The classification layer for large-scale LiDAR.

Pointly GmbH has proven to be a valuable partner in our project to create a highly accurate 3D map, which serves as a foundation for the implementation of fully automated driving systems at Digitale Schiene Deutschland, Deutsche Bahn AG. Despite challenging data conditions, Pointly delivered impressive results with their AI-based classification more quickly than anticipated.

Their deep understanding of our needs and goals, as well as their ability to tackle complex challenges with creative and effective solutions, was remarkable. The collaboration was marked by professional and friendly engagement, with communication always open and responsive. Pointly has exceeded our expectations, laid a solid foundation for the further development of our product, and is undoubtedly worthy of recommendation.

Alexander Pfitzner, Deutsche Bahn AG, Digitale Schiene Deutschland

Pointly was a level up for our manual point cloud annotation experience. We have large amounts of point clouds to be manually annotated and were struggling with this effort in the past, taking months for several point clouds to be annotated. With the Pointly platform we not only received very professional, fast and accurate annotation services, but also had a huge productivity boost on our side to review and validate the annotation results.

Key game changer option is to collaborate with annotators by tagging and commenting on point clouds directly in the 3D view. It solved the issue of endless slides with screenshots and multiple rounds of verifications. It was a pleasure to work with the team!

Martynas Kulvietis, Engineering Manager, GeoSpatial Feature Extraction Solutions, Trimble Inc.

City of Helsinki aims to be carbon neutral by 2030 and it is adapting to the changing climate. An important part of this challenge is to preserve our green areas and trees in the rapidly growing city. This can be monitored through aerial survey data, which Helsinki has collected annually for years. The classification of the original point cloud data was not good enough, but with Pointly Services we got improved cluster based classification of the vegetation classes. Pointly delivered very good & reliable results with AI-classification in just a few weeks. In comparison, a manual re-classification would have taken more than six months.

Finally, we could do different vegetation analysis with the data, for example a forest canopy analysis. We are extremely happy with the re-classification results and friendly & fast service of Pointly!

Suvi Uotila, MSc (Geoinformatics), Team leader at GIS center, Urban Environment Division / City of Helsinki

The digital twin is a central component of Smart City Munich. Through the annual collection of city-wide aerial survey data, diverse use cases in areas such as climate protection, mobility and integrated urban development can be processed. Pointly supported us in taking this project further by training a custom classifier for our latest laser scan dataset. With this classifier, a fully automated classification for the entire city of Munich was realized in a very short time.

The trained model not only added a lot of information to the current dataset, but also provided a solid basis for applying the model to future aerial surveys.

Johannes Weber, Landeshauptstadt München, Kommunalreferat GeodatenService, Zentrale Luftbildstelle

Working with Pointly has fundamentally changed the way we process our coastal survey data. Pointly's team has developed a custom AI workflow tailored to our unique coastal environment datasets, allowing us to automatically extract a precise ground model and to classify key features such as vegetation, seawalls and other coastal infrastructure.

What used to be a cumbersome process, taking days of manual finetuning for the classifications can now be done in a fraction of the time - with higher consistency and greater accuracy.

The collaboration was exceptionally smooth. Pointly didn't act like a black box - they kept us in the loop throughout development, communicating progress and discussing potential risks transparently. We can confidently say that the results have exceeded our expectations. We look forward to further exploring how this technology can improve our coastal monitoring data workflow.

Dan Amos, Worthing Borough Council, Coastal Cell 4d Data Analyst, Project Manager for the Regional Coastal Monitoring Programme

Thanks to the developed 3D Deep Learning based point cloud classification by Pointly Services we are now able to classify ground points with higher accuracy than before, leading to more precise elevation models. Pointly can detect additional objects like powerlines and vehicles for us which allows to filter for specific changes. Recurring tasks such as the inventory of georeferenced objects and the recording of terrain changes become easier and more efficient.

What stands out the most to us is Pointly's adaptability – the new approach can learn continuously. Thus, any manual correction to the automatic classification (if necessary at all) improves the process for future applications.

Dipl. Ing. Andreas Schlienkamp, Group Leader Remote Sensing at RAG Aktiengesellschaft

Modern surveying technologies (laser scanning, drone flights etc.) allow the recording of high-precision 3D point clouds from existing construction sites. With the help of this data and by using Pointly, construction sites can be better organized and processes can be monitored and improved.

