© OpenStreetMap contributors
- Add External Layer
- Upload Shapefile
- Layer Tutorial
- Close
Use the checkbox () to show or hide a layer.
Use the radio buttons () to select a layer to use with the identify function.
- Layers
- Opacity
Available layers
(ctrl+c)
Search for marine data across UK organisations
- API
- How-To
- About
- Contact MEDIN
- Share
Metadata: A new application for automated video identification of marine species (AVIMS)
Abstract:
In the course of its environmental monitoring activities, the Scottish Government’s Marine Directorate collects a large amount of underwater video to, for example, obtain information on the numbers of fish in rivers or on species living on the seabed. Manual analysis of this footage is laborious and costly, but Machine Learning algorithms can now be used to automate such image analysis. The Marine Directorate commissioned the University of East Anglia to develop a web-based application to allow staff to create, train and execute machine learning-based (semi-)automated analysis of video footage without a need to interact with the underlying computer code. The application was tested using three diverse sets of video footage and found to be usable by staff without computer science or coding experience. The tool was able to detect and count sea pens in footage from towed underwater vehicles, salmon smolts at sea in underwater footage from towed fishing gear and adult salmon and sea trout in footage from underwater or overhead cameras at fixed locations on rivers. Improving the accuracy of the models at detecting and counting organisms of interest will require the use of larger annotated datasets in further training of the algorithms, but the current application provides a basis for further developing these.
Data holder:
Scottish Government (Marine Scotland)
Use constraints:
no limitations to public access
| Other details | ||
| Internal code | Internally assigned metadata identifier | 4010 |
| Title | The title is used to provide a brief and precise description of the dataset such as 'Date', 'Originating organisation/programme', 'Location' and 'Type of survey'. All acronyms and abbreviations should be reproduced in full. | A new application for automated video identification of marine species (AVIMS) |
| File Identifier | The File Identifier is a code, preferably a GUID, that is globally unique and remains with the same metadata record even if the record is edited or transferred between portals or tools. | Marine_Scotland_FishDAC_12473 |
| Resource Identifier | This is the code assigned by the data owner. | Marine_Scotland_FishDAC_12473 |
| Resource type | The resource type will likely be a dataset but could also be a series (collection of datasets with a common specification) or a service. | dataset |
| Start date | This describes the date the resource starts. This may only be the year if month and day are not known | 2021-02-15 |
| End date | This describes the date the resource ends. This may only be the year if month and day are not known | 2023-10-13 |
| Spatial resolution | This describes the spatial resolution of the dataset or the spatial limitations of the service. | 200.00 |
| Spatial resolution unit | This describes the unit of spatial resolution which for distance must be metres. | http://standards.iso.org/ittf/PubliclyAvailableStandards/ISO_19139_Schemas/resources/uom/gmxUom.xml#m |
| Frequency of updates | This describes the frequency with which the resource is modified or updated i.e. a monitoring programme that samples once per year has a frequency that is described as 'annually'. | unknown |
| Abstract | The abstract provides a clear and brief statement of the content of the resource. | In the course of its environmental monitoring activities, the Scottish Government’s Marine Directorate collects a large amount of underwater video to, for example, obtain information on the numbers of fish in rivers or on species living on the seabed. Manual analysis of this footage is laborious and costly, but Machine Learning algorithms can now be used to automate such image analysis. The Marine Directorate commissioned the University of East Anglia to develop a web-based application to allow staff to create, train and execute machine learning-based (semi-)automated analysis of video footage without a need to interact with the underlying computer code. The application was tested using three diverse sets of video footage and found to be usable by staff without computer science or coding experience. The tool was able to detect and count sea pens in footage from towed underwater vehicles, salmon smolts at sea in underwater footage from towed fishing gear and adult salmon and sea trout in footage from underwater or overhead cameras at fixed locations on rivers. Improving the accuracy of the models at detecting and counting organisms of interest will require the use of larger annotated datasets in further training of the algorithms, but the current application provides a basis for further developing these. |
| Lineage | Lineage includes the background information, history of the sources of data, data quality statements and methods. | In this project we developed a web application entitled Automated Video Identification of Marine Species (AVIMS). The project was funded by Scottish Government Contract, CASE/216380. The objective was to develop an automated video analysis capability with a user-friendly graphical interface which could be used by the Scottish Government’s Marine Directorate biologists and stakeholders’ non-specialist staff who do not have computer science and coding expertise. The Marine Directorate collects a large amount of underwater video for a number of different purposes. Analyses of these video data is time-consuming, often requires a skilled taxonomist and hence constitutes a significant draw on resources. The high cost of the analyses of this large amount of data often results in situations where only a subset of the available video is fully analysed. Consequently, automated video analysis software performing the above tasks would be highly desirable as it would reduce the costs of carrying out the analyses and allow for the analysis of all available data. It is expected that due to a steady and rapid improvements in new sensor/camera technology and their decreasing costs, the amount of video data available will only increase making the current processing bottlenecks even more acute. To achieve that goal, the Scottish Government funded an earlier piece of work in this area - Automated Identification of Fish and Other Aquatic Life in Underwater Video (Blowers et al. 2020) in which the authors reviewed current image and video analysis methods and how these can be applied to different types of video footage and data extraction requirements used by the Marine Directorate. The authors also made recommendations for how video analysis could be automated using state of the art and open-source machine learning (deep learning) algorithms. We have followed the