文献类型： 会议论文

第一作者： S. Lhoest

作者： S. Lhoest ¹ ; J. Linchant ¹ ; S. Quevauvillers ¹ ; C. Vermeulen ¹ ; P. Lejeune ¹ ;

作者机构： 1.Forest Resources Management Axis, Biosystems engineering (BIOSE), University of Liege - Gembloux Agro-Bio Tech, Passage des Deportes, 2 - 4350 Gembloux, Belgium

关键词： Hippos;UAV;Infra-red;Thermal-imagery;Automatic count;Algorithm;QGIS

会议名称： ISPRS Geospatial Week

主办单位：

页码： 355-362

摘要： The common hippopotamus (Hippopotamus amphibius L.) is part of the animal species endangered because of multiple human pressures. Monitoring of species for conservation is then essential, and the development of census protocols has to be chased. UAV technology is considering as one of the new perspectives for wildlife survey. Indeed, this technique has many advantages but its main drawback is the generation of a huge amount of data to handle. This study aims at developing an algorithm for automatic count of hippos, by exploiting thermal infrared aerial images acquired from UAV. This attempt is the first known for automatic detection of this species. Images taken at several flight heights can be used as inputs of the algorithm, ranging from 38 to 155 meters above ground level. A Graphical User Interface has been created in order to facilitate the use of the application. Three categories of animals have been defined following their position in water. The mean error of automatic counts compared with manual delineations is +2.3% and shows that the estimation is unbiased. Those results show great perspectives for the use of the algorithm in populations monitoring after some technical improvements and the elaboration of statistically robust inventories protocols.

分类号： TP7-53