GPU-Enabled Pavement Distress Image Classification in Real Time

Pavement assessment is a crucial process for the maintenance of municipal roads. However, the detection of pavement distress is usually performed either manually or offline, which is not only time-consuming and subjective, but also results in an enormous amount of data being stored persistently before processing. State-of-the-art pavement image-processing methods executed on a CPU are not able to analyze pavement images in real time. To compensate this limitation of the methods, an automated approach for pavement distress detection is proposed. In particular, graphical processing unit (GPU) implementations of a noise removal, a background correction, and a pavement distress-detection method were developed. The median filter and the top-hat transform are used to remove noise and shadows in the images. The wavelet transform is applied in order to calculate a descriptor value for classification purposes. The approach was tested on 1,549 images. The results show that real-time preprocessing and analysis are possible.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01634076
  • Record Type: Publication
  • Files: TRIS, ASCE
  • Created Date: May 1 2017 9:45AM