I have no familiarity with Lightroom, but the problem you describe seems like a pretty typical data storage and look up issue.  This is the kind of problem that many software engineers deal with on a daily bases.  In almost every circumstance this class of problem is solved using a database.

In fact, a potentially useful analysis is that the Lightroom database is not providing the feature set you need.

It seems likely that you are not looking for a software development project, and setting up you own DB would certainly require some effort, but if this is a serious issue for your work, you hope to scale your work up, or bring many other participants into your project, it might make sense to have an information system that better fits your needs.

There are many different databases out there optimized for different sorts of things.  For this I might suggest taking a look at MongoDB with GridFS for a couple of reasons.

1. It looks like you meta data is in JSON format.  Many DBs are JSON compatible, but Mongo is JSON native.  It is especially good at storing and retrieving JSON data.  Its JSON search capabilities are excellent and easy to use.  It looks like you could export your data directly from Lightroom into Mongo, so it might be pretty easy actually.
2. Mongo with the GridFS package is an excellent repository for arbitrarily large image files.
3. It is straightforward to make a Mongo database accessible via a website.
4. They are open source (in a manner of speaking) and you can run it for free.

Disclaimer: I used to work for MongoDB.  I don't anymore and I have no vested interest at all, but they make a great product that would really crush this whole class of problem.

Hi!

I would take a look at 

Although developed for camera trap imagery, it is by no means restricted to such.

Cheers,

Lars

Frank's idea of using 2 camera traps is inspired!

I've fiddled with cheap camera traps a bit, and some (most?) of them use a low power, inaccurate timer for the time lapse function instead of the accurate real time clock.  This is ok for Michelle's purpose, but not for Nick's as he needs to specify the exact time of day to trigger.

I made this interface to allow a camera trap to be triggered by an external device.  To it you could attach, say, a timer programmed to fire at the desired times, to cause a capture.  A $4 DS3231 RTC module could do the job, after the alarm times have been programmed into it with , for example, an Arduino.

Hi Nick, 

Any update from your project? did you find good price value Camera Traps?

We in Indonesia don't have local suppliers for any research grade Camera Traps like Bushnell, Browning or Reconyx. So we need to import them and the price inflated a lot even without the distributor. So, me and my team recently use the China model like GardePro or Meidase one ($40-60). Though we bought it in the US in small quantity if some of our friends travel back to Indonesia. They have more feature than typical Bushnell with same price range. The images are AI upscale, but doesn't really bother us. So I am curious if you found any good Camera Traps to recommend? Thanks!

Cheers,

Dhanu

And finally for now, the object detectors are wrapped by a python websocket network wrapper to make it easy for the system to use different types of object detectors. Usually, it's about 1/2 a day for me to write a new python wrapper for a new object detector type. You just need to wrap in the network connection and make it conform to the yolo way of expressing the hits, i.e. the json format that yolo outputs with bounding boxes, class names and confidence level.

What's more, you can even use multiple object detector models in different parts of a single captured image and you can cascade the logic to require multiple object detectors to match for example, or a choice from different object detectors.

It's the perfect anti-poaching system (If I say so myself :) )

Hi Sam,

Impressive!  Any chance the LoRa code is open source?  I should like to take a gander.

Thanks

Hi Titus,

We've used this design/procedure for many years with our Deep Sea Camera systems, with good reliability.  Not OTS but not hard to make and most of the materials come out to be inexpensive per unit.  The most expensive item is the M101 connector ($25ea), but if you get them with extra length on the cable, you can essentially cut it off at the point where it joins the burn-loop and reuse that connector until it gets too short.  You'd also need an F101 connector integrated with your BRUV, this connecting with the burnwire and forming the the positive side of the circuit, and a ground - our ground connection goes to a large bolt on the frame near the burnwire loop - but that connector generally shouldn't need replacement unless it gets damaged.

