Group

Autonomous Camera Traps for Insects / Feed

Camera trapping for insects is becoming a reality using advances in camera, AI, and autonomous systems technologies. This group discusses the latest advances, shares experiences, and offers a space for anyone interested in the technology, from beginners to experts.

event

The Variety Hour: March

Join us on Wednesday to talk about building autonomous camera traps for insects, updates about the arbimon tool for bioacoustics, the Biodiversity Accelerator+ which is now open for applications, and to hear about an...

0
See full post
discussion

Exploring storage options for mass data collection

Hi all. I'm currently exploring options for data storage en masse. With our project we will be collecting 24hr hydrophone data, drone video 6hr per day, photography &...

1 0

Hi Adam!

I mostly live within the ecoacoustics space so I'll just speak on the hydrophone part of your request; Arbimon is a free web/cloud-based platform with unlimited storage for audio files. We've got an uploader app as well for mass-uploading lots of files. There's also a bunch of spectrogram visualization/annotation tools and analysis workflows available. It's AWS running under the hood.

I have some experience working directly with AWS & Microsoft Azure, and I've found personally that AWS was more user-friendly and intuitive for the (fairly simplistic) kinds of tasks I've done.  

See full post
discussion

Insect camera traps for phototactic insects and diurnal pollinating insects

Hello, we developed an automated camera trap for phototactic insects a few years ago and are planning on further developing our system to also assess diurnal pollinating...

4 0

Hi Sarah,

in general yellow is probably the color which attracts the widest range of different pollinators, however there are especially many bee species who are mostly (or only) attracted by e.g. white or blue/violet.

We chose the "flower" colors and shapes for our current platform version only by trying to mimic some common flowering plants like Daucus carota, Ranunculus sp. and Cichorium intybus. From our preliminary tests last year I would say there is definitely some attraction but probably not optimised for a wider range of taxa (or specific taxa if a kind of "attraction filter" should be implemented).

Currently we are running several experiments to test different materials, colors (there are many shades of yellow...), shapes and UV reflectant properties. We are especially interested in hoverfly monitoring, so this is our target group for the tests.

@tom_august, @albags and Abra Ash are also doing research on different kinds of artifical flowers and their attraction potential (more focused on bees and bumblebees).

Hi Maximiliian,

Thank you for your response and the very useful information. I've read that Diptera are less attracted to fluorescing materials than non-flourescing materials (I'm assuming you've probably read the paper assessing pan-trap colours and the capture rate of different insect orders too).

Our aim is to attract the widest range of different pollinators, so we should probably be using all three colours in order to attract the widest spectrum of pollinating insects. Having little experience in this field I'm not sure whether using flower shapes or just areas with these colours would be best for attracting pollinators, if @tom_august  or @albags or anyone else has some info from their experience on the attraction potential of different shapes and colours that they would be willing to share I'd be very grateful.

Thanks for this great and supportive community!
Sarah

Hi Sarah,

I am working with @Max_Sitt on the same project to develop artificial flowers as a platform for hoverfly monitoring (also as a landing platform for his camera trap).

We have preliminary results on the attractiveness of different shapes and colors on two hoverfly species in the lab. We can not help you with useful results without fieldwork data, but maybe some ideas.

According to the literature, bees will probably go for different (structurally more complex) flowers than hoverflies. If this is the case, you won't find a highly attractive "one-fits-all" solution for the shape or any other floral characteristic. However, the color could be the most basic flower trait and, therefore, could address a variety of pollinators. With a simple structure and a universally attractive color, you might have a chance for a good trade off between attractiveness and species spectrum.

The spray colors used as standard colors for pan traps in Germany (according to C. Westphal) could be a good start for you:

Sparvar 3107 "Leuchtblau", Sparvar 3104 (aka RAL 1026) "Leuchtgelb" and Sparvar "Leuchtweiß" 3108

These strong fluorescent colours have also been tested in Diestelhorst et al. 2014 (only available in German) and they showed a good response of pollinators in general for the white and yellow color in comparison with non-fluorescent colors. If you look for publications by Klaus Lunau, you will find a lot on fluorescent colors and UV-reflectance in (artificial) flowers. But once again, there seems to be no universal pattern among all flowers and all pollinators that we can use to trigger landings.

Currently, we are experimenting with fluorescent, translucent PMMA aka Suncatchers. When we sprayed orange Suncatchers with a strong fluorescent neon yellow on the bottom side, they were very attractive to one of our tested species. Their "sun catching effect" is then visible all over the surface as a diffuse glowing.

