Aircraft Detection from VHR Images Based on Circle-Frequency Filter and Multilevel Features. (15th September 2013)

• Record Type: Journal Article
• Authors: Gao, Feng; Xu, Qizhi; Li, Bo
• Other Names: Bourennane S. Academic Editor.; Fossati C. Academic Editor.; Marot J. Academic Editor.
• Is Part Of: TheScientificWorldjournal. Volume 2013(2013)
• Publication Date: 2013-09-15
• Subjects: Science -- Periodicals; Technology -- Periodicals; Medicine -- Periodicals; 505
• DOI: 10.1155/2013/917928
• Languages: English
• ISSNs: 2356-6140

Abstract

Abstract : Aircraft automatic detection from very high-resolution (VHR) images plays an important role in a wide variety of applications. This paper proposes a novel detector for aircraft detection from very high-resolution (VHR) remote sensing images. To accurately distinguish aircrafts from background, a circle-frequency filter (CF-filter) is used to extract the candidate locations of aircrafts from a large size image. A multi-level feature model is then employed to represent both local appearance and spatial layout of aircrafts by means of Robust Hue Descriptor and Histogram of Oriented Gradients. The experimental results demonstrate the superior performance of the proposed method.