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

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.

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

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.

Biologically Inspired Components in Embedded Vision Systems

Biological vision components like visual attention (VA) algorithms aim to mimic the mechanism of the human vision system. Often VA algorithms are complex and require high computational and memory requirements to be realized. In biologically-inspired vision and embedded systems, the computational capacity and memory resources are of a primary concern. This paper presents a discussion for implementing VA algorithms in embedded vision systems in a resource constrained environment. The authors survey various types of VA algorithms and identify potential techniques which can be implemented in embedded vision systems. Then, they propose a low complexity and low memory VA model based on a well-established mainstream VA model. The proposed model addresses critical factors in terms of algorithm complexity, memory requirements, computational speed, and salience prediction performance to ensure the reliability of the VA in a resource constrained environment. Finally a custom softcore microprocessor-based hardware implementation on a Field-Programmable Gate Array (FPGA) is used to verify the implementation feasibility of the presented model.