HYPOD – Hyperspectral Oil Leak Detection for airborne pipeline monitoring

Within the framework of the ZIM-project »Hyperspectral Oil Leak Detection HYPOD«, Fraunhofer IOSB and its industrial partners ADLARES GmbH and Flyscan Systems Inc. develop an airborne remote sensing platform equipped with sensors to detect small leaks of oil pipelines.

In the ZIM project "Hyperspectral Oil Leak Detection HYPOD", Fraunhofer IOSB, together with its industrial partners ADLARES GmbH and Flyscan Systems Inc., developed a flying platform equipped with sensors to detect the smallest oil leaks from pipelines from the air.

Oil drip pans filled with various bottom substrates.
© Fraunhofer IOSB
Test scenario for the development of reliable oil detection methods. Oil collection pans are filled with different soil substrates.
Different soil substrates are mixed with different types of crude oil, diesel and plastic objects.
© Fraunhofer IOSB
Different soil substrates are mixed with different types of crude oil, diesel and plastic objects.
Preparation of the drone flight and calibration of the hyperspectral sensor system.
© Fraunhofer IOSB
Preparation of the drone flight and calibration of the hyperspectral sensor system by staff of the Scene Analysis Department.

In Germany alone, Europe's largest refinery location, more than 2400 km of crude oil pipelines connect refineries, ports and storage facilities. In order to transport the oil volumes through these pipelines, high pressures are used, which place a strain on the pipeline material. In addition to corrosion, weak points in the pipelines, such as pipe bends or weld seams, are particularly susceptible. In order to prevent environmental damage caused by leaks, pressure and flow tests or wall thickness measurements are carried out by robots (pigs). These complex procedures usually mean an interruption to regular operations and are only carried out occasionally due to the resulting loss of profit. Monitoring of soil discoloration caused by oil leaks from the air by plane or helicopter has so far only been carried out visually.

The ZIM-funded project "Hyperspectral Oil Leak Detection HYPOD" aimed to use a sensor flight platform to record both geometrically high-resolution optical image data and spectrally high-resolution (hyperspectral) aerial images. Automated, sensor-based evaluation in real time is intended to ensure early and reliable detection of leaks, which supports or even replaces a purely visual and therefore error-prone evaluation. The underlying measuring principle lies in the detection of the material-specific reflection behavior of crude oil on the earth's surface and the suppression of false alarms by other oil-based products such as plastic.

Focus and objectives of the consortium:

  • Investigation of the technical and operational requirements for the airborne hyperspectral inspection system and the creation of a corresponding overall system concept
  • Development of the method of hyperspectral detection of oil including test data collection and development/implementation of a data processing routine
  • Integration of all system components into the flight platform and operationalization of the system

Hyperspectral remote sensing and image data analysis

Fraunhofer IOSB and its Scene Analysis department developed the methods for hyperspectral detection of oil in the HYPOD project. This involved the application of findings that had already been obtained during a measurement campaign in 2015 (see Lenz et al. 2015). 

However, other detection algorithms have also been tested for the reliable and automatic detection of oil. The basic principle of the detection method in hyperspectral remote sensing is as follows:

Ordinary (multispectral) cameras are sensitive in the range of visibly reflected solar radiation. More sophisticated cameras sometimes also record near-infrared or thermal signals. A hyperspectral camera, on the other hand, measures the entire wavelength range of visible, near-infrared and short-wave infrared light. The sensor not only has three or more channels available (as with a normal cell phone/RGB camera), but several hundred to a thousand channels. The resulting reflection spectrum forms a spectral signature that is specific to the object and material. Oil also has a specific reflection behavior. The difficulty of hyperspectral remote sensing lies in the fact that the mixing of oil and soil substrates/vegetation also overlaps the reflection properties of these materials. In addition, there are external factors such as atmospheric influences and distortions of the recorded images due to the flight movement of the flight platform.

In order to develop a reliable detection method, a test scenario was set up that was as close to reality as possible. For this purpose, several oil drip pans were filled with different soil substrates and mixed with three different types of crude oil and diesel. Some of these oil pans were used to simulate false alarms caused by plastic objects in order to provoke unintentional confusion with objects of similar material properties. For hyperspectral measurement from the air, Fraunhofer IOSB uses the latest hyperspectral sensor technology, whose ever decreasing weight now even allows installation on drones (e.g. DJI Matrice 600 Pro). Due to its low weight of 2.83 kg, the Hyperspec Co-Aligned VNIR-SWIR from Headwall enables a 12 to 18-minute flight per battery set, which corresponds to an area coverage of approx. 4.2 ha at a flight altitude of 80 m and results in an approximate pixel resolution of 4 cm.

A single flight stripe with 16 oil catch pans, detected oil spills are marked in red.
© Fraunhofer IOSB
A single flight stripe with 16 oil catch pans, detected oil spills are marked in red.

First results

The preliminary results show that reliable detection of the three types of crude oil and diesel is possible with a low number of false alarms. False alarms can be suppressed in the surrounding area and within the oil catch pans with the plastic objects, while simultaneously preserving the good detection rate. Darker soil substrates and vegetation cover slightly reduced the detection performance. For this reason, machine learning approaches will be used in hyperspectral oil detection in future studies, which could additionally reduce the false alarm rate.


Lenz, A.; Schilling, H.; Gross, W.; Middelmann, W. (2015): Evaluation and performance analysis of hydrocarbon detection methods using hyperspectral data. In: Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, Milan, 2015, pp. 2680-2683.  


Scene Analysis Department

You want to learn more about our products in the area of scene analysis? Then visit the page of our department.

Project Profile

Project Name: Hyperspectral Oil Leak Detection (HYPOD)

The project was funded within the framework of the Central Innovation Program for SMEs (ZIM)