Computer vision publications
-
GPU Accelerated Realtime Stereo for Augmented Reality
This paper presents a realtime, robust, and accurate stereo matching algorithm based on a coarse-to-fine architecture.
-
Technical Overview of the Sarnoff Acadia II Vision Processor
This paper presents a detailed technical overview of the Acadia® II, highlighting its architecture, processing capabilities, memory and peripheral interfaces.
-
Implementing Real-Time Imaging Systems Using the Sarnoff Acadia II Vision Processor
This paper will describe how to best use the power of the Acadia® II as both an all-in-one image processor and as a general purpose computer for performing other critical…
-
Lidar-Based Door and Stair Detection from a Mobile Robot
We present an on-the-move LIDAR-based object detection system for autonomous and semi-autonomous unmanned vehicle systems.
-
Special Issue on Embedded Vision
-
Automatic Blood Vessel Localization in Small Field of View Eye Images
We present an automatic technique for localizing vessels in small field of view images using multi-scale matched filters. We also estimate local vessel properties - width and orientation - along…
-
Video Synchronization and Its Application to Object Transfer
We trade some generality in estimating and aligning camera motion for reduced computational complexity and increased image-based nature.
-
Remediation of Facial Emotion Recognition in Schizophrenia: Functional Predictors, Generalisability, and Concomitant Visual Scanning of Novel Face Stimuli
This study investigated whether improved recognition generalizes to novel faces, training effects are durable over 1 month, and baseline functioning levels predict the extent of improvement.
-
Quantitative Comparison of Metrics for Change Detection in Video Patrolling Applications
This paper provides a comprehensive quantitative comparison of metrics for detecting visual anomalies between two videos that are recorded along same path but at different times by a camera on…
-
Multicamera Tracking of Articulated Human Motion Using Shape and Motion Cues
We present a completely automatic algorithm for initializing and tracking the articulated motion of humans using image sequences obtained from multiple cameras.
-
Multiple-Target Tracking Via Kinematics, Shape, and Appearance-Based Data Association
This paper presents a real time system for tracking multiple ground moving targets in aerial video.
-
Automatic Food Documentation and Volume Computation Using Digital Imaging and Electronic Transmission
Improving methodology even modestly would advance our knowledge about the influence of food intake on health.