Center for Vision Technologies
From image capture to situational understanding, SRI’s Center for Vision Technologies offers end-to-end vision solutions that translate into real-world applications.
Our scientists pioneered real-time, real-world computer vision with the early development of pyramid/wavelet processing that enabled analysis with unprecedented speed and precision. They continue today with a broad array of advances in visual navigation, 3D scene modeling, and object and activity recognition.
Our core capabilities begin at the camera, with integrated processing to enhance image quality, and include a full range of state-of-the-art “front end” signal processing functions for stabilization, fusion, enhancement, and motion and change detection. They extend to high-end capabilities for understanding and interacting with complex, dynamic environments.
These capabilities have been used widely in security and defense and are now migrating rapidly to the consumer world with applications in smart phones, video games, and image search on the Internet.
- Image and video search and indexing
- Video event understanding and search
- Augmented reality training
- Mapping and 3D modeling
- Human-oriented computing and training
- Aerial surveillance
- Geo-localization of images
- Computational sensing
- Embedded processing