So, this week I have started looking into adding new and more fine-grained details and methods to the result page og Animal Detect. Including the CameraTrapDP format (coming soon) - but first I need some date, time and location.
While images from Drones often come with detailed metadata directly with the image, most trailcamera images does not.
So the challenge? Well.. sometimes you can get the date/time from the filename, other times you can get it from metadata, with exif, but in many cases you have to get the data from the image itself, where you can find a timestamp amongst other information. This is often done by an OCR (Optical character recognition) model.
I tried out a few tools such as camtrap.R - I found the results, even with the OCR method quite disappointing on a subset of images from:
The tools I tried all seem to be based on Tesseract OCR which in my view is outdated and EasyOCR, MMocr and PaddleOCR, amongst others seems way more potent, looking at benchmarks.
For now, I started coding using EasyOCR, as its relatively fast, while with a bit of tinkering, the results of getting time/date seems way better than the tools I tested on the same data.
--------
Now for the questions: What metadata is otherwise needed?
So images sometime come with additional information, burst sequence, image size, camera brand, camera model, temperature, barometric pressure and lunar phases. Are these any usefull for wildlife conservation? I mean, full moon = werewolves (hehe) but other than that? When we were building our own cameras, from the people I asked, they said that temperature and barometric pressure was mainly used for hunters, to see if it was "good hunting weather". But seeing that some offline cameras also have it, where this claim seem a bit off, I really wanted to know how it's useful?
Additionally, would it be better to get temperature and so on from past weather data rather than cameras themselves? As the temperature and barometric pressure from cameras is very dependent on the installation. Is the camera mounted on a tree with shaddow? Is there direct sun? What height is the camera mounted on? Does the internal electronic heat up and is not accomendated for in the temperature reading? And so on.
Since the lunar phases are not present on all images a cheap hack would be to use the location + time + Pyorbital
For weather, I guess there is something as well you can pull data from, which may not be "hyper local" to the camera, but the surrounding area.
Please tell me what is needed and why! I'm super curious :)
4 August 2025 11:00pm
Hi Hugo, it's great that you are thinking about adding metadata features to Animal Detect! I'll share what I think would be useful from my perspective, but I think there is a lot of variation in how folks handle their image organization.
Time and date are probably the most important features. I rename my image files using the camtrapR package, which uses Exiftool to read file metadata and append date and time to the filename. I find this method to be very robust because of the ability to change datetimes if needed -- for example, if the camera was programmed incorrectly, you can apply a timeshift to ensure they are correct in the filenames. Are you considering adding Exif capability directly to Animal Detect? Otherwise, I think that having a tool to parse filenames would be very helpful, where users could specify which parts of the filename correspond to camera site, date, time, etc., so that this information is included in downstream processing tasks.
I have found it frustrating that information such as camera name and temperature are not included in file metadata by many camera manufacturers. I have used OCR to extract the information in these cases, but it requires a bit of manual review, and I wouldn't say this is a regular part of my workflow.
Camera brand and model can be useful for analysis, and image dimensions and burst sequence can be helpful for computer vision tasks.
Hope this helps!
Cara
Cara Appel