,这种方法在保证了较小计算量的同时可以大幅度地减少误匹配点对。
然后,利用匹配的特征点集对待配准图像进行模型变换,实现了图像的配准;并采用一种渐入渐出的融合算法对配准后的图像进行融合,消除了图像拼接中产生的明显缝隙,改善了图像的视觉效果。
最后,利用无人机在灾害地区获取的大量遥感数据,对该算法中图像配准、图像融合的效果进行了质量评价。各项实验数据均表明改进的图像拼接算法能得到良好的拼接效果,且具有高准确率、强鲁棒性等特点,有较高的使用价值。
Unmanned Aerial Vehicle(UAV) has been applied widely in battle field scouts, forest fire disaster monitoring, evaluations of natural disaster region, etc, due to four advantages of the low altitude remote sensing data from UAV: high resolution, good flexibility, high efficiency and low cost. However, UAV images possess features like small range, large amount, heavy shooting slope, irregularity overlap, which lead to bad image mosaic results based on the traditional image mosaic algorithm. So it becomes the key of successful UAV application to develop an effective image mosaic algorithm according to UAV images features.
To aim at solving problems in image mosaic such as heavy work burden and low accuracy resulted from various UAV images features, the image mosaic algorithm based on features is improved, and the process is optimized, which enhance the speed and accuracy of the image mosaic algorithm.
First, a phase correlation method used to calculate the overlap degree between reference images and registering images is realized. And a new method to carry out feature extraction and match only within the overlap region is proposed, which reduces the computational complexity dramatically, prevents non-overlap image region’s data from interfering the algorithm and increases the accuracy of the mosaic algorithm.
Second, feature points are extracted within the overlap regions between reference images and registering images by adopting the improved Harris angle point detection algorithm. And obvious unmatched points are deleted from the two feature points groups, according to the distance between reference images and registering images calculated from overlap degree. The matched feature points group can be certified finally through the similarity function. Comparing with the conventional method to match feature points before deleting, this method can reduce incorrect match points in a large amount while guarantee low computational complexity.
Third, the images registration is implemented by using the matched feature points group to perform model transformation for matching images. Moreover, a gradated in-and-out amalgamation algorithm is adopted to fuse the registered images, which makes images linking together smoothly and seamlessly and improve the visual effect of the final matched image.
Finally, based on a great amount of remote sensing data acquired from disaster region by UAV, the quality appraisements of the image registration, image fusion in the improved algorithm are conducted. Various kinds of experimental data demonstrate the improved image mosaic algorithm can obtain good mosaic result, possesses features such as high accuracy rate, good robustness, and has great application value.
引文
[1] J. Meehan. Panoramic Photography. London. Watson-Guptill Publications,1990.
[2] Y. Xiong, Y. Turkowski.“Creating image-based VR using a self-calibrating fisheye lens. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico,USA, pp. 237-243,1997.
[3] R. Szeliski. Video mosaics for virtual environments. IEEE Computer Graphics and Applications, 16(2), 3, pp. 22-30, 1996.
[4] S. Peleg, B. Rousso. Mosaicing on Adaptive Manifolds. IEEE Trans. on Pattern and machine intelligence, 22(10) ,10, pp. 1144-1154, 2000.
[5] S. Gumustekin, R.W. Hall. Mosaic image generation on a flattened Gaussian sphere. Proceedings 3rd IEEE Workshop on Applications of Computer Vision, 12, pp. 50-55, 1996.
[6] S. Gumustekin, R.W. Hall. Image registration and mosaicing using a self-calibrating camera. In Proceedings of International Conference on mage Processing, 10, 1, pp. 818-822, 1998.
[7] H.Y. Shum, R. Szeliski. Panoramic image mosaics. Technical Report MSR-TR-97-23,Microsoft research, pp. 4-20, l997.
[8] R. Szeliski, H.Y. Shum. Creating Full View Panoramic Image Mosaics and Environment Maps. In Proc. of ACM SIGGRAPH, pp. 251-258, 1997.
[9] C.D. Kuglin, D.C. Mines. The Phase Correlation Image Alignment Method. Proceedings of IEEE International Conference on Cybernetics and Society, New York. 9, pp. 163-165, 1975.
[10] E.D. Castro, C. Morandi. Registration of translated and rotated images using finite Fourier transforms, IEEE Trans. on Pattern Analysis and Machine Intelligence, 9(5), pp. 700-703, 1987.
[11] R.B. Srinivasa, B.N. Chatterji. An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans. on Image Processing, 8(5), 9, pp. 1266-1271, 1996.
