Towards the Automatic Detection of Pre-Existing Termite Mounds through UAS and Hyperspectral Imagery
| Autor: | Felipe Gonzalez, Adam Wooler, Juan Sandino |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Support Vector Machine
010504 meteorology & atmospheric sciences Computer science UAV 0211 other engineering and technologies ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Isoptera 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Article hyperspectral camera support vector machines Analytical Chemistry Artificial Intelligence Digital image processing pre-existing termite mounds Image Processing Computer-Assisted Animals Computer vision lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation Image resolution image segmentation Aerial image 021101 geological & geomatics engineering 0105 earth and related environmental sciences Contextual image classification business.industry Hyperspectral imaging Image segmentation machine learning Atomic and Molecular Physics and Optics Object detection Statistical classification RGB color model Artificial intelligence business Algorithms |
| Zdroj: | Sensors, Vol 17, Iss 10, p 2196 (2017) Sensors; Volume 17; Issue 10; Pages: 2196 Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| Popis: | The increased technological developments in Unmanned Aerial Vehicles (UAVs) combined with artificial intelligence and Machine Learning (ML) approaches have opened the possibility of remote sensing of extensive areas of arid lands. In this paper, a novel approach towards the detection of termite mounds with the use of a UAV, hyperspectral imagery, ML and digital image processing is intended. A new pipeline process is proposed to detect termite mounds automatically and to reduce, consequently, detection times. For the classification stage, several ML classification algorithms’ outcomes were studied, selecting support vector machines as the best approach for their role in image classification of pre-existing termite mounds. Various test conditions were applied to the proposed algorithm, obtaining an overall accuracy of 68%. Images with satisfactory mound detection proved that the method is “resolution-dependent”. These mounds were detected regardless of their rotation and position in the aerial image. However, image distortion reduced the number of detected mounds due to the inclusion of a shape analysis method in the object detection phase, and image resolution is still determinant to obtain accurate results. Hyperspectral imagery demonstrated better capabilities to classify a huge set of materials than implementing traditional segmentation methods on RGB images only. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|