Wildlife@Home

A Push for UAV Imagery Analysis

We're making a push to analyze recent UAV imagery taken from the Hudson Bay! Help us find birds, bears and caribou in our images collected from an unmanned aircraft (aka. Drone) in Northern Manitoba. The wildlife found in the images will be used to create training datasets for us to automate post-processing of large datasets from aerial imagery.

You can help us by reviewing images for the UAS Estimating Snow Geese project.

Welcome to Wildlife@Home

Wildlife@Home is a joint effort from University of North Dakota's Department of Computer Science and Department of Biology, aimed at analyzing video gathered from various cameras recording wildlife. Currently the project is looking at video of sharp-tailed grouse, Tympanuchus phasianellus to examine their nesting habits and ecology. The nest cameras have been set up up both near western North Dakota's oil fields and also within protected state lands. We recently have also begun studying two federally protected species, interior least terns, Sternula antillarum, and piping plovers, Charadruis melodus.

Wildlife@Home Goals

We hope that your participation will help us determine the impact of the oil development on the sharp-tailed grouse, and better understand the behaviors of least terns and piping plovers to aid in their conservation, as well as provide some interesting video for everyone to watch and discuss.

Each spring we capture hens on the lek or dancing grounds where males display for females. We fit hens with a necklace-style radio transmitter that emits a unique radio frequency which we can use to relocate the bird and find her nest.

We track grouse using radio telemetry receivers and various types of antennas such as this handheld antenna and receiver. Photo courtesy of Chris Felege.

We track grouse using radio telemetry receivers and various type so antennas such as this truck mounted antenna. Photo courtesy of Anna Mattson.

Once we find a nest, we install a miniature surveillance camera near the nest.

Nest cameras are powered by cable, from about 75 feet away with a 12 volt battery and a waterproof box housing a DVR that will record to SD cards.

A sharp-tailed grouse nest.

Hens will incubate a nest for about 23 days unless a predator finds and destroys the nest. This is a snapshot from our nest cameras of hen incubating her nest.

Sharp-tailed grouse chicks hatching.

Various predators such as this Swainson’s Hawk will attack the hen while she is sitting on the nest. This image is from one of our nest cameras.

Ground predators, such as this American Badger, will destroy the nest.

After the peak of hatch, we follow hens with broods via radio signals. Once the chicks are about a month old, we will relocate the brood and catch them in big net during the night. Chicks are then fitted with their own necklace-style radio transmitters so we monitor their survival and reproduction over the next year.

This image found in the collected video shows a lightning crash behind a piping plover incubating a nest on the Missouri River in North Dakota.

This image found in the collected video shows a piping plover chick walking across the video screen with an adult brooding the remaining chicks on the nest in the background.

The leg bands used by wildlife biologists for bird identification are clearly visible on the flying adult piping plover.

A tern chick yawns in front of the camera while the adult tern incubates the remaining egg on the nest. This image was found in the collected video.

Interior least terns exhibit biparental investment in their nests. This image found in the collected video shows a nest exchange event between two flying tern parents.

An adult tern feeds a fish to a tern incubating a nest. This image was found in collected video.

Volunteer Your Computer

Watch Wildlife Videos

Review Wildlife Images

User of the Day

[AF>Amis des Lapins] Oncle Bob
Processors never rest ! Rejoignez l'Alliance Francophone.

News

[wildlife] windows xp connection issues

I tried a fix on my end for those who have been having trouble connecting to the server with Windows XP. The scheduler in the header for the main page of csgrid had http://csgrid.org listed for the scheduler instead of https://csgrid.org

Let me know if this fixed anything (or broke anything -- hopefully not)!

Travis Desell on Saturday, May 27th
leave a comment

[wildlife] EXACT v0.25 and v0.26

There was a bug I missed in the EXACT v0.25 client which will cause it to crash from over allocating memory. Please abort any WUs running with this version ASAP so they don't eat up all your machines memory. I really apologize, it ran correctly for my local tests but I had missed a call to convert one of the input filenames to it's proper location in the client.

