Steamlined and efficient artificial-intelligence assisted underwater video analysis
The Scottish Government seeks to develop demonstrably sustainable aquaculture which places enhanced emphasis on environmental protection […and] to reform and streamline regulatory processes so that development is more responsive, transparent and efficient. Our ‘SEA-AI’ research will enable the collection of high-quality seabed-imagery and its rapid, cost-effective analysis that will facilitate consistent and transparent decision-making to the benefit of the entire Scottish aquaculture sector and beyond. SEA-AI has the direct involvement of both industry and regulators.
The ‘Strategy for Marine Nature Conservation in Scotland’s Seas’, was developed as part of delivering obligations under the Marine (Scotland) Act 2010 and requires the identification and protection of Priority Marine Features (PMFs). Under the National Marine Plan (2015), key regulatory and advisory bodies such as SEPA and NatureScot (NS) must consider PMFs in relation to evaluating proposed marine developments including fin-fish aquaculture. PMFs particularly relevant to aquaculture-impacts include beds of maerl and bivalves, northern sea fan and sponge communities, seagrass beds and polychaete aggregations. The analysis of seabed video footage plays a key role in the assessment of likely impacts of planned aquaculture developments (including expansion proposals) to PMFs. To make this assessment, SEPA/NS require applicants to submit video footage of the seabed around the proposed development site. Currently, in assessing the application, the supplied footage is manually reviewed, sometimes frame-by-frame, a task which is time-consuming, costly, subject to analyst-bias and which can result in rejections (and re-survey requirements) where it does not meet quality standards. Under new (draft) guidelines, SEPA is quadrupling the amount of seabed imagery required in support of site expansion proposals and developing new sites.
Recent innovations in artificial intelligence (particularly convolutional neural nets, CNNs), have revolutionised image analysis.
Our challenge is to develop protocols and algorithms enabling cost-effective, accurate, rapid, and consistent seabed-image collection and analysis that will facilitate timely, transparent decision-making.
We will meet our challenge by developing standardised procedures for:
1. Image (data) capture ensuring that the imagery is of sufficient quality for CNN-assisted assessment
2. Video quality checking and the generation of corrected geo-referenced orthomosaics
3. The use of CNN machines to assist human experts in the identification of PMFs (both biotopes and key taxa).
Working with our partners, SEPA, Nature Scot and Scottish Sea Farms, we will embed these new approaches into the sector via SEPA/Nature Scot published guidance documentation and will make available the trained CNN to any user. By demonstrating the potential of CNNs, we will deliver a transformation in the demonstrably sustainable development of the global aquaculture sector including that based in Scotland.
During SEA-AI we will deliver image quality assessment algorithms (A), and generate geo-referenced ortho-mosaics (B, survey track and detail from track illustrated).
At SAMS we are continuing to develop AI machines to distinguish taxa: from raw images (left) we develop machines by training them on 20 – 100 annotated images (centre). The taught-machine is then assessed against the classification (shown as 3 separate colours in this model) it makes on images it has not previously ‘seen’ (right).
Role of SAMS on project
Developing deep-learning neural nets (artificial intelligence) to assist in underwater video characterisation