Abstract
We present a method for the learning and detection of multiple rigid texture-less 3D
objects intended to operate at frame rate speeds for video input. The method is geared
for fast and scalable learning and detection by combining tractable extraction of edgelet
constellations with library lookup based on rotation- and scale-invariant descriptors. The
approach learns object views in real-time, and is generative - enabling more objects to
be learnt without the need for re-training. During testing, a random sample of edgelet
constellations is tested for the presence of known objects. We perform testing of single
and multi-object detection on a 30 objects dataset showing detections of any of them
within milliseconds from the object’s visibility. The results show the scalability of the
approach and its framerate performance.
objects intended to operate at frame rate speeds for video input. The method is geared
for fast and scalable learning and detection by combining tractable extraction of edgelet
constellations with library lookup based on rotation- and scale-invariant descriptors. The
approach learns object views in real-time, and is generative - enabling more objects to
be learnt without the need for re-training. During testing, a random sample of edgelet
constellations is tested for the presence of known objects. We perform testing of single
and multi-object detection on a 30 objects dataset showing detections of any of them
within milliseconds from the object’s visibility. The results show the scalability of the
approach and its framerate performance.
| Original language | English |
|---|---|
| Title of host publication | British Machine Vision Conference |
| Place of Publication | 2012 |
| Publisher | BMVA |
| Pages | 23.1-23.12 |
| Number of pages | 12 |
| ISBN (Print) | 1-901725-46-4 |
| DOIs | |
| Publication status | Published - 1 Sept 2012 |