That being said, v0.26 should be running fine. I made quite a few improvements to the code, so now it should require about 1/4th the memory as the v0.24 client (so the CIFAR work units will now take less memory that the MNIST work units from v0.24 and before). It's also running ~2x faster. That and I upgraded the back propagation algorithm to use batch normalization which also means we'll be getting better results from it. Pretty excited to see how it runs.

Travis Desell on Friday, May 26th
leave a comment

[wildlife] "monster" credit reimbursement update

So it looks like there's only about 100 workunits left for this application, so in order to make things fair I'm just going to wait until they all have finished and then apply the bonus credit. This will make things a bit easier on my end. Sorry for the delay!

Travis Desell on Tuesday, May 9th
leave a comment

[wildlife] review image interface should be giving new work

There was an issue with the work generator for the image review interface that should now be resolved. Let me know if there are any issues getting new work jobs!

Marshall Mattingly on Tuesday, May 2nd
leave a comment

[wildlife] PLOS One Article

Susan and her students have published an article in PLOS One on the Wildlife Biology end of things. Here's a link if you'd like to read it:

Sharp-Tailed Grouse Nest Survival and Nest Predator Habitat Use in North Dakota’s Bakken Oil Field

Travis Desell on Thursday, May 4th
leave a comment

[wildlife] "monster" workunit credit reimbursement

So I've been trying to come up with a method to reimburse users for the "monster" workunits that some of you have been experiencing. Unfortunately, by the time these come in many of them have been removed from the database so there is not much I can do in terms of reimbursing individual users for that work lost.

That being said, what I'm going to do is on this coming monday, May 8th, I'll provide a reimbursement to each user with credit from the "EXACT MNIST Convolutional Neural Network Trainer" application. I'll provide a one time award to everyone for 15% of the credit they've generated by that application. This was the best I could come up with as the users who experienced the most "monster" workunits also would have crunched the most workunits as a whole.

That being said, if you're experiencing some workunits from the "EXACT MNIST Convolutional Neural Network Trainer" application that are seeing pathologically long runtimes (multiple days), please feel free to abort them, or any workunits that won't be completed before Monday, May 8th for that matter. After the 8th I will still leave the validator up and going for this application to collect any stragglers, but this award will be one time only based on credit for that application as it stands on Monday.

Sorry for all the trouble these have caused and I hope this is a reasonable solution!

Travis Desell on Wednesday, May 10th
leave a comment

[wildlife] application updates

Had some bugs to fix in the 0.23 application so I've just released an 0.24 application which should fix them. Sorry about the computation errors!

Travis Desell on Saturday, April 29th
leave a comment

[wildlife] new app: EXACT MNIST BATCH

Well, that went quicker than I thought. The new application is released with new workunits (and they seem to be crunching without issue on my systems). This new version of the application changes the memory layout a bit which I hope will fix some of the issues we've seen with the "monster" workunits -- my hunch is that the larger workunits cause caching issues on some processors resulting in the 10x slower runtimes.

The new version of the application uses batch stochastic gradient descent, instead of stochastic gradient descent, which should keep memory accesses closer to each other and make caching better. It also has the benefit of requiring less epochs to train, so the new WUs should run a fair bit quicker in that regard as well.

I've updated the calculation for credit on these workunits which I believe should scale better to larger workunits. This means the deadlines should also be calculated more accurately. Let me know how the credit rate is (especially as the WUs get larger) and if the deadlines are okay so I can tweak things if need be.

Hoping this makes things run smoother! Let me know if you run into any issues.

Travis Desell on Friday, May 26th
leave a comment

[wildlife] downtime

I had a bit of a database issue starting things up for the new apps. So work generation will not be happening until I get things up and going with the new app. Hopefully sometime today.

Validation/Assimilation should still occur.

Travis Desell on Thursday, April 27th
leave a comment

[wildlife] "monster" workunit questions

So I had a couple ideas about the monster workunits. For those of you who are having them, are you running other workunits at the same time? Could you let me know the memory usage of those workunits? Does their performance improve if you only run one EXACT workunit at a time?

What I'm thinking may be happening is that the larger workunits require more memory, and if there are enough other workunits (especially other large EXACT workunits) running at the same time things may end up paging to disk because of memory requirements.

