Unsharp Masking Filter Based Shadow-Invariant Feature Extraction For Hyperspectral Signatures

Date

2014-04-25

Author

Sakarya, Ufuk
Demirkesen, Can
Teke, Mustafa

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

174
views

0
downloads

Hyperspectral image processing is an important research topic in remote sensing. The effect of atmosphere, especially cloud shadows need to be taken care of in hyperspectral image processing analysis. In this paper, a shadow-invariant feature extraction technique based on unsharp mask filtering is proposed for hyperspectral signatures. This technique is designed to remedy the problem of one material having different spectral signatures due to illumination condition. Similarity of the two signatures belonging to a same material in differently illuminated areas (shadow and non-shadow) is investigated before and after filtering. According to the first experiments, the proposed approach seems to be effective.

Subject Keywords

Shadow-invariant feature extraction, Unsharp masking filter, Hyperspectral signatur

URI

https://hdl.handle.net/11511/66685

Collections

Unclassified, Conference / Seminar

Suggestions

OpenMETU
Core

HYPERSPECTRAL IMAGES AND LIDAR BASED DEM FUSION: A MULTI-MODAL LANDUSE CLASSIFICATION STRATEGY Demirkesen, Can; Teke, Mustafa; Sakarya, Ufuk (2014-07-18) Hyperspectral imaging based land cover / land use classification accuracy is expected to be improved by fusion with a LIDAR based Digital Elevation Model (DEM). To this end, we propose a multi-modal architecture, as well as a filtering technique extracting a shadow invariant one dimensional feature from a pixel spectrum. The proposed approach allows treating shadow and non-shadow areas separately. DEM is incorporated into this architecture through feature extraction and post classification procedures. A dig...
DTW BASED SIGNAL ALIGNMENT FOR ENHANCING CO2 DETECTION IN MWIR HYPERSPECTRAL IMAGERY Omruuzun, Fatih; Baskurt, Didem Ozisik; Çetin, Yasemin (2015-06-05) Remote sensing and detection of gases using hyperspectral imagery is an emerging research topic. Recent developments in infrared sensor technology increase usage of these devices in various fields ranging from environmental applications to defence industry. Another research topic in remote sensing field is the detection and identification of gas emissions using these devices. This study proposes a method for improving detection accuracy of CO2 emissions in Mid-Wave Infrared (MWIR) hyperspectral imagery with...
Thermal Infrared Hyperspectral Dimension Reduction Experiment Results For Global And Local Information Based Linear Discriminant Analysis Sakarya, Ufuk (2015-05-19) Thermal infrared hyperspectral image processing has become an important research topic in remote sensing. One of the research topics in thermal infrared hyperspectral image classification is dimension reduction. In this paper, thermal infrared hyperspectral dimension reduction experiment results for global and local information based linear discriminant analysis is presented. Advantages of the use of not only global pattern information, but also local pattern information are tested in thermal infrared hyper...
Kalman filter based fusion of camera and inertial sensor measurements for body state estimation Aslan Aydemir, Gökçen; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2009) The focus of the present thesis is on the joint use of cameras and inertial sensors, a recent area of active research. Within our scope, the performance of body state estimation is investigated with isolated inertial sensors, isolated cameras and finally with a fusion of two types of sensors within a Kalman Filtering framework. The study consists of both simulation and real hardware experiments. The body state estimation problem is restricted to a single axis rotation where we estimate turn angle and turn r...
HYPERSPECTRAL CLASSIFICATION USING STACKED AUTOENCODERS WITH DEEP LEARNING Özdemir, Ataman; Cetin, C. Yasemin Yardimci (2014-06-27) In this study, stacked autoencoders which are widely utilized in deep learning research are applied to remote sensing domain for hyperspectral classification. High dimensional hyperspectral data is an excellent candidate for deep learning methods. However, there are no works in literature that focuses on such deep learning approaches for hyperspectral imagery. This study aims to fill this gap by utilizing stacked autoencoders. Experiments are conducted on the Pavia University scene. Using stacked autoencode...

Citation Formats

U. Sakarya, C. Demirkesen, and M. Teke, “Unsharp Masking Filter Based Shadow-Invariant Feature Extraction For Hyperspectral Signatures,” 2014, p. 293, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/66685.