Unsupervised Learning of Multi-Object Events
نویسنده
چکیده
We present a novel approach for automatically inferring models of multiobject events. Objects are first detected and tracked, their motion is then segmented into a set of primitive events. These primitive events then form the nodes in aMarkov network that encodes the entire event space. A bottomup/top-down search algorithm is developed to detect typical event structures that are used for classifying an observed multi-object event. We demonstrate our algorithm on clustering and inferring events in a table-laying scene.
منابع مشابه
An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملUnsupervised Learning of Multi-Object Event Classes
We present a novel approach for automatically inferring models of multiobject events. Objects are first detected and tracked, their motion is then segmented into a set of primitive events. These primitive events then form the nodes in a Markov network that encodes the entire event space. A bottomup/top-down search algorithm is developed to detect typical event structures that are used for class...
متن کاملThesis for the degree Doctor of Philosophy
In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since image motion is used for internal supervision, via the detection of spatiotemporal events of active-motion and the use of tracking. Most current work in objec...
متن کاملMulti-stage Optimization for Multi-body Motion Segmentation
Many techniques have been proposed for separating feature point trajectories tracked through a video sequence into independent motions, but objects are usually assumed to undergo general 3-D motions. As a result, the separation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we introduce unsupervised learning assuming...
متن کاملMulti-Object Tracking, Event Modeling, and Activity Discovery in Video Sequences
Title of dissertation: MULTI-OBJECT TRACKING, EVENT MODELING, AND ACTIVITY DISCOVERY IN VIDEO SEQUENCES Seong-Wook Joo Doctor of Philosophy, 2007 Dissertation directed by: Professor Rama Chellappa Department of Electrical and Computer Engineering, Department of Computer Science One of the main goals of computer vision is video understanding, where objects in the video are detected, tracked, and...
متن کامل