Research Article

Pedestrian Motion Learning Based Indoor WLAN Localization via Spatial Clustering

Algorithm 1

Pseudocode of pedestrian motion learning.
Input: Starting and ending pixels, and
Output: Motion path from to
(1) Set starting pixel as ; // Starting pixel
(2) Set ending pixel as ; // Ending pixel
(3) A certain proportion of accessible pixels are converted into inaccessible ones;
(4) Add into Possible Path Location (PPL) set;
(5) Initialize Existing Path Location (EPL) as an empty set;
(6) ; // Current pixel
(7) while   is not equal to   do
(8) for (each adjacent pixel around , ) // Pixel traversal
(9) if   is an inaccessible pixel then
(10) Continue;
(11) else if belongs to EPL set then
(12) Continue;
(13) else if is neither in EPL set nor in PPL set then
(14) Add into PPL set;
(15) Set as the father pixel of ;
(16) Calculate the Euclidean distance from to , ;
(17) Calculate the Manhattan distance from to , ;
(18) Set ;
(19) else if belongs to PPL set then
(20) Calculate the distance from to , ;
(21) ;
(22) If   then
(23) ;
(24) ;
(25) Set as the father pixel of ;
(26) end if
(27) end if
(28) end for
(29) Add into EPL set;
(30) Remove from PPL set;
(31) Update with the pixel with the smallest value in PPL set;
(32) end while
(33) ; // Initialize traversal pixel
(34) Add into set Trace as the 1st pixel;
(35) ;
(36) while is not equal to
(37) Add the father pixel of into Trace as -th pixel;
(38) ;
(39) Father pixel of ;
(40) end while
(41) Consecutively connect the pixels in Trace as the constructed motion path.