ELECTRICA

IMPLEMENTATION OF A PATH DETECTION ALGORITHM FOR MOVING IMAGES ON THE CNN UNIVERSAL MACHINE

1.

Istanbul University, Research and Application Center for Computer Sciences, 34452, Beyazit, Istanbul, Turkey

2.

Istanbul University, Engineering Faculty, Computer Eng. Dept., 34320, Avcilar, Istanbul, Turkey

ELECTRICA 2010; 10: 1235-1241
Read: 770 Downloads: 565 Published: 22 December 2019

CNN Universal Machines that contain two different processors working interactively with each other, have an important impact for image processing applications with their advanced computing features. These processors are named as ACE16k processor which is the hardware implementation of cellular neural networks and Digital Signal Processor (DSP). Bio-inspired (Bi-i) Cellular Vision System is also a CNN Universal Machine and its standalone architecture is built on CNN-type (ACE16k) and DSP-type microprocessors. In this study, certain objects in moving images are detected and their features are extracted. By using these features, an algorithm that finds out the path of moving objects is implemented on the Bi-i Cellular Vision System. Finally, the output images obtained as a result of this implementation are evaluated.

Files
EISSN 2619-9831