Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones

TL;DR

This paper evaluates and optimizes semantic segmentation models for mobile self-navigation in earthquake zones, introducing a new database and analyzing accuracy, performance, and energy efficiency on embedded platforms.

Contribution

It presents a novel dataset for earthquake zone obstacles, benchmarks state-of-the-art models on mobile hardware, and discusses trade-offs for safe autonomous navigation in disaster areas.

Findings

Optimal CNN model identified for low-power mobile platforms.

New annotated database of earthquake-affected regions created.

Models achieve a balance between accuracy, performance, and energy efficiency.

Abstract

The role of unmanned vehicles for searching and localizing the victims in disaster impacted areas such as earthquake-struck zones is getting more important. Self-navigation on an earthquake zone has a unique challenge of detecting irregularly shaped obstacles such as road cracks, debris on the streets, and water puddles. In this paper, we characterize a number of state-of-the-art FCN models on mobile embedded platforms for self-navigation at these sites containing extremely irregular obstacles. We evaluate the models in terms of accuracy, performance, and energy efficiency. We present a few optimizations for our designed vision system. Lastly, we discuss the trade-offs of these models for a couple of mobile platforms that can each perform self-navigation. To enable vehicles to safely navigate earthquake-struck zones, we compiled a new annotated image database of various earthquake impacted regions that is different than traditional road damage databases. We train our database with a number of state-of-the-art semantic segmentation models in order to identify obstacles unique to earthquake-struck zones. Based on the statistics and tradeoffs, an optimal CNN model is selected for the mobile vehicular platforms, which we apply to both low-power and extremely low-power configurations of our design. To our best knowledge, this is the first study that identifies unique challenges and discusses the accuracy, performance, and energy impact of edge-based self-navigation mobile vehicles for earthquake-struck zones. Our proposed database and trained models are publicly available.