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

Song Meter Micro experience?

Hi everyone, First off, what a great community this is! I only recently found out about it, and it seems like a game changer, especially for early career folk like me.I was...

11 1

Interesting, thanks Pshemek! I'm assuming you mean 144h on a 24/7 schedule? I wonder how schedule type could affect battery life... More writing to card = more energy, right?

I'm really intrigued that you managed to modify the Micro with Li-ion batteries. I'd definitely like to explore this possibility. 

 

 

Thanks for this Carly. I didn't know the Swifts were for sale!? I've been curious about them before, but only ever seen them advertised as "for lease" from the Cornell Lab's website. Ah well... I've got the Micros now, and I'm sure they'll be fine. Might still shoot an email over to Cornell about those though, the battery life potential could make them great long-term soundscape monitors.

So they technically are "leased" but it's expected you won't return them. I think they have to use that wording to maintain their non-profit status or something like that. 

See full post
discussion

Opportunity: networking, funding and more...

Calling early-career folks and innovative thinkers - the future leaders of their fields!  We have a fantastic opportunity to attend a virtual event that will...

2 0

Hi Alice, 

Sounds like a really interesting symposium and topic! I took a look at the link but I'm curious, is the intent of the theme of digital tools for reversing environmental degradation intended to be more geared towards developing tools that help with community practice or that are geared towards enhancing conservation and resource management? 

Cheers, Liz

Hi Liz,

A bit of both - we certainly have people from both sides of that equation. The event will be very multi-disciplinary and aims specifically to bring together a broad range of people!

Hope that helps,

Thanks

Alice

See full post
discussion

Connection needed!

Hi everyone -- I'm hoping to connect with a woman who is based in Asia (South or South East Asia) and is working on AI / machine learning to prevent and reverse environmental...

2 0

Maybe she is not based in Asia, but you could check Lily Xu, who gave a presentation at the IUCN World Congress a year ago on using AI against poaching in Cambodia. The project is called Protection Assistant for Wildlife Security (PAWS).

For a summary of this project and another ( presented by a man ) see 

See full post
discussion

Suggestions for user research/co-design methodologies

Hi everyone, I'm wondering if anyone on here has an experience with user research or user testing for conservation technology 'products'? Please get in touch, I'd love to discuss...

6 1
See full post
discussion

Global shortage of Raspberry Pis - What are the alternatives

So, there is a global shortage of Raspberry Pis, the open source micro-computer that has been popular amongst open hardware designers and hobbyists alike. Like...

5 0

Hi @tom_august this is a very important topic given the global shortages we are seeing. I tend to use really low power micros rather than Pis for my stuff if I can, but I'd be very interested to hear about alternatives. I take it you are doing some reasonably heavy processing given the need for 4Bs? I have a few old 3s you are welcome to. A great list from @PshemekZ there. I don't know much about these: 

But didn't see them in the list. 

 @Freaklabs will likey have some ideas too. Looking forward to hearing more.

Cheers,

Rob

Unfortunately not much to add. I think there was an assumption that Raspberry Pi's would always be available and it's turning out that it's unfortunately not the case. I'm guilty of this for standard chips. I didn't think there'd be such a huge shortage that spread across so many chip families which left us scrambling.  I'm sure the supply crunch will ease up soon so the RasPi shortage should ease. It should be considered thought that should something happen to the Raspberry Pi Foundation, there's a possibility that the production could end. Since Raspberry Pi's are not open source, this would be devastating to many projects that rely on them. 

As for porting to another platform, I guess the question would be which platform to bet on for the Raspberry Pi alternate and possibly eventual successor. It would probably need to be open source, widely available, and have enough community around it to support itself. Nothing immediately comes to mind (Jetson possibly but not open source and subject to whims of nVidia).

And perhaps this could turn into a community project to come up with an open platform that conservation communities can standardize on where availability could also be guaranteed. There's a lot of exciting things happening with the RISC-V architecture, which could be a good candiate.

As an update from us, we are playing around with two alternatives:

  • Banana PI BPI-M5 M5 4GB 4 x 2GHz 
  • Radxa Rock 4 SE 

I'll update once we have results!

 

See full post
discussion

Thinking out loud

I am a scat dog handler and have been looking to add tech. into my odor training. I got a fresh idea of making a self-dispensing machine that automates when a small novice puppy...

0
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...

10 1

Hi Valentin, sorry for the big delay! I forgot to set notifications for messages. 

