
EdgeAI platform targets smart city and camera intelligence applications
Measuring only 100x72mm, the innovative FPGA-based AI Inference engine comes in a pico-ITX form factor and is coupled with multiple connectivity options with support to connect multiple cameras.
Corazon-AI also incorporates a configurable deep learning processor unit in the programmable logic of the Zynq MPSoC chip. The DPU is an AI inference engine dedicated to the Convolution neural network and provides for a scalable multi-dimensional parallel architecture capable of performing major convolutional calculations, batch normalisation through deep pipelined computing engines. They consist of specialised encoders and decoders which squeeze network model size and have a unique instruction scheduler that dynamically adjusts FIFO.
Through the support of key features such as cameras, video recording and connectivity, the Zynq MPSoC provides an intelligent heart for the SBC. With support from the Xilinx Vitis AI Stack, Corazon-AI can be used as a perfect fit for various machine learning and computer-vision based applications such as number plate recognition, traffic management systems and automatic video inspection.
iWave Systems Technologies – www.iwavesystems.com
