Graphics enhanced version of this site

Past Projects, Grouped by Center Affiliation

View: By Subject | Alphabetically | By Center Affiliation

Jump to: CIMDS | CRSP | CFR | FRC | MRTC | NREC | SRI | VASC | No Center

• 2D Recognition - Illumination-Invariant Affine Templates for Object Recognition
• 2D->3D Face Model Construction - We develop a linear algorithm that uniquely recovers the 3D non-rigid shapes and poses of a human face from a 2D monocular video.
• 3D Head Motion Recovery in Real Time - A cylindrical model-based algorithm recovers the full motion (3D rotations and 3D translations) of the head in real time.
• 3D Object Recognition - We are applying our techniques for surface representation and matching to object recognition problems; for example, we have used 3D object recognition as part of the Artisan system for interior mapping.
• 3D Optical Reconstruction of Cell Shape - Reconstruction of 3D cell shapes using optical microscope
• 3D Terrain Mapping - We are developing methods for building large-scale, topographic maps of unstructured outdoor environments.
• 3D Vision for Autonomous Navigation - We are developing object representations built from range images that can be used in landmark recognition and object matching
• A Reactive System for Off-Road Autonomous Driving - We have developed an integrated obstacle avoidance system for on-road driving for avoiding discrete obstacles, or for off-road driving for avoiding untraversable regions of terrain.
• A Spherical Representation for Recognition of 3-D Curved Objects - We are investigating a new approach for representing 3-D curved objects for recognition and modeling
• AAM Fitting Algorithms - Many varieties of algorithms for fitting Cootes and Taylor's "Active Appearance Models" are developed.
• AAMs with Occlusion - We are developing algorithms to construct AAMs from occluded training images and to efficiently fit AAMs to faces containing occlusion.
• ALVINN-On-A-Chip - The ALVINN-on-a-chip project is developing an intelligent VLSI imaging sensor for road following
• AUtomotive Run-Off-Road Avoidance system - To help avoid highway accidents, we have developed a vision-based lateral position estimation system called AURORA.
• Active Sensor Control for Neural Net Lane Tracking - Panacea enables existing, fixed-camera lane-trackers such as ALVINN, to use steerable cameras without retraining.
• Anthropocentric Robotics - The goal of this project is to improve human-robot interaction by using anthropological resesarch methods to study how people think about robots.
• Assembly Plan from Observation
• Automatic 3D Modeling from Range Images - A system for generating 3D models of real-world objects without manual or mechanical aids.
• Automatic Construction of Active Appearance Models - An algorithm for the automatic (unsupervised) construction of an Active Appearance Model.
• Automatic Segmentation of Proteomic Images - Segmentation and quantification of protein differences between two proteomic images.
• Autonomous Cargo Trailer Transport System - automated system for handling USPS mail trailers
• Autonomous Land Vehicle In a Neural Network - Neural network navigation
• Bird Classification - Segmentation and classification of birds from images.
• Bookstore Project - We are developing a robot wheelchair capable of navigating Carnegie Mellon's campus, traveling from my office to the Campus Bookstore to fetch a book autonomously.
• Camera Assisted Meeting Event Observer - We are developing the Camera Assisted Meeting Event Observer (CAMEO) - a sensory system designed to provide an electronic agent with physical awareness of the real world.
• Car Tracking - Algorithms for tracking cars and generating "bird's eye views" of the surrounding road scene.
• Chimera - Multiprocessor Real-Time Operating System
• Cohn-Kanade AU-Coded Facial Expression Database - An AU-coded database of over 2000 video sequences of over 200 subjects displaying various facial expressions.
• Collaborative Agents - Cooperative robotics
• Component Analysis for Data Analysis - Component analysis (CA) is a set of techniques to decompose a signal (e.g. audio, video) into interesting components useful for classification, clustering, modeling or visualization. This project extends traditional CA techniques and unifies them, providing a cleaner theoretical framework for its analysis.
• Cooperative Stereo Vision - Development of stereo vision algorithms and supporting software.
• CyberATV - We have developed two Unmanned Ground Vehicles (UGVs) (by retrofitting two Polaris all-terrain vehicles (ATVs)
• CyberRAVE - We are developing a framework to run and simulate multiple mobile robot systems.
• Depth From Focus and Defocus - Focus interpretation is a valuable alternative to stereo vision because it doesn't require solving correspondence for depth recovery.
