Global Feed

There's always something new happening on WILDLABS. Keep up with the latest from across the community through the Global view, or toggle to My Feed to see curated content from groups you've joined. 

Header image: Laura Kloepper, Ph.D.

discussion

Subsea DIY Burnwire for Deep-sea BRUVS

Hello everyone. I'm part of a team working on a low-cost, deep-sea camera (BRUVS) project and we're currently facing challenges with our subsea burnwire release system. We're...

0
See full post
discussion

Automatic extraction of temperature/moon phase from camera trap video

Hey everyone, I'm currently trying to automate the annotation process for some camera trap videos by extracting metadata from the files (mp4 format). I've been tasked to try...

7 0

Hi Lucy

As others have mentioned, camera trap temperature readouts are inaccurate, and you have the additional problem that the camera's temperature can rise 10C if the sun shines on it.

I would also agree with the suggestion of getting the moon phase data off the internet.

 

Do you need to do this for just one project?  And do you use the same camera make/model for every deployment?  Or at least a finite number of camera makes/models?  If the number of camera makes/models you need to worry about is finite, even if it's large, I wouldn't try to solve this for the general case, I would just hard-code the pixel ranges where the temperature/moon information appears in each camera model, so you can crop out the relevant pixels without any fancy processing.  From there it won't be trivial, exactly, but you won't need AI. 

You may need separate pixel ranges for night/day images for each camera; I've seen cameras that capture video with different aspect ratios at night/day (or, more specifically, different aspect ratios for with-flash and no-flash images).  If you need to determine whether an image is grayscale/color (i.e., flash/no-flash), I have a simple heuristic function for this that works pretty well.

Assuming you can manually define the relevant pixel ranges, which should just take a few minutes if it's less than a few dozen camera models, I would extract the first frame of each video to an image, then crop out the temperature/moon pixels.

Once you've cropped out the temperature/moon information, for the temperature, I would recommend using PyTesseract (an OCR library) to read the characters.  For the moon information... I would either have a small library of images for all the possible moon phases for each model, and match new images against those, or maybe - depending on the exact style they use - you could just, e.g., count the total number of white/dark pixels in that cropped moon image, and have a table that maps "percentage of white pixels" to a moon phase.  For all the cameras I've seen with a moon phase icon, this would work fine, and would be less work than a template matching approach.

FYI I recently wrote a function to do datetime extraction from camera trap images (it would work for video frames too), but there I was trying to handle the general case where I couldn't hard-code a pixel range.  That task was both easier and harder than what you're doing here: harder because I was trying to make it work for future, unknown cameras, but easier because datetimes are relatively predictable strings, so you know when you find one, compared to, e.g., moon phase icons.

In fact maybe - as others have suggested - extracting the moon phase from pixels is unnecessary if you can extract datetimes (either from pixels or from metadata, if your metadata is reliable).

camtrapR has a function that does what you want. i have not used it myself but it seems straightforward to use and it can run across directories of images:

https://jniedballa.github.io/camtrapR/reference/OCRdataFields.html

See full post
discussion

Which market-available microphones, accelerometers and GIS sensors for dogs / pets ?

I have conducted an MSc thesis in data-science applied on bioacoustics data, and wish to carry on some experiments on my own now, using domestic environment as a lab.I am looking...

2 1

 

Hi Luigi!

 

You should have a look at the μMoth 

https://github.com/OpenAcousticDevices/Datasheets/blob/main/uMoth_Datasheet/uMoth_Datasheet.pdf

 developed by @alex_rogers and others from Open Acoustics Devices:

As an alternative audiologger meant to be animal borne, check out the Audiologger developed by Simon Chamaillé-Jammes @schamaille et al :

This one can also log acceleration and magnetometry! We have recently deployed it on muskoxen in Greenland.

For a GPS tracker, you may want take a look at the SnapperGPS by @JonasBchrt & @alex_rogers :

As an alternative the i-gotU GPS logger may be of interest:

Regarding your question on sampling frq: We have been using 8Hz (and 10 Hz on the Audiologger Acceleration logging) for our slow moving muskoxen. For an animal like a dog, you probably want to sample at somewhat higher frq. This group used 50Hz in a study of arctic fox: 

 

 

See full post
discussion

Successfully integrated deepfaune into video alerting system

Hi all, I've successfully integrated deepfaune into my Video alerting full-features security system StalkedByTheState. The yellow box around the image represents the zone of...

6 0

So my vision about using my StalkedByTheState software to deter the wolves away from the sheep can be represented something along the lines of this:

Wolf deterrant
I'm pretty sure this is how Rob Appleby described it to me. But I think all the sheep should be inside the fence.

And here's how I would explain it to the government officials in a power point. I'm making the point that the wolves have been shooed away.

