Real-time human detection application

Design and implementation of a real-time human detection application using Zynq UltraScale+ MPSoC

The ability to perform real-time, low-latency and deterministic processing at the edge is increasingly important for a range of applications, from autonomous vehicles to vision guided robotics and intelligent surveillance systems.

Processing at the edge is required for four main reasons availability, latency, security and determinism; furthermore the connection to the cloud service cannot be always guaranteed and processing time and decision making for sensitive data in the cloud will also increase the latency and decrease the determinism of the response making it unsuitable for real time safety critical decisions.

Otherwise, “Edge processing” addresses the availability, latency and determinism challenges. However, it can present additional challenges as, normally, the computational power available at the edge is much lower than is available in the cloud.

The goal will address the low power and high performance challenges of an edge processing system implementing a real time human detection application using a Zynq UltraScale+ MPSoC device to explore the potentials of those devices.

Required knowledge

• FPGA development (VHDL or Verilog)
• C/C++ or Python
  Linux knowled and AI background is considered a plus

Target domain

• Compute Science MSc, Electronics MSc, Mechatronics Msc

Notes

• The thesis shall be carried out at ROJ company offices
• Due to its cross-functional domain, the thesis could potentially be carried out by two candidates with complementary competences
• A typical duration of 6 months is foreseen for this thesis