The PICture Unsupervised Classification with Human Analysis (PICUCHA) refers to a hybrid human-artificial intelligence methodology for pavement distresses assessment. It combines the human flexibility to recognize patterns and features in images with the neural network ability to expand such recognition to large volumes of images. In this study, the PICUCHA performance was tested with images taken with area-scan cameras and flash light illumination over a pavement with dark textures. These images are particularly challenging for the analysis because of the lens distortion and non-homogeneous illumination, generating artificial joints that happened at random positions inside the image cells. The chosen images were previously analyzed by other software without success because of the dark coluor. The PICUCHA algorithms could analyze the images with no noticeable problem and without any image pre-processing, such as contrast or brightness adjustments. Because of the special procedure used by the pavement engineer for the key patterns description, the distresses detection accuracy of the PICUCHA for the particular image set could reach 100%.
On 2008 was published (Salini et al, 2008) the guidelines to use an artificial intelligence based approach to create high quality models to asphalt pavements, surpassing most of the well know problems and limitations of the current empiric and empiricmechanistic approaches. This paper describe part of this new approach called INTELLIPave, with focus in show how to totally unknown variables are considered in the model in an implicit way, regardless its nature or complexity, and how the failure criteria is used aside, and no longer inside, of the model.
Modelling the service life for asphalt pavements is widely made with base on empirical methods, developed half-century ago, with poor results. The new reality of the XXI century, with high construction costs, environmental restrictions and growing volumes of vehicles in the highways, enforce the shift to a new level of quality and accuracy to predict the service life of the pavements. This paper presents some insights either theoretical or experimental into a making from the ground, of an approach to predict and model the asphalt pavement behaviour using soft computing tools and, at the same time, create a way to accumulate the knowledge in this engineering field. The knowledge about the asphalt pavement life cycle is organized in a hierarchical way in order to be reused in a formal way, leading to an evolutionary process of adaptation and construction (Neves et al. 2007).
An accurate and regular survey of the road surface distresses is a key factor for pavement rehabilitation design and management, allowing public managers to maximize the value of the continuously limited budgets for road improvements and maintenance. Manual pavement distress surveys are labor-intensive, expensive and unsafe for highly-trafficked highways. Over the years, automated surveys using various hardware devices have been developed and improved for pavement field data collection to solve the problems associated with manual surveys. However, the reliable distress detection software and the data analysis remain challenging. This study focused on the analysis of a newly-developed pavement distress classification algorithm, called the PICture Unsupervised Classification with Human Analysis (PICUCHA) method, particularly the impact of image resolutions on its classification accuracy. The results show that a non-linear relationship exists between the classification accuracy and the image resolution, suggesting that images with a resolution around 1.24 mm/pixel may provide the optimal classification accuracy when using the PICUCHA method. The findings of this study can help to improve more effective uses of the specialize software for pavement distress classification, to support decision makers to choose cameras according to their budgets and desired survey accuracy, and to evaluate how existing cameras will perform if used with PICUCHA.
The "Santa Catarina Rural" is a Program co-funded by The World Bank for improvements on 1300 km of low volume rural roads on Southern Brazil. The pioneer project under the program was on the municipality of Santa Rosa de Lima, where the greenhouse gas (GHG) emissions resulting from the road improvement activities as well as the regular traffic were assessed on an experimental basis using the CarbonROAD software application. Here, we show details of the CarbonROAD software application and the construction emissions assessment procedure as well as the mitigating effect of the plants used for compensation. It was found that most of the emissions come from the road improvement work. This includes earthworks, fuel for motor graders, bulldozers and other machines, and materials and gravel extraction, industrialization and transportation, etc. Only a smaller portion comprises regular road traffic. The accumulated emission balance shows that the carbon absorption is larger than construction emissions after just 15 months. The potential for price appraisal of the generated carbon credits is explored.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.