Recently we’ve been hearing reports about sightings of Sasquatch in and around Prince George, British Columbia. Being a geospatial company and because Prince George is home — one of them anyway — we thought we could lend a hand in confirming these reports.

The first thing we needed to do was some mapping of the reported sightings. Much like the famous spatial statistician John Snow (this one actually knows something), we used the sighting locations to help narrow our search for Sasquatch.

Map of reported Sasquatch Sightings
Sugarbowl-Grizzly Den Provincial Park looks like a good starting point.

Satellite Imagery

We do a lot of work with satellite images and figured we could apply some of our imagery expertise to help hunt for Sasquatch. Using some domain knowledge, we know that Sasquatches (Sasquai?) prefer to gather in sparse subalpine forests. We figured that is as good a place as any to start looking.

We wanted some relatively recent imagery of the area around Prince George and didn’t necessarily want to search individual image providers for data which may or may not be useful. Using the relatively new SpatioTemporal Asset Catalog (STAC) and sat-api, we were able to search for relevant images from multiple image providers.

We grabbed some Sentinel 2 imagery (unfortunately, Sentinel 2 is not available as a Cloud Optimized GeoTiff (COG) so we had to download the entire dataset¹) and transformed it into the level of Analysis Ready Data (ARD) that was required for searching for Sasquatch. We performed a basic classification and mixed in a Digital Elevation Model (DEM) to help identify subalpine forests and to narrow our search even further.

We are getting closer. With subalpine forests identified, we accessed some more recent and higher resolution imagery from our partners at Maxar and processed it using GBDX and our own custom algorithm.

Age of AI

We pan-sharpened the image, which increases the spatial resolution at the expense of spectral information. If we were going to visually search the imagery to find Sasquatch, pan-sharpening will certainly help a human find them. However, this is the age of Artificial Intelligence (AI). We can feed this enhanced imagery through our Sasquatch locator algorithm (link below), which will automatically locate all the Sasquatch for us!


Aha! We found some. In fact, we can see a small herd of Sasquatch in the area identified earlier.

Data Cleanup

The last step is to run the identified Sasquatches through our proprietary enhancement algorithm, which enhances contrast, automatically extracts subfeatures (head vs. body components), and makes for a more visually appealing product. With the power of AI and Geospatial data, I think we can conclusively confirm those reports.

That’s all there is to it! You can find our AI model and subfeature extraction algorithms here.

If you liked the method we used to find Sasquatches, these same techniques can be used to do other interesting tasks like locating marine vessels, or counting swimming pools in a community.

Enjoy!

Thanks to Darren Wiens and Joe Burkinshaw for help.

¹COG data format

Sharing options

Experiments • Darren Wiens

How to Avoid Spoilers the Hard Way

Recently we’ve been hearing reports about sightings of Sasquatch in and around Prince George, British Columbia. Being a geospatial company and because Prince George is home — one of them…

Experiments • James Banting

STACLint: Validate your STAC

STACLint is an online validation tool for STACs. With it, you are able to validate STAC catalogs, collections, and items by supplying either a URL or JSON. The tool will…

Experiments • James Banting

COG—Huh! What is it good for?

Cloud Optimized GeoTIFF (COG) are geotiff files, like satellite imagery, that have been processed in a manner that makes it easy to consume for internet processing applications (read cloud). It…

Need a geospatial partner?

Our team complements organizations like yours—by providing on-tap access to geospatial, analytics, and mapping expertise.

Let’s talk

Join our team?

We’re always looking for skilled technologists to help us build the future of geospatial. Got a minute to find out more about us?

Working Here

Sharing options