A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment

UAV image acquisition and deep learning techniques have been widely used in field hydrological monitoring to meet the increasing data volume demand and refined quality. However, manual parameter training requires trial-and-error costs (T&E), and existing auto-trainings adapt to simple datasets a...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in plant science Vol. 15; p. 1448669
Main Authors: Chen, Yayong, Zhou, Beibei, Xiaopeng, Chen, Ma, Changkun, Cui, Lei, Lei, Feng, Han, Xiaojie, Chen, Linjie, Wu, Shanshan, Ye, Dapeng
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media SA 2024
Frontiers Media S.A
Subjects:
Accuracy
Algorithms
Altitude
auto-DL method
Automation
Cameras
Data augmentation
data augmentation automatic
Data collection
Datasets
Deep learning
Environmental monitoring
Error reduction
Genetic algorithms
Image acquisition
Machine learning
Methods
Network management systems
network training automatic
Plant Science
reinforcement learning for DL
segmentation deep learning
Standard error
Transfer learning
Unmanned aerial vehicles
Validity
Valleys
Vegetation
vegetation detection
China
Shenzhen China
data augmentation automatic
vegetation detection
reinforcement learning for DL
segmentation deep learning
auto-DL method
network training automatic
ISSN:1664-462X, 1664-462X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:UAV image acquisition and deep learning techniques have been widely used in field hydrological monitoring to meet the increasing data volume demand and refined quality. However, manual parameter training requires trial-and-error costs (T&E), and existing auto-trainings adapt to simple datasets and network structures, which is low practicality in unstructured environments, e.g., dry thermal valley environment (DTV). Therefore, this research combined a transfer learning (MTPI, maximum transfer potential index method) and an RL (the MTSA reinforcement learning, Multi-Thompson Sampling Algorithm) in dataset auto-augmentation and networks auto-training to reduce human experience and T&E. Firstly, to maximize the iteration speed and minimize the dataset consumption, the best iteration conditions (MTPI conditions) were derived with the improved MTPI method, which shows that subsequent iterations required only 2.30% dataset and 6.31% time cost. Then, the MTSA was improved under MTPI conditions (MTSA-MTPI) to auto-augmented datasets, and the results showed a 16.0% improvement in accuracy (human error) and a 20.9% reduction in standard error (T&E cost). Finally, the MTPI-MTSA was used for four networks auto-training (e.g., FCN, Seg-Net, U-Net, and Seg-Res-Net 50) and showed that the best Seg-Res-Net 50 gained 95.2% WPA (accuracy) and 90.9% WIoU. This study provided an effective auto-training method for complex vegetation information collection, which provides a reference for reducing the manual intervention of deep learning.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Edited by: Zenghui Zhang, Shanghai Jiao Tong University, China
Weiwei Guo, Tongji University, China
Reviewed by: Weitao Chen, China University of Geosciences Wuhan, China
These authors have contributed equally to this work
ISSN:1664-462X
1664-462X
DOI:10.3389/fpls.2024.1448669