Visionary Systems and Research (VSR), led by Dr. Christopher Stauffer, provides leading capabilities in computer vision, machine learning, and big data to impact how we live our lives. At VSR, we seek an honest brokering of ideas and solutions simultaneously in academic, government, and industry sectors.

With over a decade of experience in building real-time computer vision and pattern recognition systems, including building one of the first and longest running intelligent visual surveillance system at MIT, VSR is uniquely positioned to provide robust solutions through technology foresight. In addition, VSR maintains links to leading researchers at major universities and institutions. 

Dr. Christopher Stauffer performs leading research at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and provides technical solutions and guidance to academic, commercial, and defense entities. Dr. Stauffer completed his doctorate in computer science at MIT and earned three Bachelor of Science degrees from Northwestern University in the areas of Electrical Engineering, Computer Science, and Biomedical Engineering. 

Dr. Stauffer enjoys designing and implementing complex systems with unique challenges, such as real-time implementation with limited SW&P (size weight and power) constraints, big data, long-term operation, challenging interaction models, and unsolved algorithm requirements.

.02

Solutions & Awards

VSR leads through technology foresight to make an impact in how we live our lives.  VSR provides leading capabilities in computer vision, machine learning, and big data with together with industrial, commercial, and governmental partners. Capabilities include:

Calibration of Camera and Sensor networks

VSR provides solutions to self-calibrate networks of multiple cameras and sensors in physically distant locations to optimize object tracking over travel distances. Applications include traffic analysis and intelligent video surveillance among others. 

Object Classification, detection, and Real-Time tracking

Utilizing state of the art multi-target, multi-camera networks, VSR provides intelligent computer vision algorithms to classify, detect, and track multiple objects for academic, commercial, and military applications. Techniques extend well-beyond shape detection and include emerging research on hierarchical classification, appearance decomposition, and temporal analysis. 

AUTOMATED Behavior Analysis

VSR develops advanced activity understanding algorithms by combining real-time machine vision techniques with machine learning, big data processing, and data mining.  This includes learning patterns of the activities over long periods of time to detect normal, as well as anomalous, events. Applications include long term analysis and personal data understanding.

Audio-visual Analysis

Visual stimulus alone is often not sufficient for reliably discriminating between many types of activity. In many cases where the visual information required for a particular task is extremely subtle or non-existent, there is often audio stimulus that is extremely salient for a particular classification or anomaly detection task. However, unlike visual events, independent sounds are often very ambiguous and not sufficient to define useful events themselves.

VSR has developed machine learning methods to casually-linked temporal sequences of sound events that are coupled to the visual events, determine statistical anomalies, and automatically cluster these detected events into meaningful clusters.