Optimisation of a Siamese Neural Network for Real-Time Energy Efficient Object Tracking

TL;DR

This paper explores optimizing a Siamese neural network for real-time, energy-efficient object tracking in embedded systems by applying quantization and pruning techniques, achieving significant size reduction with maintained accuracy.

Contribution

It introduces a comprehensive approach to optimize Siamese networks for embedded vision, demonstrating effective quantization and pruning methods that reduce size and energy consumption while preserving tracking performance.

Findings

Quantization reduces network size up to 10 times.

Optimizations enable real-time tracking on embedded systems.

Quantization decreases overfitting during training.

Abstract

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations - from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting.