LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning

. 2020 Apr 14;20(8):2212. doi: 10.3390/s20082212

Algorithm 1 Recognition Algorithm.

1:
initial $S \leftarrow Ø;$ //The set of single frames.
2:
initial $C \leftarrow w i r e;$ //The category of S.
3:
initial $M \leftarrow [M_{0}, M_{1}, M_{2}];$ //The minimum number of frames combined into a group.
4:
repeat
5:
$F = R e a d S i n g l e F r a m e ();$ //Read single frame data.
6:
$L = S i n g l e F r a m e C l a s s i f i c a t i o n (F);$ //Single frame classification model classifies the single frame.
7:
$F S, S, C = C o m b i n e S i n g l e F r a m e s (F, L, S, C, M);$ //Combine single frames into a group. The method is shown in Algorithm 2.
8:
if $F S \neq n u l l$ then
9:
$R = M u l t i F r a m e s S e g m e n t a t i o n (F S);$ //Segmentation model recognizes the components in the combined single frames.
10:
end if
11:
until without single frame data.