We invent computer vision platforms that change how we live our lives. Our work covers the full spectrum of real-time, edge-based autonomous and augmented systems that push the frontiers of video and processing technologies.
With end-to-end vision capabilities, we make computer vision work in the real world in applications such as robotics, vehicles and people-worn systems. Areas of focus include:
- Computational sensing: smart and embedded vision
- 2D-3D reasoning: GPS-denied navigation, augmented reality
- Collaborative autonomy: semantic reasoning
- Intelligent interactive systems: human behavior estimation, biometrics
- Multi-modal data analytics: image and video search
- Machine learning: explainable AI, lifelong learning