Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWaldrop, Lauren E.-
dc.contributor.authorHart, Carl R.-
dc.contributor.authorParker, Nancy E.-
dc.contributor.authorPettit, Chris L.-
dc.contributor.authorMcIntosh, Scotlund.-
dc.identifier.govdocERDC/CRREL TR-18-7-
dc.descriptionTechnical Report-
dc.description.abstractIn support of the Terrain Characterization for Rendering and Field Evaluation effort, the U.S. Army Corps of Engineers, Engineer Research and Development Center (ERDC), Cold Regions Research and Engineering Laboratory (CRREL), assisted the Natick Soldier Research, Development, and Engineering Center (NSRDEC) in evaluating machine learning algorithms to automatically classify three vegetation types (tree, shrub, and herbaceous), and a non-vegetated type in terrestrial images. In a previous partnership between CRREL and NSRDEC, researchers developed the Global Natural Background Image Database (GNBID), a collection of natural background images classified by vegetation attributes to include vegetation type and height, leaf shape, leaf color, and many others. Following deployment, the GNBID successfully improved on-the-ground understanding of natural background environments and quickly revealed the need for a larger database. Manual classification methods proved time intensive and variable, thus CRREL explored the feasibility of automatically identifying features using machine learning algorithms. In this scope-of-work study, we explore a multitude of computer vision techniques, settling on a supervised deep-learning technique. Here we present the advantages and disadvantages of various techniques, classification results from a subset of images, and recommendations for future research in this area.en_US
dc.description.sponsorshipTerrain Characterization for Rendering and Field Evaluation Program (U.S.)en_US
dc.description.sponsorshipU.S. Army Natick Research, Development, and Engineering Center.-
dc.format.extent69 pages/3.920 Mb-
dc.publisherCold Regions Research and Engineering Laboratory (U.S.)en_US
dc.publisherEngineer Research and Development Center (U.S.)en_US
dc.relation.ispartofseriesTechnical Report (Engineer Research and Development Center (U.S.) ) ; no. ERDC/CRREL TR-18-7-
dc.rightsApproved for Public Release; Distribution is Unlimited-
dc.sourceThis Digital Resource was created in Microsoft Word and Adobe Acrobat-
dc.subjectCamouflage (Military science)en_US
dc.subjectComputer algorithmsen_US
dc.subjectComputer visionen_US
dc.subjectMachine learningen_US
dc.subjectRemote sensingen_US
dc.subjectTerrain characterizationen_US
dc.subjectVegetation classificationen_US
dc.titleUtility of machine learning algorithms for natural background photo classificationen_US
Appears in Collections:Technical Report

Files in This Item:
File Description SizeFormat 
ERDC-CRREL TR-18-7.pdf4.01 MBAdobe PDFThumbnail