Group

Data management and processing tools / Feed

Conservation tech work doesn't stop after data is collected in the field. Equally as important to success is navigating data management and processing tools. For the many community members who deal with enormous datasets, this group will be an invaluable resource to trade advice, discuss workflows and tools, and share what works for you.

discussion

Automatic extraction of temperature/moon phase from camera trap video

Hey everyone, I'm currently trying to automate the annotation process for some camera trap videos by extracting metadata from the files (mp4 format). I've been tasked to try...

7 0

Hi Lucy

As others have mentioned, camera trap temperature readouts are inaccurate, and you have the additional problem that the camera's temperature can rise 10C if the sun shines on it.

I would also agree with the suggestion of getting the moon phase data off the internet.

 

Do you need to do this for just one project?  And do you use the same camera make/model for every deployment?  Or at least a finite number of camera makes/models?  If the number of camera makes/models you need to worry about is finite, even if it's large, I wouldn't try to solve this for the general case, I would just hard-code the pixel ranges where the temperature/moon information appears in each camera model, so you can crop out the relevant pixels without any fancy processing.  From there it won't be trivial, exactly, but you won't need AI. 

You may need separate pixel ranges for night/day images for each camera; I've seen cameras that capture video with different aspect ratios at night/day (or, more specifically, different aspect ratios for with-flash and no-flash images).  If you need to determine whether an image is grayscale/color (i.e., flash/no-flash), I have a simple heuristic function for this that works pretty well.

Assuming you can manually define the relevant pixel ranges, which should just take a few minutes if it's less than a few dozen camera models, I would extract the first frame of each video to an image, then crop out the temperature/moon pixels.

Once you've cropped out the temperature/moon information, for the temperature, I would recommend using PyTesseract (an OCR library) to read the characters.  For the moon information... I would either have a small library of images for all the possible moon phases for each model, and match new images against those, or maybe - depending on the exact style they use - you could just, e.g., count the total number of white/dark pixels in that cropped moon image, and have a table that maps "percentage of white pixels" to a moon phase.  For all the cameras I've seen with a moon phase icon, this would work fine, and would be less work than a template matching approach.

FYI I recently wrote a function to do datetime extraction from camera trap images (it would work for video frames too), but there I was trying to handle the general case where I couldn't hard-code a pixel range.  That task was both easier and harder than what you're doing here: harder because I was trying to make it work for future, unknown cameras, but easier because datetimes are relatively predictable strings, so you know when you find one, compared to, e.g., moon phase icons.

In fact maybe - as others have suggested - extracting the moon phase from pixels is unnecessary if you can extract datetimes (either from pixels or from metadata, if your metadata is reliable).

camtrapR has a function that does what you want. i have not used it myself but it seems straightforward to use and it can run across directories of images:

https://jniedballa.github.io/camtrapR/reference/OCRdataFields.html

See full post
Link

Insight; a secure online platform designed for sharing experiences of conservation tool use.

A secure platform designed for those working to monitor & protect natural resources. Insight facilitates sharing experience, knowledge & tools to increase efficiency & effectiveness in conservation. By sharing we reduce time & money spent to find, test, & implement solutions.

0
discussion

DeepFaune: a software for AI-based identification of mammals in camera-trap pictures and videos

Hello everyone, just wanted to advertise here the DeepFaune initiative that I lead with Vincent Miele. We're building AI-based species recognition models for camera-trap...

6 4

Hello to all, new to this group. This is very exciting technology. can it work for ID of individual animals? we are interested in Ai for identifying individual jaguars (spots) and andean Bears (face characteristics). Any recommendation? contact? thanks!

German

That's a very interesting question and use case (I'm not from deepfaune). I'm playing with this at the moment and intend to integrate it into my other security software that can capture and send video alerts. I should have this working within a few weeks I think.

The structure of that software is that it is two stage, the first stage identifies that there is an animal and it's bounding box and then there's a classification stage. I intend to merge the two stages so that it behaves like a yolo model so that the output is bounding boxes as well as what type of animal it is.

However, my security software can cascade models. So if you were able to train a single stage classifier that identifies your particular bears, then you could cascade all of these models in my software to generate an alert with a video saying which bear it was.

Hi @GermanFore ,

I work with the BearID Project on individual identification of brown bears from faces. More recently we worked on face detection across all bear species and ran some tests with identifying Andean bears. You can find details in the paper I linked below. We plan to do more work with Andean bears in 2024.

I would love to connect with you. I'll send you a message with my email address.

Regards,

Ed

See full post
careers

ZSL Research Fellow (x3 roles)

Zoological Society of London
The Institute of Zoology (IoZ), the research division of the Zoological Society of London (ZSL), is seeking to fill three new permanent positions by recruiting outstanding early-career researchers as Research Fellows (...

0
See full post
Link

Marine Flyways - Seabird Tracking Database

To celebrate #WMBD, BirdLife is excited to share the newly identified Marine Flyways!! Seabird tracking data were shared by over 60 researchers from 48 long-distance migratory species and have revealed SIX MarineFlyways. They've created an awesome animation to go along with it!

0
discussion

Software for recording field data?

Heya - I'm after modernising our field data collection process from paper records to directly digitised recording. I'm planning on getting 2-3 tablets, and am looking for apps...

11 0

Have a look at kobocollect, very easy to use and reliable, can collect data and then send them to the cloud when you have internet.

Other solution:

QField - Efficient field work built for QGIS

SMART Conservation Software - Spatial Monitoring and Reporting Tool (smartconservationtools.org)

EarthRanger: Protecting Wildlife With Real-Time Data

I second Kobo/CyberTracker for tracks, but if you have money for an ArcGIS Online license, Survey123 is great (offline use - but can't record tracks)

See full post
Link

Digital Disruption for Conservation Toolkit

Made available by the Digital Disruption and the Future of Conservation project team at Unearthodox, the toolkit provides conservation practitioners with a comprehensive introduction to Web 3.0 and AI concepts and their potential use for nature conservation.

0