Abstract:In the present study, a novel change detection approach for high resolution remote sensing images is proposed based on the optical flow dynamic texture (OFDT), which could achieve the land use & land cover change information automatically with a dynamic description of ground-object changes. This paper describes the ground-object gradual change process from the principle using optical flow theory, which breaks the ground-object sudden change hypothesis in remote sensing change detection methods in the past. As the steps of this method are simple, it could be integrated in the systems and software such as Land Resource Management and Urban Planning software that needs to find ground-object changes. This method takes into account the temporal dimension feature between remote sensing images, which provides a richer set of information for remote sensing change detection, thereby improving the status that most of the change detection methods are mainly dependent on the spatial dimension information. In this article, optical flow dynamic texture is the basic reflection of changes, and it is used in high resolution remote sensing image support vector machine post-classification change detection, combined with spectral information. The texture in the temporal dimension which is considered in this article has a smaller amount of data than most of the textures in the spatial dimensions. The highly automated texture computing has only one parameter to set, which could relax the onerous manual evaluation present status. The effectiveness of the proposed approach is evaluated with the 2011 and 2012 QuickBird datasets covering Duerbert Mongolian Autonomous County of Daqing City, China. Then, the effects of different optical flow smooth coefficient and the impact on the description of the ground-object changes in the method are deeply analyzed. The experiment result is satisfactory, with an 87.29% overall accuracy and an 0.850 7 Kappa index, and the method achieves better performance than the post-classification change detection methods using spectral information only.
[1] Lu D, Mausel P, Brondizio E, et al. International Journal of Remote Sensing, 2004, 26(12): 2365. [2] Ashbindu Singh. Remote Sensing, 1989, 10(6): 989. [3] Huang Xin, Zhang Liangpei, Zhu Tingting. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 7(1):105. [4] Zhang R, Wu J. Intelligence Computation and Evolutionary Computation, AISC, 2013,180: 591. [5] Daniel Tomowski, Manfred Ehlers, Sascha Klonus. Urban Remote Sensing Event (JURSE), Germany, Munich, IEEE,2011, Joint: 329. [6] Antoine Lefebvre, Thomas Corpetti,Laurence Hubert-Moy. Geoscience and Remote Sensing Symposium, United States, Boston, IEEE,2008, 4): 663. [7] Daniele Ehrlich, Conrad Bielski. 2011 Institute of Electrical and Electronics Engineers Geoscience & Remote Sensing Society and International Society for Photogrammetry and Remote Sensing Joint Urban Remote Sensing Event, Germany, Munich,2011. 77. [8] Li Peijun, Cheng Tao, Gabriele Moser, et al. 2007 Institute of Electrical and Electronics Engineers International Geoscience and Remote Sensing Symposium, Spain, Barcelona,2007. 1922. [9] LI Shu-kun, LI Pei-jun, CHENG Tao(李淑坤,李培军,程 涛). Remote Sensing for Land & Resources(国土资源遥感), 2009,(3): 35. [10] SONG Ju-er, WANG Xue, LI Pei-jun(宋桔尔,王 雪,李培军). Journal of Remote Sensing(遥感学报), 2012, 16(6): 1233. [11] Aristotle (亚里士多德). Physica(物理学). Beijing:The Commercial Press(北京:商务印书馆),2004. [12] Berthold K P Horn, Brian G Rhunck. Artificial Intelligence, 1981,17(1): 185.