Scalable Recognition with a Vocabulary Tree

1
Scalable Recognition with a Vocabulary Tree
David Nistér, Henrik Stewénius
2
Scalable Recognition with a Vocabulary Tree
David Nistér, Henrik Stewénius
3
50 Thousand Images
4
110,000,000Images in5.8 Seconds
5
(No Transcript)
6
(No Transcript)
7
(No Transcript)
8
Take-Home Message
If we can get repeatable, discriminative
features, then recognition can scale to very
large databases using the vocabulary tree and
indexing approach described in Nistér
Stewénius CVPR 2006.
9
Vocabulary Tree
10
Vocabulary Tree
11
Vocabulary Tree
12
(No Transcript)
13
Adding, Querying and Removing Images at full speed
Query
Add
Remove
14
Training and Addition are Separate
Common Approach
Our approach
15
(No Transcript)
16
(No Transcript)
17
(No Transcript)
18
(No Transcript)
19
(No Transcript)
20
(No Transcript)
21
(No Transcript)
22
(No Transcript)
23
(No Transcript)
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
(No Transcript)
31
(No Transcript)
32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)
37
(No Transcript)
38
Performance
39
(No Transcript)
40
Size Matters
41
(No Transcript)
42
(No Transcript)
43
Geometric Verification
44
Robust to Clutter and Occlusion

• Local Regions
• Like Web-search