recommendations of Blowers et al. (2020) closely, making a number of important refinements. Our machine learning solution has been integrated and deployed as a user-friendly web application - AVIMS. AVIMS allows users without computer science / coding experience to create, train and execute machine learning models without any need for interaction with the underlying code. The application supports computer vision models which fall into the common framework of detection of individuals from a predefined set of marine species, tracking detected individuals across the consecutive frames in the video, and finally, counting all distinct entities in the video for each species of interest (detect/track/count). The workflow of our web-based application implementing the above detect/track/count computer vision framework allows users to: create new survey types; define a set of species of interest for each survey type; upload video and image data for training machine learning models; annotate video and image data with objects of interest; create datasets comprising annotated data for training machine learning models; train machine learning models; upload new videos for the analysis by the machine learning models created in the previous steps of the workflow and view or download the analysis results. The web application uses distributed computing to perform the required tasks. The computationally intensive tasks which include training machine learning models and analysing new videos are sent to a separate machine specifically equipped to handle this type of computations where they wait for their turn in a queue. The web application has been tested by the development team and Marine Directorate scientists on several survey types including overhead in-river fish counters, salmon smolts entrained by a trawl and videos of the seabed. The initial machine learning models created in the web application have been shown to perform the required tasks. This said, in order for the system to achieve the level of accuracy that is expected from a practical application, the current small amount of annotated video data will need to be expanded to allow the machine learning models to better learn the appearance of various marine species of interest. This can be achieved from within the delivered AVIMS application. |
| Related keywords | ||
| Keyword | General subject area(s) associated with the resource, uses multiple controlled vocabularies | Marine Environmental Data and Information Network |
| General subject area(s) associated with the resource, uses multiple controlled vocabularies | Biological oceanography | |
| General subject area(s) associated with the resource, uses multiple controlled vocabularies | Environmental monitoring facilities | |
| General subject area(s) associated with the resource, uses multiple controlled vocabularies | Biological diversity maintained | |
| General subject area(s) associated with the resource, uses multiple controlled vocabularies | Sea-floor integrity supports ecosystem | |
| Geographical coverage | ||
| North | The northern-most limit of the data resource in decimal degrees | 63.88707 |
| East | The eastern-most limit of the data resource in decimal degrees | 2.605066 |
| South | The southern-most limit of the data resource in decimal degrees | 54.43328 |
| West | The western-most limit of the data resource in decimal degrees | -14.89295 |
| Responsible organisations | ||
| Role | The point of contact is person or organisation with responsibility for the creation and maintenance of the metadata for the resource. | pointOfContact |
| Organisation name | Scottish Government (Marine Scotland) | |
| Phone | +44 (0)300 244 4000 | |
| marinescotland@gov.scot | ||
| Role | The point of contact is person or organisation with responsibility for the creation and maintenance of the metadata for the resource. | pointOfContact |
| Organisation name | Scottish Government (Marine Scotland) | |
| Phone | +44 (0)300 244 4000 | |
| Delivery point | Mailpoint 11, Area 1B South, Victoria Quay | |
| Postal code | EH6 6QQ | |
| City | Edinburgh | |
| Country | United Kingdom | |
| marinescotland@gov.scot | ||
| Role | The custodian is the person or organisation that accepts responsibility for the resource and ensures appropriate care and maintenance. If a dataset has been lodged with a Data Archive Centre for maintenance then this organisation is be entered here. | custodian |
| Organisation name | Scottish Government (Marine Scotland) | |
| Phone | +44 (0)300 244 4000 | |
| Delivery point | Mailpoint 11, Area 1B South, Victoria Quay | |
| Postal code | EH6 6QQ | |
| City | Edinburgh | |
| Country | United Kingdom | |
| marinescotland@gov.scot | ||
| Role | The distributor is the person or organisation that distributes the resource. | distributor |
| Organisation name | Scottish Government (Marine Scotland) | |
| Phone | +44 (0)300 244 4000 | |
| Delivery point | Mailpoint 11, Area 1B South, Victoria Quay | |
| Postal code | EH6 6QQ | |
| City | Edinburgh | |
| Country | United Kingdom | |
| marinescotland@gov.scot | ||
| Role | The originator is the person or organisation who created, collected or produced the resource. | originator |
| Organisation name | University of East Anglia (UEA) | |
| Phone | +44 (0) 1603 456161 | |
| Delivery point | Norwich Research Park | |
| Postal code | NR4 7TJ | |
| City | Norwich | |
| Country | United Kingdom | |
| enquiries@uea.ac.uk | ||
| Resource locators | ||
| Locator URL | Web address (URL) that links to the resource | tbc |
| Locator function | Code that describes the function of the resource. ISO function code chosen from ISO 19115-1 Codelist | download |
| Dataset constraints | ||
| 20 Limitations on Public Access - Access constraints | otherRestrictions | |
| 20 Limitations on Public Access - Other constraints | This states any limitations on access to the data and uses free text. | no limitations to public access |
| 21 Conditions for Access and Use - Use limitation | This states any constraints on use of the data. Multiple conditions can be recorded for different parts of the data resource. If no conditions apply, then `No condtions apply` is recorded. This uses free text. | The following attribution statement must be used: Contains information from the Scottish Government (Marine Scotland) licensed under the Open Government Licence v3.0. |
| Version info | ||
| Date of publication | The publication date of the resource or if previously unpublished the date that the resource was made publicly available via the MEDIN network. | 2023-10-13 |
| Harvest date | The date which this record has been (re)harvested from the provider. | 2026-04-19 |
| Metadata date | The date when the content of this metadata record was last updated. | 2023-10-13 |
| Metadata standard name | The name of the metadata standard used to create this metadata | MEDIN Discovery Metadata |
| Metadata standard version | The version of the MEDIN Discovery Metadata Standard used to create the metadata record | Version 2.3.7 |