Travis Desell on Monday, May 1st
leave a comment

Active Projects

Feel free to scroll through our image gallery above to get a better idea of what is going on with the project and see the field biologists in action, talk to us on the message boards, or watch videos about the project on our Google+ YouTube Channel. The following projects are actively being worked on by these Wildlife@Home team members:

Alicia Andes - Refined Monitoring Techniques to Understand Least Tern and Piping Plover Nest Dynamics
Paul Burr - Sharp-tailed Grouse Nest Predation Relative to Gas and Oil Development in North Dakota
Rebecca Eckroad - Nest Cameras and Citizen Science: Implications for evaluating Sharp-tailed Grouse Nesting Ecology
Kyle Goehner - Automated Wildlife Detection in Uncontrolled Environments

Contact Information

Please email any questions or suggestions to Travis Desell, or feel free to post a message in our forums.

The Wildlife@Home team includes:

Travis Desell, Assistant Professor of Computer Science, University of North Dakota
Susan Ellis-Felege, Assistant Professor of Biology, University of North Dakota
Chris Felege, Educational Outreach Coordinator, Instructor of Biology, University of North Dakota
Alicia Andes, Graduate Research Assistant in Biology, University of North Dakota
Connor Bowley, Graduate Research Assistant in Computer Science, University of North Dakota
Nickolas Conrad, Undergraduate Research Assistant in Biology, University of North Dakota
Kyle Goehner, Graduate Research Assistant in Computer Science, University of North Dakota
Marshall Mattingly III, Graduate Research Assistant in Computer Science, University of North Dakota
John Palarski, Undergraduate Research Assistant in Biology, University of North Dakota
Lindsey Wingate, Undergraduate Research Assistant in Computer Science, University of North Dakota

With agency support from:

Kaylan Carrlson, Manager of Conservation Planning, Ducks Unlimited.
Tanner Gue, Conservation Specialist, Ducks Unlimited.
Aaron Robinson, North Dakota Game and Fish.
Terry Shaffer, U.S.G.S. Northern Prairie Wildlife Research Center.
Mark Sherfy, U.S.G.S. Northern Prairie Wildlife Research Center.

With previous support from:

Robert Bergman, Graduate Research Assistant in Computer Science, University of North Dakota
Paul Burr, Graduate Research Assistant in Biology, University of North Dakota
Benjamin Carpenter, Undergraduate Research Assistant in Compute Science, University of North Dakota
Becca Eckroad, Undergraduate Research Assistant in Biology, University of North Dakota
Jaeden Lovin, Undergraduate Research Assistant in Compute Science, University of North Dakota
Adam Pachl, Undergraduate Research Assistant in Biology, University of North Dakota
Julia Johnson, Undergraduate Research Assistant in Biology, University of North Dakota
Nitin Karodiya, Graduate Research Assistant in Computer Science, University of North Dakota
Eric Kjeldergaard, Graduate Research Assistant in Computer Science, University of North Dakota
Leila Mohsenian, Undergraduate Research Assistant in Biology, University of North Dakota
Kelly Sagen, Undergraduate Research Assistant in Biology, University of North Dakota
Rebecca VanderClute, Undergraduate Research Assistant in Computer Science, University of North Dakota

Publications

All publications, talks and posters about DNA@Home can be viewed on the Citizen Science Grid's publications page.

Support

Wildlife@Home is currently being supported by NSF award no. 1319700 through the Division of Intelligent Information Systems's Information Integration and Informatics (III) program.

Wildlife@Home is collaborating with Ducks Unlimited on a project invovling blue winged teal.

Wildlife@Home has been generously supported by a collaborative research award and new faculty SEED grant from UND's Office of Research Development and Compliance. The project's video streaming server is hosted by UND's Computational Research Center and the volunteer computing server is hosted by UND's Scientific Computing Center.

North Dakota Game and Fish has provided financial support for field logistics to collect sharp-tailed grouse videos.

USGS has provided financial support for camera equipment, video storage, and field assistance to collect data for the piping plover and interior least tern.

Wildlife@Home is in part powered by the Berkeley Open Infrastructure for Network Computing (BOINC).