Skip to main content

A Decision Fusion Framework for Hyperspectral Subpixel Target Detection Die Objekterkennung in Fernerkundungsszenen ist bislang nur teilweise gelöst

Buy Article:

$39.00 plus tax (Refund Policy)

Abstract:

Target detection is one of the most challenging issues of remotely sensed data. Due to high spectral resolution of the hyperspectral images and their limited ground sampling distance, targets of interest occur at subpixel level. In such cases, spatial characteristics of targets are hard to acquire and the only way to overcome such problem is to take advantage of the spectral information. Based on the spectral characteristics of background and the targets to be detected, several methods have been proposed. Some of these methods assume a physics-based approach, while the other may be purely statistical. So, all of these methods are based on some assumptions each of which can be challenged in one way or another. One possible way to take advantage of these differences to improve the final results is the fusion of the detectors' outputs. In this paper, eight subpixel target detectors are employed as the ensemble detectors. It is also worth mentioning that the detectors should be different from each other; otherwise the overall decision will not be better than the individual detectors. So, we suggest using the genetic algorithms to select the most suitable detectors for a given decision fusion rule. Experimental results on a real world hyperspectral data as well as a synthetic dataset show the efficiency of the proposed method to improve the detection performance.

German
Im Fall von Hyperspektraldaten steht der hohen spektralen eine begrenzte räumliche Auflösung gegenüber. Daher sind viele Objekte kleiner als ein Pixel, so dass eine Aussageüber die geometrischen Eigenschaften nur eingeschränkt möglich ist. Daher kommt der spektralen Information eine erhöhte Bedeutung zu. In der Vergangenheit wurden viele Analysemethoden vorgeschlagen, die die Objekterkennung nach den spektralen Charakteristiken der gesuchten Objekte und ihrer Umgebung, dem Bildhintergrund, erlauben, Einige der Methoden verfolgen modellbasierte Ansätze während andere rein statistisch arbeiten. Alle Methoden erfordern spezifische Annahmen, die eine zusätzliche Unsicherheit für das Ergebnis bedeuten. Ein Ansatz zur Verbesserung des Gesamtergebnisses ist die Verschneidung (Fusion) der mit den unterschiedlichen Methoden (Detektoren) gefundenen Einzelergebnisse. In diesem Artikel werden acht typische Detektoren beispielhaft untersucht und gezeigt, wie mit Hilfe der Methode Genetischer Algorithmus die für eine gegebene Fragestellung geeignetste Kombination gefunden werden kann. Die Methode wird sowohl an echten als auch an synthetischen Hyperspektraldaten erprobt. Die Untersuchung zeigt, dass die vorgeschlagene Methode die Erkennbarkeit von Objekten verbessert.

Keywords: DECISION FUSION; HYPERSPECTRAL DATA; REMOTE SENSING; TARGET DETECTION

Document Type: Research Article

DOI: https://doi.org/10.1127/1432-8364/2012/0116

Publication date: 2012-06-01

More about this publication?
  • Photogrammetrie - Fernerkundung - Geoinformation (PFG) is an international scholarly journal covering the progress and application of photogrammetric methods, remote sensing technology and the intricately connected field of geoinformation processing.

    Papers published in PFG highlight new developments and applications of these technologies in practice. The journal hence addresses both researchers and student of these disciplines at academic institutions and universities and the downstream users in both the private sector and public administration.

    PFG places special editorial emphasis on the communication of new methodologies in data acquisition, new approaches to optimized processing and interpretation of all types of data which were acquired by photogrammetric methods, remote sensing, image processing and the computer-aided interpretation of such data in general.

    PFG is the official journal of the German Society of Photogrammetry and Remote Sensing.
  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more