Deep Learning for Semantic Segmentation on Minimal Hardware

TL;DR

This paper presents a semantic segmentation approach that enables real-time processing of full VGA images on minimal mobile hardware, suitable for small robots, without domain-specific training or hardware constraints.

Contribution

It introduces a novel semantic segmentation method that is efficient, adaptable to various image sizes, and capable of running on low-power devices, unlike previous domain-specific solutions.

Findings

Real-time processing of VGA images on low-power hardware

No retraining needed for different image sizes

Applicable outside of specific domains like RoboCup

Abstract

Deep learning has revolutionised many fields, but it is still challenging to transfer its success to small mobile robots with minimal hardware. Specifically, some work has been done to this effect in the RoboCup humanoid football domain, but results that are performant and efficient and still generally applicable outside of this domain are lacking. We propose an approach conceptually different from those taken previously. It is based on semantic segmentation and does achieve these desired properties. In detail, it is being able to process full VGA images in real-time on a low-power mobile processor. It can further handle multiple image dimensions without retraining, it does not require specific domain knowledge for achieving a high frame rate and it is applicable on a minimal mobile hardware.