DocumentCode :
3017837
Title :
Two camera system for robot applications; navigation
Author :
Lidholm, Jorgen ; Ekstrand, Fredrik ; Asplund, Lars
Author_Institution :
Sch. of Innovation, Malardalen Univ., Vasteras
fYear :
2008
fDate :
15-18 Sept. 2008
Firstpage :
345
Lastpage :
352
Abstract :
Current approaches to feature detection and matching in images strive to increase the repeatability of the detector and minimize the degree of outliers in the matching. In this paper we present a new approach; we suggest that a lower performance feature detector can produce a result more than adequate for robot navigation irrespectively of the amount of outliers. By using an FPGA together with two cameras we can remove the need for descriptors by performing what we call spurious matching and the use of 3D landmarks. The approach bypasses the problem of outliers and reduces the time consuming task of data association, which slows many matching algorithms down.
Keywords :
feature extraction; field programmable gate arrays; image matching; image sensors; path planning; robot vision; sensor fusion; 3D landmarks; FPGA; camera system; data association; feature detection; image matching; robot applications; robot navigation; spurious matching; Application software; Cameras; Computer vision; Detectors; Field programmable gate arrays; Image edge detection; Mobile robots; Navigation; Robot vision systems; Technological innovation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Emerging Technologies and Factory Automation, 2008. ETFA 2008. IEEE International Conference on
Conference_Location :
Hamburg
Print_ISBN :
978-1-4244-1505-2
Electronic_ISBN :
978-1-4244-1506-9
Type :
conf
DOI :
10.1109/ETFA.2008.4638417
Filename :
4638417
Link To Document :
بازگشت