• DigitEyes - DigitEyes is a noninvasive, real-time tracking system for complex articulated figures like the human hand and body.
• Distributed Architecture for Mobile Navigation - The Distributed Architecture for Mobile Navigation (DAMN) is a behavior-based architecture similar in spirit to the Subsumption Architecture.
• Distributed Robotics Systems - CyberScout - Tactical surveillance collaborative robotics.
• Distributed Surveillance & Sensing - Hierarchical, distributed, and active perception system
• Exploitation of 3-D Data - The E3D project will develop technology to detect, characterize and recognize vehicular targets in 3-D data.
• Face Databases - Miscellaneous face databases collected at CMU.
• Face Detection Databases - A collection of databases for training and testing face detectors.
• Face Model Building and Fitting - Techniques for building and fitting 2D and 3D models of human faces and heads.
• Face and Facial Feature Tracking - Rigid Tracking of Faces and Non-Rigid Tracking of Facial Features
• Factorization Method - We have developed a factorization method to robustly decompose an image stream into object shape and camera motion.
• Fast VLSI Range-Image Sensor - We have built a high-performance VLSI sensor which uses a "cell-parallel" light-stripe algorithm to increase range-image frame rates by two orders of magnitude
• Fractal Terrain Modeling - he goal of our research in fractal terrain modeling is to build dense terrain maps that accurately represent natural surfaces
• Gaze Estimation - Algorithms for estimating where someone is looking
• Gesture Based Programming - Programming by human demonstration
• Grid based Approach for Navigation by Evidence Storage and Histogram Analysis - Grid based navigation
• Gyrover - A Single-Wheel, Gyroscopically stabilized Robot
• High Bandwidth Visual Feedback for Robust Manipulation - Sensor-based robotic system that can robustly perform manipulation tasks in dynamically varying and imprecisely calibrated environments.
• Humanoid Vision - We are adding visual recognition and navigation to Honda's humanoid robots
• I-Cubes - "ICES Cubes" are a class of modular self-reconfigurable bipartite robotic systems
• Image-based Modeling and Rendering - Acquiring, manipulating, and rendering representations of real environments based on photographs.
• Interactive Robot Programming - We are developing human-machine interfaces to allow non-experts to interact in a human manner with robots.
• Knowledge-Guided Deformable Registration - Matching corresponding anatomical structures across individuals, detecting possible pathologies.
• Learning Kernel Expansions for Image Classification - Learning non-linear representations of a signal in order to improve classification performance.
• Light-fields - A variety of uses of light-fields in computer vision.
• Lucas-Kanade 20 Years On - A Unifying Framework for Image Alginment
• MARS2020 - This project seeks to develop softwares needed to program autonomous mobile robots in partially known, changing, and unpredictable environments.
• Machine learning approaches to invert the Radiative Transfer Equation - Supervised learning approaches to invert the non-linear Radiative Transfer Equation in remote sensing problems.
• Magic Eye - Computer vision based augmented reality systems
• Massively Parallel Road Following - Autonomous roadway navigation using video images
• Medical Imaging - Analysis of sequences of microscope images for the recovery of significant events and mutations in cell development
• Millibots - Heterogeneous group of small autonomous robots with modular payloads and sensing platforms
• Model Building - Surface registration is applied to a variety of problems, including object modelling and mapping of large areas.
• Modeling from Reality - Techniques for constructing solid models from observations of real objects
• Neural Network Gaze Tracking - We have developed an artificial neural network based gaze tracking system which can be customized to individual users.
• No Hands Across America! - Vehicle drives across the United States
• Non-Invasive Optical Imaging in vivo for Early Detection and Advanced Diagnosis of Cancer
• Onika - Iconically programmed interface to Chimera
• PIE Database - A database of 41,368 images of 68 people with Pose, Illumination, and Expression variation.
• Perception for Rock Sampling - We are developing a set of perception modules for extracting the potential samples from visual data, building models of their shapes, and using the models to pick up and store the sample.
• Photometric Limits on Computer Vision - An investigation into the fundamental limits imposed on computer vision algorithms by imperfect or incomplete photometric information.
• Physics-Based Inspection
• Position Estimation - We estimate the position of a robot based on the position of natural landmarks in images.
• Prediction & Planning - This project analyses the safety and interaction of moving objects in complex road scenes.
• Ranger - We are developing a software control system for cross country autonomous vehicles called RANGER, for Real-time Autonomous Navigator with a Geometric Engine.
