Intelligent Querying Techniques for Sensor Data Fusion

Download Report

Transcript Intelligent Querying Techniques for Sensor Data Fusion

MULTIMEDIA DATABASES AND
QUERYING TECHNIQUES
By: Rohit Kulkarni
CS 2310 – Spring 2008
AGENDA

Background

Problem Definition

Challenges
BACKGROUND

What is MMDBMS?

Normalization framework

What is data fusion?

The general problem

Querying technique
MMDBMS ARCHITECTURE
REQUIREMENTS FOR MMDBMS
Traditional DBMS capabilities
 Huge capacity for storage management
 Information retrieval capabilities
 Media integration, composition and
representation
 Multimedia query support
 Multimedia interface and interactivity
 Performance

ISSUES IN MMDBMS
Multimedia data modeling
 Multimedia object storage
 Multimedia integration, presentation and QOS
 Multimedia indexing, retrieval and browsing
 Multimedia query support
 Distributed multimedia database management
 System support

PROBLEM DEFINITIONS

Extended Dependencies

The relational model

Similarity theory

Tuple distance function
AN EXAMPLE

Define a functional dependency between
attributes FINGERPRINT and PHOTO of police
database, and use the fingerprint matching
function FINGERCODE for comparing digital
fingerprint [JPH00], and the similarity technique
used by QBIC for comparing photo images, we
would write as follows
FINGERPRINTFINGERCODE(t’)
PHOTOQBIC(t’’)
INFERENCE RULES FOR MFDS
Reflexive rule
 Augmentation rule
 Transitive rule
 Decomposition rule
 Union rule
 Pseudotransitive rule

NORMAL FORMS IN MULTIMEDIA
DATABASES



Normal forms are used to derive database
schemes that prevent manipulation anomalies
Similar anomalies can arise in multimedia
database
Types of normal forms are
1MNF, 2MNF , 3MNF and 4MNF
SENSOR DATA FUSION



Background:
Need for Multiple Sensors:- data from a single
sensor yields poor results in object recognition
Sensor Management Model
SENSOR MANAGEMENT MODEL
SENSOR DATA FUSION

Problems:

Association of objects from different Sensors

Tracking
NEED FOR QUERY TECHNIQUE
•
Problem with existing query techniques
•
Why not SQL?
•
To support the retrieval and fusion of multimedia
information from multiple sources and
distributed databases, a spatial/temporal query
language called QL has been proposed
FEATURES OF QL



Easy to learn as syntax is similar to SQL
Allows user to specify queries for both
Multimedia data sources and Multimedia
databases
Supports multiple sensor sources and systematic
modification of queries
OPERATOR CLASSES

The operators in QL can be categorized with
respect to their functionality.
The two main classes are:
 transformational operators (the σ-operators)
 fusion operators (the -operators).

TRANSFORMATIONAL OPERATORS

Definition: A σ-operator is defined as an operator
to be applied to any multi-dimensional source of
objects in a specified set of intervals along a
dimension. The operator projects the source along
that dimension to extract clusters
TRANSFORMATIONAL OPERATORS (CONTD)
As an example, if we write a σ-expression for
extracting the video frame sequences in the time
intervals [t1-t2] and [t3-t4] from a video source
VideoR.
 The expression will be

is σtime([t1-t2], [t3-t4]) VideoR
where VideoR is projected along the time
dimension to extract clusters (frames in this case)
whose projected positions along the time
dimension are in the specified intervals.
FUSION OPERATORS
Much more complex as it deals with Sensor data
fusion
 Requires input data in different time periods
from multiple sensors
 The output of the fusion-operator is some kind of
high level, qualitative representation of the fused
object, and may include object type, attribute
values and status values.

IS THERE A MOVING VEHICLE PRESENT
IN THE GIVEN AREA AND IN THE GIVEN
TIME INTERVAL?
IS THERE A MOVING VEHICLE PRESENT
IN THE GIVEN AREA AND IN THE GIVEN
TIME INTERVAL?
•
Corresponding query:
type,position, direction
(motion(moving) type(vehicle)
xy(*)
 (T)T mod 10 = 0 and T>t1 and T <t2
media_sources (video)media_sources
ype (vehicle) xyz(*)
 (T) T>t1 and T<t2
media_sources(laser_radar) media_sources)
EXPERIMENTAL PROTOTYPE
CHALLENGES


Handle large number of different sensors
Replacing manual query with a semi-automatic
or fully automatic query refinement process
APPLICATIONS OF MMDBMS
Education- digital libraries, training,
presentation
 Healthcare- telemedicine, health information
management
 Entertainment- interactive TV, video on demand
 Information dissemination- news, TV
broadcasting
 And many more!

REFERENCES






Intelligent Querying Techniques for Sensor Data Fusion by ShiKuo Chang, Gennaro Costagliola, Erland Jungert and Karin Camara
A Normalization Framework for Multimedia Databases by S.K.
CHANG, V. DEUFEMIA, G. POLESE
Querying distributed Multimedia databases and data sources for
sensor data fusion by S.K.Chang, Gennaro Costagliola, Erland Jungert
and Francesco Orciuoli
Multimedia database management-requirements and issues by
Donald A. Adjeroh and Kingsley C. Nwosu
Fuzzy Queries in Multimedia database system by Ronald Fagin
Bayesian Approaches to Multi-Sensor data fusion by Olena Punska,
St. John’s CollegeMultimedia database management-requirements and
issues by Donald A. Adjeroh and Kingsley C. Nwosu Querying distributed
Multimedia databases and data sources for sensor data fusion by
S.K.Chang, Gennaro Costagliola, Erland Jungert and Francesco Orciuoli
MULTIMEDIA DATABASE AND QUERYING
TECHNIQUES
By: Rohit Kulkarni
CS 2310 – Spring 2008

Thank you