Sheep safe now 

See full post
discussion

Bird Acoustic Surveys: Comparison with traditional transect methods

Baker Consultants Releases Whitepaper Comparing Traditional & Ecoacoustic Bird Survey MethodsBaker Consultants is pleased to announce the release of its latest ecoacoustics...

2 0

Thank-you for sharing this study, I read it with interest! I was wondering, in doing this study did you also get a feel for how these methods compare in terms of time and costs and required skills? As a practitioner I am still a bit worried about the amount time required for set up, maintenance, data management, species identification, and analysis. 

Hi Theresa.  In comparison to traditional survey, I think that the time/cost benefits of acoustics are good.  Certainly the set-up, maintenance, and data management requirements are minimal. And if there is significant travel time to site, and the recording period of acoustic survey is long, then I think the benefits are compounded (i.e. there are economies of scale to acoustics that you don't get with trad surveys).



Until the last year or two, the data analysis for species identification has been the time-consuming part.  However, now that systems such as BirdNET are available, this issue is fairly well dealt with (but still needs a little bit of skill/experience).



A couple of scientific papers have assessed these costs/benefits - I hope these make an interesting read.

Carlos

 

See full post
discussion

Query regarding Biologgers for Freshwater crabs

I'm new to WildLabs, I guess I'm writing in a relevant area to get addressed with my query. I'm doing my doctoral research at Bharathiar University currently. I am planning to do...

5 0

My pleasure @Abinesh and if you have any more questions etc., don't hesitate to ask. This is a great community with plenty of smart cookies that can help and also me if I am able!

All the best for your research. 

Rob

Star-Oddi in Iceland comes to mind, but I'm not 100% sure. 

See full post
Link

eDNA Collaborative Microgrants Program!

This round of microgrants will be awarded in collaboration with miniPCR bio, and each microgrant award will consist of a mini16x thermal cycler, a blueGel electrophoresis system with USB power adaptor, one pipette, and a field carrying case.

0
discussion

What is your favorite package or software for visualizing animal tracking data?

Hi all,I manage a large research collaborative focused on conservation applications of animal tracking data (Smithsonian's Movement of Life Initiative).  I'm interested in...

12 3

Hi Jennifer, Movebank can handle all kinds of location data, metadata or sensors (height, depth, speed, acceleration, IMU, heartrates) and Firetail ships with a module that can directly open Movebank data (your or other projects) and keep them up to date - most sensors will work out of the box. 

If you have any specific questions or projects in mind, don't hesitate to contact me. Cheers, Tobias

You might be interested in reaching out to the team at National Audubon Society's Migratory Bird Initiative. They just released the Bird Migration Explorer a year ago and likely have many thoughts and ideas. Erika Knight would likely be a good person to speak with. 

 

 

See full post
discussion

Is anyone or platform supporting ML for camera trap video processing (id-ing jaguar)? 

Hi wildlabbers, I have another colleague looking for support for getting started using AI for processing videos coming out of their camera traps - specifically for species ID...

6 0

I can help you with that, please send us some of the videos and will build a pipeline for it 

aakash at thinkevolvelabs dot com 

- Aakash Gupta 

ffmpeg + TrapTragger (Camtraps + re-ID) and Whiskerbook(re-ID)?

 

 

 

See full post
discussion

Data integration platforms

Anyone working in data integration or know of any other existing tools such as Palantir or Vulcan's EarthRanger?

10 0

Argos has an API 

Iridium data either arrives via email/server IP

Globalstar (unknown)
 


If you'd like the web services document for Argos, shoot me an email (tgray at woodsholegroup - dotcom).

See full post
discussion

Alternative trackers for study of grey parrots movement patterns

Hi everyone, i pray this message reaches you well. Please I am looking for alternative ideas as to which other tracker to use on the African grey parrots to track their movement...

7 0

Hi Ninying,

One benefit of the Pinpoint tags is that they are user-rechargeable, something pretty much unheard of for satellite tags for decades!  If you can recover the tags, you might be able to achieve a larger samples size with fewer tags (less $$) by redeploying the recovered tags - without the costs of having the manufacturer refurbish them.

cheers,

Kyler

See full post
discussion

Autonomizing Small Mammal Traps

If there was a product on the market that was capable of trapping, ‘tagging,’ and releasing an individual without human intervention, would you or your peers invest? Live mammal...

5 0

The Australians have invented this already for a completely different purpose - if you fill it with hair dye instead of 1080 gel it will spary a unique pattern of droplets on the target animals. You need a post-spray picture, but that should be doeable.

https://thylation.com/

One thing to keep in mind is that researchers often want or at least would like to get certain metadata on the tagged animals like sex, size, weight, apperent fitness etc. Without these the questions you can ask can get rather limited. Also, it will also often be highly desired to take samples like blood, hair, other tissue e.g.

In addition, there can be cases where it may be better not to tag the animal if it is not the right age group, is too small to carry the tag, seems like it is not in a good shape etc.

