Difference between revisions of "Hyperspectral Imaging"

From NSL

Jump to: navigation, search
(Created page with "This project addresses different challenges in the full pipeline of capturing, transmitting, and identifying remote scenes using Hyperspectral images (HSI). == People == * ...")
 
(Adaptive Identification of Remote Scenes using HSI)
 
(6 intermediate revisions by one user not shown)
Line 1: Line 1:
This project addresses different challenges in the full pipeline of capturing, transmitting, and identifying remote scenes using Hyperspectral images (HSI).  
+
Hyperspectral imaging (HSI) is a powerful tool that can provide substantial information about a scene through remote sensing. This project addresses different challenges in the pipeline of capturing, transmitting, and identifying remote scenes using hyperspectral images. One of the main significant challenges in hyperspectral imaging is analyzing the data and extracting the required information. This is mainly because of the extremely high dimensionality of hyperspectral images, which limits our ability to identify spectral signatures fast and accurately. In addition, noise in hyperspectral images makes matters even more complicated.
 
+
  
 
== People ==
 
== People ==
Line 6: Line 5:
 
* Kiana Calagari
 
* Kiana Calagari
 
* [https://www.cs.sfu.ca/~mhefeeda/ Mohamed Hefeeda]
 
* [https://www.cs.sfu.ca/~mhefeeda/ Mohamed Hefeeda]
 +
  
 
== Adaptive Identification of Remote Scenes using HSI ==
 
== Adaptive Identification of Remote Scenes using HSI ==
Line 11: Line 11:
 
''' Abstract '''
 
''' Abstract '''
  
 +
In this project we aim to thoroughly investigate and explore the scene through remote sensing. We do so by using remotely controlled drones to capture videos of a desired site. The captured information will be then transferred to a base station, where it will be processed and analyzed. As the desired site may be a remote outland with limited available bandwidth and given the size of hyperspectral data, all our methods and techniques are designed in an adaptive manner. Our methods prioritize data transfer based on the amount of detail required such that maximum accuracy is achieved using a specific amount of transferred data. This is in contrast to the state-of-the-art methods, which assume having all the data in hand before starting the analysis.
  
 
+
[[Adaptive Identification of Remote Scenes using HSI|More info [login required]]] ...
[[Adaptive Identification of Remote Scenes using HSI|More info and demo]] ...
+

Latest revision as of 21:03, 21 February 2018

Hyperspectral imaging (HSI) is a powerful tool that can provide substantial information about a scene through remote sensing. This project addresses different challenges in the pipeline of capturing, transmitting, and identifying remote scenes using hyperspectral images. One of the main significant challenges in hyperspectral imaging is analyzing the data and extracting the required information. This is mainly because of the extremely high dimensionality of hyperspectral images, which limits our ability to identify spectral signatures fast and accurately. In addition, noise in hyperspectral images makes matters even more complicated.

[edit] People


[edit] Adaptive Identification of Remote Scenes using HSI

Abstract

In this project we aim to thoroughly investigate and explore the scene through remote sensing. We do so by using remotely controlled drones to capture videos of a desired site. The captured information will be then transferred to a base station, where it will be processed and analyzed. As the desired site may be a remote outland with limited available bandwidth and given the size of hyperspectral data, all our methods and techniques are designed in an adaptive manner. Our methods prioritize data transfer based on the amount of detail required such that maximum accuracy is achieved using a specific amount of transferred data. This is in contrast to the state-of-the-art methods, which assume having all the data in hand before starting the analysis.

More info [login required] ...