Title :
Bag of Lines (BoL) for Improved Aerial Scene Representation
Author :
Sridharan, Harini ; Cheriyadat, Anil
Author_Institution :
Comput. Sci. & Eng. Div., Oak Ridge Nat. Lab., Knoxville, TN, USA
Abstract :
Feature representation is a key step in automated visual content interpretation. In this letter, we present a robust feature representation technique, referred to as bag of lines (BoL), for high-resolution aerial scenes. The proposed technique involves extracting and compactly representing low-level line primitives from the scene. The compact scene representation is generated by counting the different types of lines representing various linear structures in the scene. Through extensive experiments, we show that the proposed scene representation is invariant to scale changes and scene conditions and can discriminate urban scene categories accurately. We compare the BoL representation with the popular scale invariant feature transform (SIFT) and Gabor wavelets for their classification and clustering performance on an aerial scene database consisting of images acquired by sensors with different spatial resolutions. The proposed BoL representation outperforms the SIFT- and Gabor-based representations.
Keywords :
feature extraction; geophysical image processing; geophysical techniques; image classification; Gabor wavelets; Gabor-based representation; SIFT-based representation; aerial scene database; aerial scene representation; automated visual content interpretation; bag-of-lines; classification performance; clustering performance; low-level line primitives; robust feature representation technique; scale invariant feature transform; urban scene categories; Dictionaries; Feature extraction; Histograms; Indexes; Remote sensing; Semantics; Spatial resolution; Bag of lines (BoL); classification; clustering; feature representation; line extraction;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2014.2357392