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

Owl call detection software

I’m curious about AI software for analyzing nocturnal bird calls, particularly for detecting owl species. I currently use Nighthawk for help with processing my ARU audio files,...

8 0

I have a question about Arbimon. I'm working on a project looking for bird use of wet meadow (and associated matrices of habitat). We have two bird lists we've created for BirdNet, a "Master List" of all species (to get an understanding of community data as per input from Indigenous partners) and a "Focal Species List" as per the land managers in put. I will have volunteers doing manual verification + passive listening to attempt to catch false positives and species BirdNet has missed. I recently learned about Arbimon from the Soundscapes to Landscapes project and I'm curious about the audio detector function. Is it detecting spectrograms/sonograms from a provided classifier or does it function similar to BirdNet where we can tell it which species to look for? 

We are currently working on Eurasian Pygmy, Tengmalm's and Tawny owl calls recognition. It's not a trivial task if you want to include different call types (male, female, pair, chicks), that's why we started with only 3 species. If you are interested in these 3 European species, drop me a line. 

Hi Teresa, 

Thanks for your interest in Arbimon! The platform has a couple different analysis tools that range from unsupervised (like audio event detection & clustering, or AED-C) to semi-automated (pattern matching, random forest). We've got lots more info about each in our support docs here

The AED-C is an unsupervised machine learning model, so you aren't providing any labels (though the validation page allows you to assign events or clusters as particular species after the fact). The pattern matching is a cross-correlation template matching function where you provide 1 template (example of the species-specific call you're looking for) and the algorithm looks for matches similar to that template. Random forest is a decision-tree-based machine learning model where you provide training clips (presence & absence clips for a species) which the model uses to learn how to classify that species' call. We have developed a number of CNNs (like BirdNet is) but they have more of a regional focus (e.g., one for Kenya, one for western Sumatra, etc. etc.). Right now we run these on the backend, but we are currently working on a public-facing CNN page that we hope to phase in this year.   

Hope that helps, but feel free to reach out if you have more questions! You're welcome to also email me directly at [email protected] .

All the best,

Carly 

See full post
discussion

Using drone or other unmanned vehicle for DNA sampling on fresh elephant dung in a Baï, Congo Rainforest.

Hi all,Elephant listening project and WWF CAR are working on elephant identification in Dzanga Baï (clearance in the forest) since several years now. We would like to compare our...

4 0

I think we can habituate elephant to noise, especially if it's could looks like a natural one.

The problem is that many elephants are concentrated in the baï and if we want to avoid DNA contamination we have to sample it quite fast.

Hi Antoine,

I would recommend talking to the engineers at Outreach Robotics - @Gcharron .

We have been working on collecting tools for rare plants, and I would guess it wouldn't be a huge adjustment to collect elephant dung.  I think the amount of dung required for analysis will drive the size of the collecting drone. Maybe the drone could be up very high to not disturb the elephants with a long line sampling mechanism? 

See full post
discussion

Detection and removing of windy events in wild acoustic recordings

Hello to everyone, I have to clean my dataset of recordings concerning an African penguin colony inhabits the South African coast. In particular, since I have recordings with days...

9 0

Hi everyone! 

@baddiwad was one of our fantastic speakers in our June Variety Hour show, so we had the chance to hear about her work in a lot more detail. If you're interested in finding out more about Franscesca's project, catch up here: 

Audacity has a noise filter which one 'trains' on a piece of recorded noise. Perhaps it is worth a shot. Freeware, open source, and with a community of developers and users.

Hi Francesca! 

 

Did you managed this problem somehow? Can you post the workflow or the solution that worked for you?

See full post
discussion

Landscape of technology solution for African lion conservation

I am currently begining to research the topic of African Lion conservation, and in particular human-lion interaction, from a technological perspective. I would like to get an...

11 1

Hi Simon,

Thanks for your reply. I would be interested in having a chat with you and hear more about the work you are doing! Lets connect and we can try to schedule a call in the coming days.

Thank you,
Best,

Jacobo

Hi Maureen,

Thank you very much for your insights. I would definitely like to connect with you and discuss this further! I will reach out to you so we can potentially schedule a quick call and chat about this further.

