Re: classifier
Posted: Fri Jan 06, 2017 10:58 am
IMO you'd better start isolating "easier" parts such as vegetation or ground and then classify the tower from the remaining point cloud.
Open-source point cloud editing software
https://cloudcompare.net/forum/
how can i send you my test date?daniel wrote:I don't think the terrain is the problem (I have seen very complex scenes properly segmented). Generally the issue is more with the data. You need dense LIDAR point clouds such as TLS scans. I'm not sure an airborne scan is dense enough.
Don't hesitate to send me a cloud sample if you want me to try (cloudcompare [at] danielgm.net).
http://pan.baidu.com/s/1eSuWWPcBonnie wrote:how can i send you my test date?daniel wrote:I don't think the terrain is the problem (I have seen very complex scenes properly segmented). Generally the issue is more with the data. You need dense LIDAR point clouds such as TLS scans. I'm not sure an airborne scan is dense enough.
Don't hesitate to send me a cloud sample if you want me to try (cloudcompare [at] danielgm.net).
thank youHaowyr wrote:IMO you'd better start isolating "easier" parts such as vegetation or ground and then classify the tower from the remaining point cloud.
what should i do? how can i send youdaniel wrote:Hi Bonnie,
Sadly I couldn't download the file through Baidu (the download process is very slow and it fails after a while).
Hi Haowyr, I am also interested in reading your thesis chapter. Do you have another pdf version that allow us to copy the text into google translate so that non-french speakers can read it too ? Also can you provide us your thesis?Haowyr wrote: ↑Thu Jan 05, 2017 7:51 am https://fr.scribd.com/document/33574590 ... rrDumW81E0
Imo, the easiest way to explain the scale is "how close from the object you look at it and what general shape it has from it". When you have a scale of 5cm, you take a 5cm sphere part of the cloud and check if it looks like a line, a plane or something in 3D.