Seokju Lee
Seokju Lee
@ankurhanda Ok Thank you so much!
@ankurhanda Thanks for your inspiration, but still I'm not sure how to implement the function of "input: disparity, output: R|T". I think imagewarpingSE3 recieves two images and outputs SE3 which...
I also have the same question here. Did you find how to handle the world coordinate?
+ I wonder what are the inputs to generate each D^a_b (**computed_depth**) and D'_b (**projected_depth**). My thought is as below. Input of D^a_b: D_a, D_b, pose Input of D'_b: D_b,...
@daixiaogang We set 'R=20' to equal to the average value of approximately half of the lane thickness (paper section 5.4).
@daixiaogang What is the FP? With the grid size of 8, the center position you defined is right.
Hi, the dataset and model are preserved by Samsung Electronics. Please contact Tae-Hee Lee ([email protected]), Hyun Seok Hong ([email protected]), and Seung-Hoon Han ([email protected]). Thanks!
@weitaoatvison Hi, the algorithm speed, 20fps, includes both forward-pass and post-processing time. Specifically, the single forward pass takes about 30ms (on single Titan X) and the post-processing takes about 20ms...
@weitaoatvison Here are some helpful libraries and functions, which are fast. Please refer them. Lane-seed-sampling: https://github.com/MonsieurV/py-findpeaks IPM: https://docs.opencv.org/2.4/modules/core/doc/operations_on_arrays.html#perspectivetransform
@weitaoatvison It's for the lane clustering (visualization). This enables to subsample peak points from the probability map. Please refer our paper (related section 4.4)