 

Yes so the PICT was relatively straight forward to follow - we are not python experts either but could follow along enough. The one thing we need to sort out is capping the data storage, etc. as it crashes them. And there's not instructions per say for that but sure we can work it out. So I would say yes its certainly worth a try! We had a few students putting together the cameras as well, along with our support so always encouraging if intructions work in that scenario too. 

 

VIAME is awesome - you actually can use a cloud-based version and forgo the hefty computing requirements by going to https://viame.kitware.com. Super cool option!

Hi there! I'm actually in the process of procuring another set of camera trap hardware for our group and would be interested in this is if you had the full set of documentation for putting together hardware? We have the PICT camera's but had some problems getting Raspberry Pis so was hoping to find some alternate. But if there isn't one then of course, no problem! If easier my email is [email protected] Thanks!

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.

See full post
discussion

WILDLABS Platform Updates

Hi everyone, I'm Filip, director at Octophin Digital, a little digital agency building things for the wildlife conservation sector. The WILDLABS team have been working with us to...

12 8

Hi everyone!

Only a one item update this time but it's a major feature and one we've been working on for a while. The platform now has an email notifications system.

As technologists you'll know that often the things that seem simple end up taking the longest. Though we knew it'd be a mild challenge this ended up being a giant one. But we got there. Great work from @Cris doing much of this implementation.

A large aim was to only use notifications to guide people back to the platform if there had been any recent and directly relevant updates while they were away.

The emails will trigger at most once a week and will only trigger if you have any notifications that have been generated in that week and haven't visited the site in that time. So, if in the last week you've:

  • been mentioned in any content
  • had any replies to your content / comments
  • had any reactions to your content
  • had any direct messages.

And you haven't checked your notifications in a week, all of these will be bundled up in an email.

If you regularly check the site and your notifications you'll never receive an email as it's always triggered a week from the last time you checked in. Of course you can head to your profile and untick "I am happy to receive activity notification emails from WILDLABS" to disable all emails.

As always please let the WILDLABS team know about any issues with this in the platform help thread.

September 12th, 2022

  • New email notifications system

Sneaking into Filip's serious platfrom thread here to share that we just charged past 1,000,000 pageviews! We've seen a big uptick since we launched the new site back in May, so Filip's team definitely filled the brief of making the wealth of information held in our community easier to find and explore. Feels like a solid milestone we should celebrate :D 

Hi everyone! 

You may have noticed already but we've been hard at work here in the Octophin Digital team on a completely refreshed discussions system for WILDLABS that we've been rolling out over the last two weeks. I didn't want to write about it until a few bugs were sorted out but here's that update.

We didn't quite get the discussions user experience right at launch (especially when it comes to replies / sub threads) so we hope this new version is a lot easier to use.

November 2022 (several deployments so no clear date this time!) 

Discussions

  • Better signposting of buttons to reply to a thread or a specific comment
  • Quick, no page refresh comment editing system
  • Inline form to post a reply to a comment on a discussion
  • Deep linking to specific replies to a comment from a notification
  • Inline, collapsible display of comment replies, displaying avatars of who's replied
  • Options to expand or close all reply threads
  • Faster lazy loading of discussion threads without a flash at the start
  • Many other design and interaction changes
  • We've pushed in some replies imported from the previous version of the platform that were replies to replies to replies(...) so they are now simply listed in date order on the reply thread rather than nested so deep it was hard to find them. Replies are (hopefully uncontroversially) now limited to one level deep.

Hover states 

  • Thank you to @valeria in the Octophin team for adding many lovely hover states to things across the site that will hopefully make exploring WILDLABS more enjoyable.

Feed

  • Sorting on the site feeds (including group feeds) was stacked in favour of new content rather than updates to discussions. A new comment on a discussion will now pop a discussion to the top of the feed so you can quickly see what is new around the site. The feeds can still be filtered to specific types of content in case you want to filter out discussion updates.

---

I hope the above changes make the site much more usable. As always, please pop any feedback over to the WILDLABS team in the New Platform Help: Troubleshooting & bugs discussion. A gigantic thank you to @JakeBurton in the WILDLABS team for a mammoth amount of testing, feedback and suggestions for the above.

See full post
discussion

Introduction to CT Textbook 

So this is an idea that I've had for a while, and I have some bandwidth for it now. I want to make a purely online (free for all users) conservation technology textbook (...

