DocumentCode :
2637876
Title :
Efficient feature tracking with application to camera motion estimation
Author :
Fiore, Paul D. ; Kottke, Dane ; Krawiec, Wojciech ; Gampagna, D.
Author_Institution :
Sanders Associates Inc., Nashua, NH, USA
Volume :
2
fYear :
1998
fDate :
1-4 Nov. 1998
Firstpage :
949
Abstract :
This paper describes a high level design for camera motion estimation and details an efficient implementation of a feature point detection technique known as the "Kanade-Lucas-Tomasi" (KLT) algorithm. After making several novel approximations, an efficient, high-performance field-programmable gate-array (FPGA) design that does not sacrifice detection performance is presented. The high level design couples the FPGA with a conventional digital signal processor to enable full video rate throughput. Results of the FPGA-based feature point detection as well as its application to camera motion estimation are shown.
Keywords :
computer vision; digital signal processing chips; feature extraction; field programmable gate arrays; motion estimation; tracking; video signal processing; FPGA design; KLT algorithm; Kanade-Lucas-Tomasi algorithm; camera motion estimation; digital signal processor; efficient feature tracking; feature point detection technique; field-programmable gate-array; full video rate throughput; high level design; Algorithm design and analysis; Cameras; Computer vision; Field programmable gate arrays; Karhunen-Loeve transforms; Motion detection; Motion estimation; Signal design; Signal processing algorithms; Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signals, Systems & Computers, 1998. Conference Record of the Thirty-Second Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
ISSN :
1058-6393
Print_ISBN :
0-7803-5148-7
Type :
conf
DOI :
10.1109/ACSSC.1998.751403
Filename :
751403
Link To Document :
بازگشت