VincentCheungM
commented
5 years ago Sorry for replying you late. It seems that I use some kind of trick before the clustering process. I just simply re-organize all the spare point cloud into matrix-like dense format, e.g.:
I've got points {p1, p2, p3} from LiDAR, and I transform them from (x, y, z) into Sphere coordinates (\theta, \phi). And then it could be some 2D matrix like data. In this case, some items in the matrix are not occupied, i.e., none of points from point cloud P is transform into this (\theta_hat, \phi_hat), so I use the intensity property to mark these items are not occupied and not interested.
------------------ Original ------------------ From: "wdxpython"notifications@github.com; Date: Tue, Mar 5, 2019 01:24 PM To: "VincentCheungM/Run_based_segmentation"Run_based_segmentation@noreply.github.com; Cc: "Subscribed"subscribed@noreply.github.com; Subject: [VincentCheungM/Run_based_segmentation] voidScanLineRun::velodynecallback (#10)
Hello! Thank you very much for your work! There are a few questions when you read your code. In the void ScanLineRun::velodynecallback function, when calculating the row, how are the numbers 563, 1688 and so on? Why use this calculation method?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
PLester
Hello! Thank you very much for your work! There are a few questions when you read your code. In the void ScanLineRun::velodynecallback function, when calculating the row, how are the numbers 563, 1688 and so on? Why use this calculation method?