Dr. Dirk Ebersbach, Managing Director at VIA IMC GmbH

Together with BSF Swissphoto, Pointly worked in a focused manner toward the project goal of achieving a classification accuracy of over 95 % and developed a tailored workflow that was precisely aligned with the project requirements and target structures. The project was demanding and included a complex class catalogue with special classes such as high voltage power lines, wind turbines and solar panels.

Within the first months of production, more than 30,000 km² were processed reliably. Pointly proved to be a dependable partner throughout this phase.

We continue to work together on the ongoing project as well as on additional initiatives and are building a long term partnership for highly accurate and scalable point cloud processing.

Jörg Wertli, CEO, BSF Swissphoto

Pointly has become a close partner for our mobile mapping work. We arrived with a very specific object catalog and requirements, and Pointly's pre-trained standard classifier was already a strong base. From there they optimized the workflow iteration by iteration, on our own data until the output matched what our projects actually need.

Today we put hundreds of kilometers of dense urban mobile mapping surveys in Romania through automated classification, and each piece of street inventory is extracted and accurately positioned. Street lights, signs, traffic lights, several different pole types, overhead lines, waste bins and bus stops are among them, with artifacts and moving objects being removed in the same workflow.

The Pointly team engaged with the details that are specific to us and responded quickly throughout. The result is a process we run across a growing number of projects and we intend to keep building on this partnership.

Serea Corina Beatrice, Head of the GIS Department, Geomatics Integrated Services SRL

Pointly GmbH has proven to be a valuable partner in our project to create a highly accurate 3D map, which serves as a foundation for the implementation of fully automated driving systems at Digitale Schiene Deutschland, Deutsche Bahn AG. Despite challenging data conditions, Pointly delivered impressive results with their AI-based classification more quickly than anticipated.

Their deep understanding of our needs and goals, as well as their ability to tackle complex challenges with creative and effective solutions, was remarkable. The collaboration was marked by professional and friendly engagement, with communication always open and responsive. Pointly has exceeded our expectations, laid a solid foundation for the further development of our product, and is undoubtedly worthy of recommendation.

Alexander Pfitzner, Deutsche Bahn AG, Digitale Schiene Deutschland

Pointly was a level up for our manual point cloud annotation experience. We have large amounts of point clouds to be manually annotated and were struggling with this effort in the past, taking months for several point clouds to be annotated. With the Pointly platform we not only received very professional, fast and accurate annotation services, but also had a huge productivity boost on our side to review and validate the annotation results.

Key game changer option is to collaborate with annotators by tagging and commenting on point clouds directly in the 3D view. It solved the issue of endless slides with screenshots and multiple rounds of verifications. It was a pleasure to work with the team!

Martynas Kulvietis, Engineering Manager, GeoSpatial Feature Extraction Solutions, Trimble Inc.

City of Helsinki aims to be carbon neutral by 2030 and it is adapting to the changing climate. An important part of this challenge is to preserve our green areas and trees in the rapidly growing city. This can be monitored through aerial survey data, which Helsinki has collected annually for years. The classification of the original point cloud data was not good enough, but with Pointly Services we got improved cluster based classification of the vegetation classes. Pointly delivered very good & reliable results with AI-classification in just a few weeks. In comparison, a manual re-classification would have taken more than six months.

Finally, we could do different vegetation analysis with the data, for example a forest canopy analysis. We are extremely happy with the re-classification results and friendly & fast service of Pointly!

Suvi Uotila, MSc (Geoinformatics), Team leader at GIS center, Urban Environment Division / City of Helsinki

The digital twin is a central component of Smart City Munich. Through the annual collection of city-wide aerial survey data, diverse use cases in areas such as climate protection, mobility and integrated urban development can be processed. Pointly supported us in taking this project further by training a custom classifier for our latest laser scan dataset. With this classifier, a fully automated classification for the entire city of Munich was realized in a very short time.

The trained model not only added a lot of information to the current dataset, but also provided a solid basis for applying the model to future aerial surveys.

Johannes Weber, Landeshauptstadt München, Kommunalreferat GeodatenService, Zentrale Luftbildstelle

Working with Pointly has fundamentally changed the way we process our coastal survey data. Pointly's team has developed a custom AI workflow tailored to our unique coastal environment datasets, allowing us to automatically extract a precise ground model and to classify key features such as vegetation, seawalls and other coastal infrastructure.