I think it will take quite an effort to get automated systems (capture robots) to make these decisions to a degree you can trust.

Cheers,

Lars

See full post
discussion

Remote weather stations

Hi sensors group! I'm hoping to incorporate fine scale weather data (wind, precipitation, temperature, etc) into my research, which will be situated in a fairly remote area of...

18 0

While pretty expensive, everyone I know has had good experiences with the HOBO weather stations and can be customizable if needed. Would still be my rec if you need something ASAP 

Hi Carly, thanks for this. I forgot to mention HOBO in my original post, but I had them down as the main available option. Think it might have to be them, I'll have to check for $ down the back of the sofa...

I came across this which looks like it might work for you.

Others have mentioned Davis.  I used the Davis vantage pro2 in a previous life, and the cabled version was about USD200 IIRC. However, it must operate with a display console, which can take an optional data logger, but the console is intended to be kept indoors.  This means providing a weatherproof enclosure for it in the forest, in addition to a mast for the anemometer etc.

See full post
article

Taking on the conservation Strides

In a threatening world full of challenges to both humans and non-humans in existence, soliciting for diverse sustainable solutions to promote coexistence is vital and the answer lies in the advancement and adoption of...

1
See full post
discussion

Video camera trap analysis help

muh
Hello,I'm a complete newbie so any help would be appreciated. I never trained any ML models (have junior/mid experience with Python and R) nor annotated the data but would like to...

5 0

Hey there - we can help you, please send us some of the videos and will build a pipeline for it 

aakash at thinkevolvelabs dot com 

- Aakash Gupta 

Hi, 

our software Deepfaune works with videos. It is trained for the European fauna and try to put all birds in a 'bird' class but it includes a detection stage so at least it can filter 'empty' images or videos. Performance on videos is not as great as it is on images, so I can't promise it will match your expectations. But the installation on windows is easy, so give it a try and see for yourself. It's a point&click software. You can use it in English, French, Spanish, Italian.

https://www.deepfaune.cnrs.fr

 

See full post
article

WILDLABS Awards 2024: Further Information

More information for those interested in our newly launched WILDLABS Awards, supporting 14 outstanding conservation technology projects with $60,000, $30,000, and $10,000 grants. Read carefully ahead of submitting your...

1
See full post
article

Impacts of Rhino Fence on other Wildlife Species

Hello, My name is Rita Orahle, a Rhino Monitoring Officer from Loisaba Conservancy. In this article, I will give an update on research on the fence and key gained skills and support from the Women in Conservation...

1
See full post
event

WILDLABS AWARDS Webinar

On the 11th of December at 4pm GMT, Arm and WILDLABS will present the newly launched 2024 WILDLABS AWARDS. If you have any questions, join us !

0
See full post
discussion

Wishlist for kit in a field-based Research Station or tech testing space?

Hi wildlabbers!A colleague is looking to crowdsource some advice: what would be on your wishlist for kitting out a field based space for research and tech development?...

3 0

Regine Weckauf over on linkedin

'Little to do with research and tech development, but given how hard it is to attract and retain experienced staff to field based positions, I know it makes a difference how nice the space is. Just because it's the "field", shouldn't mean staff living in basic conditions, regardless of how many times we've been told to see it as a badge of honor. If you have the money, put in nice bathrooms, kitchen, living spaces, and private accommodation. Maybe even a nursery? It creates more local employment opportunities and people genuinely want to visit.'

 

Love the idea for in-house gear/supplies! It can be SOO difficult to travel with batteries, electronics parts with airline regs, country policies, etc. and shipping recorders/trail cams/etc. gets VERY (prohibitively) pricey in some countries with customs and taxes. Would be great to have an in-country place to source that kind of equipment. 

Housing educational resources related to that tech (in the form of people, print materials, computer tutorials) in-house would be similarly awesome. Particularly/especially in local languages.   

Having in-country wet labs as well helps the eDNA/genetics folks, since sample import/export permitting can be (always seems to be?!) a nightmare, so if you can even just do PCR and/or extractions in-country that helps a ton. 

In terms of overall field-station-wishlist - honestly, just the promise of continued funding and staff. Every field station I've been to or worked at is in a constant search for enough money to get through the next month/year, because the funding comes in the establish a station but then not to maintain it long-term. It's not sexy for a wishlist per se, but boy is it over-looked and much-needed. 

@hikinghack from Dinalab would probably have lots of good insights on this! 

My suggestion would probably be a 3D printer and Solder Station with a stock of common components. With those two things you can solve most problems.

See full post
Link

Ekobot WEAI robot - autonomous weeding at farm scale

A little off the typical path for Wildlabs - and probably not the sort of drone people typically think about here 😄 - but I find robotic agriculture very interesting, with the potential to greatly reduce use of poison and improve effective yields. Anyone working on like things?

0