Determining Dendrometry Using Drone Scouting, Convolutional Neural Networks and Point Clouds

Kim Jensen, Oskar Kondrup Krogh, Marius Willemoes Jorgensen, Daniel Lehotsky, Anton Bock Andersen, Ernest Porqueras, Jens Aksel S. Sondergaard, Rikke Gade; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 2912-2920

Abstract

This paper presents a solution for mapping the location of trees in an orchard and estimating the dendrometric data of the trees. The combined solution consists of a mapping and navigation algorithm, which allows for autonomous data collection at an orchard with a regular rectangular layout, and data processing for tree detection and dendrometric data estimation. The data collection is done using an Intel RealSense D435i camera, which can obtain both RGB and depth data. The paper presents a comparison between the performance of point cloud processing (PCP) and convolutional neural networks (CNNs) on RGB data for tree detection and dendrometric data estimation. The YOLOv3 CNN achieved a mAP50 of 63.53% with 65.5 FPS and a mean error of 20.6 cm in height estimation. Point cloud processing achieved a precision of 76.72% with 2.1 FPS and a mean error of 20.4 cm in height estimation. In conclusion, this work shows that point cloud processing shows comparable results to convolutional neural networks for height estimation, but trades off processing time for better precision in detection.

Related Material

[pdf]
[bibtex]
@InProceedings{Jensen_2021_CVPR, author = {Jensen, Kim and Krogh, Oskar Kondrup and Jorgensen, Marius Willemoes and Lehotsky, Daniel and Andersen, Anton Bock and Porqueras, Ernest and Sondergaard, Jens Aksel S. and Gade, Rikke}, title = {Determining Dendrometry Using Drone Scouting, Convolutional Neural Networks and Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2912-2920} }