Unmanned Aerial Vehicles for Marine Mammal Surveys

Home / Our Research / Research Projects / Unmanned Aerial Vehicles for Marine Mammal Surveys

Researcher

Amanda Hodgson

Collaborators

Insitu Pacific
Providing in kind support for the three years of the project, including staff for planning, engineering and operation, as well as the UAV system for trials, including imaging systems, and all support equipment

Professor Ken Pollock
Advising on quantitative approach to assessing detection probability

Dr Luis Mejias, Australian Research Centre for Aerospace Automation
Advising on development of a marine fauna detection algorithm for image analysis.

Objective

Develop methods for using unmanned aerial vehicles (UAVs) to survey marine mammals.

Specifically:

  1. Trial imaging systems
    Trial a suite of imaging systems and determine the most effective and efficient system for detecting and identifying marine mammals, with a focus on dugongs and humpback whales – so firstly, can we actually detect the animals confidently within images of some sort?
  2. Develop standardised method
    Given we can detect the animals, what methods do we then employ to ultimately determine distribution and abundance of the animals, i.e., how do we correct for detection probability.
  3. Compare manned with unmanned
    Once we’ve come up with the methods, the aim is to directly compare the results from traditional manned and UAV surveys of dugongs and humpback whales to test the efficacy of UAV surveys.

Aerial Surveys of Marine Mammals

Researchers commonly survey marine mammal populations to monitor their abundance and distribution. We use this information to determine the important habitat areas of a particular species and ensure their populations are stable.

Aerial surveys provide a broad-scale snap-shot of a population. We usually use these surveys to assess populations in a large area, such as the whole of Shark Bay.

To conduct the surveys we use a standard aircraft type flying at a standard altitude and speed. We fly along parallel transects and we have 4 observers on board the aircraft calling sightings as they see them in real time. A fifth person coordinates the flights and records the sightings.

Aerial surveys for dugongs are usually conducted by a team of 5 plus the pilot. The observers call all dugongs within a set area on either side of the aircraft. That area is marked by the rods attached to the outside of the plane.

Aerial surveys for dugongs are usually conducted by a team of 5 plus the pilot. The observers call all dugongs within a set area on either side of the aircraft. That area is marked by the rods attached to the outside of the plane.

Why UAVs?

The team from Insitu Pacific and Amanda with 'the bird' in Shark Bay

The team from Insitu Pacific and Amanda with 'the bird' in Shark Bay

Reduce costs: Aerial surveys are labour intensive and expensive – so I am hoping UAVs can reduce costs.

Eliminate human Risk: UAVs totally eliminate the human risk factor involved in having a team of 5 plus the pilot flying low and slow over vast expanses of ocean.

Better data: UAVs should provide more accurate sightings and identification of species, more precise locations and less biased
abundance estimates – at least that’s the goal.

The ScanEagle

The UAV for this project, the ScanEagle, is owned and operated by Insitu Pacific. You can check out the specs for the ScanEagle here.

First trial

Example image captured at ~500ft

Example image captured at ~500ft

The aim of our first trial, conducted in September 2010, was to see how well we could detect dugongs. The imaging system used for this first trial was an off the shelf Nikon SLR camera. We flew the UAV over an area where dugongs are commonly found and successfully captured over 600 images of these animals. The images were manually reviewed (by me!) and I could also distinguish dolphins, turtles, sharks, rays, seasnakes and birds.

Image analysis

Example image captured at ~1000ft

Example image captured at ~1000ft

With the help of Dr Luis Mejias from the Australian Research Centre for Aerospace Automation, we are also working on an animal detection algorithm which we hope will automate the image analysis process, or at least reduce the number of images that need to reviewed manually.

Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.