27Feb
On: 27 February 2020 In: Delair.ai Platform

delair.ai and SDK: What you need to know

Automation and AI are completely revolutionizing the way business is done. Tasks that used to take weeks or months can now be done in a matter of hours. What’s more, this technology is now very accessible to enterprises thanks to the delair.ai cloud platform, which collects, manages, and analyzes imagery to derive business insights – and over time, the platform’s machine learning can help you proactively manage your operations. With delair.ai’s SDK, there is an unlimited possibility for how this technology can be customized to an individual company’s need.

What are SDKs? The acronym stands for Software Development Kit, and essentially it is a set of software standardized tools which makes it possible for data exchange and processing with delair.ai. They are useful for creating, testing, and developing specific applications on top of the delair.ai platform, along with seamlessly integrating delair.ai with other applications. SDKs allow you to enrich delair.ai with advanced functionalities, specific analytics, data, etc., letting you completely bend the platform to your use case.

On delair.ai, you can specifically use the SDK to create and upload different types of datasets (such as images, rasters, point cloud, mesh, vectors and files). You can also use the SDK to have a high level interface to delair.ai HTTP APIs, with examples including:

  • Find a project and browse the missions
  • Get a list deliverables and download these files
  • Add, search, update and delete annotations associated to a project or image
  • Process a raster and deliver the result as new raster or vector
  • Run a customized algorithm
  • Upload and deliver an algorithm output

You can take the Python code for that here on Jupyter notebook.

Practical example: How to determine the best haul road for fuel consumption with the delair.ai SDK

Economizing your resources is critical for any business, so in this example we’ll look at how a quarry manager can determine the most efficient haul road path to save on fuel with delair.ai.

First, the quarry manager would use the built-in analytics on delair.ai to automatically generate the haul roads on the site. This is done by taking raw images of the site (probably with drones) and processing the images as 2D and 3D models.

Next, you need to define the fuel consumption between two points, using the vehicle-related data (rolling resistance, load, etc.) and the lengths and elevations calculated from the 3D model using the following code:

1 def fuel_consumption(load, length, delta_z):
2 return max(C_h*(1-RR)*(20000+load)/20000*length + C_v*(20000+load)/20000*delta_z,0)

Then you just need to develop the Python script using the SDK, which:

  • defines the KPI to be generated (fuel consumption)
  • calls the haul roads pattern as an input
  • calls the SDK functions
  • generates a visual map (.tiff)

This results in displaying a layer in delair.ai which shows the optimized haul road route, ultimately decreasing excess fuel consumption.

If you want to speak to us about our SDK in delair.ai to see if it will fit your use case, don’t hesitate to reach out below. We look forward to hearing about your project!

Have any questions or want to get a trial account of delair.ai? Contact our team to talk about your project.