Advances in Computer Vision

Mahony, Niall O’; Campbell, Sean; Carvalho, Anderson; Harapanahalli, Suman; Velasco-Hernandez, Gustavo; Krpálková, Lenka; Riordan, Daniel; Walsh, Joseph T.

doi:10.1007/978-3-030-17795-9

Cited by 46 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is primarily due to the poor condition of the gauges, inadequate illumination, and harsh environmental factors [ 26 ]. On the contrary, the traditional computer vision techniques often work well in noisy and complex environments, where NN-based techniques may struggle to generalize, and they are often less computationally intensive [ 27 , 28 ]. Moreover, several authors have developed algorithms only using traditional computer vision techniques that are robust and accurate, for example, Gellaboina et al [ 29 ] proposed an algorithm that can automatically identify dial gauge readings using an image captured by a handheld device.…”

Section: Background and Related Workmentioning

confidence: 99%

End-to-End Solution for Analog Gauge Monitoring Using Computer Vision in an IoT Platform

Peixoto,

Sousa,

Carvalho

et al. 2023

Sensors

View full text Add to dashboard Cite

The emergence of Industry 4.0 and 5.0 technologies has enabled the digital transformation of various processes and the integration of sensors with the internet. Despite these strides, many industrial sectors still rely on visual inspection of physical processes, especially those employing analog gauges. This method of monitoring introduces the risk of human errors and inefficiencies. Automating these processes has the potential, not only to boost productivity for companies, but also potentially reduce risks for workers. Therefore, this paper proposes an end-to-end solution to digitize analog gauges and monitor them using computer vision through integrating them into an IoT architecture, to tackle these problems. Our prototype device has been designed to capture images of gauges and transmit them to a remote server, where computer vision algorithms analyze the images and obtain gauge readings. These algorithms achieved adequate robustness and accuracy for industrial environments, with an average relative error of 0.95%. In addition, the gauge data were seamlessly integrated into an IoT platform leveraging computer vision and cloud computing technologies. This integration empowers users to create custom dashboards for real-time gauge monitoring, while also enabling them to set thresholds, alarms, and warnings, as needed. The proposed solution was tested and validated in a real-world industrial scenario, demonstrating the solution’s potential to be implemented in a large-scale setting to serve workers, reduce costs, and increase productivity.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

End-to-End Solution for Analog Gauge Monitoring Using Computer Vision in an IoT Platform

Peixoto,

Sousa,

Carvalho

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Deep learning techniques have surpassed the efficiency of statistical techniques in computer vision [49]. This consistently evolving field has helped make impressive contributions to the dynamic field of data-driven astronomy [50][51][52][53][54][55].…”

Section: Existing Deep-learning-based Approachesmentioning

confidence: 99%

Fishing massive black hole binaries with THAMES

Sharma¹,

Chandra²

2022

Preprint

View full text Add to dashboard Cite

Hierarchical mergers in a dense environment are one of the primary formation channels of intermediate-mass black hole (IMBH) binary system. We expect that the resulting massive binary system will exhibit mass asymmetry. The emitted gravitational-wave (GW) carry significant contribution from higher-order modes and hence complex waveform morphology due to superposition of different modes. Further, IMBH binaries exhibit lower merger frequency and shorter signal duration in the LIGO detector which increases the risk of them being misclassified as short-duration noisy glitches. Deep learning algorithms can be trained to discriminate noisy glitches from short GW transients. We present the THAMES -a deep-learning-based end-to-end signal detection algorithm for GW signals from quasi-circular nearly edge-on, mass asymmetric IMBH binaries in advanced GW detectors. Our study shows that it outperforms matched-filter based PyCBC searches for higher mass asymmetric, nearly edge-on IMBH binaries. The maximum gain in the sensitive volume-time product for mass ratio q ∈ (5, 10) is by a factor of 5.24 (2.92) against PyCBC − IMBH (PyCBC − HM) search at a false alarm rate of 1 in 100 years. Compared to the broad PyCBC search this factor is ∼ 100 for the q ∈ (10, 18). One of the reasons for this leap in volumetric sensitivity is its ability to discriminate between signals with complex waveform morphology and noisy transients, clearly demonstrating the potential of deep learning algorithms in probing into complex signal morphology in the field of gravitational wave astronomy. With the current training set, THAMES slightly underperforms with respect to PyCBC-based searches targeting intermediate-mass black hole binaries with mass ratio q ∈ (5, 10) and detector frame total mass MT (1 + z) ∈ (100, 200) M .

show abstract

“…Nowadays, one of the main focuses in the computer vision (CV) field is based on artificial intelligence (AI) algorithms for segmentation and classification in image domain such as machine learning (ML) and deep learning (DL) [5]. ML forgoes the traditional programming paradigm where problem analysis is replaced by a training framework, where the system is fed a large number of training patterns (sets of inputs for which the desired outputs are known) which it learns and uses to predict new patterns [6]. Additionally, DL is a subset of machine learning, based largely on Artificial Neural Networks (ANNs), a computing paradigm inspired by the functioning of the human brain.…”

Section: Introductionmentioning

confidence: 99%

MedicalSeg: A Medical GUI Application for Image Segmentation Management

et al. 2022

View full text Add to dashboard Cite

In the field of medical imaging, the division of an image into meaningful structures using image segmentation is an essential step for pre-processing analysis. Many studies have been carried out to solve the general problem of the evaluation of image segmentation results. One of the main focuses in the computer vision field is based on artificial intelligence algorithms for segmentation and classification, including machine learning and deep learning approaches. The main drawback of supervised segmentation approaches is that a large dataset of ground truth validated by medical experts is required. In this sense, many research groups have developed their segmentation approaches according to their specific needs. However, a generalised application aimed at visualizing, assessing and comparing the results of different methods facilitating the generation of a ground-truth repository is not found in recent literature. In this paper, a new graphical user interface application (MedicalSeg) for the management of medical imaging based on pre-processing and segmentation is presented. The objective is twofold, first to create a test platform for comparing segmentation approaches, and secondly to generate segmented images to create ground truths that can then be used for future purposes as artificial intelligence tools. An experimental demonstration and performance analysis discussion are presented in this paper.

show abstract

Advances in Computer Vision

Cited by 46 publications

References 39 publications

End-to-End Solution for Analog Gauge Monitoring Using Computer Vision in an IoT Platform

End-to-End Solution for Analog Gauge Monitoring Using Computer Vision in an IoT Platform

Fishing massive black hole binaries with THAMES

MedicalSeg: A Medical GUI Application for Image Segmentation Management

Contact Info

Product

Resources

About