Abstract
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 analyse pavement images in real time. To compensate this limitation of the methods, we propose an automated approach for pavement distress detection. In particular, 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 1549 images. The results show that real-time pre-processing and analysis are possible.
Highlights
In recent years, the condition of municipal roads has deteriorated rapidly, leading to increased fuel consumption, increased emissions and environmental pollution, and even greater number of vehicle damages and traffic accidents [Spielman 2014]
When applying the wavelet transform on pavement images, Zhou et al observed that a homogeneous background is transformed into the approximation subband, while distress is represented in the detail subbands
With the aim of enabling real-time pavement image processing and, reducing the amount of stored data, this paper proposed an approach based on graphics processing units (GPUs)
Summary
The condition of municipal roads has deteriorated rapidly, leading to increased fuel consumption, increased emissions and environmental pollution, and even greater number of vehicle damages and traffic accidents [Spielman 2014]. Since the idea of this work is to roughly assess the condition of the pavement surface, methods capable of detecting all types of distress need to be investigated. We chose a method based on the wavelet transform for pavement distress detection and evaluation as it fulfills the requirements mentioned above. When applying the wavelet transform on pavement images, Zhou et al observed that a homogeneous background is transformed into the approximation subband, while distress is represented in the detail subbands. Considering the latter observation, Zhou et al developed three statistical criteria for distress detection: standard deviation of wavelet coefficients (STD), high-frequency energy percentage (HFEP), and high-amplitude wavelet coefficient percentage (HAWCP).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
