THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Randal Nelson (Associate Professor )
UR > CS > Research > Vision > People > Randal Nelson
 in action

Contact:

Randal Nelson
CSB 719
Department of Computer Science
University of Rochester
Rochester, NY 14627

vox: (585)-275-8848
email: nelson@cs.rochester.edu
home: http://www.cs.rochester.edu/~nelson
vision: http://www.rochester.edu/research/vision/people/Randal_C_Nelson

About:

Randal Nelson is currently an associate professor of computer science at the University of Rochester. He received his PhD in computer science from the University of Maryland in 1988. His research interests involve machine vision and robotics with an emphasis on systems that engage in sensory-mediated interaction with the physical world. Recent and current projects include visual navigation, motion recognition and analysis, vision for manipulation and hand-eye coordination, 3D object recognition, and the relationship between vision and language. Outside interests include general science and technology (want to build a blast furnace in your backyard?), cesium, fixing cars and houses, woodworking, local flora and fauna, and bits and pieces of music.

Research Interests:

My research interests involve machine vision and robotics with an emphasis on systems that engage in sensory-mediated interaction with the physical world. Published work includes papers on visual navigation by robots, motion recognition and analysis including human motion, vision for robot manipulation and hand-eye coordination, and generic 3D object recognition. Current interests includes extending 3D object recognition to more generic classes, the connection of machine vision and recognition to notions of spatial intelligence, and the grounding of natural language abstractions in implemented perceptual and effective processes.

Projects:

Improving Augmented Reality Rendering: We improve the human-computer interaction experience in AR systems by simulating global lighting effects between virtual and real objects.

Perceptual Basis of Spatial Relations: We seek to visually recognize the spatial relations between objects in a 3-D realistic environment, using an interaction-based approach that identifies a small high-leverage set of visual features.

Quasi-static Object Discovery (QsOD): We discover quasi-static objects, objects that are stationary during some interval of observation, across image sequences acquired by any number of completely uncalibrated cameras using only temporal (no spatial) information.

The Memory Assistant: The Memory Assistant system is designed to help people with mild to moderate memory loss keep tracking of important objects in a home environment.

Semantic Scene Classification: We improve semantic scene classification by using semantic object/ material detectors and spatial models within a probabilistic framework to infer the scene type.


Publications:

Virtual Tools: A Framework for Simplifying Sensory-Motor Control in Complex Robotic Systems (Randal C. Nelson and Martin Jagersand and Olac Fuentes)
3D Recogniton via 2-Stage Associative Memory (Randal C. Nelson)
Nonparametric Recognition of Nonrigid Motion (Ramprasad B. Polana and Randal C. Nelson)
Adaptive Differential Visual Feedback for Uncalibrated Hand-Eye Coordination and Motor Control (Martin Jagersand and Randal C. Nelson)
Morphing Hands and Virtual Tools (Olac Fuentes and Randal C. Nelson)
A cubist Apprach to Object Recognition (Randal C. Nelson and Andrea Selinger)
Learning Dextrous Manipulation Strategies for Multifingered Robot Hands Using the Evolution Strategy (Olac Fuentes and Randal C. Nelson)
A Cubist Approach to Object Recognition (Randal C. Nelson and Andrea Selinger)
Large-Scale Tests of a Keyed, Appearance-Based 3D Object Recognition System (Randal C. Nelson and Andrea Selinger)
Tracking Objects Using Recgonition (Tech Report) (Randal Nelson and Issac Green)
The {OD} Theory of {TOD}: The Use and Limitations of Temporal Information for Object Discovery (Brandon C.S. Sanders and Randal C. Nelson and Rahul Sukthankar)
Tracking Objects Using Recognition (Randal Nelson and Issac Green)
A Theory of the Quasi-static World (Brandon C.S. Sanders and Randal C. Nelson and Rahul Sukthankar)
Segmentation Propagation during a Camera Saccade (Issac A. Green and Randal C. Nelson)
Discovering Objects Using Temporal Information (Brandon C.S. Sanders and Randal C. Nelson and Rahul Sukthankar)
Appearance-Based Object Recognition Using Multiple Views (Andrea Selinger and Randal C. Nelson)
Minimally Supervised Acquisition of 3D Recognition Model from Cluttered Images (Andrea Selinger and Randal C. Nelson)
Appearance-Based Object Recognition Using Multiple Views (Andrea Selinger and Randal C. Nelson)
Minimally Supervised Acquisition of 3D Recognition Model from Cluttered Images (Andrea Selinger and Randal C. Nelson)
Learning Dextrous Manipulation Skills Using the Evolution Strategy (Olac Fuentes and Randal C. Nelson)
Experimental Evaluation of Uncalibrated Visual Serving for Precision Manipulation (Martin Jagersand, Olac Fuentes, and Randal C. Nelson)
Detection and Recognition of Periodic, Non-Rigid Motion (Ramprasad Polana, and Randal C. Nelson)
The Virtual Tool Approach to Dextrous Telemanipulation (Olac Fuentes and Randal C. Nelson)
Experiments on Dextrous Manipulation without Prior Object Models (Olac Fuentes and Randal C. Nelson)
Acquiring Visual_Motor Models for Robot Hand Fine-Manipulation (Martin Jagersand, Olac Fuentes, and Randal C. Nelson)
Learning Dextrous Manipulation Skills for Multifingered Robot Hands (Olac Fuentes and Randal C. Nelson)
Using Directional Variance to Extract Curvees in Images, thus Improving Object Recognition in Clutter (Andrea Selinger and Randal C. Nelson)
A Perceptual Grouping Hierarchy for Apperarnce-Based 3D Object Recognition (Andrea Selinger and Randal C. Nelson)
Improving Appearance-Based Object Recognition in Cluttered Background (Andrea Selinger and Randal C. Nelson)
Learning 3D Recognition Models for General Object from Unlabeled Imagery: An Experiment in Intelligent Brute Force (Randal C. Nelson and Andrea Selinger)
Minimally Supervised Acquisition of 3D Recognition Models from Images (Andrea Selinger and Randal C. Nelson)