CAJ | 학술논문

提出了一种基于多特征组合的SVM土地利用变化检测算法。该算法从不同方面更加详细地对遥感影像所包含的内容进行描述，尝试将遥感影像的灰度信息和纹理信息相结合作为SVM分类的特征向量，对同一区域不周时期的遥感影像进行分类，然后通过对比影像的分类矩阵和分类结果图，得到遥感影像的土地利用变化区域。实验结果表明，本文算法简洁、快速，能正确提取绝大部分的土地利用变化区域，具有良好的可行性。
제출료일충기우다특정조합적SVM토지이용변화검측산법。해산법종불동방면경가상세지대요감영상소포함적내용진행묘술，상시장요감영상적회도신식화문리신식상결합작위SVM분류적특정향량，대동일구역불주시기적요감영상진행분류，연후통과대비영상적분류구진화분류결과도，득도요감영상적토지이용변화구역。실험결과표명，본문산법간길、쾌속，능정학제취절대부분적토지이용변화구역，구유량호적가행성。
A novel land use change detection algorithm based on multi-feature combination by using SVM is put forward.The algorithm proposed describes the content included in the remote sensing image and tries to combine the gray information and texture information of a remote sensing image as the eigenvectors of SVM algorithm.Then the remote sensing images of the same area are classified by using SVM algorithm and the change region is obtained by comparing the classification matrix and results of the two images.The experimental results show that the method proposed by the paper is simple and quick and also can obtain most of right land change region,has good feasibility.