WILDLABS logo

WILDLABS logo

Group

Camera Traps / Feed

Looking for a place to discuss camera trap troubleshooting, compare models, collaborate with members working with other technologies like machine learning and bioacoustics, or share and exchange data from your camera trap research? Get involved in our Camera Traps group! All are welcome whether you are new to camera trapping, have expertise from the field to share, or are curious about how your skill sets can help those working with camera traps. 

discussion

Discussing an Open Source Camera Trap Project

Akiba

2 April 2019 2:49am

Hi everyone.  This conversation took place in the Sensors thread and I'm moving it over here since it's more relevant in the camera trap thread.  [Alasdair...

4 0
Tim van Dam

3 April 2019 8:11am

What avout the open source OpenMV? It looks like most of the general requirements are met with this platform?

Akiba

3 April 2019 10:46am

Hi Tim.

The OpenMV is quite interesting and I haven't thought of it for a camera trap application. It's quite useful for machine learning operations, but the camera resolution is 320x240 color or 640x480 grayscale which is a bit on the low side. That's the equivalent of 0.3 MP. The main reason for the low resolution however is that they focus more on the machine learning algorithms and video capture rather than still images.  For still images, I think it'd be nice to take advantage of the 5MP cameras on up to the 10+ MP cameras for a flexible camera trap system. I'll be doing animal population surveys in the forest and mountain we manage which would mainly consist of still photos. 

As an off-the-shelf solution, Arducam actually has quite good specs. There are potentially other issues such as how long it takes to get the picture off the camera or take consecutive photos. The FPGA code is also not open but it might be a good starting point to a fully open camera trap system. 

Akiba

Arky

19 April 2019 10:30am

Perhaps the new generation of low-power and high performance boards based on RISC V might allow us to build camera traps that could handle high resolution imagery. 

Has anyone got their hands on these boards yet?

https://www.indiegogo.com/projects/sipeed-maix-the-world-first-risc-v-64-ai-module#/

 

 

See full post
discussion

Camera-trapping best-practices

Ollie Wearn

15 June 2016 4:25pm

Hi everyone,  As part of a WWF-UK conservation tech initiative, I'm putting together camera-trapping best-practice guidelines, aimed at field...

19 0
Andy_Jones

29 March 2019 11:09am

Hi Ollie

As a newbie to camera trap data, this makes interesting reading.

Just to check my understanding on terminology, in Figure 5, the reference to "Automatic filtering of blanks" - did that refer to eliminating false positives, so reducing the number of images that are not of interest ?

Andy

See full post
article

Getting up close and personal with Antarctica's orcas

Jamie Morton

4 February 2019 12:00am

In this case study, Science Reporter Jamie Morton tells the story of how Kiwi scientists are teaming up with a local underwater robotics company to gain world-first insights into the lives of whales in Antarctica.

0
See full post
discussion

Troubleshooting: Trophy Cam Agressor

Adrián Schiavini

26 November 2018 6:53pm

I work in Tierra del Fuego, Argentina. I have a Trophy Cam Agressor from 2015 (model 119776). It started to record date time wrongly with delays of different magnitude. I...

7 0
Rob Appleby

25 January 2019 3:21am

Ok no problem Peter. My colleague Neil Jordan works in Botswana, as does Lucy Ransome (who is heading there in April). Otherwise, do you have a contact I can send it to so they can get it to you?

Cheers and thanks again for the interest. 

Rob

Peter Apps

26 January 2019 7:24pm

Neil was who I was thinking of. I'm not sure when he plans to next be here.

Peter

Rob Appleby

26 January 2019 11:39pm

Hi Peter, Ok cool, I'll ask him. I know Lucy is heading back over in a couple of months for sure though, so happy to give it to her for you.

Cheers,

Rob

See full post
discussion

Troubleshooting: Trophy Camera Brown, Bushnell

Marissa_Eliza

14 November 2018 1:01am

Heej everyone, I am a Dutch student currently conducting a camera trap study in Costa Rica. I will be comparing density estimates of mammals between line transect surveys and...

