Download presentation
Presentation is loading. Please wait.
Published byKirk Northen Modified over 11 years ago
1
IMAGE RE-SEGMENTATION A new approach applied to Urban Imagery Thales Sehn Korting Leila Maria Garcia Fonseca Luciano Vieira Dutra Felipe Castro da Silva
2
Introduction Image segmentation is the identification of homogeneous regions in the image
3
Traditional approaches Few versions available for end users Algorithms dont consider the application context –Urban –Agriculture –etc
4
Urban Segmentation
5
Objective Development of a re-segmentation system, based on rectangular shapes Re-Segmentation –Rearrangement of a polygon set, merging some elements to generate objects with particular characteristics, applied to a specific context
6
Re-Segmentation Approach Band 1 Band 2 Band... Band n Input Output Over- Segmentation
7
Segmentation Based on Graph Region Adjacency Graph
8
Re-Segmentation Diagram
9
Finding Rectangles PiPi x y AV ANG(P i ) RiRi BOX(R i ) AREA(P i ) AREA(BOX(R i )) RET(P i ) =
10
Results Original image Rectangular shapes highlighted Classified regions Resultant polygons Hardware –AMD Athlon tm 3000+ –512MB RAM –Linux Mandriva 2006
11
1 st – Original
12
Over-Segmentation 1998 polygons
13
Classification trees roofs buildings streets others
14
Resultant Re-Segmentation 634 polygons 317 seconds
15
2 nd – Original
16
Over-Segmentation 2028 polygons
17
Classification trees roofs buildings streets others
18
Resultant Re-Segmentation 695 polygons 243 seconds
19
3 rd – Original
20
Over-Segmentation 2264 polygons
21
Classification trees roofs buildings streets others
22
Resultant Re-Segmentation 750 polygons 196 seconds
23
Drawbacks
24
Conclusions New approach for image re-segmentation Algorithm developed using the Free C++ Library TerraLib ( http://www.terralib.org/ )
25
IMAGE RE-SEGMENTATION A new approach applied to Urban Imagery END
Similar presentations
© 2025 SlidePlayer.com Inc.
All rights reserved.