Marine Mammal Detection from Autonomous Surface Vehicles
Lead Research Organisation:
University of East Anglia
Department Name: Computing Sciences
Abstract
The use of autonomous surface vehicles (ASV) for marine mammal detection is increasing. The ultimate goal is to develop a passive acoustic monitoring (PAM) system to be deployed for long durations at sea reporting back detections of cetaceans and making recordings when necessary. There are many obstacles that stand in the way of current PAM systems being deployed in their current form, or even with significant modification. One is the amount of current required which is normally supplied from solar panels. Unless the panels are impractically large, they are unable to provide the current required. Data communication is a further problem. Using the Iridium satellite network is slow and very expensive, making it near impossible to send the required large datasets over the network. Sending audio data is even more problematic given its size. Accurate detection of cetaceans and reduction of misclassifications also remains an area that requires further effort to improve the quality of output.
The project will build on current knowledge within Gardline and other institutions, with the aim of designing a system capable of detecting cetaceans from an ASV either with real-time monitoring, if within WIFI range, or by sending meaningful packets of data if using Iridium. There are multiple stages to the process:
1. Using suitable signal processing/machine learning tools (such as available in Labview, Mathscript or MATLAB) design detection algorithms for impulsive and tonal sounds generated by cetaceans
2. Monitor ambient and anthropogenic underwater noise
3. Development of a trigger (based on, for example, a duty cycle, manual instructions or machine learning methods) to determine when sound files are to be recorded
4. Embed the system on a chip or real-time OS, such as the compactRIO
5. Design, implementation and testing of a GUI, with possible audio feed if within WIFI range for real-time mitigation
6. Create a log of detections and other acoustic metrics for satellite communications.
The project will build on current knowledge within Gardline and other institutions, with the aim of designing a system capable of detecting cetaceans from an ASV either with real-time monitoring, if within WIFI range, or by sending meaningful packets of data if using Iridium. There are multiple stages to the process:
1. Using suitable signal processing/machine learning tools (such as available in Labview, Mathscript or MATLAB) design detection algorithms for impulsive and tonal sounds generated by cetaceans
2. Monitor ambient and anthropogenic underwater noise
3. Development of a trigger (based on, for example, a duty cycle, manual instructions or machine learning methods) to determine when sound files are to be recorded
4. Embed the system on a chip or real-time OS, such as the compactRIO
5. Design, implementation and testing of a GUI, with possible audio feed if within WIFI range for real-time mitigation
6. Create a log of detections and other acoustic metrics for satellite communications.
People |
ORCID iD |
| Ben Milner (Primary Supervisor) | |
| William Vickers (Student) |
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| NE/R012156/1 | 01/10/2017 | 30/09/2022 | |||
| 1942138 | Studentship | NE/R012156/1 | 01/10/2017 | 31/08/2021 | William Vickers |
| Description | Industry Partner |
| Organisation | Gardline Limited |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | Collaboration on research output has been made in terms of technical knowledge of ASVs and suitable at-sea devices for the problem of detection and classification. |
| Collaborator Contribution | They have provide expert industry knowledge of sensors and devices suitable of working with our research output. |
| Impact | Three papers have been output with this partnership. |
| Start Year | 2017 |
| Description | Presentation at Conference Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Presented my work on right whale detection methods at a conference satellite workshop. 50 members of the workshop were present for the presentation. The talk was 15 minutes long and time afterwards was allocated for a Q & A session. |
| Year(s) Of Engagement Activity | 2019 |