• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Pixels, Objects, Intelligence: GEOgraphic Object Based Image Analysis for the 21st Century >HIDDEN MARKOV MODELS APPLIED IN AGRICULTURAL CROPS CLASSIFICATION
【24h】

HIDDEN MARKOV MODELS APPLIED IN AGRICULTURAL CROPS CLASSIFICATION

机译：隐藏的马尔可夫模型应用于农业作物分类

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This work proposes a Hidden Markov Model (HMM) based technique to classify agricultural crops, exploring information of temporal image sequences from TM and ETM~(+)/Landsat sensors. It endeavours to combine two knowledge fields, the research on plant phenology and on multitemporal object-based classification techniques. HMMs are used to relate the varying spectral response along the crop cycle with plant phenology for different crop classes. The method recognizes different agricultural crops by analyzing their spectral profiles over a sequence of medium resolution satellite images. In our approach the temporal behaviour of each crop class is modelled by a specific HMM. A segment-based classification is performed using the average spectral values of each image segment across an image sequence, which is subsequently submitted to the HMMs of each crop class. The image segment is assigned to the crop class, whose corresponding HMM delivers the highest probability of emitting the observed sequence of spectral values. Experiments were conducted upon a set of 12 co-registered and radiometrically corrected LANDSAT images. The images cover an area of the State of Sao Paulo, Brazil with about 124.100ha, between 2002 and 2004. The following crop classes were considered: sugarcane, soybean, corn, pasture and riparian forest. Performance assessment was carried out upon a data set classified visually by two analysts and validated by extensive field work. While in our experiments a single-date classifier delivered in average an overall accuracy close to 58percent, the HMM method was able to achieve 86percent. Considering the scarcity of training samples for some crop classes in our data set, it is fair to expect even higher performances, if more representative training sets can be made available.
机译：这项工作提出了一种基于隐马尔可夫模型（HMM）的技术来对农业作物进行分类，探索来自TM和ETM〜（+）/山底壳传感器的时间图像序列的信息。它努力结合两种知识领域，植物候选研究以及基于多立体对象的分类技术。 HMMS用于沿着作物循环与不同作物类别的植物脊椎循环的不同光谱响应。该方法通过通过在一系列中分辨率卫星图像上分析它们的光谱谱来识别不同的农作物。在我们的方法中，每个裁剪类的时间行为由特定的嗯模型。使用跨图像序列的每个图像段的平均光谱值执行基于段的分类，随后将其提交给每个裁剪类的HMM。将图像段分配给裁剪类别，其对应的HMM提供发射观察到的光谱值序列的最高概率。在一组12个共登记和放射性校正的Landsat图像上进行实验。该图像涵盖巴西圣保罗州的一个地区，2002年至2004年间。以下作物课程被认为：甘蔗，大豆，玉米，牧场和河岸森林。在视觉上的两次分析师的数据集上进行性能评估，并通过广泛的现场工作验证。虽然在我们的实验中，单日分类器平均交付的整体精度接近58％，但HMM方法能够实现86平方。考虑到我们数据集中一些作物类别的训练样本的稀缺性，如果可以提供更多代表性培训集，则预计甚至更高的表现。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号