en
0.25
0.5
0.75
1.25
1.5
1.75
2
Latent Hough Transform for Object Detection
Published on Nov 12, 20125913 Views
Hough transform based methods for object detection work by allowing image features to vote for the location of the object. While this representation allows for parts observed in different training ins
Related categories
Chapter list
Latent Hough Transform for Object Detection00:00
Detection with the Hough Transform00:09
Accumulation of inconsistent votes00:11
How to enforce consistency of votes?00:53
Voting for viewpoint? (1)01:01
Voting for viewpoint? (2)01:07
Voting for type?01:20
Previous Works01:34
Can we learn the attributes to be consistent over?02:09
Hough Transform (1)02:14
Hough Transform (2)02:20
Latent Hough Transform02:32
Latent Matrix (1)02:36
Latent Matrix (2)02:47
Latent Matrix (3)02:57
Latent Matrix (4)03:08
Latent Matrix (5)03:18
Latent Matrix (6)03:23
The number of votes (1)03:37
The number of votes (2)03:40
The number of votes 93003:56
Interesting Special Cases of our Model04:08
Special Cases of W (1)04:15
Special Cases of W (2)04:25
Special Cases of W (3)04:38
Special Cases of W (4)04:52
Discriminative Learning of W05:08
Experiments05:35
Learning or Annotation?06:06
Learning or Clustering? (1)06:48
Learning or Clustering? (2)06:55
Learning or Clustering? (3)07:20
Learning or Clustering? (4)07:32
Disjoint or Shared Groups? (1)07:43
Disjoint or Shared Groups? (2)08:22
Overall Results08:30
Contributions08:55
Visualization of Groups09:09
Ignored Examples (1)09:12
Ignored Examples (2)09:40
Ignored Examples (3)09:55
Thank You!10:18