V-RBNN Based Small Drone Detection in Augmented Datasets for 3D LADAR System

. 2018 Nov 8;18(11):3825. doi: 10.3390/s18113825

Algorithm 1: The V-RBNN-based target detection.

1: // Background subtraction

2: $P o i n t X Y Z : : c l o u d_B a s e = B a c k g r o u n d_p o i n t X Y Z$

3: $P o i n t X Y Z : : c l o u d_C u r = C u r r e n t_p o i n t X Y Z$

4: $c l o u d_O c t r e e \leftarrow O c t r e e C h a n g e D e t e c t o r (P o i n t X Y Z)$

5: // V-RBNN

6: ${c a l R a n g e}_{t} \leftarrow T a r g e t R a n g e C a l (h i s t o r y_q u e_c e n B B_x y z [i])$

7: $λ = 7.0, b i a s = 0.01$ (//tunable constant parameters)

8: $r a d i u s = λ / (h_{s c a n} \times v_{s c a n}) \times tan (F O V \times (π / 180)) \times {c a l R a n g e}_{t} + b i a s$

9: $c l o u d_c l u s t e r \leftarrow S e t R B N N R a d i u s (c l o u d_O c t r e e, r a d i u s)$

10: // Outlier and occlusion removal

11: $O u t l i e r_r e m o v e \leftarrow s e t M i n N e i g h b o r s I n R a d i u s (c l o u d_c l u s t e r, n M i n)$

12: if ( $d i a g B B > 1$ )

13: $O c c l u s i o n_r e m o v e = O u t l i e r_r e m o v e - m a x D i a g B B$

14: else

15: $c l o u d_c l u s t e r_t a r g e t = O u t l i e r_r e m o v e$

16: // Sequential position estimation

17: if ( ${c a l R a n g e}_{t} < 1 | | ({c a l R a n g e}_{t} - {c a l R a n g e}_{t - 1}) > 1000$ )

18: $F i n a l_t a r g e t_B B \leftarrow e s t i m a t e B B (h i s t o r y_q u e_c e n B B_x y z [i])$

19: else

20: $F i n a l_t a r g e t_B B \leftarrow d r a w B B (c l o u d_c l u s t e r_t a r g e t)$