HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA)
The pavement surface condition assessment is a critical component for a proper pavement management system as well as for pavement rehabilitation design. A number of devices were developed to automatically record surface distresses in a continuous survey mode, but the software required for automatic...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Czech Technical University, Prague
2017-07-01
|
| Series: | Civil Engineering Journal |
| Subjects: | |
| Online Access: | http://www.civilengineeringjournal.cz/archive/issues/2017/2017_2/2-2017-0013.pdf |
| _version_ | 1797709197841793024 |
|---|---|
| author | Reus Salini Bugao Xu Regis Carvalho |
| author_facet | Reus Salini Bugao Xu Regis Carvalho |
| author_sort | Reus Salini |
| collection | DOAJ |
| description | The pavement surface condition assessment is a critical component for a proper pavement management system as well as for pavement rehabilitation design. A number of devices were developed to automatically record surface distresses in a continuous survey mode, but the software required for automatic distress identification remains a big challenge. In this study, a new method named PICture Unsupervised Classification with Human Analysis (PICUCHA) is proposed to circumvent many of the limitations of existing approaches, based on a combination of human and artificial intelligence. It was designed from scratch to be capable to identify sealed and unsealed cracks, potholes, patches, different types of pavements and others. The self-learning algorithms do not use any distresses predefinition and can process images taken by cameras with different brands, technologies and resolution. This study describes some key aspects of the new method and provides examples in which PICUCHA was tested in real conditions showing accuracy up to 96.9% in image pattern detection and classification. |
| first_indexed | 2024-03-12T06:33:58Z |
| format | Article |
| id | doaj.art-4b6c90f0f5da4147985443ba1aa54df3 |
| institution | Directory Open Access Journal |
| issn | 1805-2576 |
| language | English |
| last_indexed | 2024-03-12T06:33:58Z |
| publishDate | 2017-07-01 |
| publisher | Czech Technical University, Prague |
| record_format | Article |
| series | Civil Engineering Journal |
| spelling | doaj.art-4b6c90f0f5da4147985443ba1aa54df32023-09-03T01:27:19ZengCzech Technical University, PragueCivil Engineering Journal1805-25762017-07-012017214315310.14311/CEJ.2017.02.0013HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA)Reus Salini0Bugao Xu1Regis Carvalho21. Neogennium Technologies, Florianopolis, Brazil3. School of Human Ecology, Center for Transportation Research University of Texas at Austin, Austin, TX, USA4. Oaken Consult, LLC, Upper Marlboro, MD, USThe pavement surface condition assessment is a critical component for a proper pavement management system as well as for pavement rehabilitation design. A number of devices were developed to automatically record surface distresses in a continuous survey mode, but the software required for automatic distress identification remains a big challenge. In this study, a new method named PICture Unsupervised Classification with Human Analysis (PICUCHA) is proposed to circumvent many of the limitations of existing approaches, based on a combination of human and artificial intelligence. It was designed from scratch to be capable to identify sealed and unsealed cracks, potholes, patches, different types of pavements and others. The self-learning algorithms do not use any distresses predefinition and can process images taken by cameras with different brands, technologies and resolution. This study describes some key aspects of the new method and provides examples in which PICUCHA was tested in real conditions showing accuracy up to 96.9% in image pattern detection and classification.http://www.civilengineeringjournal.cz/archive/issues/2017/2017_2/2-2017-0013.pdfPavement SurveyPavement EvaluationArtificial IntelligencePICUCHA Method |
| spellingShingle | Reus Salini Bugao Xu Regis Carvalho HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) Civil Engineering Journal Pavement Survey Pavement Evaluation Artificial Intelligence PICUCHA Method |
| title | HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) |
| title_full | HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) |
| title_fullStr | HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) |
| title_full_unstemmed | HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) |
| title_short | HYBRID HUMAN-ARTIFICIAL INTELLIGENCE APPROACH FOR PAVEMENT DISTRESS ASSESSMENT (PICUCHA) |
| title_sort | hybrid human artificial intelligence approach for pavement distress assessment picucha |
| topic | Pavement Survey Pavement Evaluation Artificial Intelligence PICUCHA Method |
| url | http://www.civilengineeringjournal.cz/archive/issues/2017/2017_2/2-2017-0013.pdf |
| work_keys_str_mv | AT reussalini hybridhumanartificialintelligenceapproachforpavementdistressassessmentpicucha AT bugaoxu hybridhumanartificialintelligenceapproachforpavementdistressassessmentpicucha AT regiscarvalho hybridhumanartificialintelligenceapproachforpavementdistressassessmentpicucha |