Thank you,
Best regards,

Hi Jacobo,

We have launched a new tracking/logging/finding technology which you may find of interest https://www.tagranger.com/   

Based on LoRaWAN (but with yor own handheld gateway) you can communicate with your Tags in real time.  As well as requesting current GPS locations from long distances away you can also use the integrated ranging tools which give you distance to your Tag in metres when you get closer.  

Key features:

LoRaWAN (tested up to 21km line of sight) No infrastructure required, but you can also add it to your own LoRaWAN network.

UWB ranging gives distance (in metres) to the Tag up to 150m away

Hybrid Ranging combines the equivalent of a VHF pinger from a few km away (line of sight) with the UWB ranging when you get closer

Log Download remotely using UWB radio

Ultra light 39g Tag

Power Efficiency Defined by your configuration profie, 2 days to 4 years!

Let me know if you would like any further help with this.

Craig

See full post
discussion

Questions regarding the use of solar panels to extend battery life of GPS collars

Hey!If anyone here has had any experience using solar panels to extend the battery life of their tracking collars, I would love to hear from you! How effective was the...

17 1

Lars,

As always, your insights are great! The GPS Plus X battery life calculator is great! I've downloaded it and have been toying around with it, very convenient when thinking about sampling schedules. Curious as to why more tech developers don't incorporate something similar into their own programming/analysis software. Very useful.

I've got a few meetings set up with a couple different tech developers, but may reach to Vectronic here. At first glance, their collars seem great! I appreciate the recommendations.

 

I must admit, I am not well versed in Python, but I am looking into something that wold be the R equivalent. If I don't have much luck, I may try and take a look at how that package was made in Python and attempt to recreate it in R.

 

You're the best Lars! Thanks!

 

Cheers,

Travis

Hi Bill,

I don't believe I will need them to be extremely accurate, but will need a good degree of accuracy for some behavioral classification and habitat use analyses. In regards to the solar, tracking the solar cycle is a great suggestion. I have also considered having some thresholds programmed in the accelerometer to power off both sensors during periods of sleep/rest in order to conserve battery life. I did this same thing in my last study for the GPS only, so there wouldn't be instances where the trackers continued to try and unsuccessfully acquire GPS fixes while the bats where inside their caves resting. After the bat's surge axis dropped into the -1 and there was 10 unsuccessful GPS fix attempts in a row, the GPS powered down.

 

Thanks for the suggestions and insights Bill!

 

Best,

Travis

See full post
discussion

Reasonable price for drone pilot (south africa)?

Hi everyone, A colleague is looking for a cost check on going rates for drone pilots in South Africa. Is £500-£700 a day reasonable? They'd be flying drones in a project to...

7 0

Hello Stephanie,

I am not sure if you are still monitoring this thread, but if you need any information, please let me know. I have flown drones for a couple of years in Zimbabwe and South Africa in conservation and anti-poaching operations. I would be happy to answer any questions you may have.

Regarding the £500-700 range you mentioned, it seems waaaayyyy overpriced. Those rates are usually charged by lawyers and accountants in South Africa.

If you have found the information you were seeking, I wish you all the best.

Quin

Hi Steph,

I think everyone below has summarised it pretty well.

A couple of comments to add.

Select your pilot well - We offer drone flying services. This wasn't our intention, initially, however we have determined that there are many drone pilots, but fewer who do it really well. Having said that, we work predominantly with animal tracking equipment, not just flying straight line vectors, if this is what you are undertaking.

In Australia, fees to become a pilot are about $5,000 AUD, and a reasonable commercial drone with changeable payload capability costs around $20,000- $30,000 AUD, and then as is suggested below, there are insurance and factoring in repairs and maintenance, and of course eventual replacement costs, travel, an hourly rate as wages etc. Obviously, the day rates you have listed aren't profit, they include cost.

Paul

Wildlife Drones

 

Hi, I have used a commercial company for drone work for my PhD and they were willing to give me a significant discount for research purposes. One thing to consider is that in SA a drone pilot requires a pilots license and there is quite some red tape to go through which does make it much more complex than just going out and buying a drone oneself. The price you mention seems on the high side to me but I'm not sure if that already includes the drone, sensors, flight permissions, travel of the pilot to and from your location and any other costs.

See full post
discussion

Image analysis with volunteers

Hello! I'm working with volunteers on a pilot project using camera traps and PAMs to monitor a mixed species waterbird colony on an Army Corps of Engineers constructed island....

