Real-Time Dense Stereo Embedded in A UAV for Road Inspection
This work addresses road condition assessment for traffic safety, but it is incremental as it builds on existing stereo vision and filtering techniques.
The paper tackles road surface inspection by developing a real-time stereo vision system embedded in a UAV, which transforms perspective views and filters cost volumes to improve disparity accuracy and computational efficiency, enabling damaged areas to be easily distinguished in experiments.
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.