Hi Nilaksha,

Interesting idea.  My ideas are usually not that helpful, but I thought I would chime in with the following:

(1) Start small and local, this will help reduce the size of the training data set you will need.  So if you can work with a specific set of communities in a particular area that has a known set of snake species, both venemous and non-venemous, you only need images for those species and you won't need as many.

(2) iNaturalist has a pretty decent database (not thousands, but hundreds) of identified images.  I have no idea what the restrictions would be around getting access to the database, but this is a Citizen Science organization, so I don't THINK it should be too complicated, especially if your initial scope is limited.

(3) Venemous snakes need "love" too.  PLEASE make sure the app does not encourage the locals to kill the venemous snakes unless absolutely necessary.  While it is admirable to prevent the accidental killing of a non-venemous snake, you shoudl not be encouraging the purposeful killing of the venemous snakes, but should be encouraging people to stay clear if the snake is in the wild and get professional assistance if the snake somewhere that could be dangerous to humans or other animals.

(4) Look into organizations like the Rainforest Aliance, OpenAI, etc., which are non-profits doing work in or with AI, they might be able to help give you a leg up.

(5) If you start local, you could build into the app the contact information for the professionals to come in and deal with the dangerous snakes.

Hopefully some of this is useful.

Good luck,

Drue

Hi,

You should talk to @hikinghack ; also take a look here.

Thanks,

-harold

Hi Aditya, 

If you haven't already found it, you should check out our last virtual meetup, it was all about tools and spaces for collaboration and we featured a number of members who have set up and are working on conservation focused makerspaces. You can watch in and connect to the members featured here. 

Steph

Hi Femke,

At the Biological records Centre we have been tackling these issues for over 50 years! You are right to point out that with citizen scientists you can collect/review a lot of data in a relativly short period of time. Our iRecord system collect 1 million observations in 2018, and just look at how many people are reviewing images over in the zooniverse (check out snapshot serengeti).

You are also right to point our that without strict protocols, and with varying abilities, the use of citizen scientists can introduce biases, which often leads to the impression citizen science data is of lower quality. There are ways to account for this statistically when you are working on data collected in the field, and for those reviewing images online both the zooniverse and iSpot have systems in place, such as reputation and multiple reviews of a single image to reach consensus.

There is a good report on using citizen science here.

Best,

Tom

I agree with Tom's comments. A project I work with has used Zooniverse to identify animals in camera trap images, We include a field guide that helps reviewers with making trickier distinctions such as deer versus elk (challenging in partial views with IR images). We require each image to be identified by thirty reviewers before scoring it. That allows us to either be quite confident in an identification or to recognize it requires expert review. We have seen no examples of intentional misidentifications. The biggest problem is coming up with enough images to meet demand--some people will work for hours!

Dear Sdorji,

Thanks for sharing! Are you specifically looking for monitoring methods? In that case, you could probably also find relevant information outside of the HWC group, perhaps in groups focussing on camera trapping, the use of drones etc on the other WILDLABS pages. Do you know about the Bhutanese national HWC strategy? Does this also focus on wild boars? Or is your initiative not connected to that?

Best regards,

Femke

Dear Sdorji,

Thanks for sharing and your request for suppport from this group! I was thinking that perhaps @Mohan+Raj could share with you some insights from India? He has also developed fences and is involved in the technologies to improve monitoring and maintanance.

Best regards,
Femke