Research Article
A UAV Visual Relocalization Method Using Semantic Object Features Based on Internet of Things
Algorithm 1
Image similarity calculation.
(i) | Inputs: Semantic topological graphs of and to be matched, the path length of random walk: , the times of each node used as a starting node: count | (ii) | Output: Image similarity: | (1) | Construct the association graph: | (2) | for in do | (3) | for in do | (4) | if and have the same semantic labels, then | (5) | add to | (6) | end if | (7) | end for | (8) | end for | (9) | Initialize the weight matrix: , set the weights of conflicting matching pairs to zero, the weights of non-conflicting matched pairs are , | (10) | Initialize the probability transition matrix: | (11) | for in nodes of do | (12) | Random Walk (, , , count) | (13) | | (14) | end for | (15) | Get the best matching pairs | (16) | |
|