An Improved Stereo Matching Algorithm for Vehicle Speed Measurement System Based on Spatial and Temporal Image Fusion

. 2021 Jul 7;23(7):866. doi: 10.3390/e23070866

Algorithm 1:Optimum speed measurement point selection based on STIF.

Input:
$S_{c u r_s p a}$ = ${\{(p_{c u r_l_i}, p_{c u r_r_i})\}}_{i = 1}^{M_{1}}$

$S_{p r e_s p a}$ = ${\{(p_{p r e_l_j}, p_{p r e_r_j})\}}_{j = 1}^{M_{2}}$

$S_{t e m p}$ = ${\{(p_{l_c u r_k}, p_{l_p r e_k})\}}_{k = 1}^{T}$

$O_{c u r_l}$ $(x_{c u r_l}, y_{c u r_l})$
Output:
$(p_{c u r_l_m_{o p t}}, p_{c u r_r_m_{o p t}})$
1:
function $O p t i m u m$ $s p e e d$ $m e a s u r e m e n t$ $p o i n t$ $s e l e c t i o n$
2:
for $k = 1$ to T do
3:
take $(p_{l_c u r_k}, p_{l_p r e_k})$ ∈ $S_{t e m p}$
4:
search $S_{c u r_s p a}$
5:
if $p_{l_c u r_k}$ = $p_{c u r_l_i}$ then
6:
search $S_{p r e_s p a}$
7:
if $p_{l_p r e_k}$ = $p_{p r e_l_j}$ then
8:
$S_{s p a_t e m p}$ ⟸ $(p_{c u r_l_i}, p_{c u r_r_i})$
9:
end if
10:
end if
11:
end for
12:
for $m = 1$ to size of $S_{s p a_t e m p}$ do
13:
calculate $d_{m}$ = $\sqrt{{(x_{c u r_l_m} - x_{c u r_l})}^{2} + {(y_{c u r_l_m} - y_{c u r_l})}^{2}}$
14:
end for
15:
select $d_{m_{o p t}}$ = ${\{d_{m}\}}_{m i n}$
16:
return $(p_{c u r_l_m_{o p t}}, p_{c u r_r_m_{o p t}})$ $w i t h$ $d_{m_{o p t}}$
17:
end function