1 0

Hi Andrew, I think this is a great initiative, and I'd be happy to support it.  I'm an EdTech expert rather than conservation tech, although I do teach coding/camera-trapping basics etc.  What I could do is act as a sounding board and offer ideas on how to make the online resources interactive, choose EdTech tools that best support what you're trying to achieve, running it as a MOOC, open licencing of learning materials, and/or supporting sociable and peer-learning.

I'm self-employed so wouldn't be able to commit as much as several hours/week, but I could be involved at that level at particular stages, commit several hours/month, or be a resource person that you call on when needed.

See full post
discussion

Picking up signal of GPS tag

Hi all! Has anyone been able to collect any ID information from a GPS tag, by circling above with a drone? Thinking about FAD detection at sea.Thanks!

5 0

Thanks Carly! I've been in awe of what Wildlife Drones is doing, but as you say my work at the moment is focussed on existing GPS units rather than telemetry for tracking. I'll still reach out & ask though. Thanks for your help! :)

Hi Kim! Thanks for sharing, this is really interesting! I'll check out the website & see what I can find out about the mechanics of the device. Thanks again!

Hey Sol, 

The only way for you to collect information from a GPS tag attached to a FAD is if that tag transmits that data to the drone. Unfortunately most receiver packages are a bit too large for hobbyist-style drones (from what I've seen). 

Depending on the range/distance from shore, you might be able to have a shore-based receiver system?  

See full post
discussion

Using social media for Citizen Science projects - examples

Hi everyone, I am a first-year student on the MS in HCI at RIT, and I am working on a school project about using social media platforms for citizen science projects ( I am...

20 1

Hi Natalia!

This is not for birds, but we are running a whole bat monitoring programme based on citizen science, and every tool we have prepared is ready to be used at European scale! You can find all the information here: www.batmonitoring.org

Feel free to contact me if you need any information. 

All the best!!

Adrià

Hi Adrià! 

Thanks for sharing the link and congrats on the plans to upscale it! I will explore the page more and reach out with a few questions about setting up stations and the data collection process.

Thanks again! Have a nice weekend!

Natalia

See full post
discussion

Welcome to the Conservation Tech Training and Education Group!

Hello and welcome to our group!In this group, we’ll be discussing all things conservation tech education. That may seem broad and the intent of it is!...

7 7

Hello Everyone! I'm Andrew, and currently, I am a postdoc at Max Planck Institute. I worked with @cshriver to start a Conservation Technology course at Georgia Tech that has turned into a student organization named, Tech4Wildlife! We are working to generate various Tech4Wildlife curricula and new Conservation Tech projects with multiple collaborators! Would love to hear from anyone else teaching courses and from folks in industry for what is needed for the next generation of conservation technologists! 

See full post
discussion

Cameratrap flash overexposure

Hi,Having used the Bushnell E2 trophy cam and had no problems I recently purchased an E3 trophy cam. I am having issues with over exposure of the flash. I have tried it in a few...

3 0

I have not used Bushnell camera traps for quite a while, so this may not apply, but most makes have a flash intensity adjustment. If you have already tried that without success then opaque or translucent tape over the LEDs will do the same job.

We have used cut pieces of translucent milk jug plastic to make a flash attenuator.  Stack as many as you need to reduce exposure and tape on. 

Hi @LucyHReaserRe I've found a couple of layers or three of athletic/sports tape does the trick. This kind of thing: 

Good luck,

Rob

 

See full post
discussion

Looking for folks to do resume/CV reviews

Hi--I'm in the middle of my job hunt, and would love to have folks to work with and give me feedback on my resume/CV, and hoped that there might be other people here on wildlabs...

9 6

I hope for your sake that I am way too late to help you (!) but if you did put together a group and it is still going, I would be happy to get involved review - I do a lot of recruitment myself, and support others with it, and I even used to work in HR, so I have a good idea how recruiters think and know what hiring managers are looking for. 

Thanks for the kind wishes! I did just start a new job, and the group I tried to put together never really got off the ground. Hopefully some other folks can take this thread and make some connections and run with it, though.

HI folks: If anyone is looking for a teaching-focused academic careers (e.g. primarily undergraduate institution) I'd be happy to look at anything through that lens.  

See full post
discussion

Automatically detect animals in camera trap images and filter out the empties

Hi, just wanted to let you know the existence of EcoAssist. It's a no-code interface which makes the use and...

9 0
See full post
discussion

Welcome to WILDLABS!

