| Improved watershed segmentation algorithm for tree crowns extraction from multi-spectral UAV-based aerial images |
| Paper ID : 1096-GEOSPATIAL (R3) |
| Authors: |
|
Hesam Haddadi Amlashi * School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran |
| Abstract: |
| Due to many problems such as diseases and pests, low fertility, and dehydration, trees need immediate actions to be taken in time of need. Since they are an important source of fruit, food, and nutrients consumed by humans keeping track of the trees in orchards is a very important issue in recent years. Today, drones equipped with multispectral cameras are used in precision agriculture especially for monitoring and controlling trees well-being. For this cause two citrus orchards in Iran with an area of 9.2 and 2.67 hectares and a resolution of 3.6 and 0.68 cm were selected as the study area. In this study, we first improved the tree extraction algorithm and compared it with four common algorithms, which achieved an overall accuracy of 87% and 81% in the two regions. Then we investigated the effect of the number of spectral bands on the accuracy of tree extraction. With the addition of Red-Edge and NIR bands, the accuracy increased by about 5% and 7%. |
| Keywords: |
| Extraction of the tree crown, remote sensing, Improved watershed segmentation, Individual trees, Multispectral Imagery, UAV |
| Status : Paper Accepted (Poster Presentation) |
