Facial recognition technology for next-generation fish-count surveys

In the latest generation of the CAM-Trawl system developed by the Fish Management Acquisition (FMA) program, ADL worked with NMFS Alaska Fisheries Science Center making key improvements to the computer portion of the CAM-Trawl system, including higher compute performance, standards-based vision software, more rugged enclosure and user-friendly LED indicators.


This article is contributed by ADL          Download PDF version of this article


The conservation and management of fish stocks relies heavily on fish-count surveys. In an effort to improve the shortcomings of these surveys, NOAA (National Oceanic and Atmospheric Administration) and its National Marine Fisheries Service (NMFS) developed a camera-based trawl (CAM-Trawl) to bring the power of image capture and facial recognition technology to best address this problem. The Alaska Fisheries Science Center is the research branch of the National Oceanic and Atmospheric Administration National Marine Fisheries Service responsible for research on living marine resources in the coastal oceans off Alaska and parts of the West Coast of the United States. This region of nearly 3 million square miles includes the North Pacific Ocean and the East Bering Sea which support some of the most important commercial fisheries in the world. These waters are also home to the largest marine mammal populations in the nation.

The conservation and management of fish stocks relies heavily on fish-count surveys. Traditionally, this has been done through the use of fishing trawlers set up to do acoustic or bottom trawling which cast enormous nets into the sea to capture as many fish as possible over a specified area. These fish are then brought on-board and manually counted to develop the trawl survey. This methodology suffers from a number of shortcomings: errors associated with extrapolating from a small area survey to large area estimates, errors associated with extrapolating from the relatively long period of time necessary to gather and count fish over a region to real-time characteristics of the fish population, the relatively high cost of time and equipment for manual trawl surveys, the fact that some small fish species of interest are too small to be caught by the net mesh, and lastly, the fact that killing fish in the course of a trawl survey affects local fish populations which can sometimes be dangerously low.

Figure 1. First generation CAM Trawl Picture

 

As a result, NOAA (National Oceanic and Atmospheric Administration) and its National Marine Fisheries Service (NMFS) have been working for a number of years on a camera-based trawl (CAM-Trawl) technology to bring the power of image capture and facial recognition (loosely termed, Fishal Recognition) technology to best address the problem. Early generations of this CAM-Trawl system used the lengthy process of image capturing, storing images, and then removing the storage media for image analysis at some later time back at the lab.

In the latest generation of the CAM-Trawl system developed by the Fish Management Acquisition (FMA) Program, ADL Embedded Solutions worked closely with the NFMS Alaska Fisheries Science Center to make key improvements to the computer portion of the FMA CAM-Trawl system. These include the following. Upgrading to GeniCam-compliant vision platform to take advantage of the latest camera technology and image recognition algorithms. Upgrading to marine quality system enclosure with IP-67 rated ingress protection. Upgrading to a quad-core Intel Core i7 processor to enable real-time processing of image data. Design and building of a rugged small form factor system for mounting  flexibility and ease of storage and transportation. The resulting FMA computer solution from ADL has helped achieve all the stated goals for this project. Namely, real-time fish-count data analysis capability for NOAA marine researchers to aid in their fish conservation efforts is now a reality.

Figure 2. The housed ADL system

 

The new system includes an ADL main control computer shown at left and an ADL image acquisition computer on the right in figure 2.  System features include: stainless steel, water-proof (IP67) enclosures, Intel Core i7 processors, IP67-rated water-proof circular connectors with protective caps, LED activity lights for various functions, removable drive assemblies, and Topside Handrail Mounting Adapter. The ADL image acquisition computer (Vision Box) is responsible for: camera interface using up to 6x GigE ports, image capture, real-time image recognition using processing algorithms on the Intel Quad Core i7 processor, and image storage including metadata for data/time, fish identity, etc.

The ADL control computer typically resides in the wheelhouse. It will steadily monitor a number of external sensors including geo data, time, pressure sensors, RFID tag readings and will orchestrate one or more Vision Boxes based on sensor input. Remote power on/off, clock syncing, start/stop image acquisition, etc is all dictated by the ADL control computer in a one-to-many relationship.

