Ship classification in terrestrial hyperspectral data

  title={Ship classification in terrestrial hyperspectral data},
  author={G{\"o}ksu Keskin and Hendrik Schilling and Andreas Lenz and Wolfgang Gro{\ss} and Wolfgang Middelmann},
  booktitle={Remote Sensing},
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… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.