We also had good experiences with some glass droplets that resemble nectar. Specifically a half-sphere of 5 mm diameter with mirror foliage underneath. You can get them at a DIY store.

My best guess would be to paint a platform all green and then have circles in different diameters (2-8 cm) sprayed on them with the three pan trap colors. Add some glass droplets, and you might be good for now. However, the field trials will show how much my guesses are worth here:)

Best regards,

Max

See full post
discussion

Monitoring airborne biomass

We are producing hard- and software for small scale research  radars to monitor airborne biomass automatically. We can distinguish birds, bats and insects through day and...

2 0

Looks like you want to have a read of this thread: 

Our project in very short is, setting up a sensor network for monitoring airborne biomass, mainly insects, birds and bats in near realtime, and to develop a forecast model to be used for mitigation with respect various types of human-wildlife conflicts (e.g. wind power, pesticide application, aviation). Our expertise is mainly in radar monitoring, but we aim on add insect camera information to be merged with the quantitative biomass measeurments by radar.

See full post
discussion

Project introductions and updates

Tell us about your project!If you are just starting out with autonomous camera traps for insects, or if you are a seasoned expert, this is the place to share your...

25 1

I'm happy to vouch for this system. We tried it out in Panama alongside the Diopsis and AMI-trap and it got some great results. The UV light is a little weak, and it might not fair well in the rain, but at this price point it is very accessible for citizen scientists, and the image quality we got was excellent. The app i also very easy to use, nice job!

The AMI-Trap

Combining robust lighting for attracting insects with high resolution cameras, the AMI-trap can provide practical and cost-effective solutions for standardised monitoring. AMI-traps have been deployed in the UK, Canada, USA, Cyprus, Panama and Argentina, with plans to expand further.

The AMI-Trap is an iteration of the design first published by Bjerge et al 2021, and has been developed in partnership with those authors as well as researchers in Europe and North America. An open AI-process workflow has been developed at Mila (see an earlier post in this thread), which takes images from the AMI-Trap, locates and tracks individuals, and classifies individuals where possible.

AMI-traps are solar powered and run on a programmable schedule. As a result they can be left out for an entire field season to collect data, however checking every now and then to see if they are okay is recommended! The hardware has been tested underwater and in a 60C oven to unsure robustness in field conditions. The development of the AMI-Trap hardware at UKCEH, and the development of the AI, edge processing, standards and more is funded from a number of projects across the partners involved.

UKCEH can build AMI-Traps for interested researchers, funds generated are spent exclusively on supporting and developing the AMI-trap.

Find out more: 

 

See full post
discussion

Camera to follow wasps/attach on wasps

I am researching on the nesting on potter wasps in Bangalore, India. I have to follow nesting wasps to observe all its activities including where it takes rest at night. I am...

4 1

I think @Lars_Holst_Hansen is on point here. It sounds like what you are trying to do is track the insects, and the methods shown in the presentation are best for that.

The cameras would work best where you can have them cameras stationary, looking at the wasps. So they might be good for counting individuals leaving and entering the nest. Cameras inside the nest face a number of challenges. You woud need to ensure that there was good lighting inside the nest for the camera to see, and you would need to make sure that all the action was in focus of the camera. Assuming that is the case you could create an algorithm to track individuals and even look to train an algorithm to identify behaviours, but this is likely to take a lot of work. If you only have a small number of nests, then manual analysis of the recordings may be more cost-effective.

Hi @Lars_Holst_Hansen  @tom_august 

The link to the video is amazing. Thank you for it. 

The wasps that I am working on, are solitary. So, basically it is just this one female that builds the entire nest. Like what you (@tom_august) mentioned, the best option would be to keep a running camera at the nest to record the whole process of nest building. Having one placed inside will be difficult because even if we do work out a way to have lighting inside the nest, the light might be detrimental to the developing larva inside. Hence, it is likely not to be of any benefit.

I am totally smitten by the idea of having a sensor on the wasp body to track where it goes! We could get to know how far it travels to bring the prey and also to collect soil. 

@ShwetaMukundan I just saw this thesis published on tracking bees. Maybe you could use the same method? 

See full post
discussion

AMI-trap unboxing - Automated moth monitoring system

Thanks so much to @JoeBowden for recording this video of his unboxing of the AMI-Trap (Automated Monitoring of Insects Trap...

2 4

Here is the website where you can find more info about tue AMI trap.

https://www.ceh.ac.uk/ukceh-ami-trap-automated-monitoring-insects

This video is so great - I don't know what I was imagining that you were building, but this is so much bigger and more involved than whatever I was vaguely thinking. Really cool to see! 

