Scribd
Upload
174 views9 pages

Video Retrieval via MPEG Compression

This document presents a video retrieval system that uses a two-stage indexing and retrieval approach. It first classifies video shots into separate databases using motion characteristics, then searches each database for color features. The system reduces search time by half with only a slight reduction in retrieval rate. It allows users to query the video database by selecting a video type and sketching a color-based description of the desired video shot.

Uploaded by

lipika008
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
174 views9 pages

Video Retrieval via MPEG Compression

This document presents a video retrieval system that uses a two-stage indexing and retrieval approach. It first classifies video shots into separate databases using motion characteristics, then searches each database for color features. The system reduces search time by half with only a slight reduction in retrieval rate. It allows users to query the video database by selecting a video type and sketching a color-based description of the desired video shot.

Uploaded by

lipika008
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

A VIDEO RETRIEVAL SYSTEM

“A VIDEO RETRIEVAL SYSTEM


BASED ON COMPRESSED
DATA FROM MPEG FILES”
Presented
By

Malaya Kumar Das Roll no. CS 2001 17 162


Under the guidance of

Mr. R. K. Shial
Faculty in Computer Science & Engg.
MALAYA KUMAR DAS [1]
A VIDEO RETRIEVAL SYSTEM

WHAT IT DOES?
 The system uses a two-stage indexing and
retrieval approach :
 first to classify video shots into separate databases
using their motion characteristics.
 second to search each database for colour features.
 The two-stage approach reduces the search
time to almost half at a slight reduction in
retrieval rate.

MALAYA KUMAR DAS [2]


A VIDEO RETRIEVAL SYSTEM

COMPONENTS IN VIRS

 Shot Detection

 Shot Representation

 Colour Feature Representation

 Motion Feature Representation

MALAYA KUMAR DAS [3]


A VIDEO RETRIEVAL SYSTEM

GROUP OF PICTURES (GOP)

I: Intra-frame coded


P: Predictive inter-framecoded
B: Bi-directional inter-frame coded
MALAYA KUMAR DAS [4]
A VIDEO RETRIEVAL SYSTEM

VIDEO DATABASE POPULATION

 Motion-Based Classifier
 Four video categories (or types): Sport, News,
Drama, and Scenery.
 Colour Database
 Colour is quantised into 10 colors.
 In VIRS each r-frame is partitioned into nine equal
rectangular regions: N, NW, W, SW, S, SE, E, NE
and Center.

MALAYA KUMAR DAS [5]


A VIDEO RETRIEVAL SYSTEM

VIDEO DATABASE QUERY


 The graphical query interface allows a
user to make a query in two steps:
 a type query.
 a colour sketch query.
 The user specifies the type of video shot
he or she wishes to retrieve.
 The user then enters the colour-based
information about the r-frame to be
searched from the database of the
selected video type.

MALAYA KUMAR DAS [6]


A VIDEO RETRIEVAL SYSTEM

VIDEO DATABASE QUERY

 The graphical query interface consists of:


 A visual colour chart of 10 quantised colors with
known RGB vectors.
 A visual shape chart of common shapes.
 A visual texture chart of common textures with known
feature vectors.
 A menu of video type buttons.

MALAYA KUMAR DAS [7]


A VIDEO RETRIEVAL SYSTEM

GRAPHICAL INTERFACE

MALAYA KUMAR DAS [8]


A VIDEO RETRIEVAL SYSTEM

CONCLUSION

This two-step retrieval strategy reduces the


search time to half on average at a slight
reduction in retrieval rate. The system returns a
ranked list of three or more candidates. The user
can click on the returned r-frame to play the
retrieved video shot and hence, the video clip.

MALAYA KUMAR DAS [9]

You might also like