Hello and welcome to the WILDLABS community! With 6,000 members and counting, we want to get to know you a little better. In a couple of...

175 0

Good morning from Italy! 

My name is Valentina Iesari, a young biologist of the center of Italy. Currently, I'm collaborating with a NGOs (BirdLife Italia) as a provincial delegate of my region to protect birds' population and biodiversity locally. 

In the last few years, I worked abroad as an assistant resercher (particularly in Germany) to study in deep the field of movement ecology. I have collected experience in camera traps and acoustic monitoring, so I'm here to share my knowlodge with this great community. 

I'm looking foward to being part of some discussions. 

All the best, 

Valentina.

 

Hi everyone!

My name is Floor and I am part of the SPACES coalition, which aims to make spatial intelligence widely available and used by governments, businesses, NGOs, communities, and finance to operationalize commitments and targets, frame integrated strategies for nature, climate, and people & promote transparency.

We just launched a new paper with the coalition showcasing the potential of spatial data & digital tech to prioritise and track nature and climate action. Some key insights include that to unlock the potential of new spatial data and technologies for nature and climate, three things are needed: 1) more investment in, and collection of, data by private and public actors; 2) trusted, standardised measurement frameworks to ensure like for like collection and comparison; 3) radical transparency data should be made accessible and shared as a public good - the future of people and the planet depends on it.

I would be happy to connect with others to discuss the specific actions they think are needed in this space, also highlighting what specific initiatives are already working in this space. 

Hi Stephanie, hi team

Thanks for including me. 

 

I am mostly engaged with humanitarian drone efforts and I am now looking to support safe drone operations in ecology and conservation projects. 

 

I am a retired air traffic controller and safety specialist after 35 years in ATC in Australia and Ireland, and R&D globally. I retired after a one year sabbatical with the German Aerospace Centre UAS section in n 2016. I am Australian and have lived in England since 2017. On my background, I am an air traffic management specialist, focusing on safety management and remotely piloted aircraft/drone operations, now with a forty-year career in aviation taking me into the world of drones a decade ago.

As a consultant since 2017, I have advised the World Bank on drone safety, regulations, operations, airspace and harmonisation,  I don’t fly drones (yet) except my personal DJI. I have co-authored knowledge pieces through the WBG that provide guidance on risk, enabling civilian drone operations, drone traffic management (UTM) and regulatory harmonisation. And I advise the Bank during drone projects across African, South and South-East Asia, assisting in knowledge piece preparation, and previously as operations manager and safety lead for BVLOS flying competitions at the Lake Victoria Challenge Tanzania 2018 and Lake Kivu Challenge Rwanda 2020. I also run UAS safety, regulations and UTM/U-Space workshops with the WBG.

As a volunteer, I sit on the board of many drone research groups and observe or lead on a broad range of international forums addressing standards, regulations and safety for drones, such as the ICAO RPAS Panel, JARUS. I hope to bring the voice of the Global South to these often sophisticated meetings, where limited resource settings and remote locations are overlooked. I have volunteered in support of impactful humanitarian drone operations in the Global South through the African Drone Forum.

I have also funded the not for profit Global Drone Regulations Database for the last five years where I am lead researcher and we have been expanding it beyond humanitarian aid to Drone Use in Conservation: e.g., https://droneregulations.info/Malaysia/MY.html#country-search . Our kids are studying environmental science at uni Wildlife Ecology and Conservation, and Marine Biology here in England (We're Australian but moved here when I retired so that I can do my volunteer efforts in Africa)  and they've been helping out with populating the website.  I also run the Global Drone Forum (open source UTM services and risk management approaches, capacity building, and diversity and inclusion support). I am secretary of the Royal Aerosociety RPAAS Specialists Group and IFATCA observer on the ICAO RPAS Panel and UAS-Advisory Group, among other forums. I have been a judge on many drone flying competitions, Australia's Medical Express outback challenge and IMechE UAS Challenge Wales (the SDU Eagles competed there?), and Airwards.  

I love exploring the world, hiking, guitar and family. Family first!!!  

Please reach out if I can every help with anything.  I am really keen to assist with any projects for good using drones in marine or terrain based ecology and conservation.

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

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...

