An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory
- 1 January 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
An 81.6 GOPS object recognition processor is developed by using NoC and visual image processing (VIP) memory. SIFT (scale invariant feature transform) object recognition requires huge computing power and data transactions among tasks. The chip integrates 10 SIMD PEs for data/task level parallelism while the NoC facilitates inter-PE communications. The VIP memory searches local maximum pixel inside a 3times3 window in a single cycle providing 65.6 GOPS. The proposed processor achieves 15.9 fps SIFT feature extraction at 200 MHz.Keywords
This publication has 8 references indexed in Scilit:
- A case study of mobile robot's energy consumption and conservation techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Data Association Using Visual Object Recognition for EKF-SLAM in Home EnvironmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Augmenting SLAM with Object Detection in a Service Robot FrameworkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Low-power network-on-chip for high-performance SoC designIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Visconti: multi-VLIW image recognition processor based on configurable processor [obstacle detection applications]Published by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- A 51.2 GOPS scalable video recognition processor for intelligent cruise control based on a linear array of 128 4-way VLIW processing elementsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A 100-GOPS programmable processor for vehicle vision systemsIEEE Design & Test of Computers, 2003