Application of Smartphones in Pavement Deterioration Identification Using Artificial Neural Network

Moghadam, Amin; Sarlo, Rodrigo

doi:10.1007/978-3-030-75988-9_12

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decreasing amount of forest road deteriorations and the identification of abnormal events are considered an important problem that has to be solved [2]. In order to attain these goals, smart systems need to be developed for monitoring and understanding our surroundings using images, videos, sensors, or depth cameras [3][4][5][6][7][8][9][10][11][12][13]. Moreover, to be economical and widely deployable, this deterioration detector must operate on embedded processors that dissipate far less power than powerful GPUs (Graphics Processing Unit) used for benchmarking in typical computer vision experiments [14].…”

Section: Introductionmentioning

confidence: 99%

Forest Roads Damage Detection Based on Objected Detection Deep Learning Algorithms

Heidari

Najafi

Borges

2022

Preprint

View full text Add to dashboard Cite

Due to the high cost of identifying and evaluating forest roads and the subsequent issue of maintenance, forest management has always faced challenges in terms of scheduling and implementation costs. Currently, monitoring the condition of forest roads has reached a critical stage due to budget allocation problems and lack of adequate supervision and requires low-cost or cost-effective monitoring. Today, smartphones have been used on public roads to identify road deterioration due to benefits such as usability, cost, ease of access, and expected accuracy. The use of smartphones in forest road development by the proposed system is a distributed information system that converts data from enterprise mode to field mode by harvesting and assessing forest road conditions and image processing technologies. The technology proposed in this research allows different information YOLOv4-v5 with improvements to this version including mosaic data augmentation and automatic learning of enclosing frames. In this research, we applied a new hybrid YOLOv4-v5 to the dataset's general applicability. We assessment forest road dataset to run an experiment, smartphone images by various aspects of the smartphone images (SI) dataset which is specialized for detect forest road deterioration. To enhance YOLO's ability to detect damaged scenes by proposed a new technique that takes information into frames. We expanded the scope of the model by applying it to a new orientation estimation task. The main disadvantage is the provision of qualitative model information on forest road activity and the indication of potential deterioration.

show abstract