1 0
Beanstown

26 November 2018 2:57pm

Hi Marisa,

It sounds like the Iris on the lens may be stuck open or its been drifting into an open position (hence why you could see images for a while, but now the image is completely whited out). Is there the ability to alter the lens Iris on the camera?

If you can view what the image looks like directly from the camera (is there an ability to view the fiield of view as you set thecamera up?) you should  see the same problem if the Iris is wide open.

Try and isolate the problem step by step to rule out each element of the technical system, whenever you have a technical fault.  In this instance there isnt much that you have to play with on a simple trail camera. It would seem the power supply is OK because images are being captured (even though they are whited out) and the PIR is functioning to trigger the images. Check the SD card you are using works OK in another camera to rule that out as the problem too. Are the settings on this camera the same as others that are working correctly? If not alter them too.

There is also a detachable anti reflective LED cover on this Bushnell. Check its not been slipping over time and bouncing the LED illumination directly into the camera lens. That would white images out to varying degrees too.

Best,

Dave

See full post
discussion

Data Needed: Mitigating rhino poaching through multimedia data mining

Sibusiso Bakana

27 September 2018 3:43pm

Greetings everyone, I am a PhD student at Beihang University in Beijing, China. My focusing is in mitigating rhino poaching using multimedia data mining techniques. In order for...

4 0
Sibusiso Bakana

28 September 2018 11:54am

Hi Steph,

Yes, my project objective is to detect rhinos and invaders at the sametime through videos not images. The tool is to be used by the game farm owners in order to protect the rhinos, well by invaders I imply the poachers. 

Thank you very much for the information, yes I need funding as a realtime data will be advantageous for the better prediction. As we all aware mining videos is challenging as compared to images as videos are un-structured data.

Keep in touch.

Sibusiso

Sibusiso Bakana

7 October 2018 3:26pm

Greetings Everyone,

Last week I have written to this community with regards to video data for attempting to analyse videos with rhino community, in order to conduct my research for object detection, object behaviour analysis and invader detection in a protected game farm. Seems It might take time to get such data, I wish to state it clear that the idea is to understand object detection, invader detection and behaviour analysis for wildlife animals and I focused on rhinos because thats what is dangered in my country (South Africa).

Nontheless, if now we dont have specific videos for rhinos, I still welcome video data for elephants. If again there are no video data, I can work on the images of both rhinos and elephants. As we know videos are just a set of continous images linked. For me to conduct my PhD research I depend on data and surely as the project progress, maybe we might find one or two videos that can use to justify my solution. So in simple, anyone who has elephant or rhino images can assist, as both of this wild animals are attcked by poachers for various reasons.

As the objective is to mitigate the poaching of the wild animals through multimedia data mining. 

Please assist a fellow researcher...:)

Thanking you in advanced.

 

Regards

Sibusiso

Nigel Street

25 October 2018 1:44am

Hi Sibusiso,

Are you looking for huge data sets or would vacation pictures (mostly Uganda) of elephants be of any help to you?

Cheers, Nigel

See full post
article

Drones, Orangutans, and Strangler Figs in Malaysian Borneo

Sol Milne

22 October 2018 12:00am

In this case study, WILDLABS member Sol Milne takes us through his Ph.D. work investigating how changing land-use is affecting orangutan distribution in Sabah, Malaysian Borneo. With the help of five local research...

0
See full post
discussion

Recommendations Needed: Submersible Camera Traps

Chloe Aust

13 July 2018 3:15pm

Hi everyone, I am working on a project where we want to set GSM cameras up on the seashore. Theoretically the cameras shouldn't go under water but in storms there is a chance...

