The OI Analysis may be split into roughly 3 broad categories as below. Each Analysis is tied to specific data sources that it has been trained on. Click on each section to learn more about the Data Source and Analysis.

1. Object Detection: detect individual objects in satellite imagery
   • Cars
   • Trucks
   • Railcars
   • Aircrafts
   • Ships
   • Tanks
2. Geolocation: analyze location data from connected / IoT devices
   • Traffic (counts of unique number of devices in the AOI)
   • Tracks (paths of devices that visited the AOI) 3.[Land Usen): perform land classification on satellite imagery
   • High resolution (1.5m)
   • Mid resolution (3-5m)

---

1. Object Detection

1-1. Overview

Object detection is a category of computer vision (CV) classification analysis that operate on satellite imagery to identify & count individual objects that appear in the imagery.

1-2. Data Source

The following table summarizes the generally available data for object detection analysis:

1-3. List of Standard OI Analysis

---

2. Geolocation

2-1. Overview

Geolocation is a category of data science (DS) analysis that operate on location data to measure activity, analyze movements, and understand behavior in aggregate.

📘

What is location data?

Location data is captured from connected IoT (Internet of things) devices, such as mobile phones, ships, planes, etc. The raw data analyzed by Elements generally contains a device identifier, latitude & longitude coordinates of the device position, and date/times at which the device is reported to be at that location.

2-2. Data Source

The following table summarizes the generally available data for geolocation analysis:

2-3. List of Standard OI Analysis

Ships

Planes

📘

Notes regarding 'Tracks' analysis

1. How we classify track paths:

'Tracks' results are provided as before- and after-AOI layers.

We classify movements as being "before-AOI" (location before arriving at your project AOI) vs "after-AOI" (location after leaving your AOI).

Certain movements can be considered as both "before" and "after":

• Movement within your project AOI are considered both "before" and "after"
• After leaving your AOI, then comes back to it, the trip in-between is considered both "before" and "after".

2. Privacy Safeguards

The following safeguards are put in place to prevent abuse of the Tracks algorithm for individual tracking:

• Each AOI must have at least 5 unique pings over the analysis period
• Each heatmap grid cell must have at least 2 unique pings
• Heatmap grid cells cannot be smaller than ~100x100m

---

3. Land Use - coming soon!

3-1. Overview

Land use is a category of computer vision (CV) classification analysis that operate on satellite imagery to classify land use (aka land cover) type in each part of your areas of interest. In layperson terms, the analysis tells you where the buildings, roads, vegetation, etc are. By running multiple land use analyses over different periods of time, you can also identify change in terms of building / road construction, deforestation, etc.

📘

Land Use Aggregation

Our land use analysis "aggregate" analysis across multiple satellite images to deliver a single "aggregated" land use result. In land use analysis, a single satellite image is often insufficient to cover a large area of interest, and an individual image may have cloudy areas that are not usable.

As such, the land use algorithms are configured with a start and end date for which to select satellite imagery, as well as additional imagery selection parameters. It is best to select a date range of at least 1-3 months (or even up to 1 year), depending on the amount of satellite imagery available.

During the analysis, our land use computer vision algorithms are run on all satellite images from the selection step. Cloudy parts of each image are detected and discarded. The final aggregation process then combines valid results from multiple satellite images, allowing for a single cloud-free result that will cover your AOI.

3-2. Data Source

The following table summarizes the generally available data for land use analysis:

Each analysis classifies the land as below: