Robust landmine detection from thermal image time series using Hough transform and rotationally invariant features

Date

2019-07-28

Author

Kaya, Serkan
Leloğlu, Uğur Murat
Ozyer, Gulsah Tumuklu

Metadata

Show full item record

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

Item Usage Stats

182
views

0
downloads

Automated detection of buried anti-personnel landmines using remote sensing techniques is very important for clearing minefields without putting lives in danger. Although thermal infrared imaging is promising, it is far from applicable to the real world in its current state-of-the-art. The most serious problem is that experiments are generally held using sandboxes or levelled and cleared soil, but real fields are, at least partially, covered with plants. In this study, we present an algorithm for landmine detection that is robust enough to detect beyond the clutter caused by partial plant cover. The first part is a hypothesis generator based on circular Hough Transform applied to images that are filtered to enhance circular structures. The second part tests the candidate landmine coordinates using rotationally invariant features, including modified Histogram of Oriented Gaussians (HOG), over multiple images taken at different times after Wiener filtering to maximize signal-to-clutter ratio. The performances of various features and classifiers are compared. The overall performance of the algorithm is demonstrated on a dataset of real-world landmine images contaminated by simulated plants. Satisfactory results are obtained up to 40% equivalent plant coverage where more than 65% of the pixels are fully or partially covered by plants.

Subject Keywords

Histograms, Oriented gradients

URI

https://hdl.handle.net/11511/31076

Journal

INTERNATIONAL JOURNAL OF REMOTE SENSING

DOI

https://doi.org/10.1080/01431161.2019.1646941

Collections

Graduate School of Natural and Applied Sciences, Article

Suggestions

OpenMETU
Core

Evaluation of Textural Features for Multispectral Images Bayram, Ulya; Can, Gulcan; Duzgun, Sebnem; Yalabik, Nese (2011-09-21) Remote sensing is a field that has wide use, leading to the fact that it has a great importance. Therefore performance of selected features plays a great role. In order to gain some perspective on useful textural features, we have brought together state-of-art textural features in recent literature, yet to be applied in remote sensing field, as well as presenting a comparison with traditional ones. Therefore we selected most commonly used textural features in remote sensing that are grey-level co-occurrence...
Combination of physics-based and image-based features for landmine identification in ground penetrating radar data Genc, Alper; Akar, Gözde (SPIE-Intl Soc Optical Eng, 2019-4-23) Ground penetrating radar (GPR) is a powerful technology for detection and identification of buried explosives, especially with little or no metal content. However, subsurface clutter and soil distortions increase false alarm rates of current GPR-based landmine detection and identification methods. Most existing algorithms use shape-based, image-based, and physics-based techniques. Analysis of these techniques indicates that each type of algorithm has a different perspective to solve the landmine detection a...
An Adaptive, energy-aware and distributed fault-tolerant topology-control algorithm for heterogeneous wireless sensor networks Deniz, Fatih; Yazıcı, Adnan; Bağcı, Hakkı; Department of Computer Engineering (2016) Wireless sensor networks (WSNs) are being used in numerous fields, such as battlefield surveillance, environmental monitoring and traffic control. They are typically composed of large numbers of tiny sensor nodes with limited resources. Because of their limitations and because of the environments they are being used, there are problems unique to WSNs. Due to the error-prone nature of wireless communication, especially in harsh environments, fault-tolerance emerges as an important property in WSNs. Also, bec...
Multi-feature fusion for GPR-based landmine detection and classification Genç, Alper; Akar, Gözde; Department of Electrical and Electronics Engineering (2019) Ground penetrating radar (GPR) is a powerful technology for detection and identification of buried explosives especially with little or no metal content. However, subsurface clutter and soil distortions increase false alarm rates of current GPR-based landmine detection and identification methods. Most existing algorithms use shape- based, image-based and physics-based techniques. Analysis of these techniques indicates that each type of algorithms has a different perspective to solve landmine detection and i...
Multi-aspect data fusion applied to electromagnetic target classification using enetic algorithm Sayan, Gönül (2000-07-07) Electromagnetic target detection and classification is an important problem relevant not only to military applications but also to civilian use. In the problem of a breast tumor detection and identification [1], for instance, the main concern is accuracy. In the case of the recognition of a military target such as an aircraft or a ship, on the other hand, speed of classification is as important as the accuracy of the decision as such a decision should be made within a fraction of a second. For the K-pulse t...

Citation Formats

S. Kaya, U. M. Leloğlu, and G. T. Ozyer, “Robust landmine detection from thermal image time series using Hough transform and rotationally invariant features,” INTERNATIONAL JOURNAL OF REMOTE SENSING, pp. 725–739, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/31076.