A5047417992- Remote Sensing in Agriculture
- Infrastructure Maintenance and Monitoring
- Smart Agriculture and AI
- Landslides and related hazards
- Remote Sensing and Land Use
- Remote Sensing and LiDAR Applications
- 3D Surveying and Cultural Heritage
- Remote-Sensing Image Classification
- Water Quality Monitoring Technologies
- Industrial Vision Systems and Defect Detection
- Flood Risk Assessment and Management
- Water Quality and Pollution Assessment
- Water Systems and Optimization
- Aquatic Ecosystems and Phytoplankton Dynamics
- Multi-Criteria Decision Making
- Hydrological Forecasting Using AI
- Urban Stormwater Management Solutions
- Land Use and Ecosystem Services
- Spectroscopy and Chemometric Analyses
- Asphalt Pavement Performance Evaluation
- Advanced Neural Network Applications
- Advanced Vision and Imaging
- Microbial Applications in Construction Materials
- Image and Object Detection Techniques
- Robotics and Sensor-Based Localization
National Chung Hsing University
2014-2023
National Taipei University
2008-2022
Pervasive Artificial Intelligence Research Labs
2019-2021
Chaoyang University of Technology
1998-2006
National Taiwan University
2003
National Taiwan Ocean University
2003
University of Virginia
2003
The Ohio State University
1996
A rapid and precise large-scale agricultural disaster survey is a basis for relief insurance but labor-intensive time-consuming. This study applies Unmanned Aerial Vehicles (UAVs) images through deep-learning image processing to estimate the rice lodging in paddies over large area. establishes an semantic segmentation model employing two neural network architectures, FCN-AlexNet, SegNet, whose effects are explored interpretation of various object sizes computation efficiency. Commercial UAVs...
Rice lodging identification relies on manual in situ assessment and often leads to a compensation dispute agricultural disaster assessment. Therefore, this study proposes comprehensive efficient classification technique for lands that entails using unmanned aerial vehicle (UAV) imagery. In addition spectral information, digital surface model (DSM) texture information of the images was obtained through image-based modeling analysis. Moreover, single feature probability (SFP) values were...
Rice is a globally important crop that will continue to play an essential role in feeding our world as we grapple with climate change and population growth. Lodging primary threat rice production, decreasing yield, quality. assessment tedious task requires heavy labor long duration due the vast land areas involved. Newly developed autonomous scouting techniques have shown promise mapping fields without any human interaction. By combining lodged detection edge computing, it possible estimate...
The incorporation of autonomous computation and artificial intelligence (AI) technologies into smart agriculture concepts is becoming an expected scientific procedure. airborne hyperspectral system with its vast area coverage, high spectral resolution, varied narrow-band selection excellent tool for crop physiological characteristics yield prediction. However, the extensive redundant three-dimensional (3D) cube data processing have made popularization this a challenging task. This research...
To meet demand for agriculture products, researchers have recently focused on precision to increase crop production with less input. Crop detection based computer vision unmanned aerial vehicle (UAV)-acquired images plays a vital role in agriculture. In recent years, machine learning has been successfully applied image processing classification, and segmentation. Accordingly, the aim of this study is detect rice seedlings paddy fields using transfer from two models, EfficientDet-D0 Faster...
Single-plant growth monitoring aids precision agricultural decision-making to reduce the costs related pesticides, fertilizers, and labor. This study integrated visible/multi-spectral UAV imagery with two deep learning methods, object detection semantic segmentation, obtain a visualized map that could assist in precise field management for broccoli cultivation. For plant detection, feature extraction was conducted using multiscale dilated convolution, which enabled effective of images taken...
Many people use smartphone cameras to record their living environments through captured images, and share aspects of daily lives on social networks, such as Facebook, Instagram, Twitter. These platforms provide volunteered geographic information (VGI), which enables the public know where when events occur. At same time, image-based VGI can also indicate environmental changes disaster conditions, flooding ranges relative water levels. However, little has been applied for quantification levels...
Recently, unmanned aerial vehicles (UAVs) have been broadly applied to the remote sensing field. For a great number of UAV images, deep learning has reinvigorated and performed many results in agricultural applications. The popular image datasets for model training are generated general purpose use, which objects, views, applications ordinary scenarios. However, images possess different patterns mostly from look-down perspective. This paper provides verified annotated dataset that described...
As one of major underground pipelines, sewerage is an important infrastructure in any modern city. The most common problem occurring leaking, whose position and failure level typically identified through closed circuit television (CCTV) inspection order to facilitate rehabilitation process. This paper proposes a novel method computer vision, morphological segmentation based on edge detection (MSED), assist inspectors detecting pipeline defects CCTV images. In addition MSED, other...