top of page

Leverage AI for automated point cloud processing

Updated: Oct 4, 2023

Software as a Service for streamlining point cloud processing workflows

The creation of an accurately classified point cloud usually requires tremendous input from manual annotation. At Flai we believe that all those repetitive procedures can be greatly reduced by using the latest innovations in artificial intelligence. We developed a cloud-based web application that provides easy-to-use solutions for the classification, exploration and management of geospatial data, with a special focus on point cloud data sets.

Flai was created by a team of experts from various backgrounds, from geodesy and physics to computer engineering and machine learning. By utilizing our expertise in processing large quantities of data with the latest technologies and our understanding of customer needs, we have developed Flai as a solution to the increasing demand for the automation of common geospatial tasks and custom requests. Our solution enables companies working with point cloud data to shift from human labour-intensive processing to faster and more efficient autonomous flows powered by the latest machine learning (ML) and artificial intelligence (AI) techniques. Those approaches are crucial to consistently delivering accurate products faster than ever before.

Web application and data ingestion

To ease the use of our tools and be independent of the underlying hardware and operating system on which it would be run, all available operations are available through the Flai web application.

The application enables uploading, browsing and combining various geospatial datasets, such as point clouds, rasters, vectors and images.

After uploading data, they are safely stored on a secured cloud and are accessible only to the organization that initiated the data ingestion procedure. When even larger security is requested and data cannot leave its country of origin or the company that produced them, the Flai environment can be deployed on users' computing facility.

In the case of processing large data quantities, we also offer on-site batch-processing services for specific tasks, without the need of using the web application.

Our automated AI algorithm converts raw point clouds into fully annotated, ready-to-use datasets."
Our automatic artificial intelligence algorithm transforms raw point clouds into fully annotated and ready-to-use data sets.

The web application interface offers easy access to uploaded data and employs an intuitive interface for creating and running user-defined processing flows. Each of them can combine multiple input datasets of different types and simultaneously output countless new datasets generated from input data. Focusing mostly on point cloud datasets, users can choose from a broad selection of predefined processing tools. Ranging from simple operations such as class remapping and filtering to complex operations that try to understand the data and create higher-level results understandable by the wider public. The most sought tool is a point cloud semantic segmentation that takes raw measurements and assigns a meaningful semantic label to every lidar point. The generated set of labels depends on a selected field of interest and the required level of detail.

How does Flai point cloud classification work?

At Flai, we strive to use the latest approaches and best practices in all our data processing tasks. This is most pronounced in our point cloud classification task that uses the latest state-of-the AI and ML algorithms for working with point clouds.

The most challenging part of working with such data comes from their unordered structure and data specifics as even data sets acquired uniformly can have vastly different densities and height spans. To overcome these potential hazards, we first split a dataset into small overlapping sections, where each one gets treated individually.

For the classification algorithm to understand relations between points, their exact cartesian coordinates, height above ground and additional lidar attributes (intensity, return number, number of returns and RGB values) are passed to a pre-trained AI model. The output of the models' internal computations are per-point classification labels whose meaning was predefined by our team based on average customer requirements and use cases.

Flai point cloud viewer offers multiple classification tools to easily set objects in a point cloud to any user-defined label.

The ready-to-use AI models suitable for large-scale mapping, drone applications, forestry inventory creation and mobile mapping are available in our application. They have been trained on an extensive collection of diverse point cloud scenes

that were hand-picked and skilfully annotated by our team of data engineers.

This ever-growing set gets expanded whenever we encounter new types of structures, vegetation or terrain. For more advanced and specific use cases, we also offer an option to create user-tailored classification models that are trained on their data and classification labels. This feature is also available to all our users to try it on their data and create their custom models. The training process also includes an interactive component that will suggest which data are to be additionally labelled and added to a training set to improve prediction quality.

Manual point cloud annotation

After the automatic classification procedure has been completed, results can be reviewed, edited and measured in our application.