[12] S. Zokai, G..Wolberg. Image Registration Using Log-Polar Mappings for Recovery of Large-Scale Similarity and Projective Transformations. IEEE Trans. on Image Processing, 14(10), 10, pp. 1422-1434, 2005.
[13] R. Gupta, R. Hartley. Linear pushbroom cameras. IEEE Trans. On PAMI, 19(9), 9, pp. 963-975,1997.
[14]李忠新.图像镶嵌理论及若干算法研究.南京:南京理工大学博士论文, 2004, 4, 34-37.
[15]李志刚.边界重叠图像的一种快速拼接算法.计算机工程, 2000, 26(5), 37-38.
[16] A. Rosenfeld., A.C. Kak. Digital Picture Processing. Vol. I and II, Academic Press, Orlando, FL. 4, pp. 169-170, 1982.
[17] D.H. Kim, Y. I. Yoon, J.S. Cho.A Quasi-feature Based Image Mosaic Algorithms Using Modified Block Matching Criteria. IEEE of Japan. 12-C(5), pp. 892-898, 2001.
[18] A. D. Ventura, A. Rampini, R. Schettini. Image registration by recognition of corresponding structures. IEEE Trans. On Geoscience and Remote Sensing. 28(3), 3, pp. 305-314, 1990.
[19] Zhengwei Yang, F.S. Cohen. Cross-weighted moments and affine invariants for image registration and matching. IEEE Trans.on Pattern Analysis and Machine Intelligence, 21(8), 8, pp. 801-814, 1999.
[20] S.H. Chang, F.H. Cheng, W.H. Hsu, et al. Fast algorithm for point pattern matching.invariant to translation,rotations and scale changes. Pattern Recognition, 29(1), pp. 11-16, 1997.
[21] Hui Li, B.S. Manjunath, S.K. Mitra. A contour-based approach to multi-sensor image registration. IEEE Trans. on Image Processing. 4(3), 3, pp. 320-334, 1995.
[22] Zhengwei Yang, F.S. Cohen. Image registration and object recognition using affine invariants and convex hulls. IEEE Trans on Image Processing. 8(7), pp. 934-946, 1999.
[23]张迁,刘政凯,庞彦伟等.基SUSAN算法的航空影像的自动配准.测绘学报,2003,8,32(3).245-250.
[24] L.K. Heng, E.M. Hwa, H.S. KOK. High accuracy registration of translated and rotated images using hierarchical method. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 6, pp. 2211-2214, 2000.
[25]尚明姝,解凯.一种基于特征的全自动图像拼接算法.微计算机应用.2006.11,27(6).747-750.
[26] V. Jagannadan, M.C. Prakash, R.R. Sarma, et al. Feature extraction and image registration of color images using Fourier bases. IEEE Trans on Image Processing, 2, pp. 656-662, 2005.
[27] C.G. Harris, M.J. Stephens. A combined corner and edge detector. Processing Fourth Alvey Vision Conference. Manchester[J], U. K, pp. 148-150, 1988.
[28] R. Szeliski. Video mosaics for virtual environments. IEEE Computer Graphics and Applications. 16(2), pp. 21-33, 1996.
[29]件建宁.图像拼接技术研究:[硕士学位论文].西安:西安电子科技大学,2006,22-29
[30] R. Szeliski.Video mosaics for virtual environments. IEEE Computer Graphics and Applications.16(2), 3, pp. 22-30, 1996.
[31] C.D. Kuglin, D.C. Mines. The Phase Correlation Image Alignment Method. Proceedings of IEEE International Conference on Cybernetics and Society, New York. 9, pp. 163-165, 1975.
[32]李弼程,彭天强,彭波等.智能图像处理技术.北京:电子工业出版社, 2004, 260-286.
[33]刘冬梅.图像拼接算法研究:[硕士学位论文].西安:西安电子科技大学,2008,10-32
[34] Lisa Gottesfeld Brown. A survey of image registration techniques. ACM Computing Surveys, Vo1.24, No.4, pp. 325-376, December 1992.
[35] Barbara Zitova, Jan Flusser. Image registration methods. a survey. Image and Vision Computing 21 , pp977-1000, 2003.
[36]董洋.基于小波变换的遥感图像自动配准算法研究:[硕士学位论文].成都:电子科技大学,2009,8-43页
[37]文成林,周东华.多尺度估计理论及其应用.北京:清华大学出版社,2002.
