Mohamed S Kaseko

A NEURAL NETWORK-BASED METHODOLOGY FOR PAVEMENT CRACK DETECTION AND CLASSIFICATION

Abstract This paper presents a methodology for automating the processingof highway pavement video images using an integration of artificial neural network models with conventional image-processing techniques. The methodology developed is able to classify pavement surface cracking by the type, severity, and extent of cracks detected in video images. The approach is divided into five major steps: (1) image segmentation, which involves reduction of a raw gray-scale pavement image into a binary image, (2) feature extraction, (3) decomposition of the image into tiles and identification of tiles with cracking, (4) integration of the results from step (3) and classification of the type of cracking in each image, and (5) computation of the severities and extents of cracking detected in each image. In this methodology, artificial neural network models are used in automatic thresholding of the images in stage (1) and in the classification stages (3) and (4). The results obtained in each stage of the process are presented and discussed in this paper. The research results demonstrate the feasibility of this new approach for the detection, classification, and quantification of highway pavement surface cracking.

Modeling and Evaluating Safety Impacts of Access Management Features in the Las Vegas, Nevada, Valley

This paper presents results of a study that developed statistical models that relate access management (AM) features to traffic safety in midblock sections of street segments. The objective of the study was to evaluate and quantify the impact of the AM features on traffic crashes in the midblock sections. Models were calibrated for two main types of median treatments for street segments: raised medians (RM) and two-way left-turn lanes (TWLTL). Other AM features considered were signal spacing and the densities of driveways, median openings, and unsignalized crossroads. Separate models were developed to determine the impact on total crash rates and types and severity of crashes. The study results confirmed the intuitive expectation that these AM features do have a significant impact on safety. They show that the crash rate of segments with RM was lower by 23% as compared with segments with TWLTL. The results also showed that higher densities of driveways, unsignalized crossroads, and median openings resulted in higher crash rates and severity. For example, for segments with RM, each additional median opening per mile resulted in a 4.7% increase in the total crash rate. These results are compared with the results of previous similar studies. It is anticipated that the results of this study will assist local jurisdictions in the Las Vegas, Nevada, Valley in developing new AM policies and programs.

System Selection, Benefits, and Financial Feasibility of Implementing an Advanced Public Transportation System

A procedure for selecting a suitable backbone radio communications system necessary for the implementation of advanced public transportation system technologies is presented. This procedure was used by the Regional Transportation Commission of Clark County, Nevada, in preparation of a radio communications master plan for the Las Vegas Citizens Area Transit system. The procedure recognizes the importance of taking into account not only the relative costs of the alternative candidate systems, but also other important factors such as the degree of system control by the transit agency, confidence in system development and technical practicality, potential for future expansion, and technical simplicity. Several alternative technologies for radio communications are reviewed and evaluated. Selection of the recommended system is based on the procedure that assigns relative weights to the important factors and gives each candidate system a score for each factor. The system with the highest total score is recommended for implementation. Potential system benefits are discussed and financial feasibility of the recommended system is evaluated by computing the annual rate of return on invested capital. Analysis shows that the system can pay for itself and also produce significant net savings in operation and capital costs. Although the analysis considered only potential savings in fleet size, an annual rate of return of over 21 percent on the invested capital has been shown to be achievable. Such savings can enable transit agencies to provide the same level of service at significantly reduced cost or expand the service without increasing operating costs.