Projections

1. Use-case

Projections have been built with multimodality and multi-layer data in mind; it is particularly useful for handling images with a specific or non-trivial extension (ex: HDF5, TIFF...).

For example, let's say that you want to detect objects on a conveyor belt, and to achieve this, you have one camera that simultaneously captures an RGB image and an infrared image.

We will assume that these two images might have different dimensions, although they have the same aspect ratio.

As you can only "see" the RGB copy of the image, that's the one you are going to annotate, but maybe you want to train your model using those annotations and the infrared images?

You could even want to visualize a "transformed" copy of your infrared image by remapping the channels in the RGB space (just like we do with satellite images).

This is where Projections are useful; this is the system that allows you to link several visualizations of the same Data together, so you can, for example, switch between them during annotation, or from the Data panel of the Details view.

Each Data always has its main file related, and then this Data can have as many Projections as you want, knowing that each Projection must have a name.

2. Create a Projection

A. Manually using the SDK

The simplest and most flexible way to create a Projection is using our Python SDK.

The process looks like this

from picsellia import Client

client = Client()

datalake = client.get_datalake()
data = datalake.upload_data("my_NIR_data.tiff")

datalake.create_projection(data, name="RGB", path="my_rgb_data.jpg")

And that's it! You will now be able to access your RGB data once in the annotation tool, but retrieve the NIR data for training ✅

from picsellia.types.schemas import CloudObject, CloudProjectionObject

datalake = client.get_datalake()
datalake.import_cloud_projections(
    cloud_projections={
        "/bucket/path/object-1.jpg": [
            {
                "name": "view",
                "object_name": "/bucket/path/object-1-projection.jpg",
            }
        ],
        "/bucket/path/object-2.jpg": [
            CloudProjectionObject(
                name="pr1",
                object_name="/bucket/path/object-2-projection.jpg",
            )
        ],
    }
)

B. Automatically when uploading Data

When working with non-RGB Data, there is often a simple transform that can allow you to convert it to an RGB copy.

The code responsible for this transform can be integrated into the platform by our team, so it is executed automatically when you upload the Data.

This way you don't have to compute and upload the Projection yourself.