A Self-Supervised Decision Fusion Framework for Building Detection

Date

2016-05-01

Author

Senaras, Caglar
Yarman Vural, Fatoş Tunay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

252
views

0
downloads

In this study, a new building detection framework for monocular satellite images, called self-supervised decision fusion (SSDF) is proposed. The model is based on the idea of self-supervision, which aims to generate training data automatically from each individual test image, without human interaction. This approach allows us to use the advantages of the supervised classifiers in a fully automated framework. We combine our previous supervised and unsupervised building detection frameworks to suggest a self-supervised learning architecture. Hence, we borrow the major strength of the unsupervised approach to obtain one of the most important clues, the relation of a building, and its cast shadow. This important information is, then, used in order to satisfy the requirement of training sample selection. Finally, an ensemble learning algorithm, called fuzzy stacked generalization (FSG), fuses a set of supervised classifiers trained on the automatically generated dataset with various shape, color, and texture features. We assessed the building detection performance of the proposed approach over 19 test sites and compare our results with the state of the art algorithms. Our experiments show that the supervised building detection method requires more than 30% of the ground truth (GT) training data to reach the performance of the proposed SSDF method. Furthermore, the SSDF method increases the F-score by 2 percentage points (p.p.) on the average compared to performance of the unsupervised method.

Subject Keywords

Building detection, Decision fusion, Ensemble learning, Self-supervision

URI

https://hdl.handle.net/11511/34385

Journal

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING

DOI

https://doi.org/10.1109/jstars.2015.2463118

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Building Detection With Decision Fusion Senaras, Caglar; Ozay, Mete; Yarman Vural, Fatoş Tunay (Institute of Electrical and Electronics Engineers (IEEE), 2013-6) A novel decision fusion approach to building detection problem in VHR optical satellite images is proposed. The method combines the detection results of multiple classifiers under a hierarchical architecture, called Fuzzy Stacked Generalization (FSG). After an initial segmentation and pre-processing step, a large variety of color, texture and shape features are extracted from each segment. Then, the segments, represented in different feature spaces are classified by different base-layer classifiers of the F...
A new robust method for bridge detection from high resolution electro optic satellite images Gedik, Ekın; Cınar, Umut; Karaman, Ersin; Çetin, Yasemin; Halıcı, Uğur (null; 2012-05-09) In this paper, an automatic approach for identifying bridges over water in satellite images is proposed. The proposed algorithm has three main steps. It starts with extracting the water regions in the satellite image by thresholding the NIR and clustering the NDWI images. Next possible river and water canals in the extracted water mask are identified by certain geometric constraints. Finally possible bridge regions are extracted by morphological operations applied to the water and river-canal mask....
Self-supervised building detection with decision fusion Şenaras, Çağlar; Yarman Vural, Fatoş Tunay; Eren, Pekin Erhan; Department of Information Systems (2013) This thesis proposes a new building detection framework for monocular satellite images, called Self-Supervised Decision Fusion (SSDF). The model is based on the idea of self-supervision, which aims to generate training data automatically from each individual test image, without any human interaction. This principle allows us to use the advantages of the supervised classifiers in a fully automated framework. The technical shortcomings of the available supervised and unsupervised algorithms, such as difficult...
AUTOMATIC BUILDING DETECTION WITH FEATURE SPACE FUSION USING ENSEMBLE LEARNING Senaras, Caglar; Yuksel, Baris; Ozay, Mete; Yarman-Vural, Fatos (2012-07-27) This paper proposes a novel approach to building detection problem in satellite images. The proposed method employs a two layer hierarchical classification mechanism for ensemble learning. After an initial segmentation, each segment is classified by N different classifiers using different features at the first layer. The class membership values of the segments, which are obtained from different base layer classifiers, are ensembled to form a new fusion space, which forms a linearly separable simplex. Then, ...
A Computationally Efficient Appearance-Based Algorithm for Geospatial Object Detection Arslan, Duygu; Alatan, Abdullah Aydın (2012-04-27) A computationally efficient appearance-based algorithm for geospatial object detection is presented and evaluated specifically for aircraft detection from satellite imagery. An aircraft operator exploiting the edge information via gray level differences between the aircraft and its background is constructed with Haar-like polygon regions by using the shape information of the aircraft as an invariant. Fast evaluation of the aircraft operator is achieved by means of integral image. Rotated integral images are...

Citation Formats

C. Senaras and F. T. Yarman Vural, “A Self-Supervised Decision Fusion Framework for Building Detection,” IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, pp. 1780–1791, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/34385.