how to define coordinate of SURF Points?
3 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
RODIYAN GIBRAN SENTANU
el 10 de Mayo de 2013
Comentada: Sadettin Durmus Talipoglu
el 8 de Nov. de 2018
Hi guys,
I'm now learning about estimating transformation between two images.
I started to learn it from here:
It's really nice actually. I can get this picture, and also I can define the translation, rotation, and its scale.
![](https://www.mathworks.com/matlabcentral/images/broken_image.png)
My question is, is it possible to define the translation of each point?
or at least, can I get the xy-coordinate of each point?
I've tried to read the explanation of detectSURFFeatures from here, http://www.mathworks.co.jp/jp/help/vision/ref/detectsurffeatures.html
Unfortunately, I still don't understand how to define its coordinate.
Can someone teach me about this?
Thank you, Gibran
0 comentarios
Respuestas (1)
Anand
el 10 de Mayo de 2013
The SURFPoints object contains a data member called Location, which contains the co-ordinate of the point.
For example, in the original image, the first matched feature is located at
>> matchedOriginal(1).Location
ans =
139.7482 95.9542
This is matched to the feature in the distorted image located at
>> matchedDistorted(1).Location
ans =
119.7571 101.1530
I don't understand your question about translation. The distorted image was obtained by rotating and scaling the original image, so there is no translation involved.
Hope this helps.
3 comentarios
Afzal wasiullah
el 29 de Oct. de 2017
Hi,can i know how to define 119.7571 101.1530 as x-coordinate and y-coordinate
Sadettin Durmus Talipoglu
el 8 de Nov. de 2018
Hi Anand, I have been struggling the same problem. How to define outputs (interest point) of SURF and the other descripters Location ? I am trying to get interest points using canny edge filtered image for input of extractFeatures function. But I can't get location of canny filtered image like detectSURFFeatures output. I hope you can understand my question. Thanks in advance.
Ver también
Categorías
Más información sobre Computer Vision with Simulink en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!