TensorFlow enabled deep learning model optimization for enhanced realtime person detection using raspberry pi operating at the edge

In this paper Quantization effects are assessed for a real time Edge based person detection use case that is based on the use of a Raspberry Pi. TensorFlow architectures are presented that enable the use of real-time person detection on the Raspberry Pi. The model quantization is performed, performance of quantized models is analyzed, and worst-case performance is established for a number of deep learning object detection models that are capable of being deployed on the Pi for real-time applications. The study shows that the inference time for a suitably optimized TensorFlow enabled solution architecture is significantly lower than for an unquantized model with only slight cost implications in terms of accuracy when benchmarked against a desktop implementation. An industrial standard floor limit value of greater than 70% is achieved on the quantized models considered with a reduced detection time of less than 3ms. The Deep Neural Network model is trained using the INRIA Person Detection benchmark Dataset.