Zynq FPGA based and Optimized Design of Points of Interest Detection and Tracking in Moving Images for Mobility System

Abstract

In this paper, an FPGA based mobile feature detection and tracking solution is proposed for complex video processing systems. Presented algorithms include feature (corner) detection and robust memory allocation solution to track in real-time corners using the extended Kalman filter. Target implementation environment is a Xilinx Zynq SoC FPGA based. Using the HW/SW partitioning flexibility of Zynq, the ARM dual core processor performance and hardware accelerators generated by Xilinx SDSOC and Vivado HLS tools improve the system ability of processing video accurately with a high frame rate. Several original innovations allow to improve the processing time of the whole system (detection and tracking) by 50% as shown in experimental validation (tracking of visually impaired during their outdoor navigation).

Authors and Affiliations

Abdelkader BEN AMARA, Mohamed ATRI, Edwige PISSALOUX, Richard GRISEL

Keywords

Related Articles

Performances Comparison of IEEE 802.15.6 and IEEE 802.15.4 Optimization and Exploitation in Healthcare and Medical Applications

In this paper, we simulate the energy consumption, throughput and reliability for both, Zigbee IEEE 802.15.4 Mac protocol and BAN IEEE 802.15.6 exploited in medical applications using Guaranteed Time Slot (GTS) and polli...

Improving Security of the Telemedicine System for the Rural People of Bangladesh

Telemedicine is a healthcare system where healthcare professionals have the capability to observe, diagnose, evaluate and treat the patient from a remote location and the patient have the ability to easily access the med...

Development Process Patterns for Distributed Onshore/Offshore Software Projects

The globalisation of the commercial world, and the use of distributed working practices (Offshore/ onshore/ near-shore) has increased dramatically with the improvement of information and communication technologies. Many...

A Comprehensive IoT Attacks Survey based on a Building-blocked Reference Model

Internet of Things (IoT) has not yet reached a distinctive definition. A generic understanding of IoT is that it offers numerous services in many domains, utilizing conventional internet infrastructure by enabling differ...

Toward Evolution Strategies Application in Automatic Polyphonic Music Transcription using Electronic Synthesis

We present in this paper a new approach for polyphonic music transcription using evolution strategies (ES). Automatic music transcription is a complex process that still remains an open challenge. Using an audio signal t...

Download PDF file
  • EP ID EP408215
  • DOI 10.14569/IJACSA.2018.091053
  • Views 104
  • Downloads 0

How To Cite

Abdelkader BEN AMARA, Mohamed ATRI, Edwige PISSALOUX, Richard GRISEL (2018). Zynq FPGA based and Optimized Design of Points of Interest Detection and Tracking in Moving Images for Mobility System. International Journal of Advanced Computer Science & Applications, 9(10), 430-437. https://europub.co.uk/articles/-A-408215