An Energy-Efficient Matching Accelerator Using Matching Prediction for Mobile Object Recognition
| Autor: | Byeong-Gyu Nam, Hwanyong Lee, Seongrim Choi |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Scheme (programming language)
Matching (statistics) business.industry Computer science 020208 electrical & electronic engineering Bandwidth (signal processing) Process (computing) Cognitive neuroscience of visual object recognition Pattern recognition 02 engineering and technology Object (computer science) Electronic Optical and Magnetic Materials Reduction (complexity) 0202 electrical engineering electronic engineering information engineering Computer vision Artificial intelligence Electrical and Electronic Engineering business computer Auxiliary memory computer.programming_language |
| Zdroj: | JSTS:Journal of Semiconductor Technology and Science. 16:251-254 |
| ISSN: | 1598-1657 |
| Popis: | An energy-efficient object matching accelerator is proposed for mobile object recognition based on matching prediction scheme. Conventionally, vocabulary tree has been used to save the external memory bandwidth in object matching process but involved massive internal memory transactions to examine each object in a database. In this paper, a novel object matching accelerator is proposed based on matching predictions to reduce unnecessary internal memory transactions by mitigating nontarget object examinations, thereby improving the energy-efficiency. Experimental results show a 26% reduction in power-delay product compared to the prior art. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|