language
person_outline

Aquabyte System

Platform
Sales planner
Performance
WISE Welfare

Decision support based on over one million images per day and artificial intelligence

Aquabyte SYSTEM combines robust camera hardware with an optional winch, advanced technology based on machine learning and artificial intelligence (AI), and a user portal that provides access to essential data on lice counts, fish weight, welfare, and behavior. The information delivered by the system offers unique insights into the fish and its environment, serving as a valuable decision-support tool throughout the entire production process.

Aquabyte camera

Our two camera models, Atlas and Hammerhead, are designed for seamless operation at great depths and can be used in all types of production – whether on land, in surface pens, or submerged operations. The cameras feature two lenses and function as stereo cameras, which in practice means they capture images with depth perception. This is essential for accurately calculating the fish’s weight, size, and biomass with high precision.

Over the course of a day, Aquabyte cameras capture over one million high-resolution images. Each image is analyzed directly within the camera, and a selection is sent to the cloud for deeper analysis using our advanced machine learning and AI technology.

Integrated sensors

Both camera models have integrated environmental sensors that measure depth and temperature. Additionally, the Hammerhead camera can be equipped with two extra sensors to monitor oxygen and salinity levels in the water. Data from all sensors is displayed in the Aquabyte User Portal alongside information on lice, weight, welfare, and behaviour. This allows you, as a user, to observe correlations between changing environmental factors and the fish’s status and development.

Learn more about Aquabyte Hammerhead

Aquabyte Winch

The Aquabyte cameras can be combined with the Aquabyte Winch. The winch allows the camera’s position in the pen to be adjusted quickly, either from the cabinet mounted on the pen’s edge or via the control panel in the Aquabyte User Portal. Since the fish’s position within the pen can vary, the winch makes it easy to reposition the camera, ensuring that the images it captures provide a representative and accurate sample.
The winch can also be programmed to move the camera automatically in a predefined pattern throughout the day or set to auto mode, where the camera itself determines the optimal position.

Aquabyte machine learning and artificial intelligence

The images captured by the Aquabyte camera in the pen are analyzed using advanced machine learning algorithms and artificial intelligence. Several types of lice are identified and counted, the fish’s biomass, weight, and growth are calculated, and critical welfare parameters are recorded based on 14 indicators from the LaksVel protocol, along with our own additional indicators. Every day, vast amounts of image data are processed and presented in the Aquabyte User Portal.

Aquabyte User Portal

The Aquabyte User Portal provides an easy access to the data and information collected and analyzed by our system. The information is accessible on all types of devices (computer, tablet, and mobile) and is presented both as raw data and graphs, covering up to 12 months of history. The graphs are based on daily updated data, making it easy to identify status, trends, and developments over time.

As part of our open system approach, the User Portal also allows you to view the camera images that form the basis of the system’s analyses and calculations.

Aquabyte Penflix

As the only system on the market for lice counting, biomass calculation, and welfare and behavior monitoring, we stream live video directly from the Aquabyte camera in the pen. We call this Penflix. Compared to still images, live video provides unique insights into the fish’s behavior in the pen. With Penflix, you can observe the fish up close during feeding, locate the fish, and position the camera accurately (in combination with the winch). The Aquabyte camera and Penflix can also be used alongside feeding cameras – or as a backup if the feeding camera is out of service.

Learn more about Aquabyte Penflix

Book demo

Q&A

Machine learning is a form of artificial intelligence. It is software, a network of algorithms, that is trained to recognize and interpret patterns in images and data sets. The technology behind it is the same that is used in facial recognition on social media, to analyze surroundings for self-driving cars – and to recommend movies and music on Spotify and Netflix based on your previous selections.

In a normal software, a calculation is performed on the basis of data that is entered into the software. In machine learning, software and algorithms evolve as they are “trained” with new datasets. This training becomes a form of pattern recognition, where the algorithms learn what to look for based on prior examples. As new training data and examples are provided to the machine learning software, the algorithms generate more and more precise results.

Let’s say that the algorithms are trained to recognize salmon lice. The algorithms are given training data, consisting of many images of salmon with annotations of lice in different stages. Through feedback in the form of these examples, the algorithms become increasingly accurate in recognizing salmon lice. It is important that the photos are taken under real conditions in the cage: changing lighting conditions, different angles of the fish, for example.

The quality of the algorithms is important. Algorithms may need to be adjusted along the way to emphasize biological factors in the data that make the results more accurate. For example, consider an algorithm that recognizes individual fish based on unique spot patterns. If algorithms are to recognize the same fish over time, these algorithms must also have the capacity to understand how these spot patterns change with the growth of the fish.

Images are taken with an underwater camera in the cage. Per Erik Hansen, Product Manager for Lice and Welfare at Aquabyte, mentions that the company uses a standard two-lens camera with particularly good optics to be able to measure 3D distance to the fish. The camera continuously takes images, and is placed in an optimal location such that as many fish as possible can swim past. Software running on the camera filters out unused images and analyzes the best ones.

“Customers who have used the system for a long time report that the results turn out to be in line with reality,” Per Erik Hansen continues. Farmers get daily lice numbers for each cage, with lice counts on far more fish than possible with manual counting. “The software distinguishes individual fish from each other, such that the same fish is only counted once. This contributes to Aquabyte delivering lice numbers with great accuracy,” notes Hansen.

Precise counting of salmon lice and accurate estimation of weight data and distribution are two use cases that have received fully developed solutions. Fish welfare is another important application area, including detection of winter sores, deformations, and other external changes on the fish. By giving the farmer much better insight and basis for decision making, it will be possible to improve daily operations, and in general achieve more efficient and sustainable fish farming.

keyboard_arrow_up