Spectral angle automatic cluster routine (SAALT): an unsupervised multispectral clustering algorithm

Weisberg, A.; Najarian, M.A.; Borowski, Bret; Lisowski, J.J.; Miller, Bill

doi:10.1109/aero.1999.792099

Cited by 10 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other similarity criteria incorporate neighboring pixels to regions such as spectral angle distance (SAD), which is invariant to unknown multiplicative scalings of spectra that may arise due to differences in illumination and angular orientation [12]. However, these effects do not seem important in the images used in this study considering the classification results, although they might be relevant in other applications.…”

Section: Supervised Image Classificationmentioning

confidence: 99%

“…In this study, we expect that classification over the multispectral data will achieve a satisfactory segmentation. Furthermore, the a priori knowledge available about the study region, e.g., the location of each lake of interest, allows us to identify appropriate training sites and use a supervised classification approach based on support vector machines (SVM) rather than an unsupervised classification technique, e.g., clustering or mathematical morphology [12]- [14]. The SVM is a novel type of learning machine based on statistics learning theory introduced by Vapnik [15] and applied by many others [16].…”

mentioning

confidence: 99%

See 1 more Smart Citation

A shape-based approach to change detection of lakes using time series remote sensing images

Narayanan

2003

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-Shape analysis has not been considered in remote sensing as extensively as in other pattern recognition applications. However, shapes such as those of geometric patterns in agriculture and irregular boundaries of lakes can be extracted from the remotely sensed imagery even at relatively coarse spatial resolutions. This paper presents a procedure for efficiently retrieving and representing shapes of interesting features in remotely sensed imagery using supervised classification, object recognition, parametric contour tracing, and proposed piecewise linear polygonal approximation techniques. In addition, shape similarity can be measured by means of a computationally efficient metric. The study was conducted on a time series of radiometric and geometric rectified Landsat Multispectral Scanner (MSS) images and Thematic Mapper (TM) images, covering the scenes containing lakes in the Nebraska Sand Hills region. The results validate the effectiveness of the proposed processing chain in change detection of lake shapes and show that shape similarity is an important parameter in quantitatively measuring the spatial variations of objects.

show abstract

Section: Supervised Image Classificationmentioning

confidence: 99%

mentioning

confidence: 99%

A shape-based approach to change detection of lakes using time series remote sensing images

Narayanan

2003

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Supervised classification such as Bayesian [1] and Support Vector Machines [2] can be applied when training data and/or ground truth data can be obtained from the study area. Unsupervised classification techniques like clustering [3] or mathematical morphology [4] may be used to find similar groups in the data, each representing a class. A label will then be assigned to each class by domain experts during the postclassification processing.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical land cover information retrieval in object-oriented remote sensing image databases with native queries

2007

Proceedings of the 45th Annual Southeast Regional Conference

View full text Add to dashboard Cite

Classification and change detection of land cover types in the remotely sensed images is one of the major applications in remote sensing. This paper presents a hierarchical framework for land cover information storage and retrieval from object-oriented (OO) remote sensing image databases. Multi-spectral (band) remotely sensed images are classified by an optimized k-means clustering algorithm. The land cover maps are then decomposed and indexed with region quad-tree data structure stored in an OO database. Native queries (NQs), which use the semantics of the OO programming language for query composition, are developed to retrieve land cover distribution information and detect the changes of each land cover type at multi levels. A prototype system was implemented and the experiments were conducted on a time series Landsat Thematic Mapper (TM) images. The results show the effectiveness of the framework and the potentials in other remote sensing applications like urban planning and drought monitoring.

show abstract

“…Indeed, vectors belonging to the same category most likely occupy the same region in the high-dimensionality space and therefore the angle between them is expected to be small. Despite its simplicity, this measure has proven its effectiveness with hyper and multispectral images for remote sensing [11,12], where it is called "spectral angle" due to the origin of the observation vectors, which represent the spectral reflectance of the soil in the observed area. This measure has also been effectively used in color image segmentation [13,14].…”

Section: Vector Angle Similarity Measurementioning

confidence: 99%

A Robust and Low‐Complexity Gas Recognition Technique for On‐Chip Tin‐Oxide Gas Sensor Array

et al. 2008

View full text Add to dashboard Cite

Gas recognition is a new emerging research area with many civil, military, and industrial applications. The success of any gas recognition system depends on its computational complexity and its robustness. In this work, we propose a new low-complexity recognition method which is tested and successfully validated for tin-oxide gas sensor array chip. The recognition system is based on a vector angle similarity measure between the query gas and the representatives of the different gas classes. The latter are obtained using a clustering algorithm based on the same measure within the training data set. Experimented results on our in-house gas sensors array show more than 98% of correct recognition. The robustness of the proposed method is tested by recognizing gas measurements with simulated drift. Less than 1% of performance degradation is noted at the worst case scenario which represents a significant improvement when compared to the current state-of-the-art.

show abstract

Spectral angle automatic cluster routine (SAALT): an unsupervised multispectral clustering algorithm

Cited by 10 publications

References 1 publication

A shape-based approach to change detection of lakes using time series remote sensing images

A shape-based approach to change detection of lakes using time series remote sensing images

Hierarchical land cover information retrieval in object-oriented remote sensing image databases with native queries

A Robust and Low‐Complexity Gas Recognition Technique for On‐Chip Tin‐Oxide Gas Sensor Array

Contact Info

Product

Resources

About