Side comment - could we make conservation tech unboxings a thing? 

See full post
discussion

Solar panels in the tropics

We are deploying automated systems in the topics and hope to use solar panels, but this closed canopy in most places I'm seeing this as a challenge.Past the obvious: 'find a...

4 0

Hi Tom,

I'm with Akiba, you have to test.  A collaborator has deployed solar-augmented kit in secondary jungle and some of them got enough light, and others didn't, so it can work.  The open circuit voltage of solar panels doesn't change a whole lot in dim light, but the current drops drastically.  So you would choose an oversize panel of the same voltage (or a bit higher).

Thanks

I've been intrigued by this topic. Thinking about ways you could use drones or some kind of launcher to deploy panels above the canopy. Sadly I live in the great white north so I have no way of testing any concepts. Maybe even some kind of solar balloon that could float above the canopy. Interesting design problem.

Hey Tom,
Since the output is dependent on a couple of factors such as the solar irradiance of the place, shading from the canopy, the type of solar panels (mono, poly or amorphous) and orientation of the panels, etc, I'd suggest you use a software to simulate the different parameters to get an almost accurate estimation of the output. You can try PVsyst- it has a free month trial (I haven't used it before but I hear it's great) or any other PV software :)

See full post
discussion

What is the best light for attracting moths?

We want to upgrade the UV lights on our moth traps. We currently use a UV fluorescent tube...

3 0

We are about to try that by modifying the new traps that we build. [email protected] will know more about what we have tried so far. One thing that I know he wants to try is to use glass tubes with good transmission properties

If people come to any findings about loght trap lights let us know!

 

Another question i had on this front is about how continuous do light sources need to be?

 

Since us and @Hubertszcz are controlling our lights anyway with an Automated relay, we can potentially reduce power consumption in a couple different ways. For instance (hypothetically) maybe insects wouldn't care if we turned the lights off every 5 seconds for 3 seconds . Maybe they would even prefer blinking lights? Maybe they would hate it even if the light took a 20 second break every 10 minutes?

 

I have no idea, but if anyone else has thoughts, let us know!

We have also thought about these sorts of things. We have chosen to keep the light on continuously for the night, but turn it off before dawn to allow the moths to fly away before predators arrive. 

We are going to be trying out the EntoLEDs and LepiLEDs in Panama in the last two weeks of January, I'll post here on my thoughts.

See full post
discussion

Capture And Identify Flying Insects

Hello EveryoneI already found a lot of helpful information on this page though I am having a hard time finding a system which is confirmed to be able to identify insects that fly...

1 0

This sounds like an interesting challenge. I think depth of focus and shutter speeds are going to be challenging. You'll need a fast shutter speed to be able to get shape images of insects in flight. Are you interested in species ID or are you more interested in abundance. having a backboard on the other side of the hotel would be a good idea to remove background clutter from your images.

See full post
discussion

Cameras - pros and cons

So, what makes a good camera for an autonomous camera trap for insects?We use a web camera in our system, which seems to work well a lot of the time, it produces...

12 1

Hi Liz, unfortunately you will still need a Raspberry Pi as host for the OAK-1 camera to reproduce our hardware setup. It's also possible to use another Linux-based system (e.g. Raspberry Pi alternatives), but I didn't test this myself and the setup process will be different to our documentation (and probably not so straightforward). I'm planning to publish the documentation website in the next weeks, but I can already send you detailed information about putting together the hardware if you are still interested.

Hello,

 

I'm working on a light weight light trap based on Bjerge et al 2021, however I opted to use an ArduCam 64mp (9152 x 6944 resolution). Designed for the pi specifically and at $60 it checks many of your criteria. I haven't put everything together yet so I can't speak for white balance and power usage, but the autofocus appears to work well from initial tests, and it is tiny.

 

Cheers,

Hubert

Awesome! it would be great to hear how you get on, maybe you can share your results here when you have them. Is the camera only for the Pi? That could be a problem for scaling as Pis are quite hard to come by at the moment.

See full post
discussion

Metadata standards for Automated Insect Camera Traps

Have others watched this webinar from GBIF introducing the data model for camera trap data. I wonder if this is something we can easily adopt/adapt for our sorts of camera traps?

3 2

I did attend the webinar and had a strong feeling that this standard will be well supported and taken up in the camera trapping community! I would also love to hear if someone has tried to use it.

I've added this to the main camera trap thread as it would be good to get thoughts from those folk too.

Yes. I think this is really the way to go!

See full post
Link

Easy-RIDER project Workshop IV: Pollinator monitoring recording

In case you missed our webinar on Pollinator monitoring, here is the recording.

