arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.2416cs.CV
收藏

基于非加性熵的卫星图像分类与分割

Satellite image classification and segmentation using non-additive entropy

São Carlos Institute of Physics, University of São Paulo (USP)(圣保罗大学圣卡洛斯物理研究所);Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP), Universidade de São Paulo (USP)(圣保罗大学里贝朗普雷图哲学、科学与文学学院);Instituto Nacional de Ciências e Tecnologia de Sistemas Complexos(国家复杂系统科学技术研究所)

Lucas Assirati, Alexandre Souto Martinez, Odemir Martinez Bruno

摘要:

在这里,我们比较玻尔兹曼吉布斯香农(标准)与Tsallis熵的模式识别和分割的彩色图像获得的卫星,通过“谷歌地球”。通过分割,我们的意思是分割图像以定位感兴趣的区域。在这里,我们根据训练基础来区分和定义图像分区类。该培训基础包括三个模式类:水生,城市和植被地区。我们的数值实验表明,Tsallis熵,作为一个特征向量组成的不同的熵指标$q$优于标准熵。我们提出的方法有几个应用,一旦卫星图像可以用来监测从农村到城市地区的移民,农业活动,石油在海洋上的蔓延等。

英文摘要:

Here we compare the Boltzmann-Gibbs-Shannon (standard) with the Tsallis entropy on the pattern recognition and segmentation of coloured images obtained by satellites, via "Google Earth". By segmentation we mean split an image to locate regions of interest. Here, we discriminate and define an image partition classes according to a training basis. This training basis consists of three pattern classes: aquatic, urban and vegetation regions. Our numerical experiments demonstrate that the Tsallis entropy, used as a feature vector composed of distinct entropic indexes $q$ outperforms the standard entropy. There are several applications of our proposed methodology, once satellite images can be used to monitor migration form rural to urban regions, agricultural activities, oil spreading on the ocean etc.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