[38] B S. Reddy, B N. Chatterji. A FFT-Based Technique for Translation, Rotation, and Scale Invariant Image Registration. IEEE Trans on Image Processing, 2, pp. 4-8, 1996.
[39] X.L. Dai, K. Siamak. Development of a feature-based Approach to Automated Image Registration for Multitemporal and Multisensor Remotely Sensed Imagery. Proceedings of the 1997 IEEE International Geoscience and Remote Sensing Symposium, pp. 243-245, 1997.
[40] A. Goshtasby, G.C. Stockman, C.V. Page. A region-based approach to digital image registration with subpixel accuracy. IEEE Trans. On Geoscience and Remote Sensing, GE-24(3), 5, pp. 390-399, 1986.
[41] D. Marr. Vision-A computational investigation into the human representation and processing of visual information. W.H. Freeman and Company, San Francisco.1982.
[42] L.G. Robert. Machine perception of three-dimension solids. Optical and Electro-Optimal Information Processing, Cambridge, MA, MIT Press, pp. 159-197,1965.
[43] J. Canny.A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 8(6), 11, pp. 679-698, 1986.
[44]冈萨雷斯,伍兹.阮秋琦,阮宇智译.数字图像处理.北京:电子工业出版社.2003.2:460-507.
[45] Zhengwei Yang, F.S. Cohen. Image registration and object recognition using affine invariants and convex hulls. IEEE Trans On Image Processing, 8(7), 7, pp. 934-946, 1999.
[46] W.A. Forstner. A feature based correspondence algorithm for image matching. International Society for Photogrammetry and Remote Sensing, Rovaniemi, Finland, 26-Ⅲ, 1986.
[47] H.P. Moravec. Towards Automatic Visual Obstacle Avoidance. Proceedings of the 5thInternational Joint Conference on Artificial Intelligence,Cambridge,Massachusetts.1977.
[48] S.M. Smith, J.M. Brady.SUSAN-A new approach to low level image processing. International Journal of Computer Vision, 1, pp. 45-78, 1997.
[49] H. Li, B.S. Manjunath, S. K. Mitra. A Contour-Based Approach to Multisensor Image Registration. IEEE Transactions on Image Processing, Vol.4, No.3, pp. 320-334, 1995.
[50] S.M. Smith and J.M. Brady. SUSAN-a new approach to low level image processing. International Journal of Computer Vision, 23(1), pp. 45-78, 1995.
[51] C. Harris and M. Stephen. A combined corner and edge detector. In 4th Alvey Vision Conf, pp. 146-152, 1988.
[52]郑柯,唐娉.资源一号卫星02星图像质量评价.资源一号卫星02星在轨测试报告.北京:中国资源卫星应用中心.2003,524-533
[53]李小英.传感器在轨辐射定标及MTF评价与补偿研究:[博士学位论文].北京:中国科学院遥感应用研究所.2006,36-47
[54]章权兵,罗斌.基于仿射变换模型的图像特征点集配准方法研究.中国图像图形学报,2003,8(10):1121-1125
[55] A. Goshtasby. Piecewise Linear Mapping Functions for Image Registration. Pattern Recognition, Vol.19, No.6, pp. 459-466, 1986.
[56] A. Goshtasby. Piecewise Cubic Mapping Functions for Image Registration. Pattern Recognition, Vol.20, No.5, pp. 525-533, 1987.
[57] J. Flusser. An adaptive method for Image Registration. Pattern Recognition, Vol.25, No.1. pp. 45-54, 1992
[58]周丽雅.遥感影像融合及质量评价研究.郑州:[硕士学位论文].解放军信息工程大学,2006,50-64
[2] Y. Xiong, Y. Turkowski.“Creating image-based VR using a self-calibrating fisheye lens. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico,USA, pp. 237-243,1997.
[3] R. Szeliski. Video mosaics for virtual environments. IEEE Computer Graphics and Applications, 16(2), 3, pp. 22-30, 1996.
[4] S. Peleg, B. Rousso. Mosaicing on Adaptive Manifolds. IEEE Trans. on Pattern and machine intelligence, 22(10) ,10, pp. 1144-1154, 2000.
[5] S. Gumustekin, R.W. Hall. Mosaic image generation on a flattened Gaussian sphere. Proceedings 3rd IEEE Workshop on Applications of Computer Vision, 12, pp. 50-55, 1996.
[6] S. Gumustekin, R.W. Hall. Image registration and mosaicing using a self-calibrating camera. In Proceedings of International Conference on mage Processing, 10, 1, pp. 818-822, 1998.