The results for the new FMA system have been very positive after experimental trawl surveys in 2016. Work is now underway to standardize the key components of the new system as a means of promoting the adoption of this real-time Fishal Recognition FMA system on many more surveys in the near future.


Related


Tackling the challenges of IoT device development

This article describes the ARIS (Arrow Renesas IoT Synergy) development platforms, which leverage the Renesas Synergy framework and address the specific needs of IoT device developers in ways that...

Embedded modules simplify processor integration

This article presents the advantages provided by the new TI Sitara AM572x processor integrated in the modules offered by Phytec. By Florian Gross, Texas Instruments and Ralf Orschau, Phytec&nb...

Cooling Options for PET and SPECT Scanners

Thermal management of medical imaging systems is more challenging than ever. Given the complexity of some PET and SPECT systems, the use of a custom designed liquid cooling systems with plug-and-play ...

IP-classes in rugged computing

Far away from protected server rooms or automation lines in air-conditioned production halls, embedded computers need to withstand the toughest conditions in modern vehicles and moving machines, o...

 


Taking SiC Mainstream: The Story of Littelfuse Power Semiconductors

Since 1964, Littelfuse has brought its legacy of stability and reliability in circuit protection to the power semiconductor space. Now, the company is pioneering a series of in-house technology breakt...


Intel and Wind River Lead Technology Innovation Delivering Resilient and Secure Functional Safety Solutions

Together, industry leaders Wind River and Intel are delivering innovative Industrial IEC 61508 functional safety certification solutions that reduce project risk. A holistic approach is used to combin...


Wind River Titanium Control Advances Industrial IoT

Gareth Noyes, Chief Strategy Officer at Wind River introduces Wind River Titanium Control, a software platform that enables critical infrastructure companies to cost-effectively evolve aging legacy co...


WSI's OLED Professional innovations create more value for You.

WSI are the PMOLED manufacturer and our factory located in Chun-Nan in Taiwan. Our products are the market leader and pioneer in PMOLED module, including the monochrome, area colors and full color one...


SKIPPER UBT21 - a Bluetooth 4.0 USB serial adapter for industrial and medical use

SKIPPER UBT21 is a Bluetooth 4.0 USB serial adapter for industrial and medical use. It incorporates a Bluetooth Dual-Mode Stack, supports ranges of up to 300 meters and transferrates of 720 kbit/s (ne...


Three of a kind - Versatility based on Low Power ARM Cortex-A15

At this year's Embedded World, MEN has presented three low power, ARM Cortex-A15-based solutions on different form factors: a VMEbus SBC, an industrial box PC and a COM Express Mini module. All so...


Enabling Embedded IoT

Eurotech, a long-time leading provider of embedded systems and a global leader in IoT enablement, showed its new modules and Multi-service IoT Gateways at Embedded World 2017. The newly introduced Eu...


PLS’ UDE and new UAD2next allow more powerful trace analysis of embedded multicore systems

The new Universal Debug Engine 4.8 from PLS Development Tools offers a bunch of new and improved features for trace analysis of embedded multicore systems. With the new access device UAD2next PLS cont...


Disruptive technologies

Rahman Jamal, Global Technology & Marketing Director, National Instruments, talks about disruptive technologies in the consumer world, but also in measurement, automation, and the embedded industr...


AdaCore Announces Availability of QGen Debugger at Embedded World 2017

Jose Ruiz, technical lead at AdaCore for the company's QGen automatic code generator toolset for model-based development, discusses that product and explains what differentiates it from other prod...


SECO IoT roadmap: from the proof of concept to the market

During Embedded World 2017 Gianluca Venere, SECO Director of Global Sales, leads us to discover the company's Industrial IoT roadmap showcased at SECO's main booth, along with the latest UDOO ...


Internet of Chocolate

HCC show off an embedded chocolate vending machine using MQTT to connect to a broker in the cloud. There is an important message behind this cool demo – security and reliability of embedded soft...