GPS-free positioning
for drones
Technology
Visual-Inertial Positioning
Computes the location of a device by fusing data from cameras, IMU and other optional sensors.
Our SDK implements a high-performance proprietary VISLAM solution (patent pending), and an efficient AI-based aerial Visual Positioning System (VPS).
Product
Spectacular AI SDK
- Runs in real time on embedded CPUs
- State-of-the-art accuracy
- Resilient supply chain: supports a wide range of sensors and processors
Use cases
GPS-free navigation
for UAVs and ground vehicles
The state-of-the-art Visual-Inertial Positioning System in the Spectacular AI SDK allows GPS-free navigation based on fusion of data from the camera, IMU and barometric sensors. The method can run under very tight computational constraints in embedded processors.
Inside-out tracking
for AR/VR/XR headsets and controllers
6-DoF pose tracking of virtual, augmented and external reality (VR/AR/XR) headsets creates the illusion of virtual reality without external lighthouses. With properly configured sensors, our solution allows centimeter-level accuracy at millisecond-level latency, and can run on embedded processors inside a headset.
Free VISLAM SDK
for rapid prototyping and research
Our public SDK wrappers are ideal for rapid prototyping with off-the-shelf OAK-D, RealSense, Kinect, and Orbbec devices. They can be applied in a wide range of robotics, virtual reality, and computer vision research scenarios.
Team
Spectacular AI is a university spin-off company from Helsinki, founded in 2021.
Our team is a unique mixture of seasoned software professionals plus established computer vision and machine learning researchers. We solve challenging problems related to Computer Vision, Spatial AI, Sensor Fusion and SLAM.
Research
Spectacular AI SDK implements a high-performance proprietary VISLAM solution (patent pending) that represents the next step of evolution after the best-in-class HybVIO method. The team have also co-authored, among others, the following recent relevant scientific articles:
- O. Seiskari, P. Rantalankila, J. Kannala, J. Ylilammi, E. Rahtu, A. Solin. HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry. 2022 IEEE Winter Conference on Applications of Computer Vision (WACV)
- O. Seiskari, J. Ylilammi, V. Kaatrasalo, P. Rantalankila, M. Turkulainen, J. Kannala, A. Solin. Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion. 2024 European Conference on Computer Vision (ECCV)
- V. Ye, R. Li, J. Kerr, M. Turkulainen, B. Yi, Z. Pan, O. Seiskari, J. Ye, J. Hu, M. Tancik, A. Kanazawa. gsplat: An open-source library for Gaussian splatting. arXiv preprint, 2024
- A. Solin, S. Cortés, E. Rahtu, J. Kannala. PIVO: Probabilistic Inertial-visual Odometry for Occlusion-robust Navigation. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
- A. Solin, S. Cortés, E. Rahtu, J. Kannala. Inertial Odometry on Handheld Smartphones. 2018 21st International Conference on Information Fusion (FUSION)
- S. Cortés, A. Solin, E. Rahtu, J. Kannala. ADVIO: An Authentic Dataset for Visual-Inertial Odometry. 2018 European Conference on Computer Vision (ECCV)