[7] H.Y. Shum, R. Szeliski. Panoramic image mosaics. Technical Report MSR-TR-97-23,Microsoft research, pp. 4-20, l997.
[8] R. Szeliski, H.Y. Shum. Creating Full View Panoramic Image Mosaics and Environment Maps. In Proc. of ACM SIGGRAPH, pp. 251-258, 1997.
[9] C.D. Kuglin, D.C. Mines. The Phase Correlation Image Alignment Method. Proceedings of IEEE International Conference on Cybernetics and Society, New York. 9, pp. 163-165, 1975.
[10] E.D. Castro, C. Morandi. Registration of translated and rotated images using finite Fourier transforms, IEEE Trans. on Pattern Analysis and Machine Intelligence, 9(5), pp. 700-703, 1987.
[11] R.B. Srinivasa, B.N. Chatterji. An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans. on Image Processing, 8(5), 9, pp. 1266-1271, 1996.
[12] S. Zokai, G..Wolberg. Image Registration Using Log-Polar Mappings for Recovery of Large-Scale Similarity and Projective Transformations. IEEE Trans. on Image Processing, 14(10), 10, pp. 1422-1434, 2005.
[13] R. Gupta, R. Hartley. Linear pushbroom cameras. IEEE Trans. On PAMI, 19(9), 9, pp. 963-975,1997.
[14]李忠新.图像镶嵌理论及若干算法研究.南京:南京理工大学博士论文, 2004, 4, 34-37.
[15]李志刚.边界重叠图像的一种快速拼接算法.计算机工程, 2000, 26(5), 37-38.
[16] A. Rosenfeld., A.C. Kak. Digital Picture Processing. Vol. I and II, Academic Press, Orlando, FL. 4, pp. 169-170, 1982.
[17] D.H. Kim, Y. I. Yoon, J.S. Cho.A Quasi-feature Based Image Mosaic Algorithms Using Modified Block Matching Criteria. IEEE of Japan. 12-C(5), pp. 892-898, 2001.
[18] A. D. Ventura, A. Rampini, R. Schettini. Image registration by recognition of corresponding structures. IEEE Trans. On Geoscience and Remote Sensing. 28(3), 3, pp. 305-314, 1990.
[19] Zhengwei Yang, F.S. Cohen. Cross-weighted moments and affine invariants for image registration and matching. IEEE Trans.on Pattern Analysis and Machine Intelligence, 21(8), 8, pp. 801-814, 1999.
[20] S.H. Chang, F.H. Cheng, W.H. Hsu, et al. Fast algorithm for point pattern matching.invariant to translation,rotations and scale changes. Pattern Recognition, 29(1), pp. 11-16, 1997.
[21] Hui Li, B.S. Manjunath, S.K. Mitra. A contour-based approach to multi-sensor image registration. IEEE Trans. on Image Processing. 4(3), 3, pp. 320-334, 1995.
[22] Zhengwei Yang, F.S. Cohen. Image registration and object recognition using affine invariants and convex hulls. IEEE Trans on Image Processing. 8(7), pp. 934-946, 1999.
[23]张迁,刘政凯,庞彦伟等.基SUSAN算法的航空影像的自动配准.测绘学报,2003,8,32(3).245-250.
[24] L.K. Heng, E.M. Hwa, H.S. KOK. High accuracy registration of translated and rotated images using hierarchical method. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 6, pp. 2211-2214, 2000.
[25]尚明姝,解凯.一种基于特征的全自动图像拼接算法.微计算机应用.2006.11,27(6).747-750.
[26] V. Jagannadan, M.C. Prakash, R.R. Sarma, et al. Feature extraction and image registration of color images using Fourier bases. IEEE Trans on Image Processing, 2, pp. 656-662, 2005.
[27] C.G. Harris, M.J. Stephens. A combined corner and edge detector. Processing Fourth Alvey Vision Conference. Manchester[J], U. K, pp. 148-150, 1988.
[28] R. Szeliski. Video mosaics for virtual environments. IEEE Computer Graphics and Applications. 16(2), pp. 21-33, 1996.
[29]件建宁.图像拼接技术研究:[硕士学位论文].西安:西安电子科技大学,2006,22-29
[30] R. Szeliski.Video mosaics for virtual environments. IEEE Computer Graphics and Applications.16(2), 3, pp. 22-30, 1996.
[31] C.D. Kuglin, D.C. Mines. The Phase Correlation Image Alignment Method. Proceedings of IEEE International Conference on Cybernetics and Society, New York. 9, pp. 163-165, 1975.
