Title :
Vehicle detection using a hardware-implemented neural net
Author :
S. Mantri;B. Bullock;J. Garrett
Author_Institution :
Cincinnati Bell Inf. Syst., OH, USA
Abstract :
The authors describe how they developed a vehicle-detection model based on a radial basis function network and implemented it using the NI1000 recognition accelerator, which can classify up to 32,000 patterns per second-several hundred times faster than the software approach to neural net processing. A detection system using this implementation had a success rate greater than 90%.
Keywords :
"Vehicle detection","Neural networks","Vehicles","Detectors","Radial basis function networks","Information systems","Fluid flow measurement","Moisture","Digital images","Image recognition"
Journal_Title :
IEEE Expert
