The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 661–668, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-661-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 661–668, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B4-2022-661-2022
 
02 Jun 2022
02 Jun 2022

COMPUTER VISION SYSTEM FOR DETECTING ORCHARD TREES FROM UAV IMAGES

H. Jemaa1, W. Bouachir2, B. Leblon2,3, and N. Bouguila1 H. Jemaa et al.
  • 1Concordia University, Montreal, QC, H3G 1M8, Canada
  • 2Université TELUQ, Montreal, QC, H2S 3L4, Canada
  • 3Faculty of Forestry and Environmental Management, University of New Brunswick, Fredericton, NB, E3B 5A3, Canada

Keywords: Orchards, Unmanned Aerial Vehicles (UAV), Tree Detection, YOLO, DeepForest, CNN

Abstract. Orchard tree inventory plays an important role in acquiring up-to-date information on planted trees for effective treatments and crop insurance purposes. Determining tree damage could help assess orchards’ health faster and cheaper. Having accurate information on the tree’s status could also help managers to plan necessary fieldwork and predict productivity. Traditional orchard inventory is often performed manually, and thus is time-consuming, costly, and subject to error. An alternative is computer vision algorithms that could automatically detect orchard trees based on UAV imagery. The objective of this study is to develop a method using advanced computer vision algorithms to automatically detect apple trees on UAV multispectral images. This task is challenging since apple trees are overlapping over the UAV images, and hence distinguishing different crowns could be difficult. Motivated by the latest advances in UAV imagery and deep-learning models, addressed the tree detection problem by exploring the two CNN models YOLO (You Only Look Once) and DeepForest for detecting apple trees on UAV images. We first constructed a labelled dataset by dividing the study area into equally sized patches. Then we manually annotated all apple trees seen in RGB images. The annotated dataset was then randomly divided into three subsets (training, validation, and testing), for training and testing machine learning models. The performed experiments demonstrate the efficiency and validity of the proposed approach for orchard tree inventory. In particular, the proposed framework achieved a precision of 91% and an F1-score of 87% by adopting the DeepForest model for tree detection.