We had presentations from three teams who will be presenting their work in designing automated monitoring tools for flower-visiting insects, different ways for creating datasets for training machine learning algorithms for insect identification and how these new technologies can be integrated in traditional monitoring schemes. The talks were followed with a discussion session.

0
discussion

Implementation of video surveillance to quantify the predation rate

Hello everyone,First of all, thank you for all the information on your great website. My name is Julien Péters and I am a PhD student at the University of Liège (Belgium). For my...

2 0

RaspberryPi-maggedon!

We are having this problem too and it might be worthy of its own thread! The lack of RaspberryPis is a big problem and we are currently looking into alternatives. We haven't found one yet, but if we do I will let you know. @Max_Sitt might have some suggested alternatives for his system?

Hi Julien,

 

we are working with the Luxonis OAK-1 which can run lightweight detection models (e.g. YOLOv5n/s) directly on-device. However you will still need a host, for outdoor deployment Raspberry Pi (e.g. Zero 2 W) is perfect. But for testing you could also use another Linux-based system as host device or just connect it to e.g. your notebook. You can find more info in the Luxonis Docs.

 

Regarding the Raspberry Pi availability, this blog post from Jeff Geerling probably sums up the current situation pretty well. I hope in Q1 2023 the situation will get better, but at the moment nobody really knows for sure.

See full post
discussion

Welcome to the Autonomous camera traps for insects group!

Hello and welcome to the Autonomous Camera Traps for Insects group :).In this group we will be discussing the use of autonomous camera traps as a tool for long-term remote...

11 5

Hi folks! Great to have this group online! I actually am a marine ecologist specializing in bioacoustics but recently joined a Pollinator Monitoring group a Cal-State San Marcos and am helping with an automated camera aspect of the project. We are using the PICT guide and recently migrated to use of VIAME for insect track detection (well, we are just trying it out now). Very exciting work, look forward to learning from you all! Has anyone worked work PICTS? 

- Liz Ferguson

Hi Tom

I am a farmer in Devon researching silvopasture with several research organisations. I have just landed a farmer lead grant to research dung beetles using camera traps and AI. I am collaborating with Rothamsted. 

 

Do you have any tips on sourcing the right camera trap please?

Andy

 

Hi there!

I am a field biologist and research technician working with ecosystem monitoring at the research station Zackenberg in Northeast Greenland. For the last couple of years we have been cooperating with Toke Høye and have deployed his timelapse cameras on Dryas flowers to monitor polinator activity but also to compare to our nearby flower phenology monitoring plots. We have also done yellow pit fall trap monitoring in plots and have a long time series of 25 years. We are considering testing camera based methods for this though and I am happy to see many folks working along those lines. Hopefully I can get some inspiration here and we can start testing it out.

Cheers, Lars

 

 

 

See full post
event

Workshop IV: Pollinator monitoring

This workshop is part of a series of online meetings to share experiences around the globe using automated technology (Cameras + AI) to monitor moths and other nocturnal insects.

2 1
This sounds amazing and I advertised it among my colleagues. Unfortunately, most probably I will not be able to attend, however, would be nice if you can provide the recording...
See full post
discussion

Most interesting images / sightings 'caught on camera'

A thread for people to upload the most interesting or unusual sightings recorded by their traps. To get the ball rolling here's a coy looking crow..

5 3

No - the trap was in their path and they just walked through it. I've now moved it to a place they can't go. The biggest threat to the moths is from pied currawongs. I schedule the trap so it shuts off at least two before sunrise to try to avoid them feasting on the larger insects.

At first I was finding wings below the screen in the morning when I put our units out. So I put a game camera on the units to see what was feeding and when. I found three bird species, likely 3 individuals, quickly found it to be a good bird feeder- Song Sparrow (most frequent), House Wren, and this Tufted Titmouse. I changed my units to turn off about 1.5 hours before dawn and that worked! Nearly all the moths left the scene before the birds came to visit. 

My most prized camera trap image - a hummingbird caught on camera!

Image

See full post
discussion

Identify animal from Image

I am thankful to the members of Wildlabs net for giving us the right information to enable us to plan Bioacoustics solution implementation. It seems to be on track as of now....

2 2

Hi Jitendra.

If they are still images, many people are using Megadetector to analyze their images. I'm not sure how it will do in species classification, but it can tell you if there are images of interest in the shots. Others here can probably give you more detailed instructions on how to use it to batch process camera trap images.

 

Have you considered creating a Kaggle competition? If you already have lots of images, and some that have been labelled, then this could be a good way to get people working on a solution

See full post