Accurate Crack Detection Based on Distributed Deep Learning for IoT Environment

Kim, Youngpil; Yi, Shinuk; Ahn, Hyunho; Hong, Cheol-Ho

doi:10.3390/s23020858

Cited by 7 publications

(3 citation statements)

References 32 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed solution classifies road anomalies at predefined intervals and promptly notifies the concerned authorities. Furthermore, in [68], an innovative solution for edge-based crack detection is introduced. This solution combines a crack detection model called Real-Time Segmentation using Effective Feature Extraction (Rsef) with edge computing capabilities on the NVIDIA Jetson TX2 platform.…”

Section: Compute Vision Algorithmsmentioning

confidence: 99%

Crowdsensing for Road Pavement Condition Monitoring: Trends, Limitations, and Opportunities

Jan,

Khattak,

Khan

et al. 2023

IEEE Access

View full text Add to dashboard Cite

RPCM forms a crucial element of preventive maintenance strategies, particularly in light of escalating vehicular pressures and the advent of extreme weather patterns. Consequently, there is a growing demand for cost-effective solutions that leverage emergent technologies such as the IoT, AI, and cloud computing. This research intends to articulate the evolutionary trajectory of road solutions while delineating the prevalent challenges and offering viable trajectories for future enhancements. To achieve this objective, a systematic literature review was executed using the Scopus and Web of Science databases, the aim of which was to discern the inherent challenges of existing solutions. Following a stringent elimination process of duplicates and irrelevant studies, a corpus of 74 research papers was assembled for review. Assessment criteria encompassed the sensing platforms and algorithms deployed, the variety of road deformities detected, and the overall accuracy of the proposed solutions. The analysis revealed a variety of methodologies applied to RPCM, each bearing distinct advantages and limitations. Notably, SPbased monitoring solutions utilizing ML techniques and improved data gathering methodologies exhibited superior outcomes relative to alternative approaches. To conclude, this research elucidates the wide-ranging methodologies in RPCM, critically examining their respective advantages and drawbacks. Among the methodologies surveyed, SP-based monitoring deploying ML techniques emerges as a compelling approach, demonstrating the potential for enhancing accuracy and data gathering techniques. These insights form a valuable foundation for the conception and development of future cost-effective and efficacious RPCM solutions.

show abstract

Section: Compute Vision Algorithmsmentioning

confidence: 99%

Crowdsensing for Road Pavement Condition Monitoring: Trends, Limitations, and Opportunities

Jan,

Khattak,

Khan

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Unfortunately, modern CNN algorithms, including object detection in bioimages, demand a substantial amount of computational resources during inference due to the deep structure of these algorithms. Recent powerful graphics processing units (GPUs) can expedite fast deep learning inference by enabling massive parallel computation [3]. However, it is challenging to maintain large in-house GPU facilities in a small hospital or biomedical research laboratory due to the high initial equipment costs and significant power consumption [4].…”

Section: Introductionmentioning

confidence: 99%

BioEdge: Accelerating Object Detection in Bioimages with Edge-Based Distributed Inference

Ahn,

Lee,

Seong

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have enabled effective object detection tasks in bioimages. Unfortunately, implementing such an object detection model can be computationally intensive, especially on resource-limited hardware in a laboratory or hospital setting. This study aims to develop a framework called BioEdge that can accelerate object detection using Scaled-YOLOv4 and YOLOv7 by leveraging edge computing for bioimage analysis. BioEdge employs a distributed inference technique with Scaled-YOLOv4 and YOLOv7 to harness the computational resources of both a local computer and an edge server, enabling rapid detection of COVID-19 abnormalities in chest radiographs. By implementing distributed inference techniques, BioEdge addresses privacy concerns that can arise when transmitting biomedical data to an edge server. Additionally, it incorporates a computationally lightweight autoencoder at the split point to reduce data transmission overhead. For evaluation, this study utilizes the COVID-19 dataset provided by the Society for Imaging Informatics in Medicine (SIIM). BioEdge is shown to improve the inference latency of Scaled-YOLOv4 and YOLOv7 by up to 6.28 times with negligible accuracy loss compared to local computer execution in our evaluation setting.

show abstract

“…Since small targets occupy fewer pixels in an image and contain less feature information, how to better extract feature information is one of the main problems that must be solved in this paper. Finally, the video transmission post-processing approach causes a certain delay, which is deployed using edge computing [28,29] in this paper. This limits the volume and computational capacities of the model due to the limited arithmetic power of the edge nodes.…”

Section: Introductionmentioning

confidence: 99%

Detection of Floating Objects on Water Surface Using YOLOv5s in an Edge Computing Environment

Li,

Yang,

Zhang

et al. 2023

Water

View full text Add to dashboard Cite

Aiming to solve the problems with easy false detection of small targets in river floating object detection and deploying an overly large model, a new method is proposed based on improved YOLOv5s. A new data augmentation method for small objects is designed to enrich the dataset and improve the model’s robustness. Distinct feature extraction network levels incorporate different coordinate attention mechanism pooling methods to enhance the effective feature information extraction of small targets and improve small target detection accuracy. Then, a shallow feature map with 4-fold down-sampling is added, and feature fusion is performed using the Feature Pyramid Network. At the same time, bilinear interpolation replaces the up-sampling method to retain feature information and enhance the network’s ability to sense small targets. Network complex algorithms are optimized to better adapt to embedded platforms. Finally, the model is channel pruned to solve the problem of difficult deployment. The experimental results show that this method has a better feature extraction capability as well as a higher detection accuracy. Compared with the original YOLOv5 algorithm, the accuracy is improved by 15.7%, the error detection rate is reduced by 83% in small target task detection, the detection accuracy can reach 92.01% in edge testing, and the inference speed can reach 33 frames per second, which can meet the real-time requirements.

show abstract

Accurate Crack Detection Based on Distributed Deep Learning for IoT Environment

Cited by 7 publications

References 32 publications

Crowdsensing for Road Pavement Condition Monitoring: Trends, Limitations, and Opportunities

Crowdsensing for Road Pavement Condition Monitoring: Trends, Limitations, and Opportunities

BioEdge: Accelerating Object Detection in Bioimages with Edge-Based Distributed Inference

Detection of Floating Objects on Water Surface Using YOLOv5s in an Edge Computing Environment

Contact Info

Product

Resources

About