Vision & Cognition Laboratory

Department of Computer Science, Drexel University

 
home  |  projects  |  people  |  publications  |  facilities  |  sponsors

Projects

Optimal Random Matchings on Trees and Applications  [Abrahamson, Csaba, Shokoufandeh]
In this project we will consider tight upper- and lower-bounds on the weight of the optimal matching for random point sets distributed among the leaves of a tree, as a function of its cardinality.

Subset Selection Using Nonlinear Optimization  [Denton, Shokoufandeh]
A generalization framework for selecting canonical subsets of data points that are highly representative of the original larger dataset.

Drexel Object Occlusion Repository (DOOR)   [Denton, Novatnack, Shokoufandeh]
The Drexel Object Occlusion Repository is a reference set of images for computer vision and object recognition researchers. The images are constructed by overlapping input objects from the COIL-20 database and occluding them by various amounts.

Many-to-Many Matching  [Demirci, Shokoufandeh]
An algorithm to for many-to-many matching between noisy, vertex-labeled graphs.

Skeletal Shape Abstraction
[Demirci, Dickinson, Shokoufandeh]
An technique for detecting abstract attributes of images and graphs through many-to-many correspondences.

Locally Linear Montage  [Nishino]
Face recognition under varying illumination, using only a single gallery image per subject taken under unknown lighting.

Eyes for Relighting  [Nishino]
Extracting an illumination distribution from an image of an eye in an unstructured setting.

The World in Eyes  [Nishino]
Reconstructing what a person sees by analyzing reflective images in their eyes.

Re-rendering from a Sparse Set of Images  [Nishino]
P hotorealistic rendering of real-world objects from a sparsely sampled appearance variation.

Eigen-Texture Rendering  [Nishino]
Sampling appearances of a real object under various conditions and compressing them in the 2D coordinate system defined on the 3D model surface.

Illumination Eigenspace and Shadow Removal  [Nishino]
Eliminating shadows from image sequences using intrinsic images.

Color Constancy with Inverse-Intensity Chromaticity Space  [Nishino]
Estimating the illumination chromaticity from a single/multi-colored surface.

Digital Archive of Cultural Heritages  [Nishino]
Techniques for digital preservation of ancestral objects mainly in Japan and other countries in Asia.

Integrated Driver Model  [Salvucci]
A computational model of human driver behavior developed in the ACT-R cognitive architecture.

Modeling Human Multitasking  [Salvucci]
The study of how people prioritize, integrate, and perform multiple tasks simulataneously.

Driver Distraction  [Salvucci]
The study of how in-vehicle devices (e.g., cell phones, navigation aids) distract drivers and how to design and build less distracting systems.

iPod Distraction  [Salvucci]
The study of interaction with an iPod while driving and its effects on driver performance.

Distract-R  [Salvucci]
A rapid prototyping and evaluation system for in-vehicle devices.

Mind Tracking  [Salvucci]
A computational architecture for tracking cognitive processes — that is, how machines can read our minds.

ACT-Simple  [Salvucci, Lee]
A basic, high-level computational modeling framework based in the ACT-R architecture and used for rapid prototyping of simple behavioral models.

Driving Simulator  [Salvucci]
An instrumented Nissan 240sx platform with virtual driving environment and integrated eye tracker.

EMMA  [Salvucci]
A computational model of human eye movements and visual encoding integrated with the ACT-R/PM architecture.

Gaze-Based Interfaces
Computer interfaces that users control with their eye movements, allowing for faster and easier interaction for physically-disabled and able-bodied users alike.