Title :
Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint
Author :
Xinwei Zheng ; Xian Sun ; Kun Fu ; Hongqi Wang
Author_Institution :
Key Lab. of Spatial Inf. Process. & Applic. Syst. Technol., Beijing, China
Abstract :
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.
Keywords :
geographic information systems; geophysical image processing; geophysical techniques; image classification; MFJSC discriminative power; MFJSC model; QuickBird images; annotation framework; annotation task; automatic annotation; common sparsity pattern; l1-mixed-norm regularization; l2-mixed-norm regularization; land-use classes; large image patches; large-satellite-image annotation; multifeature joint sparse coding; spatial relation constraint; spatial-relation-constrained classifier; Accuracy; Dictionaries; Feature extraction; Image reconstruction; Joints; Satellites; Support vector machines; Large-image annotation; multifeature joint sparse coding (MFJSC); spatial information;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2012.2216499