Automated Data Interpretation

Automated interpretation of 3D and image data

Today, high-performance cameras or laser scanners are used for many surveying tasks and condition monitoring. They deliver high-resolution images and very accurate, geo-referenced measurement data. The data are usually interpreted manually. Advances in artificial intelligence enable the use of innovative techniques and algorithms to automate the evaluation process.

Today, complex learning algorithms based on the concept of »deep learning« with artificial neural networks (ANN) are used for the evaluation of 3D data. These algorithms have been shown to be superior to traditional methods of object recognition. Just a few years ago, the situation was different: The training of bespoke algorithms took weeks or even months. Today, thanks to massive parallelization, this process can be accomplished in just a few hours. The evaluation of new data sets based on a trained ANN is then even conducted in real time. In ANN, the fed-in information passes through a large number of interconnected artificial neurons, where it is processed and passed to other neurons. ANNs learn the output patterns corresponding to specific input patterns with the help of manually annotated training data. Based on this »experience«, new types of input data can then be analyzed in real time. ANNs have proven to be very robust to variations on characteristic colors, edges and shapes.

 

Transport Infrastucture

 

Objective and reliable analysis of condition monitoring data

 

 

Structural Features

 

Automatic recognition of surface distress in data

Further information

 

Press release / 26.7.2021

AI Champions Baden-Württemberg

A novel planning tool uses artificial intelligence methods to automatically interprete 3D environmental data to generate smart planning maps. The research team has now received an award for its development in the "AI Champion Baden-Württemberg" competition.

 

KI innovation competition Baden-Württemberg

3D-Hydra: AI-based 3D object recognition for flood simulations

The 3D-Hydra project is developing a new automated process for 3D object recognition in drone data. AI-based evaluation of data from point clouds delivers a high-resolution 3D model that is to be able to assess the risk of flooding more accurately and efficiently in the future.  

 

Fraunhofer Initiative »Lighthouse Projects«

»Cognitive Agriculture«

Since November 2018, eight Fraunhofer Institutes have jointly been conducting research on technologies for the digitalization, automation, and electrification of agricultural processes. Fraunhofer IPM's task within this project is to develop robust 3D sensors, sensors for N2O based on laser spectroscopy, multispectral laser scanning methods and specific tools for data processing.

 

Whitepaper

Building and construction surveying with laser scanning technology

Topics: Automated object regocnition in 3D data, data acquisition from the air, sensor concept for tunnel inspection.

 

Press release / 11.10.2018

Software supports optimized route planning

Deutsche Telekom AG will optimize the planning for new fiber-optic cables in the future using infrastructure data it collects itself. To achieve this, the company is investing in optical measurement technology with automated data analysis.