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

WOBURN, MA, SEPTEMBER 21, 2021 — Smoltification is a complex series of physiological changes that allow young Atlantic salmon to adapt from living in fresh water to living in seawater. In salmon farming, this transition from “parr” to “smolt” is controlled using lights or functional feed to ensure a continuous and predictable supply of fish to grocery stores, restaurants and other seafood markets.

Scientists at SINTEF, one of Europe’s largest independent research institutes located in Trondheim, Norway, recently developed a hyperspectral imaging (HSI) system1 to study the vital aspects in detecting smoltification, relying in part upon a BitFlow Camera Link frame grabber to grab high-speed video frames for analysis at more than 100 frames-per-second.

The ability to verify smoltification is critical since incomplete seawater adaptation may result in 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 chloride content in blood samples after exposing fish to saline water, or by detecting the presence of ion-transporting enzymes through analysis of tissue samples from gills. These methods are time-consuming so only a few salmon are typically tested from populations of several hundreds of thousands of fish.

To evaluate the robustness of its HSI approach, SINTEF placed emphasis on collecting diverse data with variations in fish color, patterning, size, and shape using three different salmon farming sites. Data were collected weekly in synchronization with the sites’ respective production and testing schedules. A Shuttle SH110G computer with Intel i7 processor had the BitFlow frame grabber installed to grab frames from a Specim® FX10 hyperspectral camera (Figure 1) equipped with a 23 mm/f.2.4 (OLE23) lens. Exposure settings were regularly adjusted depending on local conditions and the state of the fish. And because smolt transition involves salmon becoming more reflective, shutter speed was adjusted to keep the exposure within the sensor’s dynamic range. To make all data sets comparable, despite differences in ambient lighting conditions and exposure settings, 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 gray-scale 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-wise procedure was used to process and analyze the data so the low-dimensional spectral characteristics could be observed, and classification of parr or smolt made possible. Wavelengths were optimized by factoring in water temperature, dissolved oxygen, water opacity, and color, as well as lighting and feeding regimes.

Upon conclusion of its study, SINTEF demonstrated a HSI system where only three wavelengths are needed to identify smoltification status of Atlantic salmon, and that this system could serve either as a supplementary or free-standing verification tool in fish production. In doing so, the researchers also laid a pathway to manufacturing low-cost HSI instruments for use in production tanks or integrated in existing sorting and vaccination systems for faster, wider and more cost-effective population sampling of Atlantic salmon.

BitFlow Returns to VISION Trade Show in Stuttgart, Germany

WOBURN, MA, SEPTEMBER 15, 2021 — BitFlow, a leading innovator in frame grabbers for industrial and commercial imaging applications, today announced details of its in-person participation in VISION, the world’s leading trade fair for machine vision, to be held in Stuttgart, Germany, October 5 to 7, 2021. BitFlow encourages VISION attendees to visit booth #10H46 to engage with its trained engineers and see firsthand its newest CoaXPress and Camera Link frame grabbers.

Because VISION could not be held last year due to the pandemic, its relaunch is a positive signal to the international machine vision market. More than 250 companies will take part in VISION, providing visitors with a current overview of the wide range of machine vision products, software and services now available, together with global insights into future technologies.

“Coronavirus halted VISION and other industry events in 2020, making us all acutely aware of the value of face-to-face, in-person business meetings,” said Donal Waide, Director of Sales, BitFlow, Inc. “Keeping connected and moving forward with events like VISION is critically important for economic recovery. We are very excited to get back on the road to meet with our customers, colleagues and distribution partners.”

BitFlow will showcase at VISION its entire portfolio designed to meet the most demanding imaging needs within diverse industries such as machine vision, quality control, defense, medical research and robotics. In addition, BitFlow will join with several of its camera partners to present live demonstrations of its high-speed frame grabbers, including the new line of fan-cooled Cyton CXP4-V CoaXPress models engineered for use with small form-factor fanless computers, like the NVIDIA® Jetson Xavier Developer Kit.

BitFlow CoaXPress Frame Grabber Used in Groundbreaking New 3D Imaging System

WOBURN, MA, JULY 16, 2021 — Research scientists with the Energy Materials Telecommunications Center, National Institute for Scientific Research in Quebec, Canada, have developed a groundbreaking technique to acquire 3D images at over 1000 frames per second with resolution as high as 1180 x 860 — far beyond the capabilities of available systems today — by eliminating information redundancy in data acquisition. Certain to open new opportunities for 3D applications, the dual-view band-limited illumination profilometry (BLIP) with temporally interlaced acquisition (TIA) system or simply BLIP-TIA, relies upon the BitFlow Cyton-CXP CoaXPress frame grabber to transmit images from two CMOS cameras to a computer for processing at rates surpassing 12.5 Gb/S.

Existing 3D systems based on the widely used technique of Fringe Projection Profilometry (FPP) have two main limitations. First, each camera captures the full sequence of fringe patterns, therefore imposing redundancy in data acquisition that ultimately clamps the systems’ imaging speeds. Second, the cameras are placed on different sides of a projector. This arrangement often induces a large intensity difference from the directional scattering light and the shadow effect from the occlusion by local surface features, both of which reduce the reconstruction accuracy.

To overcome these limitations, the scientists developed BLIP-TIA with a new algorithm for coordinate-based 3D point matching from different views. Implemented with two cameras from Optronis placed side-by-side and the BitFlow Cyton-CXP frame grabber, it allows each camera to capture half of the sequence of the phase-shifted patterns, reducing the individual camera’s data transfer load by 50%, and freeing up capacity to transfer data from more pixels on each camera’s sensor or to support higher frame rates.