These burnwires generally break in 3-7min, burning at about 1Amp, ~14.5V.  A thinner version of the coated wire could go faster or with less power required.

We do also employ galvanic releases as backups.  I really like redundancy on recovery mechanisms!  The ones we use are made by International Fishing Devices, Inc.  Various distributors sell certain models of their products (i.e. different time durations) but if you contact them directly, they can also make custom duration ones for you.

Hi Titus,

I've used latching solenoids as a release in a fresh water application. The product linked to is the one I have used, but has been discontinued (it's been quite a while).  Anyway these little devices hold a plunger in place with a permanent magnet, but release the plunger when a coil is energised that counters the magnet.  The holding force is not great, but more than enough to keep the safety on a mechanical trigger.  The whole device can be potted and sealed (ideally under vacuum to eliminate voids).  When pushing the plunger in to arm the solenoid, there is a definite click when the magnet kicks in, to confirm the locked state.

A similar device is the electropermanent magnet, which doesn't have a plunger, in fact it has no moving parts.  You provide the steel piece that that this device will release when energised, as with a latching solenoid. It generally has greater holding force than a latching solenoid. I've used these in a seawater application.  It's worth noting that there exist ferromagnetic stainless steels that can be used here to avoid corrosion.

Thanks,

-harold

Hi,

This is a really late answer but I was new to wildlabs then. I have a security appliance that uses state of the AI models and user defined polygon areas of interest that generates video alerts of intrusions in typically under a second.

Although its setup to install automatically on an NVidia AI on the edge boxes of your intentions were to monitor a great deal of cameras you could also install it on a desktop with a high end GPU for very high performance. At home I use a desktop with an rtx 2080ti and monitor around 15 cameras and a thermal imaging camera (old one).

I have also tested a high end model (yolov7) on a high end thermal imaging camera image and it works fine as well.

Thermal imaging cameras are hellishly expensive though and I’ve found that new extremely light sensitive cameras like the HIKvision colorvu series almost obsoletes them in terms of people detection at night at a fraction of the cost.

If you are interested I’d be happy to show you a demo in a video meeting sometime if you like. I’m pretty sure it would meeting all your intrusion detection and alerting needs.

My project page is

Hi there!, 

You should definitely check out VIAME, which includes a video annotation tool in addition to deep learning neural network training and deployment. It has a user friendly interface, has a publicly available server option that mitigates the need for GPU enabled computer for network training, and has an amazing support staff that help you with your questions. You can also download the VIAME software for local use. The tool was originally developed for marine life annotation, but can be used for any type of video or annotation (we are using it to annotate pollinators in video). Super easy to annotate as well. Worth checking out!  

Cheers, 
Liz Ferguson

Hey there community! Im new here and looking after lots of answers too! ;-)

We are searching aswell for the most ideal App / AI technology to ID different cats, but also other mammals if possible 

- Panthera onca

- Leopardus wiedii

- Leopardus pardalis

and if possible:

- Puma concolor

- Puma yagouaroundi

- Leopardus colocolo

- Tapirus terrestris

Every recommendation is very welcome, thanks!

Sam

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

Great discussion! Pet (and other 'home') cams are an interesting option as @antonab mentioned. I've been testing one at home that physically tracks moving objects (and does a pretty good job of it), connects to my home network and can be live previewed, all for AUD69 (I bought it on special. Normal retail is AUD80): 

On the Wifi front, and a bit of a tangent, has anyone done any work using 'HaLow' (see below for example) as it seems like an interesting way to extend Wifi networks?

Cool thread!

I will be testing Reolink Wi-Fi cameras in combination with solar powered TP-Link long range Wi-Fi antennas/repeaters later this field season for monitoring arctic fox dens at our remote off grid site in Greenland. The long range Wi-Fi antennas are rather power hungry but with sufficient solar panel and battery capacity I am hopeful it will work. 
I am looking forward to explore the links and hints above after the field season. 
Cheers,