Fruit Tree Canopy Segmentation by Unmanned Aerial Vehicle Photogrammetry Coupled on Convolutional Neural Network and Attention Mechanism

被引：0

作者：

He H. ^{[1
,2
]}

Zhou F. ^{[1
,2
]}

Chen M. ^{[3
]}

Chen T. ^{[4
]}

Guan Y. ^{[1
,2
]}

Zeng H. ^{[5
]}

Wei Y. ^{[1
,2
]}

机构：

[1] School of Surveying and Geoinformation Engineering, East China University of Technology, Nanchang

[2] Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources, East China University of Technology, Nanchang

[3] Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu

[4] School of Water Resources and Environmental Engineering, East China University of Technology, Nanchang

[5] National Field Observation and Research Station of Landslides in the Three Gorges Reservoir Area of Yangtze River, China Three Gorges University, Yichang

来源：

Journal of Geo-Information Science | 2023年 / 25卷 / 12期

基金：

中国国家自然科学基金;

关键词：

attention mechanism; convolutional neural network; deep learning; receptive field; semantic feature; transfer learning; tree canopy segmentation; unmanned aerial vehicle photogrammetry;

D O I：

10.12082/dqxxkx.2023.230370

中图分类号：

学科分类号：

摘要：

The segmentation of fruit tree canopy based on Unmanned Aerial Vehicle (UAV) visible spectral images is greatly influenced by complex background information such as topographic relief, shrubs, and weeds. Although existing deep neural networks can improve the robustness of canopy segmentation to a certain extent, they ignore the global context and local detailed information of the canopy due to limited receptive field and information interaction, which restricts the improvement of canopy segmentation accuracy. To address these issues, this paper introduces the Canopy Height Model (CHM) and deep learning algorithms, and proposes a fruit tree canopy segmentation method that couples Convolutional Neural Networks (CNN) and Attention Mechanisms (AM) based on UAV photogrammetry. This method first constructs a coupled deep neural network based on CNN and AM through transfer learning to extract both the local and global high-level contextual features of fruit tree canopies. Meanwhile, considering the correlation between deep semantic features and the position information of fruit tree canopies, a local and global feature fusion module is designed to achieve collaborative tree canopy segmentation of attributes and spatial positions. Taking the citrus tree canopy segmentation as an example, the experimental results demonstrate that the use of the CHM can effectively suppress the influence of topographic relief. Our proposed method can also significantly reduce the interference of underlying weeds or shrubs on canopy segmentation, and achieves the highest Overall Accuracy (OA), F1 score, and mean Intersection over Union (mIoU) of 97.57%, 95.49%, and 94.05%, respectively. Compared with other state-of-the-art networks such as SegFormer, SETR_PUP,TransUNet, TransFuse, and CCTNet, the mIoU obtained by the proposed method increases by 1.79%, 8.83%, 1.16%, 1.43%, and 1.85%, respectively. The proposed method can achieve high-precision segmentation of fruit tree canopies with complex background information, which has important practical value for understanding the growth status of fruit trees and fine management of orchards. © 2023 Chinese Society of Agricultural Engineering. All rights reserved.

引用

页码：2387 / 2401

页数：14

共 31 条

[11] Wang H, Chen X Z, Zhang T X, Et al., CCTNet: Coupled CNN and transformer network for crop segmentation of remote sensing images, Remote Sensing, 14, 9, (2022)
[12] Lin Y, Zhao Q H, Li Y., A remote sensing image classification method based on deep transitive transfer learning[J], Journal of Geo-Information Science, 24, 3, pp. 495-507, (2022)
[13] Heng X B, Xu H W, Tang L, Et al., Research on land cover classification method based on improved fully convolutional neural network model[J], Journal of Geo- information Science, 25, 3, pp. 495-509, (2023)
[14] Morales G, Kemper G, Sevillano G, Et al., Automatic segmentation of mauritia flexuosa in unmanned aerial vehicle (UAV) imagery using deep learning[J], Forests, 9, 12, (2018)
[15] Guirado E, Blanco-Sacristan J, Rodriguez-Caballero E, Et al., Mask R-CNN and OBIA fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors[J], Sensors, 21, 1, (2021)
[16] Braga J R G, Peripato V, Dalagnol R, Et al., Tree crown delineation algorithm based on a convolutional neural network[J], Remote Sensing, 12, 8, (2020)
[17] Li G A, Han W T, Huang S J, Et al., Extraction of sunflower lodging information based on UAV multi- spectral remote sensing and deep learning[J], Remote Sensing, 13, 14, (2021)
[18] Hao Z B, Lin L L, Post C J, Et al., Automated tree- crown and height detection in a young forest plantation using mask region- based convolutional neural network (Mask R- CNN) [J], ISPRS Journal of Photogrammetry and Remote Sensing, 178, pp. 112-123, (2021)
[19] Martins J A C, Nogueira K, Osco L P, Et al., Semantic segmentation of tree-canopy in urban environment with pixel- wise deep learning, Remote Sensing, 13, 16, (2021)
[20] Osco L P, Nogueira K, Ramos A P M, Et al., Semantic segmentation of citrus- orchard using deep neural networks and multispectral UAV-based imagery[J], Precision Agriculture, 22, 4, pp. 1171-1188, (2021)

← 1 2 3 4 →