What used to be a cumbersome process, taking days of manual finetuning for the classifications can now be done in a fraction of the time - with higher consistency and greater accuracy.

The collaboration was exceptionally smooth. Pointly didn't act like a black box - they kept us in the loop throughout development, communicating progress and discussing potential risks transparently. We can confidently say that the results have exceeded our expectations. We look forward to further exploring how this technology can improve our coastal monitoring data workflow.

Dan Amos, Worthing Borough Council, Coastal Cell 4d Data Analyst, Project Manager for the Regional Coastal Monitoring Programme

Thanks to the developed 3D Deep Learning based point cloud classification by Pointly Services we are now able to classify ground points with higher accuracy than before, leading to more precise elevation models. Pointly can detect additional objects like powerlines and vehicles for us which allows to filter for specific changes. Recurring tasks such as the inventory of georeferenced objects and the recording of terrain changes become easier and more efficient.

What stands out the most to us is Pointly's adaptability – the new approach can learn continuously. Thus, any manual correction to the automatic classification (if necessary at all) improves the process for future applications.

Dipl. Ing. Andreas Schlienkamp, Group Leader Remote Sensing at RAG Aktiengesellschaft

Modern surveying technologies (laser scanning, drone flights etc.) allow the recording of high-precision 3D point clouds from existing construction sites. With the help of this data and by using Pointly, construction sites can be better organized and processes can be monitored and improved.

Dr. Dirk Ebersbach, Managing Director at VIA IMC GmbH

Together with BSF Swissphoto, Pointly worked in a focused manner toward the project goal of achieving a classification accuracy of over 95 % and developed a tailored workflow that was precisely aligned with the project requirements and target structures. The project was demanding and included a complex class catalogue with special classes such as high voltage power lines, wind turbines and solar panels.

Within the first months of production, more than 30,000 km² were processed reliably. Pointly proved to be a dependable partner throughout this phase.

We continue to work together on the ongoing project as well as on additional initiatives and are building a long term partnership for highly accurate and scalable point cloud processing.

Jörg Wertli, CEO, BSF Swissphoto

Pointly has become a close partner for our mobile mapping work. We arrived with a very specific object catalog and requirements, and Pointly's pre-trained standard classifier was already a strong base. From there they optimized the workflow iteration by iteration, on our own data until the output matched what our projects actually need.

Today we put hundreds of kilometers of dense urban mobile mapping surveys in Romania through automated classification, and each piece of street inventory is extracted and accurately positioned. Street lights, signs, traffic lights, several different pole types, overhead lines, waste bins and bus stops are among them, with artifacts and moving objects being removed in the same workflow.

The Pointly team engaged with the details that are specific to us and responded quickly throughout. The result is a process we run across a growing number of projects and we intend to keep building on this partnership.

Serea Corina Beatrice, Head of the GIS Department, Geomatics Integrated Services SRL

Pointly GmbH has proven to be a valuable partner in our project to create a highly accurate 3D map, which serves as a foundation for the implementation of fully automated driving systems at Digitale Schiene Deutschland, Deutsche Bahn AG. Despite challenging data conditions, Pointly delivered impressive results with their AI-based classification more quickly than anticipated.

Their deep understanding of our needs and goals, as well as their ability to tackle complex challenges with creative and effective solutions, was remarkable. The collaboration was marked by professional and friendly engagement, with communication always open and responsive. Pointly has exceeded our expectations, laid a solid foundation for the further development of our product, and is undoubtedly worthy of recommendation.

Alexander Pfitzner, Deutsche Bahn AG, Digitale Schiene Deutschland

Pointly was a level up for our manual point cloud annotation experience. We have large amounts of point clouds to be manually annotated and were struggling with this effort in the past, taking months for several point clouds to be annotated. With the Pointly platform we not only received very professional, fast and accurate annotation services, but also had a huge productivity boost on our side to review and validate the annotation results.

Key game changer option is to collaborate with annotators by tagging and commenting on point clouds directly in the 3D view. It solved the issue of endless slides with screenshots and multiple rounds of verifications. It was a pleasure to work with the team!

Martynas Kulvietis, Engineering Manager, GeoSpatial Feature Extraction Solutions, Trimble Inc.

