论文信息 - Driver assistance system design and its optimization for FPGA based MPSoC

Driver assistance system design and its optimization for FPGA based MPSoC

This paper discusses the design and optimization of an FPGA based MPSoC dedicated to Multiple Target Tracking (MTT) application. MTT has long been used in various military and civilian applications but its use in automotive safety has been little investigated. The system attains a desired processing speed and uses minimum FPGA resources. We profile the software to identify performance bottlenecks and then gradually tune the hardware and software to meet system constraints. The result is a complete embedded MTT application running on a multiprocessor system that fits in a contemporary medium sized FPGA device.

Yassin Elhillali | Atika Rivenq | Smaïl Niar | Mazen A. R. Saghir | Jehangir Khan

[1] R. E. Kalman,et al. A New Approach to Linear Filtering and Prediction Problems , 2002 .

[2] Dimitri P. Bertsekas,et al. A forward/reverse auction algorithm for asymmetric assignment problems , 1992, Comput. Optim. Appl..

[3] E. Brookner. Tracking and Kalman Filtering Made Easy , 1998 .

[4] Zoran Salcic,et al. FPGA-based adaptive tracking estimation computer , 2001 .

[5] Yassin Elhillali,et al. An MPSoC architecture for the Multiple Target Tracking application in driver assistant system , 2008, 2008 International Conference on Application-Specific Systems, Architectures and Processors.