Category Archives: Research

Finished master projects with NTNU and UiB

Brage Alvsvåg just finished his masters thesis at Department of Informatics at UiB. The title was “Improving fish detection using efficient neural networks”, and the project was done in association with Mohn Technology using our dataset. In his project, Brage tested different ways of improving our fish detection AI, with different kinds of neural networks and post-training quantization he managed to develop some promising algorithms that might proove to be very useful for us. We are looking forwards to testing out these strategies in real life operations in the coming months!

Håvard Ullaland also finished his master thesis this summer at Department of Engineering Cybernetics at NTNU. Håvards project was titled “Positioning and localization for underwater vehicle in fish pen using VSLAM”, and the work is related to our automatic net inspection tool that is supported by FHF. Håvards contribution to the project is related to navigate based on machine vision and IMU (Inertial measurement unit). The localization algoritms use the input from the machine vision and sensors to estimate where it is, and where it is going. If we succeed in only using VSLAM (Visual simultaneous localization and mapping) algoritms we can reduce the hardware cost and complexity of the system, and it will also require less setup of hardware on site before operation.

The photos above shows the stereo camera navigational points on the net to the left, and the right shows the algorithms estimated travel route along the net pen. The results are very promising.

After the masters thesis was delivered Håvard started working for us full time on the project, and will continue his work on underwater localization and navigation.  

Humpback salmon research at Tana Bru

In cooperation with Tanafisk we have installed a dual FRS camera pole in the Tana River. The humpback salmon mainly enters the rivers every other year, where they reproduce and die. The system will be used to verify the efficiency of the guide fence so that we are ready for the 2023 season where we expect a large invation of the humpack / pink salmon.

The humpback salmon is an invasive species in Norway, and the problem is spreading from the northern parts of Norway from Russia. Local fishing associations and river authorities have done a heroic job in 2021 and caught tens of thousands of fish based on volantary work.

Mohn Technology is working on a automatic fish trap that is based on our machine vision and underwater technology experience. We hope the system will be able to stop the spread of the invasive species and protect our own wild salmon, while also generating value from the catch. More info to come!

Installation in progress

New research equipment for remote areas

The decline in stocks of sea trout and wild salmon on the west coast of Norway has highlighted the need for a autonomous, non-destructive sampling method. For this reason, fish biologist at NORCE LFI are currently developing a trap with the overall goal of recording wild fish for research or conservation purposes.

Mohn Technology contribute with our high resolution FRS camera applying AI to detect passing fish. This new solar powered surveillance system was just deployed at Dale, Norway. The camera system is designed to use as little power and data traffic as possible, and the solar system was assembled and tested at Mohn Technology before deployment.

The system allows the researchers at NORCE LFI to get information about fish population and migrations directly to their computers from remote areas without access to electricity, and we hope more systems like this can aid research in this important field.

New FRS camera in the water

NORCE Research has installed a new FRS camera in the Bolstad River. It was important to get the system up and running before the spring flooding due to snow melting.

The system was installed by NORCE field biologists, who bolted the durable stainless steel frame to a large boulder . The boulder was then moved to deeper waters. The frame / bracket is designed to withstand heavy impacts by objects that float down the river.

Two FRS pilot projects live

In a cooperation project with NORCE Research, we have delivered our two first pilot systems of the FRS cameras to BKK. BKK, who is interested in the local fish population and migration patterns, has installed the systems at two suitable fish ladders. We are looking forewards to working together with both BKK and NORCE to further develop the system and implement customer ideas and requirements.

AI based fish detection machine vision

Mohn Technology is continuously working on testing and improving our machine vision algorithms for our different camera systems. After we completed a prototype test of our FRS camera (Fish Research System) this winter with NORCE LFI at Byglandsfjord, we got new footage to test.

Machine vision is one of the most important aspects of the FRS camera, and high precision algorithms help us deliver the best possible results. The FRS allows the user to efficiently monitor underwater life with greatly reduced manual data processing efforts.

This version was trained on a small data set, but the results were pretty impressive. The machine vision algorithm detects fish that are hard to see manually (especially those inside the net).

The system provides both still images and video, which makes it easy to verify and classify the fish.

Theis particular setup, with a fishing net funneling fish past the FRS camera, is used by NORCE to research fish population in lakes and fjords. It is one of many ways to use the FRS camera to gather data about marine life.

Stereo camera accuracy testing with IMR

Mohn Technology is currently testing an underwater stereo camera system with Institute of Marine Research. The accuracy testing performed this time was done by comparing the distance between the white dots on a calibration bar to the camera based measurements. The distance between the dots is 596,4 mm, and most measurements had a margin of error around 0,5%

These kinds of tests are important to verify the hardware accuracy under different conditions and improve software. Underwater machine vision measurements are more complex due to the poor light and contrast. The underwater stereo camera is a compact version of what is used in the autonomous Fish Research System (FRS)