Translator Disclaimer
Paper
15 October 2013 An automatic geo-spatial object recognition algorithm for high resolution satellite images
Author Affiliations +
Abstract
This paper proposes a novel automatic geo-spatial object recognition algorithm for high resolution satellite imaging. The proposed algorithm consists of two main steps; a hypothesis generation step with a local feature-based algorithm and a verification step with a shape-based approach. In the hypothesis generation step, a set of hypothesis for possible object locations is generated, aiming lower missed detections and higher false-positives by using a Bag of Visual Words type approach. In the verification step, the foreground objects are first extracted by a semi-supervised image segmentation algorithm, utilizing detection results from the previous step, and then, the shape descriptors for segmented objects are utilized to prune out the false positives. Based on simulation results, it can be argued that the proposed algorithm achieves both high precision and high recall rates as a result of taking advantage of both the local feature-based and the shape-based object detection approaches. The superiority of the proposed method is due to the ability of minimization of false alarm rate and since most of the object shapes contain more characteristic and discriminative information about their identity and functionality.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mustafa Ergul and A. Aydın Alatan "An automatic geo-spatial object recognition algorithm for high resolution satellite images", Proc. SPIE 8897, Electro-Optical Remote Sensing, Photonic Technologies, and Applications VII; and Military Applications in Hyperspectral Imaging and High Spatial Resolution Sensing, 88970J (15 October 2013); https://doi.org/10.1117/12.2029136
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top