Ask Your Question

AGAST keypoints size evaulates to 7.0?

asked 2019-02-07 07:21:55 -0500

droog_the_droog gravatar image

I'm doing a project where I'm extracting keypoints using the AGAST algorithm. One curious thing popped out to me - keypoint.size for AGAST keypoints evaluates to 7.0 for every keypoint. Why is this? Is there something I'm missing with the AGAST algorithm?

edit retag flag offensive close merge delete

1 answer

Sort by » oldest newest most voted

answered 2019-02-07 07:45:04 -0500

LBerger gravatar image

updated 2019-02-07 08:07:06 -0500

I think (may be i am wrong) that there is no meaning. If you read source code 7.0 is defined here or hereor it's always 7.0. keypoint constructor needs a sizewhen you give a location. Why 7.0 ? ask to author ( may be read this

edit flag offensive delete link more


Yeah that makes sense. But isn't it the size of a keypoint that is used when computing the overlap error for computing e.g. reliability though? Or have I misunderstood?

droog_the_droog gravatar imagedroog_the_droog ( 2019-02-07 07:59:12 -0500 )edit

you are right so 7 is not here may be read this but here : may be read this : Like SUSAN, also FAST uses a Bresenham’s circle of diameter 3.4 pixels as test mask (Adaptive and Generic Corner Detection Based on the Accelerated Segment Test) 3.4 * 2=6.8 read section 4.1 too

LBerger gravatar imageLBerger ( 2019-02-07 08:06:34 -0500 )edit

Yeah it makes sense that it comes from the radius of the Bresenham's circle that is used in order to evaulate the interest point. So, a correspondence between two AGAST points is going to be very rare, isn't that right? Considering that the keypoint region is so tiny I mean.

Also, I suspect you didn't intend to link to the wikipedia article on the number 7. :D

droog_the_droog gravatar imagedroog_the_droog ( 2019-02-07 08:13:57 -0500 )edit

Question Tools

1 follower


Asked: 2019-02-07 07:21:55 -0500

Seen: 101 times

Last updated: Feb 07 '19