[HN Gopher] Intuitively Understanding Harris Corner Detector
___________________________________________________________________
Intuitively Understanding Harris Corner Detector
Author : anilz
Score : 140 points
Date : 2023-09-11 12:35 UTC (9 hours ago)
(HTM) web link (comsci.blog)
(TXT) w3m dump (comsci.blog)
| ur-whale wrote:
| PSA : The Harris Corner detector, while interesting to understand
| if you like linear algebra, is not exactly what you'd call state
| of the art in the feature detection layer of computer vision.
| DougMerritt wrote:
| Yes? What _is_ the state of the art?
| jhoydich wrote:
| I believe the SIFT algorithm is most commonly used. Harris
| struggles when features change in scale between images,
| whereas SIFT does not. Harris can be outfitted with a
| Laplacian pyramid to overcome the scale issue though.
| mathisfun123 wrote:
| which is funny since SIFT is basically just as ancient.
| glitchc wrote:
| I had to write one for an interview many moons ago. It's a fun
| little exercise.
| arketyp wrote:
| I remember the eigenvector analysis of the original paper [1]
| wasn't terribly inaccessible. I think an alternative title for
| this blog post could be "Intuitively Understanding the Harris
| Corner Detector Optimizations".
|
| [1]
| https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&d...
___________________________________________________________________
(page generated 2023-09-11 22:00 UTC)