Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint
Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint
复制标题
DOI：
10.1109/lgrs.2012.2216499
复制
发表时间：
2013-07
影响因子：
4.8
通讯作者：
Xinwei Zheng;Xian Sun;Kun Fu;Hongqi Wang
中科院分区：
文献类型：
--
作者：
Xinwei Zheng;Xian Sun;Kun Fu;Hongqi Wang
在这封信中，我们提出了一个新的框架，大卫星图像注释使用多特征联合稀疏编码（MFJSC）与空间关系约束。MFJSC模型对特征的编码系数施加l1，2-混合范数正则化。正则化将鼓励系数共享共同的稀疏模式，这将保留交叉特征信息并消除它们必须具有相同系数的约束。大图像块之间的空间依赖性对于注释任务是有用的，但在其他方法中通常被忽略或利用不足。在这封信中，我们设计了一个空间关系约束的分类器，利用MFJSC的输出和空间依赖性更精确地注释图像。在21个土地利用类别和QuickBird图像的数据集上进行的实验显示了MFJSC的区分能力和我们的注释框架的有效性。
In this letter, we propose a novel framework for large-satellite-image annotation using multifeature joint sparse coding (MFJSC) with spatial relation constraint. The MFJSC model imposes an l1, 2-mixed-norm regularization on encoded coefficients of features. The regularization will encourage the coefficients to share a common sparsity pattern, which will preserve the cross-feature information and eliminate the constraint that they must have identical coefficients. Spatial dependences between patches of large images are useful for the annotation task but are usually ignored or insufficiently exploited in other methods. In this letter, we design a spatial-relation-constrained classifier to utilize the output of MFJSC and the spatial dependences to annotate images more precisely. Experiments on a data set of 21 land-use classes and QuickBird images show the discriminative power of MFJSC and the effectiveness of our annotation framework.