2 0

I have a little experience with Timelapse and would say it is definetely worth the invested time.

The developer Saul Greenberg has made a ton of documentation on its use and is also very approachable in person, if you have any issues.

I can only highly recommend it.

 

 

See full post
discussion

Jupyter Notebook: Aquatic Computer Vision

Dive Into Underwater Computer Vision Exploration OceanLabs Seychelles is excited to share a Jupyter notebook tailored for those intrigued by the...

3 0

This is quite interesting. Would love to see if we could improve this code using custom models and alternative ways of processing the video stream. 

This definitely seems like the community to do it. I was looking at the thread about wolf detection and it seems like people here are no strangers to image classification. A little overwhelming to be quite honest 😂

While it would be incredible to have a powerful model that was capable of auto-classifying everything right away and storing all the detected creatures & correlated sensor data straight into a database - I wonder if in remote cases where power (and therefore cpu bandwidth), data storage, and network connectivity is at a premium if it would be more valuable to just be able to highlight moments of interest for lab analysis later? OR if you do you have cellular connection, you could download just those moments of interest and not hours and hours of footage? 

Am working on similar AI challenge at the moment. Hoping to translate my workflow to wolves in future if needed. 

We all are little overstretched but it there is no pressing deadlines, it should be possible to explore building efficient model for object detection and looking at suitable hardware for running these model on the edge. 

 

 

See full post
discussion

Replacement screen for Bushnell cameratrap

Hi all,I have an arboreal camera trap array using the Bushnell E3 Trophy cam. One of the cameras has suffered damage at the hands of white faced capuchins. The camera trap still...

3 0

Hey Lucy!

You should be able to pick up a small piece of infrared emitting plastic online for super cheap that would allow for the IR lights to pass through, but block UV from coming in. Anything should be able to be glued and sealed using expoy, which shouldn't damage any electronic components, but will ensure weatherproofing.

 

Goodluck!

 

Best,

Travis

I have fixed Bushnell TrophyCam IR windows with plastic cut from the bottom of a supermarket fruit package. Any thin, clear plastic will be OK. I stuck it in with silicone, but make sure you get the neutral cure type that does not emit acetic acid as it sets.

See full post
discussion

Power managment/Recharging System and Communication System

As we know Power managment/Recharging System and Communication System are chalanges for forest, so any one please suggest the Device and Power source to monitor sound in forest...

15 0

Power usage for microcontrollers with solar is  much more manageable. For Raspberry Pi's and higher it gets expensive and big.

I'm quite impressed by the specs from the Goal Zero Yeti devices. This can have high capacity and be charged with Solar. Not small though. And the price is not in proportion to the Pi's.

So this 200x model for example, would be close to 16 days running the audio recorder. Let's say 10. without solar. Add solar? Depends on the size of the panels I guess. Power usage for mobile networking? Depends on how much you transmit.

Probably some well documented experiments would be really nice for people here. Sounds like something nice for the next set of grants :)

See full post
discussion

Using drones and camtraps to find sloths in the canopy

Recently, I started volunteering for Sloth Conservation Foundation and learned that it is extremely difficult to find sloths in the canopy  because: 1) they hardly move,...

16 1

I was under then impression that "Infrared Imaging" meant shining an infrared light source on to the subject and capturing primarily the reflected light.  As opposed to "Thermal Imaging" which meant capturing the infrared signatures generated by the subjects themselves?  That said, I'm sure some others are much better informed on this subject than me.

 

I took delivery of the DJI Mavic Enterprise 3 Thermal the other day. The short hand nomenclature used on the controller for the thermal imagery is "IR" (short for infrared) so it is used even for cases where no IR lighting is in play.

 

 

See full post
discussion

Need advice - image management and tagging 

Hello Wildlabs,Our botany team is using drones to survey vertical cliffs for rare and endangered plants. Its going well and we have been able to locate and map many new...

6 0

I have no familiarity with Lightroom, but the problem you describe seems like a pretty typical data storage and look up issue.  This is the kind of problem that many software engineers deal with on a daily bases.  In almost every circumstance this class of problem is solved using a database.

In fact, a potentially useful analysis is that the Lightroom database is not providing the feature set you need.

It seems likely that you are not looking for a software development project, and setting up you own DB would certainly require some effort, but if this is a serious issue for your work, you hope to scale your work up, or bring many other participants into your project, it might make sense to have an information system that better fits your needs.

