Road Damage Detection Based on Unsupervised Disparity Map Segmentation
This work addresses road damage detection for infrastructure maintenance, presenting an incremental improvement with a parameter-free method.
The paper tackles road damage detection by developing an unsupervised disparity map segmentation algorithm that transforms disparity maps via energy minimization and uses Otsu's thresholding, achieving a pixel-level accuracy of approximately 97.56%.
This paper presents a novel road damage detection algorithm based on unsupervised disparity map segmentation. Firstly, a disparity map is transformed by minimizing an energy function with respect to stereo rig roll angle and road disparity projection model. Instead of solving this energy minimization problem using non-linear optimization techniques, we directly find its numerical solution. The transformed disparity map is then segmented using Otus's thresholding method, and the damaged road areas can be extracted. The proposed algorithm requires no parameters when detecting road damage. The experimental results illustrate that our proposed algorithm performs both accurately and efficiently. The pixel-level road damage detection accuracy is approximately 97.56%.