Anomaly Based Target Detection in Hyperspectral Images via Graph Cuts

Date

2015-05-19

Author

Bati, Emrecan
Erdinc, Acar
Cesmeci, Davut
Caliskan, Akin
Koz, Alper
AKSOY, SELİM
Erturk, Sarp
Alatan, Abdullah Aydın

Metadata

Show full item record

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

Item Usage Stats

93
views

0
downloads

The studies on hyperspectral target detection until now, has been treated in two approaches. Anomaly detection can be considered as the first approach, which analyses the hyperspectral image with respect to the difference between target and the rest of the hyperspectral image. The second approach compares the previously obtained spectral signature of the target with the pixels of the hyperspectral image in order to localize the target. A distinctive disadvantage of the aforementioned approaches is to treat each pixel of the hyperspectral image individually, without considering the neighbourhood relations between the pixels. In this paper, we propose a target detection algorithm which combines the anomaly detection and signature based hyperspectral target detection approaches in a graph based framework by utilizing the neighbourhood relations between the pixels. Assuming that the target signature is available and the target sizes are in the range of anomaly sizes, a novel derivative based matched filter is first proposed to model the foreground. Second, a new anomaly detection method which models the background as a Gaussian mixture is developed. The developed model estimates the optimal number of components forming the Gaussian mixture by means of utilizing sparsity information. Finally, the similarity of the neighbouring hyperspectral pixels is measured with the spectral angle mapper. The overall proposed graph based method has successfully combined the foreground, background and neighbouring information and improved the detection performance by locating the target as a whole object free from noises.

Subject Keywords

Graph cuts, Anomay, Spectral signature, Hyperspectral image

URI

https://hdl.handle.net/11511/52942

Conference Name

23nd Signal Processing and Communications Applications Conference (SIU)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Vision based obstacle detection and avoidance using low level image features Senlet, Turgay; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2006) This study proposes a new method for obstacle detection and avoidance using low-level MPEG-7 visual descriptors. The method includes training a neural network with a subset of MPEG-7 visual descriptors extracted from outdoor scenes. The trained neural network is then used to estimate the obstacle presence in real outdoor videos and to perform obstacle avoidance. In our proposed method, obstacle avoidance solely depends on the estimated obstacle presence data. In this study, backpropagation algorithm on mult...
SPT-based probabilistic and deterministic assessment of seismic soil liquefaction triggering hazard Çetin, Kemal Önder; Kayen, Robert E.; Moss, Robb E. S.; Bilge, Habib Tolga; Ilgaç, Makbule (Elsevier BV, 2018-12-01) This study serves as an update to the Cetin et al. (2000, 2004) [1,2] databases and presents new liquefaction triggering curves. Compared with these studies from over a decade ago, the resulting new Standard Penetration Test (SPT)-based triggering curves have shifted to slightly higher CSR-levels for a given N-1,N-60,N-cs for values of N-1,N-60,N-cs greater than 15 blows/ft, but the correlation curves remain essentially unchanged at N-1,N-60,N-cs values less than 15 blows/ft. This paper addresses the improv...
REALISTICALLY SIMULATING SARS-COV-2 WASTEWATER METAGENOME SEQUENCING DATA Fidan, Fatma Rabia; Somel, Mehmet; Goldman, Nick; Department of Biology (2022-9) Wastewater surveillance for SARS-CoV-2 is seeing increasingly widespread use as it proved useful in tracking variants and their prevalence in an unbiased manner. It has been shown that it is possible to detect an emerging variant from wastewater samples up to two weeks earlier than its detection at hospital clinics (Karthikeyan et al., 2021). Such data are critical for policies regarding the measures taken against variants of concern. Since such surveillance has important consequences, it is also vital to t...
Near-Infrared Embedded Metamaterial Composed of Circular Ring Resonator with Wire Strip Topology for Free-Space Applications Gunduz, Ozan T.; Sabah, Cumali; Leitgeb, Erich (2016-07-23) A Near-Infrared (NIR) embedded metamaterial (MTM) structure is proposed in this study. The computational design process of the complex material and the results of that process are covered and discussed. According to the simulations, periodically engineered silver resonators that are combined with SiO2 give good transmission characteristics at NIR frequency range when their lattice and resonator parameters are well adjusted. Besides, the simulation results are in somehow agreement with the mathematical formu...
Range parameterized bearings only tracking using particle filter Arslan, Ali Erkin; Demirekler, Mübeccel; Department of Electrical and Electronics Engineering (2012) In this study, accurate target tracking for bearings-only tracking problem is investigated. A new tracking filter for this nonlinear problem is designed where both range parameterization and Rao-Blackwellized (marginalized) particle filtering techniques are used in a Gaussian mixture formulation to track both constant velocity and maneuvering targets. The idea of using target turn rate in the state equation in such a way that marginalization is possible is elaborated. Addition to nonlinear nature, unobserva...

Citation Formats

E. Bati et al., “Anomaly Based Target Detection in Hyperspectral Images via Graph Cuts,” presented at the 23nd Signal Processing and Communications Applications Conference (SIU), Malatya, Turkey, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52942.