[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118688-en":3,"doc-seo-118688-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118688,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Pothole Detection Using Machine Learning and Computer Vision Techniques","Road infrastructure underpins safety and efficiency in transportation systems, yet pavement defects such as potholes and cracks create substantial hazards for vehicles and drivers while raising maintenance costs. Traditional inspection is often slow, risky, and inefficient, motivating automated road condition monitoring. This thesis develops computer vision and machine learning approaches to detect and segment road defects, supported by a review of vision-based methods and performance evaluation of UNet, UNet++, DeepLabv3+, and PSPNet on dashboard camera images. Results show UNet++ with EfficientNet-B5 delivers the best segmentation accuracy and reliability.","Pothole Detection Using Machine Learning and Computer Vision  \nTechniques  \nby  \n© Yashar Safyari  \nA Thesis submitted to the School of Graduate Studies in partial fulfillment of the requirements  \nfor the degree of  \nMaster of Engineering  \nFaculty of Engineering and Applied Science  \nMemorial University of Newfoundland  \nOctober 2025  \nSt. John’s  \nNewfoundland and Labrador  \nDedicated to my family  \nAbstract  \nRoad infrastructure plays a crucial role in ensuring safety and efficiency in transportation systems. However, road surface defects, such as potholes and cracks, cause significant risks to vehicles and drivers while increasing maintenance costs. Traditional inspection methods are often time-consuming, hazardous, and inefficient, emphasizing the need for automated approaches to road condition monitoring. This research investigates advanced computer vision and machine learning techniques for detecting and segmenting road defects, providing a robust and efficient solution for road maintenance. The thesis begins with a comprehensive review of current vision-based methods for pothole detection, including traditional 2D image processing, 3D point cloud techniques, machine learning, and hybrid approaches. The review highlights that combining traditional and advanced machine learning methods offers superior accuracy and adaptability for road defect detection. Building on this foundation, this research evaluates the performance of state-of-the-art deep learning models, such as UNet, UNet++, DeepLabv3+, and PSPNet, for semantic segmentation using dashboard camera images. The results illustrate that UNet++ with an EfficientNet-B5 backbone outperforms other models, achieving higher accuracy and reliability in segmenting road defects. By combining in-depth analysis of existing techniques with the development of high-performing deep learning models, this thesis contributes to the design of effective systems for automated road surface condition assessment. These advancements aim to enhance roadway safety, reduce maintenance costs, and improve infrastructure management.  \nAcknowledgment  \nI would like to express my deepest gratitude to my supervisors, Dr. Mahdianpari and Dr. Shiri, for their invaluable guidance, support, and encouragement throughout my research. Through their expertise, patience, and constructive feedback, I have been able to shape my work and manage the challenges ofthis journey.  \nAdditionally, I extend my appreciation to Memorial University and the faculty for providing the resources and environment needed to complete this research.  \nFinally, I am deeply grateful to my family for their unwavering support, encouragement, and belief in me throughout this endeavor. Their constant presence and understanding have been a source of strength during the most challenging moments ofthis journey.  \nTable of Contents  \nAbstract .......................................................................................................................................i  \nAcknowledgment .......................................................................................................................ii  \nTable of Contents ..................................................................................................................... iii  \n[Lists of Tables...........................................................................................................................vi](Lists of Tables...........................................................................................................................vi)  \n[List of Figures ...............................](List of Figures ...............................)...........................................................................................vii  \nList of Abbreviations ............................................................................................................. viii  \n1. Introduction ..............................................................","cbCaiqzSxNL8egZz","https://ap.wps.com/l/cbCaiqzSxNL8egZz","pdf",2893188,1,123,"English","en",105,"# 1. Introduction\n## 1.1. Background\n## 1.2. Research Motivation\n## 1.3. Scope and Objectives\n## 1.4. Contribution and Novelty\n## 1.5. Structure of Thesis\n# 2. Literature Review\n## 2.1. Importance of Road Infrastructure\n## 2.2. Potholes: Causes and Impacts\n## 2.3. Significance of Pothole Detection\n## 2.4. Vision-Based Pothole Detection\n## 2.5. Pothole Detection Processing Pipeline\n## 2.6. Related Work\n# 3. Public Dataset for Pothole Detection\n## 3.1. Sensors and Systems\n## 3.2. Public Datasets\n# 4. Pothole Detection Methods","[{\"question\":\"Why is pothole detection important for transportation systems?\",\"answer\":\"Road surface defects such as potholes and cracks increase safety risks for vehicles and drivers and also elevate maintenance costs. Automated monitoring addresses these issues more efficiently than manual inspection.\"},{\"question\":\"Which deep learning models are evaluated for road defect segmentation?\",\"answer\":\"The thesis evaluates state-of-the-art semantic segmentation models including UNet, UNet++, DeepLabv3+, and PSPNet using dashboard camera images.\"},{\"question\":\"What model performs best in the experiments?\",\"answer\":\"UNet++ with an EfficientNet-B5 backbone achieves the highest accuracy and reliability for segmenting road defects compared with the other tested models.\"}]","Pothole Detection Using Machine Learning and Computer Vision Techniques | PDF",1785684900,310,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"pothole-detection-using-machine-learning-and-computer-vision-techniques","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/pothole-detection-using-machine-learning-and-computer-vision-techniques/118688/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is pothole detection important for transportation systems?","Question",{"text":75,"@type":76},"Road surface defects such as potholes and cracks increase safety risks for vehicles and drivers and also elevate maintenance costs. Automated monitoring addresses these issues more efficiently than manual inspection.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which deep learning models are evaluated for road defect segmentation?",{"text":80,"@type":76},"The thesis evaluates state-of-the-art semantic segmentation models including UNet, UNet++, DeepLabv3+, and PSPNet using dashboard camera images.",{"name":82,"@type":73,"acceptedAnswer":83},"What model performs best in the experiments?",{"text":84,"@type":76},"UNet++ with an EfficientNet-B5 backbone achieves the highest accuracy and reliability for segmenting road defects compared with the other tested models.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]