Search For:

Displaying 1-12 out of 12 total
A Modular Computer Vision System for Picture Segmentation and Interpretation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Martin D. Levine,Samir I. Shaheen
Issue Date:May 1981
pp. 540-556
The objective of a computer vision system is to outline the objects in a picture and label them with an appropriate interpretation. This paper proposes a new paradigm for a modular computer vision system which is both data directed and knowledge based. The...
 
Authors' Reply
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Martin D. Levine,Ahmed M. Nazif
Issue Date:May 1986
pp. 676
No summary available.
   
Dynamic Measurement of Computer Generated Image Segmentations
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Martin D. Levine,Ahmed M. Nazif
Issue Date:February 1985
pp. 155-164
This paper introduces a general purpose performance measurement scheme for image segmentation algorithms. Performance parameters that function in real-time distinguish this method from previous approaches that depended on an a priori knowledge of the corre...
 
3D Part Segmentation Using Simulated Electrical Charge Distributions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kenong Wu, Martin D. Levine
Issue Date:November 1997
pp. 1223-1235
<p><b>Abstract</b>—A novel approach to 3D part segmentation is presented. It is a well-known physical fact that electrical charge on the surface of a conductor tends to accumulate at a sharp convexity and vanish at a sharp concavity. Thus...
 
Cell Tracking: A Modeling and Minimization Approach
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Frank P. Ferrie,Martin D. Levine,Steven W. Zucker
Issue Date:March 1982
pp. 277-291
This paper presents a model of motion suitable for cell tracking. It includes a representation for cell dynamics enabling it to maintain a correspondence between successive images of cells undergoing morphological changes. This model is based on a minimiza...
 
Real-Time Semantics-Based Detection of Suspicious Activities in Public Spaces
Found in: 2012 Canadian Conference on Computer and Robot Vision
By Mohannad Elhamod,Martin D. Levine
Issue Date:May 2012
pp. 268-275
Behaviour recognition and video understanding are core components of video surveillance and its real life applications. Recently there has been much effort to devise automated real-time high accuracy video surveillance systems. In this paper, we introduce ...
 
Multiple Resolution Skeletons
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andreas R. Dill,Martin D. Levine,Peter B. Noble
Issue Date:April 1987
pp. 495-504
This paper presents a new algorithm to compute skeletons of noisy images of objects which can be described as ``amorphous blobs.'' Such a requirement arose from our research to obtain a better understanding of the role of the pseudopod in leukocyte locomot...
 
Low Level Image Segmentation: An Expert System
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ahmed M. Nazif,Martin D. Levine
Issue Date:May 1984
pp. 555-577
A major problem in robotic vision is the segmentation of images of natural scenes in order to understand their content. This paper presents a new solution to the image segmentation problem that is based on the design of a rule-based expert system. General ...
 
Registering Multiview Range Data to Create 3D Computer Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gérard Blais, Martin D. Levine
Issue Date:August 1995
pp. 820-824
<p><it>Abstract</it>—This research deals with the problem of range image registration for the purpose of building surface models of three-dimensional objects. The registration task involves finding the translation and rotation parameters ...
 
The McGill Object Detection Suite
Found in: Computer and Robot Vision, Canadian Conference
By Donovan H. Parks, Martin D. Levine
Issue Date:June 2006
pp. 47
Evaluation of object detection systems requires a set of test images with objects in heterogeneous scenes. Unfortunately, existing publicly available object databases provide few, if any, test images suitable for evaluating object detection systems. Here w...
 
Fully Automated Recognition of Spontaneous Facial Expressions in Videos Using Random Forest Classifiers
Found in: IEEE Transactions on Affective Computing
By Mostafa K. Abd El Meguid,Martin D. Levine
Issue Date:April 2014
pp. 1-1
This paper discusses the design and implementation of a fully automated comprehensive facial expression detection and classification framework. It uses a proprietary face detector (PittPatt) and a novel classifier consisting of a set of Random Forests pair...
 
Online Dominant and Anomalous Behavior Detection in Videos
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Mehrsan Javan Roshtkhari,Martin D. Levine
Issue Date:June 2013
pp. 2611-2618
We present a novel approach for video parsing and simultaneous online learning of dominant and anomalous behaviors in surveillance videos. Dominant behaviors are those occurring frequently in videos and hence, usually do not attract much attention. They ca...
 
 1