Aiming at the problem of segmentation and extraction of cropland parcels in remote sensing images with complex background, a method of segmentation and extraction of cropland in high-resolution remote sensing images i...
详细信息
ISBN:
(纸本)9781510657274;9781510657267
Aiming at the problem of segmentation and extraction of cropland parcels in remote sensing images with complex background, a method of segmentation and extraction of cropland in high-resolution remote sensing images is proposed. Firstly, the linear spectral clustering (lsc) algorithm is applied to the remote sensing image to obtain the segmentation results of superpixel blocks in the target area and the background area;then, the maximum similarity region merging algorithm (MSRM) algorithm is used to merge the superpixel blocks of two different areas separately, which effectively reduces the phenomenon of under-segmentation and over-segmentation of the image and obtains the binary image containing the cultivated land parcels and non-cultivated land parcels. Based on this, the total arable area is calculated using MATLAB. Finally, in order to verify the correctness and effectiveness of the proposed method, the remote sensing image data provided by Beijing Guosheng Xingmai Information Technology Co. The simulation results show that the proposed method can effectively segment and extract remote sensing cropland images.
Aiming at the shortcoming that the efficiency of k-nearest neighbor algorithm (kNN) greatly decreases with the increase of the number of samples, a two-screen k-nearest neighbor algorithm is proposed. Its purpose is t...
详细信息
ISBN:
(纸本)9781665423144
Aiming at the shortcoming that the efficiency of k-nearest neighbor algorithm (kNN) greatly decreases with the increase of the number of samples, a two-screen k-nearest neighbor algorithm is proposed. Its purpose is to increase the calculation speed of the algorithm while ensuring that the accuracy rate does not decrease, so that the improved algorithm can handle big data problems. Firstly, large-scale spectral clustering based on landmark representation (lsc algorithm) is used to cluster the data to find the cluster closest to the point to be measured;secondly, triangle inequality is used to process the data set close to the point to be measured and far from the nearest cluster center. The data after these two screenings is then used as the final training sample of the k-nearest neighbor algorithm. It can improve the diversity and effectiveness of data on the basis of reducing the number of training samples. Finally, it was verified on a public data set and compared with the traditional k nearest neighbor algorithm. The results show that the speed of the algorithm has been improved, the calculation amount has been reduced by 49%, and the accuracy has been maintained at about 95%.
暂无评论