A5043094888- Underwater Vehicles and Communication Systems
- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Image Enhancement Techniques
- Indoor and Outdoor Localization Technologies
- Advanced Image Fusion Techniques
- Optical measurement and interference techniques
- Maritime Navigation and Safety
- Color Science and Applications
- Advanced Vision and Imaging
- Satellite Communication Systems
- Advanced Image and Video Retrieval Techniques
- Opportunistic and Delay-Tolerant Networks
- Advanced Image Processing Techniques
- Underwater Acoustics Research
- 3D Surveying and Cultural Heritage
Heriot-Watt University
2019-2023
Constructor University
2015-2019
Compagnie Maritime d'Expertises (France)
2018
Institute of Mathematical Machines
2015
The calibration and refraction correction process for underwater cameras with flat-pane interfaces is presented that very easy convenient to use in real world applications while yielding accurate results. derived from an analysis of the axial camera model cameras, which among others computationally hard tackle. It shown how realistic constraints on distance window can be exploited, leads approach dubbed Pinax Model as it combines aspects a virtual pinhole projection function model. allows...
Underwater manipulation is a challenging problem. The state-of-the-art technology dominated by remotely operated vehicles (ROVs). ROV operations typically require an offshore crew consisting of, at minimum, intendant (or supervisor), operator, and navigator. This must often be doubled or even tripled due to work shifts. In addition, customer representatives wish physically present offshore. Furthermore, underwater intervention missions are still significant amount of lowlevel, manual control...
In this paper, we propose an approach for robust visual Simultaneous Localisation and Mapping (SLAM) in underwater environments leveraging acoustic, inertial altimeter/depth sensors. Underwater SLAM is challenging due to factors including poor visibility caused by suspended particles water, a lack of light insufficient texture the scene. Because this, many state-of-the-art approaches rely on acoustic sensing instead vision navigation.Building sparse system ORB-SLAM2, paper proposes improve...
Autonomous Underwater Vehicles (AUVs) are becoming increasingly important for different types of industrial applications. The generally high cost AUVs restricts the access to them and therefore advances in research technological development. However, recent have led lower commercially available Remotely Operated (ROVs), which present a platform that can be enhanced enable degree autonomy, similar high-end AUV. In this article, we how low-cost commercial-off-the-shelf ROV used as foundation...
Underwater scenarios are challenging for visual Simultaneous Localization and Mapping (SLAM) due to limited visibility intermittently losing structures in image views. In this paper, we propose a acoustic bundle adjustment system which fuses camera Doppler Velocity Log (DVL) graph SLAM framework reliable underwater localization mapping. order fuse the vision with measurements, an calibration algorithm is also designed estimate extrinsic parameters between DVL using features detected scenes....
Robust and accurate navigation of underwater vehicles is an essential cornerstone for mission success. Integrative techniques, e.g., using inertial or Doppler velocity logs (DVL), can show significant drift. Even absolute input, such as GNSS input magnetometers, either be biased by surrounding structures very noisy. For good performance in critical maneuvers close to like sea mounts, cliffs man-made constructions where DVLs fail, based on visual helpful. This paper presents a technique...
This paper presents a robust underwater simultaneous localisation and mapping (SLAM) framework using autonomous relocalisation. The proposed approach strives to maintain single consistent map during operation updates its current plan when the SLAM loses feature tracking. updated transverses viewpoints that are likely aid in merging into global map. We present sub-systems of framework: SLAM, viewpoint generation, high level planning. In-water experiments show advantage our used on an vehicle...
Underwater images suffer from extremely unfavourable conditions. Light is heavily attenuated and scattered. Attenuation creates change in hue, scattering causes so called veiling light. General state of the art methods for enhancing image quality are either unreliable or cannot be easily used underwater operations. On other hand there a well known method haze removal air, Dark Channel Prior. Even though adaptations this to applications, they do not always work correctly. This elaborates...
This paper presents an adaptive heading approach for perception awareness during trajectory following. By adapting the of a robot to improve feature tracking in current mapped environment, accuracy localisation can be improved. have significant advantage autonomous operations GPS-denied environments such as subsea or caves. The aim proposed is position sensor used and way that it; obtains view contains good observation previously face forward along direction travel, reduces change perceived...
Scenario: A rescue team needs to cross a partially damaged bridge in flooded area. It is unknown whether the construction still able carry vehicle. Assessing construction's integrity can be accomplished by analysis of bridge's eigenfrequencies. Rather than using proprietary expensive Vibration Measurement Systems (VMS) we propose utilize off-the-shelf smartphones as sensors - which require placed at spot on best suited for picking up vibrations. Within this work, use an Unmanned Ground...
One fundamental problem in Simultaneous Localization and Mapping is place recognition, used to create loop closures, necessary improve map quality. Ideally, the sensor data alone should be detect referred as appearance-based methods. Such methods usually employ feature descriptors, especially popular underwater research are 2D visual features, bag-of-words approach. Here we demonstrate combined use of 3D surface which specifically interesting context mapping with stereo data. Different types...
This paper presents a novel dataset for the development of visual navigation and simultaneous localisation mapping (SLAM) algorithms as well underwater intervention tasks. It differs from existing datasets it contains ground truth vehicle's position captured by an motion tracking system. The distortion-free rectified stereo images along with calibration parameters camera setup. Furthermore, experiments were performed recorded in controlled environment, where current waves could be generated...
In this paper, we describe how an autonomy engine can work together with operator to perform human-machine collaborative inspection of offshore structures using shared autonomy.The approach is driven by the robot's autonomy, which make suggestions what considers be desirable actions fulfil a mission.The at any time inject its own action, choose from generated or allow robot continue fully autonomously until next user input.The removes need for constant monitoring and enable single control...
Autonomous Underwater Vehicles (AUVs) are becoming increasingly important for different types of industrial applications. The generally high cost restricts the access to them and therefore advances in research technological development. However, recent have led lower commercially available Remotely Operated (ROVs), which present a platform that can be enhanced enable degree autonomy, similar high-end (AUV). In this article, we how low-cost commercial-off-the-shelf (ROV) used as foundation...