Tree Health Assessment from UAV Images: Improving Object Detection and Classification Using Hard Negative Mining and Semi-Supervised Autoencoder

Orchard tree inventory has been an essential step to obtain up-to-date information for effective tree treatments and crop insurance purposes. Inventorying trees is often performed manually through fieldwork surveys, which are generally time-consuming, costly, and subject to errors. Motivated by the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2023 20th Conference on Robots and Vision (CRV) s. 312 - 319
Hlavní autoři: Jemaa, Hela, Bouachir, Wassim, Leblon, Brigitte, LaRocque, Armand, Haddadi, Ata, Bouguila, Nizar
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2023
Témata:
Autoencoder
Autonomous aerial vehicles
DeepForest
Feature extraction
Hard Negative Mining (HNM)
Object detection
Robustness
semi-supervised learning
Surveys
UAV
Vegetation
Vegetation mapping
YOLO
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Orchard tree inventory has been an essential step to obtain up-to-date information for effective tree treatments and crop insurance purposes. Inventorying trees is often performed manually through fieldwork surveys, which are generally time-consuming, costly, and subject to errors. Motivated by the latest advances in UAV imagery and deep learning, we propose a new framework for individual tree detection and health assessment. We adopt a divide-and-conquer approach to address the problem of orchard trees' health assessment in two stages. First, we build a tree detection model based on a hard negative mining strategy to improve object detection. In the second stage, we address the health classification problem using a new convolutional autoencoder architecture mainly designed to extract relevant features. The performed experiments demonstrate the robustness of the proposed framework for orchard tree health assessment from UAV images. In particular, our framework achieves an F1-score of 86.24% for tree detection and an overall accuracy of 98.06% for tree health assessment. Moreover, our work could be generalized for a wide range of UAV applications involving a detection/classification process.
DOI:10.1109/CRV60082.2023.00047