A5085338970- Robotics and Sensor-Based Localization
- Advanced Optical Sensing Technologies
- Water Quality Monitoring Technologies
- Underwater Vehicles and Communication Systems
- Optical measurement and interference techniques
- CCD and CMOS Imaging Sensors
- Aquaculture disease management and microbiota
- Identification and Quantification in Food
- Parasite Biology and Host Interactions
- Analytical Chemistry and Sensors
- Advanced Vision and Imaging
- Photonic and Optical Devices
- Landslides and related hazards
- Industrial Vision Systems and Defect Detection
- Advanced Image and Video Retrieval Techniques
- QR Code Applications and Technologies
- Cryospheric studies and observations
- Winter Sports Injuries and Performance
- Advanced optical system design
- Calibration and Measurement Techniques
- Medical Imaging Techniques and Applications
- Interactive and Immersive Displays
- Digital Radiography and Breast Imaging
- Environmental Monitoring and Data Management
- Advanced MEMS and NEMS Technologies
SINTEF
2007-2023
SINTEF Digital
2018-2023
Camera estimation of fish size in aquaculture production and fisheries is crucial for enabling knowledge-based decision making. Automatic lengths on an individual population basis are key steps to automate biomass estimation. We propose use underwater 3D range-gated camera accurate fish-length free-swimming fish. The proposed algorithm requires no manual work or contact with the done in-situ. A robust algorithmic pipeline consisting detection, tracking length stages proposed. show accuracy...
Aquaculture net cage inspection and maintenance is a central issue in fish farming. Inspection using autonomous underwater vehicles promising solution. This paper proposes laser-camera triangulation for pose estimation to enable following an vehicle. The laser 3D data experimentally compared doppler velocity log (DVL) active farm. We show that our system comparable performance DVL distance angular measurements. Laser as short ranging sensor at low cost acoustic sensors.
Recently, Range Imaging (RIM) cameras have become available that capture high resolution range images at video rate. Such measure the distance from scene for each pixel independently based upon a measured time of flight (TOF). Some cameras, such as SwissRanger(tm) SR-3000, TOF on phase shift reflected light modulated source. are shown to be susceptible severe distortions in due scattering within lens and camera. Earlier work induced using simplified Gaussian point spread function inverse...
This paper proposes a low-cost solution for localizing remotely operated vehicle (ROV) inside fish net pen. The consists of kinematic Kalman Filter capable estimating the absolute ROV position and orientation in pen using primarily onboard compass, laser-camera triangulation, model cylindrical is demonstrated real pen, under realistic operating conditions, performance comparable to that specialized positioning sensor systems such as ultra short baseline Doppler velocity loggers.
High-precision underwater 3D cameras are required to automate many of the traditional subsea inspection, maintenance and repair (IMR) operations. In this paper we introduce a novel multi-frequency phase stepping (structured light) method for high-precision estimation even in turbid water. We an adaptive phase-unwrapping procedure which uses phase-uncertainty determine highest frequency that can be reliably unwrapped. Light scattering adversely affects estimate. propose remove effect forward...
Sensors that can provide detailed 3D data underwater are a prerequisite for enabling autonomous inspection of e.g. seafloor integrity, ocean habitats and subsea installations with unmanned vehicles. Sonars currently the primary source on moving platforms but have limited depth lateral resolution. Several optical approaches exist such as passive stereo, which problems textureless objects, LIDARs slow low In this work we explore use structured light, to achieve high-resolution objects in an...
We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots better interact with their surroundings. The is based on time-of-flight laser scanning technology, where each range distance measurement performed individually for increased quality. Micro-mirrors enable detailed control and when sample point acquired in scene. By finding regions-of-interest (ROIs) mainly concentrating data acquisition here, spatial resolution...
This paper presents a real-time contour tracking and object segmentation algorithm for 3D range images. The is used to control novel micro-mirror based imaging laser scanner, which provides dynamic trade-off between resolution frame rate. micro-mirrors are controllable, enabling us speed up acquisition significantly by only sampling on the that tracked of interest. As hardware under development, we benchmark our algorithms data from SICK LMS100-10000 scanner mounted tilting platform. We find...
We present a Structured Light Imaging system developed for Space Applications, where accurate 3D measurements in direct sunlight is an absolute requirement. Through spectral filtering of the camera and use high power VCSEL, we have demonstrated that provides megapixel resolution images with sub-mm depth precision at 1 m distance, when operating sunlight. discuss theoretical observed as function signal levels.
Employing digital micro-mirror devices to simultaneously select illumination and detection regions in a scene, increases flexibility spectral measurements. Presented here, is method for collecting regional reference spectra, which necessary optimum accuracy, while maintaining the of system.
This work presents a promising method for automatic non-contact detection and counting of salmon lice infested on in an aquacultural farm setting. The uses fluorescence the visual part spectrum to enhance contrast between fish skin lice. wavelengths used are compatible with underwater measurement system.
Summary Snow avalanches along road network is one of the major natural hazards in Norway and arctic countries. To improve forecasting monitoring avalanche events, use UAS to record data complement ground measurements investigated. Several sensors are tested including remote sensing such as optical, thermal multispectral cameras geophysical (ground penetrating radar). The collected datasets validated against truth measurement integrated together help for forecasting. We concluded that methods...