Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Hyperspectral data to relative lidar depth: an inverse problem for remote sensing
Date
2019-07-13
Author
Akar, Gözde
Metadata
Show full item record
Item Usage Stats
109
views
0
downloads
Cite This
Hyperspectral data provides rich information about a scene in terms of spectral details since it encapsulates measurements/observations from a wide large range of spectrum. To this end, it has been used in different problems mostly related to identification and detection processes. However, the main limitation arises for the accessibility of data. More precisely, there is no sufficient amount of hyperspectral data available compared to visible range data for trainable models. In this paper, we tackle an inverse problem to estimate the relative lidar depth from hyperspectral data. To solve its limitation, we integrate semantic information existed in data with supervised labels to decrease the possibility ofparameter overfitting. Moreover, details of the output responses are enhanced with Laplacian pyramids and attention layers in which the model makes predictions from each subsequent scale instead of a single shot prediction from the top of the model. In our experiments, we use the 2018 IEEE GRSS Data Fusion Challenge dataset. From the experimental results, we prove that use of hyperspectral data instead of visible range data improves the performance. Moreover, we show that results are significantly improved if a sparse set of depth measurements is used along with hyperspectral data. Lastly, the integration of semantic information to the solution yields more stable and better results compared to the baselines.
URI
https://hdl.handle.net/11511/84026
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9025362
DOI
https://doi.org/10.1109/CVPRW.2019.00126
Conference Name
32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW (2019)
Collections
Department of Electrical and Electronics Engineering, Conference / Seminar
Suggestions
OpenMETU
Core
Catadioptric hyperspectral imaging, an unmixing approach
Baskurt, Didem Ozisik; BAŞTANLAR, YALIN; Çetin, Yasemin (Institution of Engineering and Technology (IET), 2020-10-01)
Hyperspectral imaging systems provide dense spectral information on the scene under investigation by collecting data from a high number of contiguous bands of the electromagnetic spectrum. The low spatial resolutions of these sensors frequently give rise to the mixing problem in remote sensing applications. Several unmixing approaches are developed in order to handle the challenging mixing problem on perspective images. On the other hand, omnidirectional imaging systems provide a 360-degree field of view in...
Continuous dimensionality characterization of image structures
Felsberg, Michael; Kalkan, Sinan; Kruger, Norbert (Elsevier BV, 2009-05-04)
Intrinsic dimensionality is a concept introduced by statistics and later used in image processing to measure the dimensionality of a data set. In this paper, we introduce a continuous representation of the intrinsic dimension of an image patch in terms of its local spectrum or, equivalently, its gradient field. By making use of a cone structure and barycentric co-ordinates, we can associate three confidences to the three different ideal cases of intrinsic dimensions corresponding to homogeneous image patche...
Computational Spectral Imaging Techniques for High-Resolution and Instantaneous Observations of the Solar Corona
Öktem, Sevinç Figen; Davila, Joseph M (2014-08-18)
Spectral imaging is a fundamental diagnostic technique for the study of the solar coronal plasma, and spectral data is routinely used to measure the temperature, density, and flow velocity in coronal features. However, obtaining the spectra of a multi-dimensional region with inherently two-dimensional detectors poses intrinsic limitations on the spatio-temporal extent of the technique. In particular, slit spectrographs suffer from a limited instantaneous field-of-view (IFOV), and filter-based spectral image...
Lateral stiffness estimation in frames and its implementation to continuum models for linear and nonlinear static analysis
EROĞLU AZAK, TUBA; Akkar, Dede Sinan (2011-08-01)
Continuum model is a useful tool for approximate analysis of tall structures including moment-resisting frames and shear wall-frame systems. In continuum model, discrete buildings are simplified such that their overall behavior is described through the contributions of flexural and shear stiffnesses at the story levels. Therefore, accurate determination of these lateral stiffness components constitutes one of the major issues in establishing reliable continuum models even if the proposed solution is an appr...
Dual band quasi-yagi antenna array structure for the side loop reduction by using binomial weighting
Karaçuha, Kamil; Çelik, Feza Turgay (2019-12-01)
In this study, a double-loop resonant type dual-band quasi-Yagi microstrip antenna array is designed. The numerical and experimental analyses are done and the prototype is produced. The antenna array is fed by Binomial weighting to reduce the sidelobes. Operating frequencies are chosen as the free unlicensed Wi-Fi band (2.4-2.48 GHz) and one of the planned 5G band for Europe Zone (3.4-3.8 GHz). The main aim is to have a directive radiation pattern for the higher frequency band and an Omni-like radiation pat...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
G. Akar, “Hyperspectral data to relative lidar depth: an inverse problem for remote sensing,” Long Beach, CA, 2019, p. 956, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/84026.