Abstract
Abstract. Unmanned air vehicle (UAV) became an alternative airborne remote sensing technique, due to providing very high resolution and low cost spatial data and short processing time. Particularly, optical UAVs are frequently utilized in various applications such as mapping, agriculture, and forestry. Especially for precise agriculture purposes, the UAVs were equipped with multispectral cameras which enables to classify land cover easily. In this study, the land cover classification potential of DJI Phantom IV Multispectral, one of the most preferred agricultural UAVs in the world, was investigated using spectral angle mapper, minimum distance and maximum likelihood pixel-based classification techniques and object-based classification. In the investigation, a part of Gebze Technical University (GTU) Northern Campus, includes a large variety of land cover classes, was selected as the study area. The UAV aerial photos were achieved from 70 m flight altitude and processed using structure from motion (SfM)-based image matching software Agisoft Metashape. The pixel-based and object-based land cover classification processes were completed with ENVI and eCognition software respectively. 16 independent land cover classes were classified and the results demonstrated that the accuracies are 73.46% in spectral angle mapper, 75.27% in minimum distance and 93.56% in maximum likelihood pixel-based classification techniques and 90.09% in nearest neighbour object-based classification.
Highlights
In the geomatics engineering discipline, the data is acquired by using space-borne or airborne remote sensing techniques and terrestrial surveys
The accuracies of the classifications were achieved as 73.46% for spectral angle mapper (SAM), 75.27% for minimum distance classifier (MDC) and 93.56% for maximum likelihood classification (MLC)
The results demonstrated that the orthomosaic derived from DJI Phantom IV multispectral Unmanned aerial vehicle (UAV) has more than 90% accuracy both for pixel-based and object-based land cover classification
Summary
In the geomatics engineering discipline, the data is acquired by using space-borne or airborne remote sensing techniques and terrestrial surveys. Satellites pass over a specific area on certain dates and instantaneous data cannot be obtained. On the other hand, collecting data with terrestrial surveys has disadvantages in terms of time, labor, and high cost for large application areas. Low cost and very high resolution data acquisition abilities and the performance of final three dimensional (3D) products make the UAV technology very popular. Satellite imagery is generally insufficient regarding the temporal and spatial resolution, in projects that require high accuracy and precision. Providing multispectral imagery with high spatial and temporal accuracy instantaneously multispectral UAVs are quickly becoming popular (Doğan and Yıldız, 2019). In this study, using the data obtained from DJI Phantom IV Multispectral UAV, pixel-based and object-based land cover classification performance of multispectral UAVs were analyzed. Spectral angle mapper (Girouard et al, 2004), minimum distance (Sisodia et al, 2014) and maximum likelihood (Ahmad and Quegan, 2012) pixel-based classification techniques and nearest neighbour object-based classification were applied on 16 independent land cover classes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