[32]李弼程,彭天强,彭波等.智能图像处理技术.北京:电子工业出版社, 2004, 260-286.
[33]刘冬梅.图像拼接算法研究:[硕士学位论文].西安:西安电子科技大学,2008,10-32
[34] Lisa Gottesfeld Brown. A survey of image registration techniques. ACM Computing Surveys, Vo1.24, No.4, pp. 325-376, December 1992.
[35] Barbara Zitova, Jan Flusser. Image registration methods. a survey. Image and Vision Computing 21 , pp977-1000, 2003.
[36]董洋.基于小波变换的遥感图像自动配准算法研究:[硕士学位论文].成都:电子科技大学,2009,8-43页
[37]文成林,周东华.多尺度估计理论及其应用.北京:清华大学出版社,2002.
[38] B S. Reddy, B N. Chatterji. A FFT-Based Technique for Translation, Rotation, and Scale Invariant Image Registration. IEEE Trans on Image Processing, 2, pp. 4-8, 1996.
[39] X.L. Dai, K. Siamak. Development of a feature-based Approach to Automated Image Registration for Multitemporal and Multisensor Remotely Sensed Imagery. Proceedings of the 1997 IEEE International Geoscience and Remote Sensing Symposium, pp. 243-245, 1997.
[40] A. Goshtasby, G.C. Stockman, C.V. Page. A region-based approach to digital image registration with subpixel accuracy. IEEE Trans. On Geoscience and Remote Sensing, GE-24(3), 5, pp. 390-399, 1986.
[41] D. Marr. Vision-A computational investigation into the human representation and processing of visual information. W.H. Freeman and Company, San Francisco.1982.
[42] L.G. Robert. Machine perception of three-dimension solids. Optical and Electro-Optimal Information Processing, Cambridge, MA, MIT Press, pp. 159-197,1965.
[43] J. Canny.A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 8(6), 11, pp. 679-698, 1986.
[44]冈萨雷斯,伍兹.阮秋琦,阮宇智译.数字图像处理.北京:电子工业出版社.2003.2:460-507.
[45] Zhengwei Yang, F.S. Cohen. Image registration and object recognition using affine invariants and convex hulls. IEEE Trans On Image Processing, 8(7), 7, pp. 934-946, 1999.
[46] W.A. Forstner. A feature based correspondence algorithm for image matching. International Society for Photogrammetry and Remote Sensing, Rovaniemi, Finland, 26-Ⅲ, 1986.
[47] H.P. Moravec. Towards Automatic Visual Obstacle Avoidance. Proceedings of the 5thInternational Joint Conference on Artificial Intelligence,Cambridge,Massachusetts.1977.
[48] S.M. Smith, J.M. Brady.SUSAN-A new approach to low level image processing. International Journal of Computer Vision, 1, pp. 45-78, 1997.
[49] H. Li, B.S. Manjunath, S. K. Mitra. A Contour-Based Approach to Multisensor Image Registration. IEEE Transactions on Image Processing, Vol.4, No.3, pp. 320-334, 1995.
[50] S.M. Smith and J.M. Brady. SUSAN-a new approach to low level image processing. International Journal of Computer Vision, 23(1), pp. 45-78, 1995.
[51] C. Harris and M. Stephen. A combined corner and edge detector. In 4th Alvey Vision Conf, pp. 146-152, 1988.
[52]郑柯,唐娉.资源一号卫星02星图像质量评价.资源一号卫星02星在轨测试报告.北京:中国资源卫星应用中心.2003,524-533
[53]李小英.传感器在轨辐射定标及MTF评价与补偿研究:[博士学位论文].北京:中国科学院遥感应用研究所.2006,36-47
[54]章权兵,罗斌.基于仿射变换模型的图像特征点集配准方法研究.中国图像图形学报,2003,8(10):1121-1125
[55] A. Goshtasby. Piecewise Linear Mapping Functions for Image Registration. Pattern Recognition, Vol.19, No.6, pp. 459-466, 1986.
[56] A. Goshtasby. Piecewise Cubic Mapping Functions for Image Registration. Pattern Recognition, Vol.20, No.5, pp. 525-533, 1987.
[57] J. Flusser. An adaptive method for Image Registration. Pattern Recognition, Vol.25, No.1. pp. 45-54, 1992
[58]周丽雅.遥感影像融合及质量评价研究.郑州:[硕士学位论文].解放军信息工程大学,2006,50-64