- Maritime Navigation and Safety
- Ship Hydrodynamics and Maneuverability
- Historical Geography and Cartography
- Arctic and Antarctic ice dynamics
- Inertial Sensor and Navigation
- Arctic and Russian Policy Studies
- Fire Detection and Safety Systems
- Traffic control and management
- Geophysics and Gravity Measurements
- Maritime Transport Emissions and Efficiency
- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Autonomous Vehicle Technology and Safety
- Soil Moisture and Remote Sensing
- Aerospace Engineering and Control Systems
- Advanced Research in Science and Engineering
- Software Engineering and Design Patterns
- Marine and Coastal Research
- Icing and De-icing Technologies
- Evacuation and Crowd Dynamics
- Maritime Ports and Logistics
- Power System Optimization and Stability
- Historical Astronomy and Related Studies
- Infrared Target Detection Methodologies
Shanghai Maritime University
2018-2024
National Taiwan University
2013-2017
National Taiwan Ocean University
2011
Rutgers, The State University of New Jersey
1998
3D object perception in maritime is a promising means to enhance the ability of autonomous navigation. However, automatic reconstruction dynamic targets remains challenging task systems. In this paper, we present an innovative GAN-based deep learning neural network for ship reconstruction. The method able reconstruct models from single view images or videos using shape prior knowledge and vessel generative adversarial (Vessel-GAN), which can effectively extract features single-view videos....
Ice navigation is currently one of the important issues in path planning studies. Most studies are using sea ice models or charts for large-scale planning, but weather and conditions polar waters usually change quickly not easy to predict. Under these conditions, small-scale that can be adjusted time collision avoidance needed. This study uses marine radar imaging reconstruct scene, establishes a visual-ization function warning on image. We combine bidirectional rapidly-exploring random tree...
Determining the appropriate number and position of waypoints on a great circle route (GCR) helps to shorten sailing distance, reduce course changes, well-approximate GCR through small rhumb line (RL) legs. In this study, genetic algorithm-based method (i.e., GA method) is proposed optimize positions when given. Furthermore, fuzzy logic-based evaluation for FL judge whether add new waypoint or stop process by using non-fixed values while considering both remaining benefit GCR. According...
Abstract In ship navigation, the most widely used technology is global navigation satellite systems (GNSS), which provide ship’s position and velocity continuously over a period of time. However, when ships are blocked by port buildings or bridges, quality signals received from shipborne GNSS receivers may be reduced, resulting in inaccurate positioning that poses risk to navigational safety. an occluded environment, measurement process during signal processing nonstationary prone anomalies,...
Abstract A great circle route (GCR) is the shortest on a spherical earth model. Do we have visual diagram to handle route? In this paper, graphical method (GM) proposed solve GCR problems based celestial meridian (CMD) in navigation. Unlike developed algebraic methods, GM geometric method. Appling computer software graph, does not use any equations but as accurate using methods. addition, GM, which emphasizes rotational surface, can depict and judge its benefit.
The accurate design of ship routing plans in arctic areas is not easy, considering that navigation conditions (e.g., weather, visibility, and ice thickness) may change frequently. A ship’s crew identifies sea channels with the help radar echoes, maneuvering decisions are made to avoid interference. Ship officials must manually consistently route travel, which time-consuming tedious. To address this issue, we propose a near-field optimization model for purpose automatically selecting an...
The continuous improvement in the seaworthiness of Arctic shipping routes has caused an urgent international demand for meteorological and sea ice information. In view diversity information websites uneven service levels websites, to assist navigation ships selecting timely, stable, reliable information, this paper summarizes providing Constructing evaluation indicator system level from two dimensions data quality browsing experience, integrates cloud model, Dempster–Shafer (D-S) evidence...
In open sea sailing, as opposed to sailing with satellite navigation systems, the astronomical vessel position (AVP) is not limited by military codes. If programs can be developed solve AVP directly, drawbacks of current methods for performing marine operations greatly improved. Complete computations have two necessary points: compute observed altitude and bodies. Thus, this paper utilizes Matlab® programming language develop (ObsAltPro) using intercept method (IMPro-2) programs,...
Ramp metering can effect on mitigating the traffic congestion freeway. In Taiwan, conventional Local Traffic Responsive (LTR) ramp model based capacity and demand algorithm has been adopted for freeway control since long time. For enhancing technology, this paper aimed at developing a new Fuzzy Logic Control (FLC) real situation highway tunnel, by taking Freeway No.5 as case, which is with longest tunnel of 12.9km, in order to enhance performance relieving congestion. Through comparative...
The Great Elliptic Sailing (GES), which can reduce sailing distance, is important to navigators. Whether a Ellipse (GE) worth using depends on whether the distance saved significant. Otherwise, Rhumb Line (RL) easier steer. We propose simple criterion evaluate difference in between GE and RL. that when vertex lies departure destination. In order take advantage of shorter usually approximated as series waypoints. Unlike currently practised methods, we Longitude Bisection Method (LBM)...
Mastering the real-time dynamics of near-field sea ice is primary condition to guaranteeing navigation safety autonomous ships in polar region. In this study, a radar image fusion process combining marine and proposed, which can effectively solve problems redundant information spatial registration during fusion. Then, using fused images, study proposes set risk assessment warning processes applicable both low- high-sea-ice-concentration situations. The indexes these two situations are...
In order to improve tracking, interference and multipath mitigation performance from that possible with existing signals, a new Global Navigation Satellite System (GNSS) signal is needed can offer additional degrees of freedom for shaping its pulse waveform spectrum. this paper, modulation scheme called Quinary Offset Carrier (QOC) proposed as GNSS design. The waveforms QOC are divided into two types: convex concave waveforms. modulations be easily constructed by selecting different...
Spherical trigonometry formulae are widely adopted to solve various navigation problems. However, these only express the relationships between sides and angles of a single spherical triangle. In fact, many problems may involve different types shapes. If we can develop for specific shapes, it will help us directly. Thus, propose two combined triangles. The first set divided triangle, second quadrilateral. By applying waypoints on great circle track be obtained directly without finding initial...
Global navigation satellite systems reflectometry (GNSS-R) involves making measurements from the reflections Earth of signals GNSS. In this paper, a resolution enhancement technique based on Truncated Singular Value Decomposition (TSVD) approach is described to obtain given spatial in Normalized radar Cross Section (NRCS) images GNSS-R's Delay-Doppler Maps (DDMs). The ocean target information contained DDMs obtained by GNSS-R instrument aboard British TechDemoSat-1 (TDS-1) have been inverted...
Intelligence testing and verification of autonomous sailing capability is crucial to the development deployment ships. The prevailing approach establish a real test site on sea or create life-like simulator functions. However, due high dimensionality naturalistic environment rareness encounter events, hundreds millions miles long cycles would be required demonstrate collision avoidance performance A novel presented generate adversarial (NASE) by employing sparse but adjustments into...
In the process of offshore fire protection, discovering situation and grasping development trend are basis for formulating scientific reasonable firefighting strategies. However, existing perception algorithms were mainly applied in onshore indoor outdoor or forest scenes, cannot be used marine environment due to complex weather conditions work conditions. Aiming at autonomous detection problem unmanned vessels sea, we propose a method based on an improved dark channel prior coordinate...