We develop an approach for the detection of ruins of livestock enclosures (LEs) in alpine areas captured by high-resolution remotely sensed images. These structures are usually of approximately rectangular shape and appear in images as faint fragmented contours in complex background. We address this problem by introducing a rectangularity feature that quantifies the degree of alignment of an optimal subset of extracted linear segments with a contour of rectangular shape. The rectangularity feature has high values not only for perfectly regular enclosures but also for ruined ones with distorted angles, fragmented walls, or even a completely missing wall. Furthermore, it has a zero value for spurious structures with less than three sides of a perceivable rectangle. We show how the detection performance can be improved by learning a linear combination of the rectangularity and size features from just a few available representative examples and a large number of negatives. Our approach allowed detection of enclosures in the Silvretta Alps that were previously unknown. A comparative performance analysis is provided. Among other features, our comparison includes the state-of-the-art features that were generated by pretrained deep convolutional neural networks (CNNs). The deep CNN features, although learned from a very different type of images, provided the basic ability to capture the visual concept of the LEs. However, our handcrafted rectangularity-size features showed considerably higher performance.
%0 Journal Article
%1 journals/tgrs/ZingmanSPL16
%A Zingman, Igor
%A Saupe, Dietmar
%A Penatti, Otávio Augusto Bizetto
%A Lambers, Karsten
%D 2016
%J IEEE Transactions on Geoscience and Remote Sensing
%K from:leonkokkoliadis sfbtrr161 2016 A05
%N 8
%P 4580-4593
%R 10.1109/TGRS.2016.2545919
%T Detection of Fragmented Rectangular Enclosures in Very High Resolution Remote Sensing Images
%U https://ieeexplore.ieee.org/document/7452408
%V 54
%X We develop an approach for the detection of ruins of livestock enclosures (LEs) in alpine areas captured by high-resolution remotely sensed images. These structures are usually of approximately rectangular shape and appear in images as faint fragmented contours in complex background. We address this problem by introducing a rectangularity feature that quantifies the degree of alignment of an optimal subset of extracted linear segments with a contour of rectangular shape. The rectangularity feature has high values not only for perfectly regular enclosures but also for ruined ones with distorted angles, fragmented walls, or even a completely missing wall. Furthermore, it has a zero value for spurious structures with less than three sides of a perceivable rectangle. We show how the detection performance can be improved by learning a linear combination of the rectangularity and size features from just a few available representative examples and a large number of negatives. Our approach allowed detection of enclosures in the Silvretta Alps that were previously unknown. A comparative performance analysis is provided. Among other features, our comparison includes the state-of-the-art features that were generated by pretrained deep convolutional neural networks (CNNs). The deep CNN features, although learned from a very different type of images, provided the basic ability to capture the visual concept of the LEs. However, our handcrafted rectangularity-size features showed considerably higher performance.
@article{journals/tgrs/ZingmanSPL16,
abstract = {We develop an approach for the detection of ruins of livestock enclosures (LEs) in alpine areas captured by high-resolution remotely sensed images. These structures are usually of approximately rectangular shape and appear in images as faint fragmented contours in complex background. We address this problem by introducing a rectangularity feature that quantifies the degree of alignment of an optimal subset of extracted linear segments with a contour of rectangular shape. The rectangularity feature has high values not only for perfectly regular enclosures but also for ruined ones with distorted angles, fragmented walls, or even a completely missing wall. Furthermore, it has a zero value for spurious structures with less than three sides of a perceivable rectangle. We show how the detection performance can be improved by learning a linear combination of the rectangularity and size features from just a few available representative examples and a large number of negatives. Our approach allowed detection of enclosures in the Silvretta Alps that were previously unknown. A comparative performance analysis is provided. Among other features, our comparison includes the state-of-the-art features that were generated by pretrained deep convolutional neural networks (CNNs). The deep CNN features, although learned from a very different type of images, provided the basic ability to capture the visual concept of the LEs. However, our handcrafted rectangularity-size features showed considerably higher performance.},
added-at = {2020-02-26T16:47:54.000+0100},
author = {Zingman, Igor and Saupe, Dietmar and Penatti, Otávio Augusto Bizetto and Lambers, Karsten},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24194485d4d6daa5ebe482e8c65337be0/sfbtrr161},
doi = {10.1109/TGRS.2016.2545919},
ee = {http://dx.doi.org/10.1109/TGRS.2016.2545919},
interhash = {1bee3baaa531fffe5f5c99c32ad92895},
intrahash = {4194485d4d6daa5ebe482e8c65337be0},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
keywords = {from:leonkokkoliadis sfbtrr161 2016 A05},
number = 8,
pages = {4580-4593},
timestamp = {2020-02-26T15:47:54.000+0100},
title = {Detection of Fragmented Rectangular Enclosures in Very High Resolution Remote Sensing Images},
url = {https://ieeexplore.ieee.org/document/7452408},
volume = 54,
year = 2016
}
