Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Ship classification in terrestrial hyperspectral data

 
: Keskin , Gösku; Schilling, Hendrik; Lenz, Andreas; Gross, Wolfgang; Middelmann, Wolfgang

:

Bruzzone, L. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Image and Signal Processing for Remote Sensing XXII : 26-28 September 2016, Edinburgh, United Kingdom
Bellingham, WA: SPIE, 2016 (Proceedings of SPIE 10004)
ISBN: 978-1-5106-0412-4
ISBN: 978-1-5106-0413-1
Paper 100040U, 9 S.
Conference "Image and Signal Processing for Remote Sensing" <22, 2016, Edinburgh>
Englisch
Konferenzbeitrag
Fraunhofer IOSB ()
hyperspectral classification; Bag-of-Words; nearest neighbor; random forest; harbor monitoring

Abstract
This work analyzes the applicability of using hyperspectral data for ship classification in coastal or harbor environment. An approach for hyperspectral feature selection based on bag-of-words method was developed. Nearest neighbor and random forest classifiers were used for evaluating hyperspectral bag-of-words features. The evaluation dataset was self-acquired at the Kiel Harbor in Germany, using Aisa Eagle in VNIR and Aisa Hawk in SWIR sensors. The dataset included 547 samples of 72 objects ranging from passenger ferries to sailing boats in different illumination conditions. An object library was created from the dataset and bag-of-words features were extracted. Two different separation strategies for separating training and test sets were selected: Random subsets and chronologically separated subsets. Chronological separation was more challenging than the random separation for both classifiers. In order to allow a future sliding window operation for object detection, the training and the classification were performed additionally on rectangular windows including background pixels. The performance of nearest neighbor classifier dropped whereas the performance of random forest classifier slightly improved. Overall performance of random forest classifier is better than nearest neighbor classifier; however it requires a more comprehensive dataset for training. The evaluations indicated that the bag-of-words feature selection is feasible for the given application.

: http://publica.fraunhofer.de/dokumente/N-423493.html