A5055199057- Advanced Optical Sensing Technologies
- Robotics and Sensor-Based Localization
- Remote Sensing and LiDAR Applications
- Infrared Target Detection Methodologies
- Advanced Neural Network Applications
- AI in cancer detection
- Underwater Vehicles and Communication Systems
- Maritime Navigation and Safety
- Radiomics and Machine Learning in Medical Imaging
- Advanced Vision and Imaging
- Optical Wireless Communication Technologies
- Marine Biology and Environmental Chemistry
- Cell Image Analysis Techniques
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Image Enhancement Techniques
- Cephalopods and Marine Biology
- Brain Tumor Detection and Classification
- Marine Bivalve and Aquaculture Studies
Hong Kong University of Science and Technology
2023-2024
University of Hong Kong
2023-2024
VinUniversity
2022
Vinh University
2022
Seoul National University
2020-2021
Current research on deep learning for medical image segmentation exposes their limitations in either global semantic information or local contextual information. To tackle these issues, a novel network named SegTransVAE is proposed this paper. built upon encoder-decoder architecture, exploiting transformer with the variational autoencoder (VAE) branch to reconstruct input images jointly segmentation. best of our knowledge, first method combining success CNN, transformer, and VAE. Evaluation...
The 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Surface (USV). Three challenges categories are considered: (i) UAV-based Object Tracking with Re-ideruification, (ii) USV-based Obstacle Segmentation Detection, (iii) Boat Tracking. Detection features three sub-challenges, including a new embedded challenge...
This paper presents a simple yet effective design of platform to automate the task shellfish aquaculture, specifically pearl oysters. Compared traditional methods, our can eliminate tedious cleaning oysters due fouling. Inspired by low and high tide characteristics intertidal zone, employs an air-water displacement mechanism periodically float above water's surface, exposing fouling organisms air sunlight. While have developed ability stay alive during tide, these cannot survive after...
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Surface (USV). Three challenges categories are considered: (i) UAV-based Object Tracking with Re-identification, (ii) USV-based Obstacle Segmentation Detection, (iii) Boat Tracking. Detection features three sub-challenges, including a new embedded challenge addressing efficicent inference real-world devices. This report offers comprehensive overview of the...
In recent years, light detection and ranging (LiDAR) sensors have been widely utilized in various applications, including robotics autonomous driving. However, LiDAR relatively low resolutions, take considerable time to acquire laser range measurements, require significant resources process store large-scale point clouds. To tackle these issues, many depth image sampling algorithms proposed, but their performances are unsatisfactory complex on-road environments, especially when the rate of...
Omnidirectional camera is a cost-effective and information-rich sensor highly suitable for many marine applications the ocean scientific community, encompassing several domains such as augmented reality, mapping, motion estimation, visual surveillance, simultaneous localization mapping. However, designing constructing high-quality 360$^{\circ}$ real-time streaming system underwater challenging problem due to technical complexity in aspects including resolution, wide field of view, power...
Light Detection and Ranging (LiDAR) sensors have relatively low resolutions, require considerable time to acquire the laser range measurement, store large-scale point clouds. In order address these issues, this paper presents a sampling algorithm which finds optimal rates in region of interest (ROI) minimize total mean-absolute-error (MAE). Eventually, MAEs both ROIs overall scene decrease significantly. Experimental results show that proposed scheme reduces MAE object area by up 63.3% 34.2%.
Current research on deep learning for medical image segmentation exposes their limitations in either global semantic information or local contextual information. To tackle these issues, a novel network named SegTransVAE is proposed this paper. built upon encoder-decoder architecture, exploiting transformer with the variational autoencoder (VAE) branch to reconstruct input images jointly segmentation. best of our knowledge, first method combining success CNN, transformer, and VAE. Evaluation...