City of Helsinki aims to be carbon neutral by 2030 and it is adapting to the changing climate. An important part of this challenge is to preserve our green areas and trees in the rapidly growing city. This can be monitored through aerial survey data, which Helsinki has collected annually for years. The classification of the original point cloud data was not good enough, but with Pointly Services we got improved cluster based classification of the vegetation classes. Pointly delivered very good & reliable results with AI-classification in just a few weeks. In comparison, a manual re-classification would have taken more than six months.

Finally, we could do different vegetation analysis with the data, for example a forest canopy analysis. We are extremely happy with the re-classification results and friendly & fast service of Pointly!

Suvi Uotila, MSc (Geoinformatics), Team leader at GIS center, Urban Environment Division / City of Helsinki

The digital twin is a central component of Smart City Munich. Through the annual collection of city-wide aerial survey data, diverse use cases in areas such as climate protection, mobility and integrated urban development can be processed. Pointly supported us in taking this project further by training a custom classifier for our latest laser scan dataset. With this classifier, a fully automated classification for the entire city of Munich was realized in a very short time.

The trained model not only added a lot of information to the current dataset, but also provided a solid basis for applying the model to future aerial surveys.

Johannes Weber, Landeshauptstadt München, Kommunalreferat GeodatenService, Zentrale Luftbildstelle

Working with Pointly has fundamentally changed the way we process our coastal survey data. Pointly's team has developed a custom AI workflow tailored to our unique coastal environment datasets, allowing us to automatically extract a precise ground model and to classify key features such as vegetation, seawalls and other coastal infrastructure.

What used to be a cumbersome process, taking days of manual finetuning for the classifications can now be done in a fraction of the time - with higher consistency and greater accuracy.

The collaboration was exceptionally smooth. Pointly didn't act like a black box - they kept us in the loop throughout development, communicating progress and discussing potential risks transparently. We can confidently say that the results have exceeded our expectations. We look forward to further exploring how this technology can improve our coastal monitoring data workflow.

Dan Amos, Worthing Borough Council, Coastal Cell 4d Data Analyst, Project Manager for the Regional Coastal Monitoring Programme

Thanks to the developed 3D Deep Learning based point cloud classification by Pointly Services we are now able to classify ground points with higher accuracy than before, leading to more precise elevation models. Pointly can detect additional objects like powerlines and vehicles for us which allows to filter for specific changes. Recurring tasks such as the inventory of georeferenced objects and the recording of terrain changes become easier and more efficient.

What stands out the most to us is Pointly's adaptability – the new approach can learn continuously. Thus, any manual correction to the automatic classification (if necessary at all) improves the process for future applications.

Dipl. Ing. Andreas Schlienkamp, Group Leader Remote Sensing at RAG Aktiengesellschaft

Modern surveying technologies (laser scanning, drone flights etc.) allow the recording of high-precision 3D point clouds from existing construction sites. With the help of this data and by using Pointly, construction sites can be better organized and processes can be monitored and improved.

Dr. Dirk Ebersbach, Managing Director at VIA IMC GmbH

Together with BSF Swissphoto, Pointly worked in a focused manner toward the project goal of achieving a classification accuracy of over 95 % and developed a tailored workflow that was precisely aligned with the project requirements and target structures. The project was demanding and included a complex class catalogue with special classes such as high voltage power lines, wind turbines and solar panels.

Within the first months of production, more than 30,000 km² were processed reliably. Pointly proved to be a dependable partner throughout this phase.

We continue to work together on the ongoing project as well as on additional initiatives and are building a long term partnership for highly accurate and scalable point cloud processing.

Jörg Wertli, CEO, BSF Swissphoto

Pointly has become a close partner for our mobile mapping work. We arrived with a very specific object catalog and requirements, and Pointly's pre-trained standard classifier was already a strong base. From there they optimized the workflow iteration by iteration, on our own data until the output matched what our projects actually need.

Today we put hundreds of kilometers of dense urban mobile mapping surveys in Romania through automated classification, and each piece of street inventory is extracted and accurately positioned. Street lights, signs, traffic lights, several different pole types, overhead lines, waste bins and bus stops are among them, with artifacts and moving objects being removed in the same workflow.

The Pointly team engaged with the details that are specific to us and responded quickly throughout. The result is a process we run across a growing number of projects and we intend to keep building on this partnership.

Serea Corina Beatrice, Head of the GIS Department, Geomatics Integrated Services SRL