10 1

Machine Learning for Automated Monitoring of Moths


We are an interdisciplinary team focused on building a centralized platform and library of machine learning tools for moth camera trap systems. This work is being carried out by David Rolnick (McGill, Mila), Aditya Jain (University of Toronto, Mila), Maxim Larrivée (Montreal Insectarium), Fagner Cunha (Federal University of Amazonas), and Michael Bunsen (eButterfly, Fieldguide.ai), in collaboration with teams at UKCEH, Vermont Centre for Ecostudies, Aarhus University, and elsewhere.
 

We are building a software architecture whose central theme is to be agnostic to trap hardware (camera type, background sheet color, lighting conditions, and geography of operation)  and which requires minimal expert labeling of moth species to train the machine learning system. Our current updates are the following:

  • A pipeline for training a moth species classifier for any region using open-source labeled data from GBIF (this will soon be released on GitHub)
  • A binary classifier that distinguishes moths from non-moths
  • Modules for localization and tracking of moths

Our ongoing work focuses on using unsupervised/semi-supervised methods for improving the model classification using unlabelled trap data. The below figure shows our localization and classification pipeline:
 

                                                   

We have tested our software on data collected from traps deployed in Quebec, Canada and Vermont, USA. We will soon deploy them on data from Denmark and the UK through our partners.


 

Hi Maximillian

I would also like to give the set up a try, if that would be OK? Could you email [email protected] 

We would want to use it for dung beetles, using a dung based bait, do you think it would be suitable in that context? 

yours

Andy Gray

 

Multi-point insect pollination monitoring using computer vision for agriculture

We are an interdisciplinary team from Monash University and RMIT University, Melbourne, Australia. The core-team members are Alan Dorin (Monash University), Adrian Dyer (RMIT University/Monash University), Malika Ratnayake (Monash University), Chathurika Amarathunga (Monash University) and Asaduz Zaman (Monash University). Our research mainly focuses on designing computer vision-based systems for automated pollination monitoring in agriculture. 

Last year, we developed a computer vision system for pollination monitoring in an industrial strawberry farm. It comprised (1) Edge computing-based multi-point video recording, (2) Automated multispecies insect tracking and (3) Insect behavioural analysis. 

  1. Edge computing-based multi-point video recording

We used Raspberry Pi-based units as camera traps to record videos of pollinators across multiple monitoring stations on a strawberry farm. We used Raspberry Pi 4 with Raspberry Pi camera v2 to record continuous videos of insects at 1920 × 1080 resolution at 30fps. Camera units were powered using 20000 mAh battery banks and mounted on a combination of tripods of monopods. [More info: pub3]

  1. Automated multispecies insect tracking

We developed an automated multispecies tracking algorithm to extract insect tracks from recorded videos. Our algorithm (Hybrid Detection and Tracking - HyDaT) uses a hybrid detection model consisting of a deep learning-based object detection model (YOLO) and a background subtraction-based detection model (KNN background subtractor) to track insects. Here, the YOLO model is used to detect insects at their first appearance in the frame and identify their species. The background subtraction is used to detect insects’ position in all other frames, provided that there are no multiple detections in the foreground. If the environment is too dynamic, and the background subtraction cannot accurately identify the insect’s position, the YOLO model is used for the detection. This enables tracking of unmarked and free-flying insects amidst the changes in the environment. In addition, the YOLO model is used to detect and track flowers enabling insect-flower interaction monitoring. [More info: pub1, pub2, pub3]

  1. Insect behavioural analysis

We analysed the pollination behaviour of four insect types (Honeybee, Syrphidae, Lepidoptera and Vespidae) using the insect and flower tracks extracted using the methods described above. This analysis involved insect and flower-visit counting across the study area. In addition, we used the extracted data to analyse the contribution made by each insect type towards strawberry pollination. We also curated a dataset of over 2300 insect trajectories of four insect types and YOLOv4 annotated images. [More info: pub3]

References 

[1] Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring [Code][Dataset]

[2] Towards Computer Vision and Deep Learning Facilitated Pollination Monitoring for Agriculture [Code][Dataset]

[3] Spatial Monitoring and Insect Behavioural Analysis Using Computer Vision for Precision Pollination [Code][Dataset]

[4] Towards precision apiculture: Traditional and technological insect monitoring methods in strawberry and raspberry crop polytunnels tell different pollination  stories [Dataset]

For more information, contact me on Twitter or send me a message.

See full post
article

Dear AI, We Have Trust Issues

Dave Thau
This essay is the third in a series on the promise and challenges of using AI and machine learning to create a planetary environmental management system.  

0
See full post