Real-Time Dense Stereo Embedded in A UAV for Road Inspection

TL;DR

This paper introduces a real-time stereo vision system embedded in a UAV for road surface inspection, transforming images to improve disparity accuracy and using GPU acceleration to identify damaged road areas effectively.

Contribution

It presents a novel UAV-based stereo vision system with a perspective transformation and GPU implementation for real-time damaged road detection.

Findings

Effective disparity map transformation enhances damage visibility

GPU implementation achieves real-time processing

Damaged areas are clearly distinguished from the road surface

Abstract

The condition assessment of road surfaces is essential to ensure their serviceability while still providing maximum road traffic safety. This paper presents a robust stereo vision system embedded in an unmanned aerial vehicle (UAV). The perspective view of the target image is first transformed into the reference view, and this not only improves the disparity accuracy, but also reduces the algorithm's computational complexity. The cost volumes generated from stereo matching are then filtered using a bilateral filter. The latter has been proved to be a feasible solution for the functional minimisation problem in a fully connected Markov random field model. Finally, the disparity maps are transformed by minimising an energy function with respect to the roll angle and disparity projection model. This makes the damaged road areas more distinguishable from the road surface. The proposed system is implemented on an NVIDIA Jetson TX2 GPU with CUDA for real-time purposes. It is demonstrated through experiments that the damaged road areas can be easily distinguished from the transformed disparity maps.