A5100643560- Robotics and Sensor-Based Localization
- Autonomous Vehicle Technology and Safety
- Advanced Vision and Imaging
- Topic Modeling
- Video Coding and Compression Technologies
- Vehicle License Plate Recognition
- Remote Sensing and LiDAR Applications
- Video Surveillance and Tracking Methods
- Smart Parking Systems Research
- Advanced Neural Network Applications
- Advanced Battery Materials and Technologies
- Robotic Path Planning Algorithms
- Advanced Data Compression Techniques
- Advanced Battery Technologies Research
- Image Processing and 3D Reconstruction
- Space Satellite Systems and Control
- Advancements in Battery Materials
- Spacecraft Design and Technology
- Natural Language Processing Techniques
- Solar Radiation and Photovoltaics
- Vehicle emissions and performance
- Structural Load-Bearing Analysis
- Optical measurement and interference techniques
- Structural Behavior of Reinforced Concrete
- Text Readability and Simplification
Korea University
2018-2024
Korea Advanced Institute of Science and Technology
2022-2024
LG (South Korea)
2023-2024
Hong Kong University of Science and Technology
2022
University of Hong Kong
2022
Nvidia (United Kingdom)
2022
Chungbuk National University
2018-2022
Hanyang University
2019
Hyundai Mobis (South Korea)
2018
Kwangwoon University
2016-2017
As drone attracts much interest, the industry has opened their market to ordinary people, making drones be used in daily lives. However, as it got easier for by more safety and security issues have raised accidents are likely happen: colliding into people losing control or invading secured properties. For purposes, is essential observers aware of an approaching drone. In this paper, we introduce a comprehensive detection system based on machine learning. This designed operable with camera....
Abstract The state-of-the-art all-solid-state batteries have emerged as an alternative to the traditional flammable lithium-ion batteries, offering higher energy density and safety. Nevertheless, insufficient intimate contact at electrode-electrolyte surface limits their stability electrochemical performance, hindering commercialization of batteries. Herein, we conduct a systematic investigation into effects shear force in dry electrode process by comparing binder-free hand-mixed pellets,...
Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin Zhang. Proceedings of the 60th Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2022.
Autonomous driving is becoming one of the leading industrial research areas. Therefore many automobile companies are coming up with semi to fully autonomous solutions. Among these solutions, lane detection vital driver-assist features that play a crucial role in decision-making process vehicle. A variety solutions have been proposed detect lanes on road, which ranges from using hand-crafted state-of-the-art end-to-end trainable deep learning architectures. Most architectures trained traffic...
The time resolution and prediction accuracy of the power generated by building-integrated photovoltaics are important for managing electricity demand formulating a strategy to trade with grid. This study presents novel approach improve short-term hourly photovoltaic output predictions using feature engineering machine learning. Feature selection measured importance score input features model-based variable importance. It verified that normative sky index in weather forecasted data had least...
Although numerous road segmentation studies have utilized vision data, obtaining robust classification is still challenging due to sensor noise and target object deformation. Long-distance images are problematic because of blur low resolution, these features make distinguishing roads from objects difficult. This study utilizes light detection ranging (LiDAR), which generates information that camera lack, such as distance, height, intensity, a reliable supplement address this problem. In...
In this paper, I propose a bird eye view image detection method for parking areas and collision risk at the same time in situations. Deep learning algorithms using area semantic segmentation were used. The main architecture of described paper is based on harmonic densely connected network cross-stage partial network. dataset used training was calibrated to four 190° wide-angle cameras generate around monitor (AVM) images Chungbuk National University lot, an experiment performed dataset....
In this paper, we address the design, fabrication and test of a qualification model wire thermal cutting based non-explosive actuation (NEA) device for small satellite. The important design parameters such as maximum allowable preload release time are investigated through theoretical analysis. After it is fabricated on results, implemented mechanical performance tests to assure operability reliability compact size NEA device. From result preload, shock level tests, found that proposed can be...
Automobile demand has been widely and extensively investigated because of its effects on many related fields such as travel behavior, public policy management, transportation impact analysis. Although importance well perceived in the field transportation, models developed frequently emphasize short-term forecasting, interactions simultaneity among endogenous variables are rarely investigated. In addition, a large number existing adopt simple regression methods with time-series data. However,...
The PLDWS (Parking Line Departure Warning System) is one of the important ADAS (Advanced Driving Assistance functions when a driver recognizes parking situations. We proposed new real-time algorithm and its implementation based on NVIDIA Jetson TX2, which an embedded board environment. showed processing speed that applicable to actual production vehicle same performance result as PC A wide-angle camera mounted front, rear, left right sides vehicle, AVM (Around View Monitoring) images are...
Unmanned aerial vehicles (UAVs) have been widely used in complex applications, such as military, exploration, and rescue. Although there are many quadcopter the bi-copter like a coaxial helicopter has apparent energy efficiency scalability advantages. What makes challenging to use is difficulty control because additional mechanical structures essential for stable movement. This paper tackles this problem by proposing novel bi-rotor design called M-BRIC with rotatable weight rods...
Lifelong learning aims to accumulate knowledge and alleviate catastrophic forgetting when tasks sequentially. However, existing lifelong language methods only focus on the supervised setting. Unlabeled data, which can be easily accessed in real-world scenarios, are underexplored. In this paper, we explore a novel setting, semi-supervised (SSLL), where model learns sequentially arriving with both labeled unlabeled data. We propose an data enhanced learner SSLL. Specially, dedicate...
Recognizing traversable terrain from 3D point cloud data is critical, as it directly impacts the performance of autonomous navigation in off-road environments. However, existing segmentation algorithms often struggle with challenges related to changes distribution, environmental specificity, and sensor variations. Moreover, when encountering sunken areas, their frequently compromised, they may even fail recognize them. To address these challenges, we introduce B-TMS, a novel approach that...