There are many different databases out there optimized for different sorts of things.  For this I might suggest taking a look at MongoDB with GridFS for a couple of reasons.

  1. It looks like you meta data is in JSON format.  Many DBs are JSON compatible, but Mongo is JSON native.  It is especially good at storing and retrieving JSON data.  Its JSON search capabilities are excellent and easy to use.  It looks like you could export your data directly from Lightroom into Mongo, so it might be pretty easy actually.
  2. Mongo with the GridFS package is an excellent repository for arbitrarily large image files.
  3. It is straightforward to make a Mongo database accessible via a website.
  4. They are open source (in a manner of speaking) and you can run it for free.

Disclaimer: I used to work for MongoDB.  I don't anymore and I have no vested interest at all, but they make a great product that would really crush this whole class of problem.

See full post
discussion

LoRaWAN IoT gateway, low power and solar cell driven

A friend drew my attention to a LoRaWAN IoT gateway solution that seems to have high applicability potential in remote nature conservation projects using LoRa sensors. It is...

3 0

Lorawan is a great tech for various applications. In essense, a lorawan gateway communicates with a provider endpoint to send through data that is receives. This can then be received by applications with subscriptions to that data over the Internet. Gateways can be had quite cheaply, Seeed Studios has one for around 100 euros. This is just adding a solar charge unit and there must be some sort of Internet communications, be it cell based or otherwise satellite I guess.

You should aware of all of the profiles of Lora and the constraints, it's intended for low bandwidth data. There are several modes of operation, Lora itself uses spread spectrum transmission with error correction. If you use a high degree of error correction you can transmit successfully longer distances, but with a longer period between allowable transmissins. For example, on spreading factor 12 (SF12) I think you may only transmit again 5 minutes or so later. With SF7, you have less power and less error correction and you can retransmit 5 seconds later.

So think it terms of small amounts of information to be transmitted. It's not a network replacement. The same also applies to zigbee or xbee pro, although they would be more suitable for larger amounts of data and can be used as I understand it as a sort of very, very low bandwidth meshed network. But lorawan is really for individual packets of data.

The Things Network has a lot of information regarding Lorawan in general that's well written I think.

The things network can also be used for free up to a certain number of nodes as a understand it.

I’ve used the things network before. It was developed in the Netherlands. The things network can be seen like an ISP. TTN just developed their ISP so to speak.

I'd be happy to chat with you over video to discuss your case and help you with whatever I know if you like.

See full post
article

New paper - An integrated passive acoustic monitoring and deep learning pipeline for black-and-white ruffed lemurs in Ranomafana National Park, Madagascar

We demonstrate the power of using passive acoustic monitoring & machine learning to survey species, using ruffed lemurs in southeastern Madagascar as an example.

2 0
What an awesome paper! Loved learning about such a promising research tool in PAM combined with a CNNs, and that lemur vocalizations are termed as "roar-shrieks" :)
See full post
discussion

Cat Island, Bahamas biologger recovery

Hi everyone,A random request to see if any WILDLAB members may live in, or near the Bahamas on the off chance that you could help to recover one of our plastic...

4 0

Were you guys able to recover the tag? @Alasdair 

Hi Alasdair,

I am also curious with the result, were you able to recover the tag? Also is there any that ended up in Indonesia sea? We would love to help the recovery if any.

Cheers,

Dhanu

Hi @ThomasGray_Argos, @YvanSG  and @hjayanto,

Thank you all for getting in touch. Luckily the Cat Island Institute via YME Bahamas got in touch and prepared an expedition to recover it. They couldn't access the beach during the first attempt, but a second attempt is planned. I'll hopefully be able to recover it shortly. 

Thanks again,

Alasdair

See full post
Link

Questionnaire for Pain Points and Needs in Bioacoustics

Hi! We're engineers eager to understand how technology can simplify acoustic work. If you use recorders, your input would be invaluable. Please consider taking our 5min survey. As a thank you, participants will be entered into a draw for a Audio Moth Recorder! Thank you so much!!

0
discussion

Monitoring setup  in the forest based on the wifi with 2.4 GHz frequency.

I am planning to setup the network using the wireless with frequency 2.4GHz. Can I get the the data for this signal distortion in the forest area?Is there any any special...

