DocumentCode :
3228516
Title :
A real-time image recognition system for tiny autonomous mobile robots
Author :
Mahlknecht, Stefan ; Oberhammer, Roland ; Novak, Gregor
Author_Institution :
Inst. of Comput. Technol., Vienna Univ. of Technol., Austria
fYear :
2004
fDate :
25-28 May 2004
Firstpage :
324
Lastpage :
330
Abstract :
Intelligent sensors for mobile robots play an important role in many technical applications. In this paper a real-time image recognition system for a tiny soccer-playing robot is presented, capable of detecting objects in real-time at a frame rate of up to 60 frames/s. The image recognition module has very low power consumption of less than 250 mW and fits into a package of only 35 × 35 mm including a CMOS camera and a low power, high performance signal processor. We propose an object recognition algorithm that is optimized for deeply embedded systems used in energy and performance constrained devices. The algorithm is based on a combination of edge and color detection and uses a fixed model for each object to be recognized. Results of the ball recognition application show that its relative polar coordinates are found within 11 ms.
Keywords :
CMOS image sensors; computer games; edge detection; embedded systems; intelligent sensors; mobile robots; object detection; CMOS camera; autonomous mobile robot; color detection; edge detection; embedded system; intelligent sensor; object detection; real-time image recognition system; signal processor; tiny soccer-playing robot; Energy consumption; Image recognition; Intelligent sensors; Mobile robots; Object detection; Packaging; Real time systems; Robot kinematics; Robot sensing systems; Signal processing algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Real-Time and Embedded Technology and Applications Symposium, 2004. Proceedings. RTAS 2004. 10th IEEE
ISSN :
1545-3421
Print_ISBN :
0-7695-2148-7
Type :
conf
DOI :
10.1109/RTTAS.2004.1317278
Filename :
1317278
Link To Document :
بازگشت