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

by   Dominika Przewlocka, et al.

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.


page 1

page 2

page 3

page 4


Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Deep neural networks virtually dominate the domain of most modern vision...

Towards real-time and energy efficient Siamese tracking – a hardware-software approach

Siamese trackers have been among the state-of-the-art solutions in each ...

Optimisation of the PointPillars network for 3D object detection in point clouds

In this paper we present our research on the optimisation of a deep neur...

SiamSNN: Spike-based Siamese Network for Energy-Efficient and Real-time Object Tracking

Although deep neural networks (DNNs) have achieved fantastic success in ...

Depth-Adaptive Computational Policies for Efficient Visual Tracking

Current convolutional neural networks algorithms for video object tracki...

The Impact of Frame-Dropping on Performance and Energy Consumption for Multi-Object Tracking

The safety of automated vehicles (AVs) relies on the representation of t...

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Siamese networks have drawn great attention in visual tracking because o...

Please sign up or login with your details

Forgot password? Click here to reset