5 0

Hi Dilip,

I do not have data about signal distortion in a forest area and with the signal you are intended to use.

However, in a savannah environment, when I put a tour on the highest point of the park, Lora signal (avg 900MHz) is less distorted than WiFi signal (2.4GHz). This is normal as a physics law: the frequency determines the wave length, and the less the length (obviously the less the frequency), the less obstructed the signal.

So, without interfering with your design, I would say that in a forest configuration, WiFi will need more access points deployed and may be more costly, and in your context, even when using LoRa, you will need more gateways than I have in a savannah.

To design the approximate number of gateways, you may need to use terrain Visibility analysis.

To design the cameras deployment, you will need to comply with the sampling methods defined in your research. However, if it is on for surveillance reasons, you may need to rely on terrain visibility analysis also.

Best regards.

I've got quite a lot of experience with wireless in forested areas and over long(ish) ranges.

Using a wifi mesh is totally possible, and it will work.  You will likely not get great range between units.  You will likely need to have your mesh be fairly adaptable as conditions change.

Wireless and forests interact in somewhat unpredictable ways it turns out.  Generally, wireless is attenuated by water in the line-of-sight between stations.  From the Wifi perspective, a tree is just a lot of water up in the air.  Denser forest = more water = worse communications. LoRa @ 900Mhz is less prone to this issue than Wifi @ 2.4Ghz and way less prone than Wifi @ 5Ghz.  But LoRa is also fairly low data rate.  Streaming video via LoRa is possible with a lot of work, but video streaming is not at all what LoRa was build to do, and it does it quite poorly at best.

The real issue I see here is to do with power levels.  CCTV, audio streaming, etc are high data rate activities.  You may need quite a lot of power to run these systems effectively both for the initial data collection and then for the communications.

If you are planning to run mains power to each of these units, you may be better off running an ethernet cable as well.  Alternatively, you can run "power line" networking, which has remarkably good bandwidth and gets you back down to a single twisted pair for power and communications.

If you are planning to run off batteries and/or solar, you may need a somewhat large power system to support your application?

 

I would recommend going with Ubiquity 2.4Ghz devices which have performed relatively well in dense foliage of the California Redwood forests. It took a lot of tweaking to find paths through the dense tree cover as mentioned in the previous posts. 

 

See full post
discussion

Audiomoth Bat Call Triggering Settings

We are considering buying audiomoth for recording bat calls for our Citibats Cambodia project[1]. I would like to learn about your experience of using Audiomoth for record bat...

2 0

Nils Bouillard (@Nilsthebatman) would be good to talk with! 

Adrià López-Baucells also has lots of useful info on his website.

See full post
careers

Program Officer - Bioacoustics, WILDLABS

Come join our team! We're looking for a Program Officer to join the WILDLABS Community, hosted by WCS in Argentina. This role will support our research program, with the chosen candidate leading our horizon scanning...

3
See full post
discussion

How are Outdoor Fire Detection Systems Adapted for Small Forest Areas, Considering the Predominance of Indoor Fire Detectors?

How are fire detection mechanisms tailored for outdoor environments, particularly in small forest areas, given that most fire and smoke detectors are designed for indoor use?

1 0

Fire detection is a sort of broad idea.  Usually people detect the products of fire, and most often this is smoke.

Many home fire detectors in the US use a radioactive source and measure the absorption of the radiation by the air.  More smoke means more absorption.

For outdoor fire detection, PM2.5 can be a very good smoke proxy, and outdoor PM2.5 sensing is pretty accessible.

This one is very popular in my area. 

 

See full post
discussion

Open-source kinetic energy harvesting collar - Kinefox

Hello everyone,I ran across an article today (at the bottom) that talks about an open-source, kinetic energy harvesting collar ("Kinefox"). It sounds pretty neat...anyways,...

6 3

This is super cool! 

I was wondering if the development will further touch marine or aquatic animals, make it like water wheel (even might give burden to aerodynamic). Thank you for sharing!

Best,

Dhanu

See full post
Link

Kenya Forest Club, Central Region – Kenya Forest Club

It has been an exciting challenge as a member of Kenya Forest Club whose main aim is solving climate change challenges through early childhood education and training, with a particular interest in forestry.
The club hopes to have members in all schools and setup of tree nurseries

0