Classification of Hyperspectral imagery Using SIFT for Spectral Matching

Xu, Yiping; Hu, Kaoning; Tian, Yan; Peng, Fuyuan

doi:10.1109/cisp.2008.114

Cited by 14 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For remote sensing HSI, Xu et al [17] proposed a 1D SIFT algorithm for image classification. In this work, spectral keypoints were extracted from pixels (spectral signatures) to achieve invariant spectral features.…”

Section: Sift For Hyperspectral Imagementioning

confidence: 99%

“…Distinctive features are identified and extracted from different spectral-spatial scales, so they are invariant to spectral and spatial dimension changes. Our method is inspired from Scale-Invariant Feature Transform (SIFT) algorithm [15] which has been modified for 3D images, multispectral and hyperspectral images in recent research [16], [17]. Another related work is 3D SIFT which was proposed for video or 3D medical images [18], [19], [20], but it has not been applied to HSI cube.…”

Section: Introductionmentioning

confidence: 99%

“…However, all these methods have been implemented on individual bands of multispectral image without exploiting the abundant spectral information. On hyperspectral images, attempts have been made to use SIFT algorithms for scale, rotation and affine transformation invariant feature extraction [17], [23], [24], [25]. These works were applied on either spectral or spatial domain only.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images

Al-khafaji

Zhou

Zia

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Spectral-spatial feature extraction is an important task in hyperspectral image processing. In this paper we propose a novel method to extract distinctive invariant features from hyperspectral images for registration of hyperspectral images with different spectral conditions. Spectral condition means images are captured with different incident lights, viewing angles, or using different hyperspectral cameras. In addition, spectral condition includes images of objects with the same shape but different materials. This method, which is named spectral-spatial scale invariant feature transform (SS-SIFT), explores both spectral and spatial dimensions simultaneously to extract spectral and geometric transformation invariant features. Similar to the classic SIFT algorithm, SS-SIFT consists of keypoint detection and descriptor construction steps. Keypoints are extracted from spectral-spatial scale space and are detected from extrema after 3D difference of Gaussian is applied to the data cube. Two descriptors are proposed for each keypoint by exploring the distribution of spectral-spatial gradient magnitude in its local 3D neighborhood. The effectiveness of the SS-SIFT approach is validated on images collected in different light conditions, different geometric projections, and using two hyperspectral cameras with different spectral wavelength ranges and resolutions. The experimental results show that our method generates robust invariant features for spectral-spatial image matching.

show abstract

Section: Sift For Hyperspectral Imagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images

Al-khafaji

Zhou

Zia

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The common methods include spectral encoding match, spectral correlation coefficient, spectral angle match, spectral information divergence method, etc. In [38], Xu et al proposed the spectral matching approach based on scale-invariant feature transform(SIFT). In [39], Murphy et al introduced the variable information into the spectral angle match to improve the classification accuracy.…”

Section: Related Workmentioning

confidence: 99%

When Low Rank Representation Based Hyperspectral Imagery Classification Meets Segmented Stacked Denoising Auto-Encoder Based Spatial-Spectral Feature

2018

View full text Add to dashboard Cite

When confronted with limited labelled samples, most studies adopt an unsupervised feature learning scheme and incorporate the extracted features into a traditional classifier (e.g., support vector machine, SVM) to deal with hyperspectral imagery classification. However, these methods have limitations in generalizing well in challenging cases due to the limited representative capacity of the shallow feature learning model, as well as the insufficient robustness of the classifier which only depends on the supervision of labelled samples. To address these two problems simultaneously, we present an effective low-rank representation-based classification framework for hyperspectral imagery. In particular, a novel unsupervised segmented stacked denoising auto-encoder-based feature learning model is proposed to depict the spatial-spectral characteristics of each pixel in the imagery with deep hierarchical structure. With the extracted features, a low-rank representation based robust classifier is then developed which takes advantage of both the supervision provided by labelled samples and unsupervised correlation (e.g., intra-class similarity and inter-class dissimilarity, etc.) among those unlabelled samples. Both the deep unsupervised feature learning and the robust classifier benefit, improving the classification accuracy with limited labelled samples. Extensive experiments on hyperspectral imagery classification demonstrate the effectiveness of the proposed framework.

show abstract

“…While they can be reduced to monochrome images (that could be a simple input to classical interest point algorithms), that conversion is not trivial and could lose structural information (Dorado-Munoz et al, 2012). Most approaches in hyperspectral domain are based on the SIFT algorithm: as classification support (Xu et al, 2008), algorithm extension (Mukherjee et al, 2009;Dorado-Munoz et al, 2012), aligning image strips for change detection (Ringaby et al, 2010) or optimizing parameters for hyperspectral image matching (Sima and Buckley, 2013). A different approach is taken in (Vakalopoulou and Karantzalos, 2014), where SIFT and SURF are combined in working with spectral bands groups.…”

Section: Introductionmentioning

confidence: 99%

Performance of Interest Point Descriptors on Hyperspectral Images

Głomb

Cholewa

2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Interest point descriptors (e.g. Scale Invariant Feature Transform, SIFT or Speeded-Up Robust Features, SURF) are often used both for classic image processing tasks (e.g. mosaic generation) or higher level machine learning tasks (e.g. segmentation or classification). Hyperspectral images are recently gaining popularity as a potent data source for scene analysis, material identification, anomaly detection or process state estimation. The structure of hyperspectral images is much more complex than traditional color or monochrome images, as they comprise of a large number of bands, each corresponding to a narrow range of frequencies. Because of varying image properties across bands, the application of interest point descriptors to them is not straightforward. To the best of our knowledge, there has been, to date, no study of performance of interest point descriptors on hyperspectral images that simultaneously integrate a number of methods and use a dataset with significant geometric transformations. Here, we study four popular methods (SIFT, SURF, BRISK, ORB) applied to complex scene recorded from several viewpoints. We presents experimental results by observing how well the methods estimate the 3D cameras' positions, which we propose as a general performance measure.

show abstract

Classification of Hyperspectral imagery Using SIFT for Spectral Matching

Cited by 14 publications

References 8 publications

Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images

Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images

When Low Rank Representation Based Hyperspectral Imagery Classification Meets Segmented Stacked Denoising Auto-Encoder Based Spatial-Spectral Feature

Performance of Interest Point Descriptors on Hyperspectral Images

Contact Info

Product

Resources

About