Real-time embedded system for valve detection in water pipelines

Rayhana, Rakiba; Jiao, Yutong; Liu, Zheng; Wu, Angie; Kong, Xiangjie

doi:10.1007/s11554-021-01178-9

Cited by 7 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rayhana et al [10] proposed MFPN, a valve detection model based on MobileNet-160 and feature pyramid network. Rayhana et al [9] proposed real-time valve detection based on the lightweight algorithm YOLOv 3tiny Valve. Pahwa et al [15] proposed a technology based on multi-stage deep learning to accurately detect faults in orbit valves.…”

Section: Valve Target Detectionmentioning

confidence: 99%

“…The advantage of this is that the lowlevel features can provide more detailed information, while the high-level features can provide higher-level semantic information. Rayhana et al [9] proposes a valve recognition model based on YOLOv3-tiny, which not only fuses multiscale local similarity features of the top network, but also sequentially fuses multiscale features of different network layers.…”

Section: Multi-path Feature Fusionmentioning

confidence: 99%

“…Therefore, it is necessary to enhance the feature representation of the target and explore the multiple correlations and differences between the target and the background. Rayhana et al [8][9][10][11] of valves to a certain extent, but they all ignore the feature enhancement of different feature layers in different feature spaces and do not consider the correspondence between different granularity of contextual features in multi-layer feature spaces. As shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

Zhang,

Huang,

2024

Preprint

View full text Add to dashboard Cite

Valves Detection is a basic function of rescue robots in various disaster situations. However, due to the small differences between similar valves, rescue robots suffer great challenges in valve detection in complex environments. To address this challenge, this paper proposes a multi-path hybrid attention deep neural network (MHADNN). By weighting features at different scales and spatial positions, the MHADNN can help valve detection models focus on more discriminative subtle features, thereby enhancing the ability to distinguish similar valves. This paper combines the MHADNN with the YOLOv5n to develop a valve detection model. The comparative experiments are conducted on a similar valve dataset collected in the simulated environment of a chemical industrial park. The experimental results show that compared with YOLOv5n, the proposed valve detection model has an average precision improvement of 4.20%. It has excellent performance in distinguishing similar valves.

show abstract

Section: Valve Target Detectionmentioning

confidence: 99%

Section: Multi-path Feature Fusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

Zhang,

Huang,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In traditional farming practice, the farmers need to visit the agriculture fields frequently to monitor crop conditions. However, this monitoring process is laborious and can consume up to 70% of farmer's time [11,12]. Hence, advanced technologies such as sensor networks, ubiquitous computing [13,14], and grid computing with satellite navigation services can improve the monitoring process and help make beneficial decisions for farmers.…”

Section: Introductionmentioning

confidence: 99%

A Review on Sensing Technologies for High-Throughput Plant Phenotyping

Rayhana

Feng

et al. 2022

IEEE Open J. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

The current epidemic, population growth, and decreasing arable lands lead to a severe food crisis, which calls for productive and efficient agricultural methods to ensure a sustainable food supply for mankind. Crop monitoring is considered to be a potential solution for the improvement of food production. Current crop monitoring combines agriculture methodologies with other advanced technologies, including sensing technology, geographical information systems (GIS), Internet of Things (IoT), information and communication technology (ICT), robotics, and drone techniques to increase production with low labor cost. The high-throughput plant phenotyping is crucial for crop monitoring on the data acquisition of large-scale crop characteristics. The high-throughput plant phenotyping studies aim to achieve fast and precise large-scale crop monitoring techniques with minimum environmental impact by applying special plant phenotyping platforms. The phenotyping platforms are integrated with various sensors and data communication systems, which can help to achieve automatic data acquisition and transmission. This paper reviews the current high-throughput plant phenotyping development in crop monitoring, including sensors, communication protocols, data management, and plant phenotyping platforms. State-of-art challenges are reviewed and discussed. Also, the paper provides discussions on the current situation, upcoming challenges, and possible future trends for researchers in this field.

show abstract

Real-time and accurate defect segmentation of aluminum strip surface via a lightweight network

Qian

2023

J Real-Time Image Proc

View full text Add to dashboard Cite

Real-time embedded system for valve detection in water pipelines

Cited by 7 publications

References 48 publications

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

A Review on Sensing Technologies for High-Throughput Plant Phenotyping

Real-time and accurate defect segmentation of aluminum strip surface via a lightweight network

Contact Info

Product

Resources

About