Building an Image-classification Library for Deep-learning Algorithms
The purpose of BILDA is to improve the detection rate of the detection algorithm we use.
Until now, the detection rate has been too low for it to be possible to use only analyzes from the algorithm.
This means that a third party must manually verify data that the algorithm cannot approve on its own.
By creating an application where other people can verify the data from the algorithm by simply swiping on images,
it is expected that the detection rate can be improved with up to 95% accuracy,
which will drastically reduce resources spent on manually verifying the data.
Innovasjon
L.A.R.E.S
Lightwave Algorithm for a Radiometric Entrainment System
The overall goal is to develop a solution to predict anomalies, faults and malfunctions in materials, by measuring thermal radiation from constructions and critical infrastructure.
The project aims to utilize handheld radiometric microbolometers, combined with freely available earth observations from satellites and the possibility of using aerial robotics to gather data with variances and deviations in infrared radiation from the source material in property assets.
F.E.N.G
Financial Exposure Network Geometry
FENG use infrared drone data capture technology for solar panel inspections in combination with advanced feature detection and machine learning algorithms to identify defective solar cells and reduced performance.
Utilization of aerial robotics ensures swifter, safer, and more efficient and repetitive inspections for a fraction of the cost of traditional inspection methods. We then strategize using smart tools and global resources in order to understand the implications of every choice our clients can make.
L.I.S.E.R.A
Lightwave Information System for Electronic Remote Assessment
The overall goal is to develop a system for robotic life cycle analysis and a new "best practice" for real estate development.
The idea is to develop a system that catches faults and deficiencies during a construction project, from start to remediation.
Using advanced drone and laser technology, we want to scan buildings throughout their life cycle to detect and document any deviations and deficiencies.
Our system eliminates the subjectivity of human observations and instead uses computer vision algorithms to offer a virtual network of experience and expertise.
Z.E.L.M.A
Zero Emission Last Miles Aviation
ZELMA aims to develop new knowledge in the interspace of long haul and last mile logistics and carry out novel, smart unmanned net zero emission aviation solutions by developing, testing and piloting RPA’s (Remotely Piloted Aircrafts) communication and big data technologies.
The project will contribute to new knowledge and services related to net zero carbon emission of connecting last mile drone delivery hubs and solving interconnected logistics.
M.A.P.S
Multiple Aircraft Piloting System
MAPS enables you to act as a PIC (Pilot In Command) on serveral unmanned- or optionally piloted aicrafts simultaniusly.
The solution is based on simple principles of real time onboard processed semantics, to ensure only vital data and information is presented the pilot.
B.I.L.D.A
Building an Image-classification Library for Deep-learning Algorithms
The purpose of BILDA is to improve the detection rate of the detecion algorithm we use.
Until now, the detection rate has been too low for it to be possible to use analyses from the algorithm exclusively.
This means that a third party must manually verify the data that the algorithm cannot approve on its own.
By creating an application where other people can verify the data from the algorithm by simply swiping on images, it is expected that the detection rate can be improved by up to 95% accuracy, which will drastically reduce resources spent on manually verifying the data.