For this purpose, we embedded an intuitive three-dimensional viewer that allows users to seamlessly fly through even the largest datasets. Discovered miss-classifications can be at the same time corrected by a range of point selection tools. Those include strip, box and polygonal selections that can be interchangeably combined to achieve desired results by remapping points of one or multiple labels into a new label.

The manual classification task can also be distributed among multiple people in your organization through virtual tiles that seamlessly split the data set into multiple smaller, more manageable chunks. Whenever any annotator has a problem deciding on an object type it can initiate a conversation by placing a note directly in a point cloud.

How can I benefit from using Flai?

The possible applications for point clouds are diverse and go far beyond the described classification task. The Flai team is constantly developing and adding new tools that extract more informative and easier-to-manage vector products from point clouds. Our team can also develop custom solutions to simplify and speed up your current workflow to ease the digitalization of construction sites, urban planning, mining operations and surveying among others.

Large-scale aerial mapping

The majority of large lidar acquisition companies still use half-automatic scripts that can extract only the most basic and simple objects from their acquired point clouds. For extraction of additional classification labels and post-processing, they still rely on labour-intensive human-produced annotations. With the help of Flai, some of them are already leaving behind their old methodologies and replacing them with our automated solutions.

We provide reliable ground extraction even for the most complex scenarios such as overhangs, terraces and boulder-filled regions.

Our main task for large-area mapping data sets is to extract reliable ground representation without any outliers as the production of digital elevation models is the main product of such extensive mappings. Additionally, depending on customers’ needs, we can also deliver annotations for buildings, vegetation, bridges, water, powerline infrastructure and all other remaining man-built structures. Over the last year, our AI models enabled significant time savings for the end clients. Reported time savings regarding the time allocated to the manual annotation range between 30% – 80%, depending on the complexity of the use case.

Mapping with drones

The same approaches can also be applied to typically much denser data sets that were acquired by unmanned vehicles such as drones. Here we focus on processing small areas captured to understand a specific region. Those regions require high-frequency monitoring which is usually not feasible from the ground, or the ground measurements are too time-consuming to produce. Therefore, drone scanning combined with our automatic procedures is the optimal solution for the timely and constant delivery of reliable products for monitoring critical infrastructure and risk assessment.

Our clients come from many different sectors such as mining, urban planning, landslides and rockface monitoring, transmission wire inspection and many others. Our application helped multiple UAV mapping companies to complete their projects in a matter of days compared to weeks as was previously the case.

Forest inventory

With the growing demand for sustainable processes and the need to account for and measure greenhouse gas sinks and sources, a growing number of initiatives tries to produce as accurate forest inventories as possible. Typically, extracting inventory information, such as tree size, diameter and species is very labour-intensive and limited to only a few sample locations in vast forests.

To ease this work and produce more accurate results, a growing demand for extracting this information directly from point clouds has emerged. When their point density is high enough and an adequate number of lidar points penetrate the canopy down to the ground level and hit tree trunks, they are ideal sources for the estimation of biomass at the individual tree level.

Vectorization of tree trunks
Our solution for single tree delineation solution can report all relevant tree information such as tree height, canopy distribution, trunk length and radius.

To ease the transition, we developed a custom classifier that can discern forest volume into three important segments, namely tree canopy, trunks and understory. They are used to create accurate maps of individual tree top locations and heights, trace canopy outlines and compute vertical crown density profiles. Additionally, single trunk classification enables us to follow tree trunks in the 3-dimensional space, create radial profiles along their length and estimate individual volumes. The described approach was already used by multiple customers around the world who unlocked the untapped potential for the use of AI and ML in forest inventory and carbon trading applications.


Flai application has been proven useful for numerous different applications analysing point cloud data coming from diverse data sources. Regardless of whether you own aerial data of low-density or very high-density terrestrial scanning, our application can handle any of them. To test our application without any risk and understand how Flai can help your business, we offer a freemium plan with limited processing resources for all our existing tools.

For more information about our products and inquiries regarding potential new features, you can reach us at We are always ready to answer any question.


bottom of page