Besides its high-speed data transfer, the Cyton-CXP two-channel frame grabber incorporates the Gen 2.0 x8 PCI Express bus interface on its back-end for high speed access to host memory in multi-camera systems such as the BLIP-TIA. It also allows control commands, triggers and power to be sent to and from cameras over the same coaxial cable to simplify overall design.

To verify high-speed 3D surface profilometry, the researchers used BLIP-TIA in a number of tests including recording non-repeatable 3D dynamics by imaging the process of glass breaking while being struck by a hammer. The growth of cracks and the burst of fragments with different shapes and sizes were clearly shown in the reconstructed 3D images.

Besides technical improvements, researchers are now exploring new applications for BLIP-TIA. For example, it could be integrated into structure illumination microscopy, frequency-resolved multidimensional imaging, dynamic characterization of glass in its interaction with the external forces, recognizing hand gestures for human–computer interaction, in robotics for object tracking and reaction guidance, vibration monitoring in rotating machinery, and for behavior quantification in biological science.

BitFlow Offers Starter Kit Version of BitBox High Density I/O Solution

Connect and control up to 36 devices from one BitBox

WOBURN, MA, MARCH 11, 2021 — BitFlow, one of the world’s leaders in machine vision innovation, now offers a starter kit version of its popular BitBox™ device, providing designers with a simple, cost-effective means to connect and continuously control up to 36 strobes, solenoids, actuators and other accessories in high-density input/output (I/O) applications, plus acquire data input from equipment ranging from photo detectors to triggers.

“In general, BitFlow frame grabbers come with a fairly large number of inputs and outputs, but for some systems this is simply not enough,” explained Donal Waide, Director of Sales for BitFlow. “Now, instead of purchasing another device to manage the I/O which adds expense and requires another slot, driver and SDK, they can simply deploy our BitBox which is straightforward and can be controlled solely by a BitFlow frame grabber, using the same SDK.”

The BitFlow BitBox kit (IOB-ISO-C144-KIT) contains everything a system integrator needs to save time and money, while maximizing space inside a machine. It provides 36 inputs and 36 outputs in a compact, DIN-rail mounted form factor that supports TTL, LVDS, open collector, opto-isolated and 24V signaling. All transmitters and receivers are situated in the BitBox on the DIN rail in close proximity to other equipment. This configuration isolates noisy, high-voltage signals generated by a PC, keeping those signals away from the system where they could cause data drops, video problems, malfunctions and random network errors. A 15-wire proprietary cable runs between the BitBox and frame grabber. Maximum cable length is 10 meters, providing flexibility in positioning equipment within the machine.

The BitFlow BitBox contains 12-pin connector blocks that can be added or removed, but will still lock securely in-place for factory floor reliability. Blocks are grouped by signal type and have snap-in connectors that permit fabrication of a harness without directly wiring the BitBox. 

For information, visit

Google Healthcare Relies on BitFlow CoaXPress Frame Grabber for Augmented Reality Microscope

WOBURN, MA, AUGUST 6, 2020 – BitFlow frame grabber technology has been incorporated into a prototype Augmented Reality Microscope (ARM) platform that researchers at Google AI Healthcare (Mountain View, CA) believe will accelerate the adoption of deep learning tools for pathologists around the world in the critical task of visually examining both biological and physical samples at sub-millimeter scales.

The application driving the ARM platform runs on a standard off-the-shelf computer with a BitFlow Cyton CoaXPress (CXP) 4-channel frame grabber (CYT-PC2-CXP4) connected to an Adimec S25A80 25-megapixel CXP camera for live image capture, along with an NVidia Titan Xp GPU for running deep learning algorithms. Using Artificial Intelligence (AI), the platform enables real-time image analysis and presentation of the results of machine learning algorithms directly into the field of view.

Importantly, the ARM can be retrofitted into existing light microscopes found in hospitals and clinics around the world using low-cost, readily-available components, such as the BitFlow Cyton frame grabber, and without the need for whole slide digital versions of the tissue being analyzed. This innovation comes as welcome news: despite significant advances in AI research, integration of deep-learning tools into real-world diagnosis workflows remains challenging because of the costs of image digitization and difficulties in deploying AI solutions in microscopic analysis. Besides being economical, the ARM platform is application-agnostic and can be utilized in most microscopy applications.

According to Google researchers, opto-mechanical component selection were driven by final performance requirements, specifically for effective cell and gland level feature representation. The Adimec camera’s 5120×5120 pixel color sensor features high sensitivity and global shutter capable of capturing images at up to 80 frames/sec, while the BitFlow Cyton CXP-4 has a universal PCI-E interface to the computer that simplifies set-up. The eMagin SXGA096,1292×1036 pixel microdisplay mounted on the side of the microscope includes an HDMI interface for receiving images from the computer. This opto-mechanical design can be easily retrofitted into most standard bright field microscopes. Including the computer, the overall cost of the ARM system is at least an order of magnitude lower than conventional whole-slide scanners, without incurring the workflow changes and delays associated with digitization.

The basic ARM pipeline consists of a set of threads that continuously grab an image frame from the camera, debayer it to convert the raw sensor output into an RGB color image, prepare the data, run the deep learning algorithm, process the results, and finally display the output.

Google researchers believe that the ARM has potential for a large impact on global health, particularly for the diagnosis of infectious diseases, including tuberculosis and malaria, in developing countries. Furthermore, even in hospitals that will adopt a digital pathology workflow in the near future, ARM could be used in combination with the digital workflow where scanners still face major challenges or where rapid turnaround is required as is the case with cytology, fluorescent imaging, or intra-operative frozen sections.

Since light microscopes have proven useful in many industries other than pathology, the ARM can be adapted for a broad range of applications across healthcare, life sciences research, and material science. Beyond the life science, the ARM can potentially be applied to other microscopy applications such as material characterization in metallurgy 12 and defect detection in electronics manufacturing.