Cacophony Blog

22 Jul 2023 - 14:50

We are proud to announce that, as part of the latest Tools To Market investments, DOC are now providing funding for two of our projects; the first to deliver a new version of our thermal camera, and the second to deliver a number of improvements to our monitoring platform, including adding support for trailcams.

28 Nov 2022 - 16:21
Around New Zealand, a number of highly dedicated people have spent some of their precious funds to install predator-proof fences to protect sanctuaries.  Fences leak, predators often finding ways to get around the ends of the fence.  Today we share some very pleasing updates from Mamaku Point on Rakiura. 
5 Sep 2022 - 17:18

One of the most important components in our set of tools is a digital trigger.  We define a digital trigger as using a camera to decide when to activate a trap rather than using a trip plate or motion sensor.  Such a trigger would allow trap designers (including us) to design open trap entrances without having to worry about the risk of harming our precious taonga.  So we've been working on just such a trigger and today we'd like to share some of our findings with you.

30 Aug 2022 - 10:53

Conservation projects need to make hard decisions based on the cost of deployments and the cost of a camera network can be considerable.  As with any technology purchase, it can be misleading to consider only the initial purchase cost of the device - there are a number of factors that influence the Total Cost of Ownership (TCO) of your camera setup.  We've worked with DOC to look into what the true TCO of a camera set up is. 

4 Jul 2022 - 20:54

One of the most common questions we get asked is how accurate our Artificial Intelligence(AI) solution for predator identification is. But we suggest more useful questions are:

  • How accurate is predator identification at different distances? 
  • How does accuracy compare to humans?
  • How accurate does it need to be in order to be useful?
21 Jun 2022 - 12:20
We are proud to be part of the latest round of funding from Predator Free 2050 Ltd.  The funding will allow us to take the trap to the next level with the development of an auto-reset mechanism, an intelligent trigger to keep our taonga safe, and an automated kill and clear mechanism.  
12 Jun 2022 - 22:38
We've had our trap out in the field and, over a sustained period, the trap has shown a catch rate 10x higher than traditional traps. 

10 Feb 2022 - 11:18

2021 was a very productive year for us here.  So we thought it was time for a recap of our products and an overview of what the products can do for you.  Today we focus on our Thermal Camera.

 

26 Jan 2022 - 11:25

There are some really good comparisons between NZ’s Covid-19 response and its predator elimination strategy. Most of the world has no chance of a successful Covid-19 elimination and hence are using methods for Covid-19 suppression. For Covid, NZ was applying an elimination strategy that acknowledges there will still be cases but they can be controlled. With predators, NZ has great success with elimination on islands and in fenced sanctuaries. There are now numerous projects attempting elimination on the mainland. An analogy with Covid is useful as it helps understand the key tools needed for an elimination strategy. 

 

2 Dec 2021 - 15:30
We've been thinking again.  There is an interesting analogy to be drawn between how we catch fish and how we catch predators.
5 Nov 2021 - 16:32
The team have been busy again - new software features, new products from our partners at 2040.co.nz, and an update on manufacturing.  Check out the latest newsletter here: https://www.2040.co.nz/blogs/newsletter/battery-meters-car-batteries-trap-updates 

 

8 Sep 2021 - 15:50
Some great research on hedgehogs in the McKenzie Basin by Nick Foster.
23 Aug 2021 - 15:57
A brief update sharing more video evidence of low interaction rates on tree-mounted devices. 
10 Aug 2021 - 12:24

New software updates to our online portal and our Sidekick app.

26 Jul 2021 - 12:57

Our high catch rate trap has now been out in the wild in a few areas so it's time to give you a brief update. We've identified some key next steps in the trap's development. 

21 Jun 2021 - 10:45

One of our customers has had our thermal camera in front of a tree based possum and rat trap for three weeks in the hope of seeing how well it performed. In this case the trap was the AT220 from NZ auto traps. 

2 Jun 2021 - 18:18

The Cacophony Project exists to put better tools in the hands of everyone engaged in the battle to make Aotearoa Predator Free.  So when we hear DOC's Program Manager for Predator Free 2050 excited about our tools having the possibility to "really change the game", it helps confirm our belief that we're on the right journey.

27 May 2021 - 15:03

For a period a 3 months last year we had the pleasure of having Sapphire Hampshire join the project as an intern.  Saphy was a Master's student in International Nature Conservation at Lincoln University, from Georg-August-Universität in Göttingen.

 

27 May 2021 - 14:40

Our delivery partner at 2040.co.nz has just announced a number of improvements that are now going live.

3 May 2021 - 10:34
Proud moment for us here at the project as we see our camera spotting the invader at Shakespear National Park
29 Mar 2021 - 13:08
Our high interaction rate traps are out in the field catching predators at multiple sites. Today we share some early results and a short update on some of the improvements we're making as we learn more.  One of our traps at a test site in Akaroa caught 8 possums in 12 nights (update - and 8 more in the following 6 weeks) - read on for details.

24 Feb 2021 - 15:48

Once an area has been cleared of predators, how can we defend it?  The traditional answer has been static fences.  Today we introduce a new concept - making those fences active.

11 Jan 2021 - 12:38

A group from Auckland University has been training AI models using our thermal video library.

 

8 Dec 2020 - 17:01

In the area of monitoring, we suspect that Cacophony’s thermal cameras have the potential to deliver three keys benefits:

  1. A substantial reduction in the effort required to monitor a reserve
  2. A substantial increase in the amount of data produced from monitoring efforts
  3. A substantial increase in the quality of data produced from monitoring efforts
But those are just assumptions, and they need challenging.  So a field experiment was born.  And today we share some of the results.
28 Nov 2020 - 11:00
The Cacophony Project is pleased to confirm our agreement with Predator Free 2050 to fund the development of our Blind-Snap Model A Trap. 
15 Nov 2020 - 16:46

Earlier in the year we were asked if we could expand the machine vision used with our thermal camera to automatically detect wallabies with the goal of monitoring and controlling the wallaby population. 

16 Sep 2020 - 13:01

If you're a regular reader of our blog, it might be easy to get the impression that we are randomly trying lots of things.  The reality of life on the project is somewhat different - there is a targeted structure to what we are doing. This post gives a summary of that strategy.  To bring back the Cacophony of native fauna in NZ there are a number of separate parts of the puzzle that we are trying to solve. What follows is a summary of each sub-goal as we see it along with an indication of where we are up to with our progress.

8 Sep 2020 - 13:19

Our previous blogs have highlighted how most predators in well trapped areas just walk past existing traps. This blog shows our first attempt at a device designed to trap hard to trap predators or re-invading predators. At the moment the competition for this sort of application is pretty much manual hunting or very intense trapping and baiting (which often never gets to zero).

1 Sep 2020 - 18:18

In recent blog posts we have gone into detail on different trapping strategies.  We chose to do this because we are convinced that many approaches that may seem intuitively to be great strategies won’t actually make much of a difference to the elimination of predators. Our camera experiments have shown consistently and across a number of different environments that, for an area that has been trapped for a while, there is a persistent population that avoids existing traps.  Today we introduce a collection of approaches and ideas that we believe can actually improve the predator interaction rate and give us a real chance of achieving our predator-free goals.