Pavement distress detection using convolutional neural networks with images captured via UAV

Pavement distress detection is crucial in the decision-making for maintenance planning. Unmanned aerial vehicles (UAVs) are helpful in collecting pavement images. This paper proposes the collection of pavement distress information using a UAV with a high-resolution camera. A UAV platform for pavemen...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Automation in construction Ročník 133; s. 103991
Hlavní autoři:	Zhu, Junqing, Zhong, Jingtao, Ma, Tao, Huang, Xiaoming, Zhang, Weiguang, Zhou, Yang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Amsterdam Elsevier B.V 01.01.2022 Elsevier BV
Témata:	Algorithms Artificial neural networks Asphalt pavement distress Convolutional neural network (CNN) Datasets Decision making Image quality Inspection Object-detection algorithms Pavements Unmanned aerial vehicle (UAV) Unmanned aerial vehicles Unmanned aerial vehicle (UAV) Convolutional neural network (CNN) Asphalt pavement distress Object-detection algorithms
ISSN:	0926-5805, 1872-7891
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Pavement distress detection is crucial in the decision-making for maintenance planning. Unmanned aerial vehicles (UAVs) are helpful in collecting pavement images. This paper proposes the collection of pavement distress information using a UAV with a high-resolution camera. A UAV platform for pavement image collection was assembled, and the flight settings were studied for optimal image quality. The collected images were processed and annotated for model training. Three state-of-the-art object-detection algorithms—Faster R-CNN, YOLOv3, and YOLOv4, were used to train the dataset, and their prediction performances were compared. A pavement image dataset was established with six types of distress. YOLOv3 demonstrated the best performance of the three algorithms, with a mean average precision (MAP) of 56.6%. The findings of this study assist in the inspection of non-destructive automatic pavement conditions. •UAV flight parameters are examined for pavement image collection.•An UAV pavement image dataset (UAPD) was established.•Anchor size is researched for pavement distress detection.•YOLOv3 outperforms YOLOv4 and Faster R-CNN.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0926-5805 1872-7891
DOI:	10.1016/j.autcon.2021.103991