{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/road-damage-detection-using-deep-neural","title":"Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone","arxiv_id":"1801.09454","date":"2018-01-29","proceeding":null,"authors":["Hiroya Maeda","Yoshihide Sekimoto","Toshikazu Seto","Takehiro Kashiyama","Hiroshi Omata"],"abstract":"Research on damage detection of road surfaces using image processing\ntechniques has been actively conducted, achieving considerably high detection\naccuracies. Many studies only focus on the detection of the presence or absence\nof damage. However, in a real-world scenario, when the road managers from a\ngoverning body need to repair such damage, they need to clearly understand the\ntype of damage in order to take effective action. In addition, in many of these\nprevious studies, the researchers acquire their own data using different\nmethods. Hence, there is no uniform road damage dataset available openly,\nleading to the absence of a benchmark for road damage detection. This study\nmakes three contributions to address these issues. First, to the best of our\nknowledge, for the first time, a large-scale road damage dataset is prepared.\nThis dataset is composed of 9,053 road damage images captured with a smartphone\ninstalled on a car, with 15,435 instances of road surface damage included in\nthese road images. In order to generate this dataset, we cooperated with 7\nmunicipalities in Japan and acquired road images for more than 40 hours. These\nimages were captured in a wide variety of weather and illuminance conditions.\nIn each image, we annotated the bounding box representing the location and type\nof damage. Next, we used a state-of-the-art object detection method using\nconvolutional neural networks to train the damage detection model with our\ndataset, and compared the accuracy and runtime speed on both, using a GPU\nserver and a smartphone. Finally, we demonstrate that the type of damage can be\nclassified into eight types with high accuracy by applying the proposed object\ndetection method. The road damage dataset, our experimental results, and the\ndeveloped smartphone application used in this study are publicly available\n(https://github.com/sekilab/RoadDamageDetector/).","url_abs":"http://arxiv.org/abs/1801.09454v2","url_pdf":"http://arxiv.org/pdf/1801.09454v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"road-damage-detection-using-deep-neural","repo_url":"https://github.com/sekilab/RoadDamageDetector","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"road-damage-detection-using-deep-neural","repo_url":"https://github.com/nitz21/RoadDamage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"road-damage-detection","task_name":"Road Damage Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}