3 0
Rachel Kramer

13 August 2018 8:50pm

Hi @Chloe+Aust - great to see that you've found the right GSM camera trap for your needs. I was following this thread with interest as well: https://www.wildlabs.net/community/thread/388. A friend who works with underwater equipment said that he had some ideas. I'll put you in touch - it would be great if you can discuss via this thread so others can see his recommendations as well.

smandel

14 August 2018 1:38am

Hi Chole, there is a fellow named Sebastian Kennerknecht who is a camera trap wizzard.  He has done a ton of work for Panthera.  He might be a guy you want to speak with.  You can find him on FB or I can privatley connect you.  And, we should put your findings on the forum here so everyone can benefit.

 

Chloe Aust

24 August 2018 3:51pm

Amaxing, thank you! We had to put them out already so have gone with the super-tech solution of a  *very* high pole for now but will look at speaking to Sebastian, or with your contact Rachel if that fails. Thank you so much! Chloe

See full post
discussion

New Paper: Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

Stephanie O'Donnell

7 June 2018 5:04pm

A new paper just came out in PNAS that seems to be getting quite a bit of attention - researchers have developed a type of artificial intelligence called "deep neural...

1 0
Ollie Wearn

20 July 2018 3:58pm

Thanks, Steph. The camera trap ML nerds among us will have seen drafts of this kicking around in pre-print for a while now. Very cool to see it out finally.  

I'll also draw everyone's attention to another study (involving some of the same authors) which has just come out in draft form: "Machine learning to classify animal species in camera trap images: applications in ecology". 

 

See full post
discussion

Recommendations Needed: Best sensors and cameras to install along fence gaps in a conservancy

Damian

16 April 2018 10:38am

Looking for sensors and cameras to install along fence gaps in a conservation area to uniquely and precisely identify animal movement patterns. Any ideas?

8 0
Stephanie O'Donnell

2 May 2018 12:27pm

Hi Damian, 

This may be part of your conversation with Alasdair and the ZSL team already, but you might want to connect with @Institute+IRNAS as well. They're collaborating with Alasdair's Arribada Initative, ZSL and others to tackle some of the challenges you've also been looking into (e.g LoRA systems). There's some more info about their work here: http://irnas.eu/conservation

Luka (if it is indeed you who is manning the Institute IRNAS member profile here on wildlabs), maybe you can jump in here? 

Steph 

 

Damian

2 May 2018 1:16pm

Hello Stephanie,

Thank you for the Introduction. This is nice and I think they can be very helpful to us at this moment. Especially on the acoustic sensors and LoRa network setup initiative.

Looking forward to getting intouch with them.

 

Regards,

Damian

Institute_IRNAS

7 May 2018 11:04am

Hi Damien,

Lora technology enables a range of very efficient solutions that you can deploy over a large area. We provide consultancy and field support for deploying such networks and work with Arribada team on developing custom hardware solutions for various applications in the conservation field. I suggest you explore the existing options and let us know if you need more customized solutions.

Regards,

Luka
Institute IRNAS

See full post
discussion

Recommendations Needed: Camera for remote work using Irriduim for image upload

Stephanie Winnard

15 February 2018 1:02pm

Hi all,   I'm looking for advice on companies that can provide me with a camera to be deployed on a sub-Antarctic island. It's not for counting, it is more of...

3 0
Institute_IRNAS

9 April 2018 12:30pm

Hi swinnard,

we have built a system this year for Arribada Initiative http://blog.arribada.org/ that is working closely with ZSL that implements the functions you require to a large extent. The Arribada FMP device is open source open hardware and you can find more details here: https://github.com/IRNAS/arribada-fmp

The device has the following features:
* Solar powered
* Built-in camera
* RockBlock Iridium modem
* WiFi and LoraWAN communications (not required in you application)
* Ultrasonic distance sensor (not required in you application)

We have built a version of this device for Arribada Penguin monitoring: https://github.com/IRNAS/arribada-pmp which captures images hourly on Antarctica of penguins and stores to the SD card, without the Iridium comunication.

Note that the cost of Iridium system may be prohibitively expensive, see http://www.rock7mobile.com/products-rockblock

2000 credits for 800GBP will give about 100MB of capacity, which can translate to about one photo per day if a compressed resolution is sufficient. A full HD image will for example be 2.4MB. 

