event thumbnail image
6th IARP -TC-15 Workshop on Graphbased Representations in Pattern Recognition
Pascal

Qualitative Spatial Relationships for Image Interpretation by using Semantic Graph

author: Aline Deruyver, LSIIT - The Image Sciences, Computer Sciences and Remote Sensing Laboratory

Description

In this paper, a new way to express complex spatial relations is proposed in order to integrate them in a Constraint Satisfaction Problem with bilevel constraints. These constraints allow to build semantic graphs, which can describe more precisely the spatial relations between subparts of a composite object that we look for in an image. For example, it allows to express complex spatial relations such as “is surrounded by”. This approach can be applied to image interpretation and some examples on real images are presented.

You might be experiencing some problems with Your Video player.
Slides
0:00 Image interpretation by using conceptual graph: introducing complex spatial relations
0:18 Spatial relations are a key point of image understanding
1:17 Image interpretation
1:20 Matching of heterogeneous graphs
1:53 Graph matching
2:41 Image interpretation
2:48 AC4 Algorithm : solve the graph matching problem by solving a problem of constraint satisfaction
3:27 Limits
3:57 Image interpretation
4:01 Solution: checking arc-consistency with bilevel constraints
4:16 Constraint satisfaction problem with two levels of constraint
5:12 How to match? (1)
5:58 How to match? (2)
6:15 How to match? (3)
6:32 How to match? (4)
7:04 How to match? (5)
7:15 How to match? (6)
7:21 How to match? (7)
7:28 How to match? (8)
8:04 How to match? (9)
8:04 Intra-node constraints: compatibility between two values (Cmpi) (1)
8:18 Intra-node constraints: compatibility between two values (Cmpi) (2)
8:35 Image interpretation
9:03 Complex spatial relations (1)
9:36 Complex spatial relations (2)
10:34 Complex spatial relations (3)
10:59 Complex spatial relations (4)
12:01 Connectivity-Direction-Metric Formalism (1)
12:46 Connectivity-Direction-Metric Formalism (2)
13:01 Connectivity-Direction-Metric Formalism (3)
13:14 Connectivity-Direction-Metric Formalism (4)
14:06 How to combine these relations? (1)
14:37 How to combine these relations? (2)
15:57 We want more ! (1)
16:14 We want more ! (2)
16:29 We want more ! (3)
16:58 We can linked one interface with different nodes of the shell and described any logical combination
17:37 An example with the relation « is around of » to describe a flower: (1)
18:43 An example with the relation « is around of » to describe a flower: (2)
18:59 Connectivity-Direction-Metric Formalism (5)
19:42 Connectivity-Direction-Metric Formalism (6)
20:11 Experimentations (1)
20:43 Experimentations (2)
21:08 Conclusion

Lecture rating

People found this lecture:
Worth seeing
because it is:
 Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment: