No Fish Story: BitFlow Frame Grabber Optimizes Hyperspectral Imaging System to Assess Salmon Health


Illustration of hyperspectral measurements in the form of a 3D image cube, i.e. a hyperspectral cube. The cube on the right shows a cross section through the lateral axis of the fish

Scientists developed a hyperspectral imaging system to detect smoltification, relying on the BitFlow Camera Link frame grabber to capture video images for analysis

WOBURN, MA, United States, September 22, 2021 / – Smoltification is a complex series of physiological changes that allow young Atlantic salmon to adapt from freshwater life to saltwater life. In salmon farming, this transition from parr to seawater. “Smolt” is controlled using lights or functional foods to ensure a continuous and predictable supply of fish to grocery stores, restaurants and other seafood markets.

Scientists from SINTEF, one of Europe’s largest independent research institutes located in Trondheim, Norway, recently developed a hyperspectral imaging (HSI) system1 to study vital aspects of smoltification detection, relying in part on a BitFlow Camera link Image Capture to capture high-speed video images for analysis at over 100 frames per second.

The ability to verify smoltification is essential as incomplete adaptation to seawater can lead to poor animal welfare and increased mortality. Animal welfare is of increasing importance in salmon farming as the industry is under pressure to improve production and farming operations due to ethical concerns. Conventional smoltification assessments measure the chloride content in blood samples after exposing fish to salt water, or by detecting the presence of ion transport enzymes through analysis of samples of tissue from the gills. These methods take time and only a few salmon are usually tested from populations of several hundred thousand fish.

To assess the robustness of its HSI approach, SINTEF focused on collecting diverse data with variations in color, pattern, size and shape of fish using three different salmon rearing sites. Data was collected weekly in sync with the sites’ respective production and test schedules. A Shuttle SH110G computer with an Intel i7 processor had the BitFlow Image Capture installed to grab the frames of a specimen® Hyperspectral camera FX10 (Figure 1) equipped with a 23 mm / f.2.4 (OLE23) lens. Exposure settings were regularly adjusted according to local conditions and the condition of the fish. And because the smolt transition involves the salmon becoming more reflective, the shutter speed has been adjusted to keep the exposure within the dynamic range of the sensor. To make all data sets comparable, despite differences in ambient lighting conditions and exposure parameters, all were normalized for comparison using white and dark reference images.

The raw data obtained from HSI were multidimensional images of individual fish, including their background. Each layer of this multidimensional image represented a single grayscale image corresponding to the intensity of the reflectance measurement at a specific wavelength. When stacked, all the layers and reflectance measurements represented a 3D cube (Figure 2). A step-by-step procedure was used to process and analyze the data so that low dimensional spectral characteristics could be observed and classification of parr or smolts was made possible. The wavelengths have been optimized taking into account water temperature, dissolved oxygen, water opacity and color, as well as lighting and power regimes.

At the end of its study, SINTEF demonstrated an HSI system where only three wavelengths are needed to identify the smoltification state of Atlantic salmon, and that this system could serve as an additional or stand-alone verification tool in the fish production. In doing so, the researchers also paved the way for the manufacture of low-cost HSI instruments for use in production reservoirs or integrated into existing sorting and vaccination systems for faster, larger, and more cost-effective sampling. of the Atlantic salmon population.

For more information, visit www.bitflow.

Donal waide
+1 781-932-2900
[email protected]
Visit us on social networks:


Leave A Reply