A more optimal method would be to take a photo several times a day, process them using OpenCV or other image processing library to determine if the image is interesting and then send it via Iridium. This can save some data as well as generate interesting photos. All of them can be stored to the SD card and retrieved at a later point.

Stephanie Winnard

16 April 2018 3:26pm

Hi Institiue IRNAS, 

Thank you very much for your response, it is very helpful information. 

I will have a look in more detail into your camera. For us it is not possible to choose photos to be sent back, we need them all to come back via irridium, so it is definitely the part of the project that can quickly become cost prohibitive. 

I've been in touch with a research group that used an Instant Detect camera from ZSL which they now want to sell, so I may well end up using that system. If not though, the system you are using looks great. 

Thanks for sharing it with me. 

 

 

 

 

Paul Meek

26 April 2018 11:39pm

Dear All

 

Our group in Australia has developed a device for monitoring wild dogs/dingoes in remote areas and have a fully authomated system using Iridium and or 3-4G if available. This device is officially called Wild Dog Alert Node and will be capable of being deployed into remote areas, gathering image data using a unique sensor system, processing the image and sending it to the cloud where it is identified as a wild dog-dingo and an alarm is immediately triggered. In our case it is to prevent predation on livestock but this technology could easily be modified for any species. The R&D is being refined and we are expecting to start disseminating information soon in both scientific papers and general media https://invasives.com.au/research/wild-dog-alert

See full post
discussion

Data Needed: Camera trap images for machine vision training

Neil Sheridan

29 March 2017 8:06pm

Hi everyone, I'm working on an object detection system for detecting elephants! It's detailed here https://www.wildlabs.net/community/thread/284 and at my project...

8 0
Stephanie O'Donnell

7 February 2018 3:22pm

Hey, this is really interesting @theraido, thanks for sharing. Kirk has a nice writing style that's really easy to understand.. to the point where I feel lulled into confidence that I'd be able to replicate the project without too much fuss (I suspect this might be rather a strong case of over confidence). I was also amused that waiting for the birds to appear at the feeder seemed to be the slowest part of the project. 

It looks like it's going to be a series of tutorials, with the goal being to build an open platform for exploring crow intelligence. Eventually, he says like to identify individual crows in the wild, and give them the opportunity to pass a series of tests. So it'll be interesting to follow along and see whether he reaches this goal. 

In case anyone is interested, the next tutorial posted so far is 'building the rich man's deep learning camera', where he shares how to build a self-contained deep learning camera to detect birds in the wild.

 

Anton Zhang

20 April 2018 4:19am

Sounds great!

I am doing the almost same thing, since here we have a problem between elephant and human living in the same area and conflict a lot. We would like to warn people when elephants are approching by camera trap's detection of elephants.

How is your work now? Maybe we could share some info and put it forward together.

Anton

See full post
discussion

Recommendations Needed: Software for sampling photos from video

nunonegroes

6 July 2017 7:42pm

Hello Camera trappers :) I am using video in our cameratraps sampling but need to extract picture from them to identify jaguar individuals. Any suggestion of good software to...

6 0
David Neils

17 April 2018 8:23pm

My preference is to use Adobe Lightroom, allowing me to move forwards or backwards one frame at a time. I can also adjust the exposure. This is an example from one of my videos. 

I hope this is helpful. 

 

See full post
discussion

Camera Trapper from Colorado

David Neils

17 April 2018 8:19pm

I'm honored to be part of this WILDLABS group and specifically this Camera Trap forum. I hope that what I've learned weekly over the past 14 years will help others. Most...

0
See full post
event

Camera trapping workshop, London

Amy Fitzmaurice

16 April 2018 12:00am

This one day workshop will cover key aspects of planning, executing and analysing camera trap surveys in the field. It will also examine the various survey techniques for which remote cameras provide a powerful tool and...

0
See full post