• Rapidly Adapting Lateral Position Handler - adaptive steering
• Real and Virtual Environment for Multiple Robots - General-purpose framework to run and simulate multiple mobile robot systems
• Real-time Autonomous Car Chaser Operating Optimally at Night - RACCOON is a taillight-tracker that can drive an intelligent vehicle at night, when the road is not visible, by following other cars.
• Reconfigurable Modular Manipulator System - Sensor-Based Manipulators
• Reconfigurable Software Design for Robotic and Automation Applications - We are developing a novel software framework, based on the notion of dynamically reconfigurable real-time software
• Reflectance Analysis for Computer Graphics Model Generation - New approach to obtain photometric information as well as geometric information of an object model automatically by observing a real object
• Robot Improv - We are developing realistic dramatic behavior for mobile robotics.
• Robotic Neurosurgery Probe Guide - Assists surgeons in choosing an incision site.
• Robotics Lexicon Project - The goal of this project is the computer-aided collection, recording and dissemination of robotics terminology.
• Sage - Sage is a completely autonomous mobile multimedia exhibit built on top of the XR4000 robot base by Nomadic Technologies, Inc.
• Scene Flow - Methods of computing dense, non-rigid motion of 3D scenes.
• Self-Mobile Space Manipulator - A simple, independently mobile, modular, low mass, low cost robot for space station EVA.
• Setting Low-Level Vision Parameters - Techniques for feeding back information from high-level vision modules to low-level modules to improve the performance of the overall system.
• Side Collision Warning System for Transit Buses - To develop a warning system which helps a driver of a transit bus to avoid side collisions with pedestrians, other vehicles, or stationary objects.
• Simulated Highways for Intelligent Vehicle Algorithms - SHIVA is a microsimulation of a highway environment, designed specifically for testing intelligent vehicle tactical algorithms.
• Simultaneous Localization and Mapping with Detection, Tracking, and Classification of Moving Objects - We are developing the algorithms to solve Simultaneous Localization and Mapping (SLAM) and Detection, Tracking and Classification of Moving Objects (DTCMO) problems for both indoor and outdoor applications.
• Situational Awareness Planner Implementing Effective Navigation in Traffic - SAPIENT is a distributed approach to tactical decision making for intelligent vehicles.
• Sonar Mapping for Underwater Vehicles - Elevation map refinement from bathymetric side-scan sonar images
• Spatial Frequency - Our space / frequency representation has proven useful for solving the combined problem of segmentation and shape from texture.
• Spatial Layout - Locate a set of objects in a housing unit
• Spatio-Temporal View Interpolation - An image-based rendering algorithm for view interpolation across both space and time.
• Supervised TeleRobotics using Incremental Polyhedral-Earth geometry - Teleoperating vehicles over low bandwidth links.
• Tactical Mobile Robotics - As part of the DARPA Tactial Mobile Robotics program, we are developing techniques for semi-autonomous navigation of a small robot in urban environments.
• Tele-Graffiti - A system that allows two or more users to communicate remotely via hand-drawn sketches.
• Template Update - We are developing an algorithm to update template tracking that avoids the "drifting" problem of the naive update algorithm.
• Tessellator - Space Shuttle Tile Inspector
• Textureless Layers - Techniques for the 3D reconstruction of scenes consisting of constant intensity piecewise planar regions (layers).
• Transformer Winding Automation - Increase the production speed and quality of transformer winding through sensing and automation
• Transit Bus Collision Warning Systems - Research and integration of side and front collision warning systems for transit buses.
• Unmanned Ground Vehicles - Developing autonomous navigation capabilities for mobile robots driving in complex, unstructured outdoor terrain.
• Video Surveillance and Monitoring - cooperative multi-sensor military surveillance system
• Video Verification of Identity - We address the problem of tracking object in video sequences and of recognizing the tracked objects in subsequent sequences.
• Video-rate Stereo Machine - Multiple images obtained by multiple cameras to produce different baselines in lengths and in directions
• Virtualized Reality^TM - Construct views of real events from nearly any viewpoint
• Vision Algorithm Compiler
• Visual Position Estimator - The VIPER project aims at building a teleoperation interface which can analyze images sent by a mobile robot in space missions and estimate the position of the robot.
• Z-Keying - A new image keying method which merges synthetic and real image in real time.
• Zoom Lens Calibration - We have developed new algorithms and techniques to build models for cameras with automated zoom lenses