Products

Autonomy software

Skarv Technologies proprietary autonomy architecture, navigation solution, and unmatched situational awareness (driven by real-time data streams) provide an ideal platform to automate a wide range of tasks underwater, such as autonomous net- and hull cleaning, coverage mapping, pipe tracking, subsea inspection, etc. We also provide adaptive mission planning capabilities to support long duration missions at full ocean depth, as well as simulation and optimization software. Reduce time and cost while also increasing the prospect of retrieving relevant data. Our software is flexible and can be implemented on various platform and tailored to perform a wide range of tasks.

Services

Data analysis

We offer consultancy services and tools for doing complex data processing and analysis. This includes modern machine vision and intelligence methods such as: machine learning, object detection, segmentation, and classification. We specialize on data streams captured in the ocean such as 2D/3D video, point clouds, hyperspectral imaging, acoustic imaging and communications, and typical time-series data.

Autonomous platform services and survey support

We offer help with customized sensor- and software integrations for marine robotic solutions. Based on over 15 years experience doing autonomous underwater operations at various depths and in the Arctic, using USVs, AUVs, and ROVs. We can help turning concepts into solutions and offer expertise and support for complex survey missions where autonomy is required.

Data visualization

Do you have large data structures that you either need to visualize or work with interactively? We can provide web-based portals to explore, query, visualize, and analyse geospatial data. Gain overview and new insight into your data and share this with clients or public users. We have experience with spatio-temporal data formats such as netCDF and HDF5, GIS data, as well as conventional video and imaging data types.

Examples from use cases

Automatic detection of known objects

Using custom trained artificial neural nets we are able to detect and track anomalous objects on the seafloor, such as trash, garbage, and anomalous objects. The systems can be trained on new data to do custom detection of underwater objects.

Anomaly detection of new objects

Finding unknown object without prior information is also possible using attention-based neural architectures. The system can be used to look for lost objects, damages, irregularities, and conspicuous elements.

3D reconstruction of underwater scenes

Using structure from motion (SfM) and CNN-based feature descriptors we are able to reconstruct 3D-information from difficult underwater scenes amidst schools of fish and suspended particles. Our tools can deliver geo-referenced 3D models in standard formats for integration into BIM-models.