Research On Typical Area Objects Extraction In Remote Sensing Image Based On Texture Features

With the development of technologies of sensor, aerial and space platform, and data communication, remote sensing technique has entered a new era that can obtain various earth data actively, rapidly, accurately, and through multi-way. It possesses omni-directional and all-weather ability to acquire space information. Therefore, it is an important data source to update spatial information, and have extensive application potential in national economy and military affairs. As far as the interpretation of spatial images and the digitization work in surveying and mapping field are concerned, this paper has researched a method, based on texture features of remote sensing images, to semi-automatically extract canonical area objects. The key contents of the method are texture feature extraction, feature matching, and region extraction etc.The major works of this paper are listed as follows:1. The concept, significance, difficulty of remote sensing image interpretation is introduced. Current status and developing trend of area objects extraction from remote sensing images is analyzed. Based on texture features, relating technologies of area objects extraction are discussed.2. The basic method, principle and main process of area objects' texture segmentation is introduced,two common methods of texture segmentation are proposed and analyzed. Region growth method and K- means clustering method.3. Semi-automatic extraction's process of area objects is introduced, experiments on typical area objects are done by common extraction algorithm.Then, the algorithm is analyzed that based on the experimental results.4. The semi-automatic extraction's method of typical area objects is analyzed in detail. We combine Radon transform with tree-structured wavelet transform and combine gray-grads level co-occurrence matrix with laws texture in vegetation's extraction. We combine log-polar transform with Fourier transform and combine gray level co-occurrence matrix with Gabor wavelet in settlement place's extraction. Sevral integration and improvement is proposed aiming at the method which are stated above,then good result of experiments is acquired.