Asset.Insight, a company specialized in digitization services and asset management, has partnered with Xomnia to build a scalable Azure-based data platform that can transport 3D point cloud data securely and immediately. This platform will help VolkerWessels, Dutch construction company and Asset.Insight’s client, in transferring its 3D point cloud data, paving the way for implementing advanced analytics.
We have known Xomnia for years now, and from the onset we have only had good experiences with the experts from Xomnia.
Steven Woudenberg, Manager Advanced Analytics, Asset.Insight.
Asset.Insight. is the data service provider for VolkerWessels, a Dutch construction company managing assets related to railways, roads, and water.
Like most construction companies, VolkerWessels is increasingly relying on 3D point cloud data for accurate and fast records of the 3D geometries within its projects. Point cloud is data made up of dimensions and numbers, and is collected by special scanners that scan 3D geometry and turn it into files with numbers that represent measurements.
Previously, VolkerWessels did not have a secure and automated way of storing and distributing its 3D point cloud data. After being collected, this data used to get stored on hard drives, and a courier used to physically transport those hard drives every now and then to Asset.Insight. This process, however, is not time efficient, and puts the hard drives at the risk of being lost due to accidents on the way.
By migrating to storing their data on cloud infrastructure, VolkerWessels would make data sharing easier among its 120 local operating companies worldwide, and increase the searchability and security of its data. The stored data could also help VolkerWessels’ companies advance their asset management. For example, they could use this data to predict potential equipment failures.
Asset.Insight. created a proof of concept for the project and turned to Xomnia to help turn it into a scalable solution. In order to save time and prevent duplicate work, the challenge was to make this vast amount of data easily searchable and convenient to use.
In collaboration with the Asset.Insight. team, we created a platform to safely store large 3D datasets, accessible to users within and outside of VolkerWessels. Through a web portal as well as APIs, users can search through these data sets and can download partial or complete files.
As a next step, we enabled the user of this platform to not only download 3D point clouds, but to also apply state-of-the-art algorithms on the point clouds on the platform. For example, if a client would like to know the location and height of all trees in an area, the user can select that area and an algorithm for estimating tree height is applied on the available 3D point cloud data in that area.
With Azure Active Directory integration, clients can seamlessly use the same credentials they use within their company to authenticate to Asset.Insight.’s services. Azure Data Lake Storage is used to provide a scalable and fault tolerant storage solution with isolation between each clients’ provisioned storage.
The various processing tasks to be carried out are scheduled on a Kubernetes cluster for scalability and efficient use of resources. We utilized Cesium and their 3D tiles standard in order to display available data in 3D, overlaid on existing maps and terrain models.
The immediate business impact is two-fold. Sharing the 3D point clouds through a platform, which is always accessible and is updated instantaneously with 3D point cloud data as soon as it is collected, enables the clients to easily find and re-use the 3D point cloud data for all projects. The solution does not limit itself to 3D point clouds; any type of file can be uploaded and made available. Furthermore, clients can have easy access to the results of algorithms that are applied on the uploaded data.
At the moment, Asset.Insight. is attracting more users to the platform to test it and store their data. Once the product is fully developed, it will be possible to utilize the data to accurately predict asset failures. The state of the art algorithms used for this can then be integrated into the platform. This has enormous potential for further future-proofing Asset.Insight.