Research Article
Key-Skeleton-Pattern Mining on 3D Skeletons Represented by Lie Group for Action Recognition
Algorithm 3
Informative skeleton sequence (
).Input: key-skeleton-pattern dataset , mining sequence dataset of all actions | Output: The dataset of the most informative skeleton sequences | (1) Obtaining training dataset from | (2) ; | (3) for the dataset of each action class U do | (4) T is the table that includes all symbols in | (5) for each symbol do | (6) if and then | (7) | (8) append to K | (9) MinP-PrefixSpan() | (10) end if | (11) end for | (12) end for | (13) for each element do | (14) for each key-skeleton-pattern do | (15) if m is a subsequence of d.L then | (16) | (17) | (18) for do | (19) | (20) end for | (21) end if | (22) end for | (23) for z=1 to Len(d.L) do | (24) if patternpos[i]==1 then | (25) append d.LA[z] to s | (26) end if | (27) end for | (28) Append s to | (29) end for | (30) return |
|