Просмотреть запись

Road Pavement Crack Detection Using Deep Learning with Synthetic Data

Электронный архив ТПУ

Информация об архиве | Просмотр оригинала
 
 
Поле Значение
 
Заглавие Road Pavement Crack Detection Using Deep Learning with Synthetic Data
 
Автор Kanaeva, I. A.
Ivanova, Yulia Aleksandrovna
 
Тематика automatic pavement crack detection
synthetic data generation
deep convolutional neural network
semantic segmentation
image processing
автоматическое обнаружение
трещины
синтетизм
генерация
данные
сверточные нейронные сети
сегментация
обработка изображений
 
Описание Robust automatic pavement crack detection is critical to automated road condition evaluation. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this process. This study makes literature review of detection issues of road pavement's distress. The paper considers the existing datasets for detection and segmentation distress of road and asphalt pavement. The work presented in this article focuses on deep learning approach based on synthetic training data generation for segmentation of cracks in the driver-view image. A synthetic dataset generation method is presented, and effectiveness of its applicability to the current problem is evaluated. The relevance of the study is emphasized by research on pixel-level automatic damage detection remains a challenging problem, due to heterogeneous pixel intensity, complex crack topology, poor illumination condition, and noisy texture background.
 
Дата 2020-01-23T09:13:05Z
2020-01-23T09:13:05Z
2019
 
Тип Conference Paper
Published version (info:eu-repo/semantics/publishedVersion)
Conference paper (info:eu-repo/semantics/conferencePaper)
 
Идентификатор Kanaeva I. A. Road Pavement Crack Detection Using Deep Learning with Synthetic Data / I. A. Kanaeva, Yu. A. Ivanova // 14th International Forum on Strategic Technology (IFOST-2019), October 14-17, 2019, Tomsk, Russia : [proceedings]. — Tomsk : TPU Publishing House, 2019. — [С. 320-325].
http://earchive.tpu.ru/handle/11683/57474
 
Язык en
 
Связанные ресурсы 14th International Forum on Strategic Technology (IFOST-2019), October 14-17, 2019, Tomsk, Russia : [proceedings]. — Tomsk, 2019.
 
Права Open access (info:eu-repo/semantics/openAccess)