No abstract

No abstract

No abstract

Worcester Polytechnic I n s t i t u t e , Worcester, Massachusetts University of V i r g i n i a , C h a r l o t t e s v i l l e , V i r g i n i a A b s t r a c t The development of algorithms f o r r e a l -t i m e , automatic systems capable of t r a c k i n g 2-D t a r g e t s i n complex scenes i s discussed. The problems and c o n s t r a i n t s involved i n such an undertaking as w e l l as previous e f f o r t s a r e summarized. I n a d d i t i o n , a mathematical model of scene s p a t i a l and temporal e v o l u t i o n i s developed f o r c e r t a i n c l a s s e s of targ e t s and t a r g e t p e r t u r b a t i o n s . I t i s shown t h a t f o r s m a l l t a r g e t p e r t u r b a t i o n s t h e 2-D t r a c k i n g problem may be approximated as a 1-D time-varying parameter e s t i m a t i o n problem. Algorithms r e s u l t i n g from s e v e r a l e s t i m a t i o n approaches a r e discussed. I n t r o d u c t i o n A s t h e speed, c a p a b i l i t y and economic advant a g e s of modern s i g n a l p r o c e s s i n g devices continue t o i n c r e a s e , t h e r e i s simultaneously an i n c r e a s e i n e f f o r t s aimed a t developing s o p h i s t i c a t e d , r e a ltime automatic systems capable of emulating human ( o r perhaps more g e n e r a l l y , b i o l o g i c a l ) f u n c t i o n s . The r e s e a r c h d e s c r i b e d h e r e i n concerns t h e development and implementation of algorithms f o r a r e a ltime v i d e o t r a c k i n g system, i n p a r t i c u l a r , a dedic a t e d d i s c r e t e -a n a l o g computer capable of processi n g complex, time-varying v i s u a l information i n o rd e r t o e x t r a c t t h e camera mount c o n t r o l o r guidance s i g n a l s necessary t o follow a predetermined v i s u a l t a r g e t . The attempted automation of t h i s c a p a b i l i t y r e s u l t s i n an extremely complicated problem. This i s a t least p a r t i a l l y due t o t h e f a c t t h a t " . The t a r g e t t o be t r a c k e d is l o c a t e d through a viewing system (a CCD camer and mount w i t h a z imuth, e l e v a t i o n and zoom c o n t r o l s i s assumed) i n such a way t h a t automatic f e a t u r e e x t r a c t i o n i s nade p o s s i b l e . Once t h e t a r g e t i s l o c a t e d , it i s d e s i r e d t h a t t h e automatic system provide c o n t r o l s i g n a l s t o t h e camera mount t o keep t h e t a r g e t cent e r e d i n t h e camera f i e l d of view (FOV), i n s p i t e of t a r g e t t r a n s l a t i o n , r o t a t i o n (3-D), magnificat i o n , and p o s s i b l y temporary occlusion ( p a r t i a l o r t o t a l ) . Thus, t h e o v e r a l l problem i s t o design a "2-D r e g u l a t o r " f o r a c l o s e d loop c o n t r o l system w i t h both 1 -D and 2-D " l i n k s , " * and t h e r e f o r e i t should be expected t h a t both c o n t r o l and image proc e s s i n g theory w i l l be employed i n t h e s o l u t i o n . The m i l i t a r y and i n d u s t r i a l a p p l i c a t i o n s f ...

No abstract