A5059337878- Underwater Vehicles and Communication Systems
- Underwater Acoustics Research
- Software Reliability and Analysis Research
- Safety Systems Engineering in Autonomy
- Risk and Safety Analysis
- Target Tracking and Data Fusion in Sensor Networks
- Water Quality Monitoring Technologies
- Advanced Vision and Imaging
- Industrial Vision Systems and Defect Detection
- Advanced Optical Sensing Technologies
- Non-Destructive Testing Techniques
- Robotics and Sensor-Based Localization
- Adversarial Robustness in Machine Learning
- Distributed Sensor Networks and Detection Algorithms
- Video Surveillance and Tracking Methods
Heriot-Watt University
2017-2024
Simulations are highly valuable in marine robotics, offering a cost-effective and controlled environment for testing the challenging conditions of underwater surface operations. Given high costs logistical difficulties real-world trials, simulators capable capturing operational subsea environments have become key developing refining algorithms remotely-operated autonomous vehicles. This paper highlights recent enhancements to Stonefish simulator, an advanced open-source platform supporting...
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) has resulted the pressing need to assure their functional safety. As for traditional safety, emerging consensus within both, industry and academia, is assurance cases this purpose. Typically support claims reliability can be viewed as a structured way organising arguments evidence generated from safety analysis modelling activities. While such activities are...
Subsea pipelines are crucial offshore assets aiding transportation of oil and gas. Regular inspections required for assessing their integrity to ensure continual use avoid possible marine ecosystem damage. This paper proposes a novel real-time algorithm pipeline detection tracking at close proximity using only multibeam echosounder with noisy measurements. The proposed method provides accurate pipe detections also estimates orientation the pipe. robustly filters out false alarms produced by...
When working with real data, underlying parameters such as the detection or clutter rates are generally unknown and possibly varying over time, however right parametrisation is crucial to extract proper statistics about monitored objects. In this article, a single cluster Probability Hypothesis Density (PHD) filter used jointly estimate location number of set objects rate time. The algorithm verified on simulated scenario designed emulate challenging nature Single-Molecule Localisation...
Integrity assessment of subsea oil and gas transmission lines is crucial for safe environment-friendly operations. These are usually very expensive without employing Autonomous Underwater Vehicles (AUVs). Buried sections long pipelines pose a major hurdle in effective pipeline tracking through an AUV. If pipe track lost, then the vehicle needs to invest resources relocate pipeline. This work presents heuristic-based method detect buried pipes using magnetometers followed by Kalman filter...
Regular inspection of subsea pipelines is crucial for assessing their integrity and maintenance. These inspections usually are very expensive without employing Autonomous Underwater Vehicles (AUVs). Most the research focus in this area has been directed automating process to reduce operational costs done by using multiple perceptive sensors. This paper investigates problem pipeline detection optical sensors highly turbid scenarios. A deep neural network designed segment pipes from images....
Inspection of subsea pipelines is crucial for avoiding any hazards and minimizing the risks to infrastructure environment. These inspections are achieved using Autonomous Underwater Vehicles (AUVs) in favour reduced operational costs. This work presents a vehicle agnostic approach tracking at close-range autonomous guidance along pipeline an AUV. A multibeam echosounder used as primary sensor augmented by fluxgate magnetometers that can track buried over short ranges until they exposed...
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) has resulted the pressing need to assure their functional safety. As for traditional safety, emerging consensus within both, industry and academia, is assurance cases this purpose. Typically support claims reliability can be viewed as a structured way organising arguments evidence generated from safety analysis modelling activities. While such activities are...
Calibrating multiple cameras is a fundamental prerequisite for many Computer Vision applications. Typically this involves using pair of identical synchronized industrial or high-end consumer cameras. This paper considers an application on low-cost portable with different parameters that are found in smart phones. addresses the issues acquisition, detection moving objects, dynamic camera registration and tracking arbitrary number targets. The acquisition data performed two standard phone...