A spatial concordance correlation coefficient with an application to image analysis

Vallejos, Ronny; Pérez, Joaquín; Ellison, Aaron M.; Richardson, Andrew D.

doi:10.1016/j.spasta.2019.100405

Cited by 6 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With those results of RMSE, the calibration camera coefficients are identified as: i) F is the focal length in pixels; ii) Cx and Cy are point offset principal in pixel also; iii) The radial distortion coefficients are identified as K1, K2, and K3; and iii) Tangential distortion coefficients identified P1 and P2. The matrix in Table 7 is the correlation matrix from the camera coefficients [21]: The correlation coefficient can vary from -1 to 1, 0 indicates that there is no linear relationship between the variables, and they are not correlated. 1 indicates a perfect positive linear relationship and -1 indicates a perfect negative linear relationship.…”

Section: Analysis Of Accuracy and Calibration Coefficientsmentioning

confidence: 99%

An improved mining image segmentation with K-Means and morphology using drone dataset

Haqiq,

Zaim,

Sbihi

et al. 2024

IJECE

View full text Add to dashboard Cite

The mining industry faces the challenge of incorporating advanced technology to explore new ways of increasing productivity and reducing costs. Our focus is on integrating drone technology to revolutionize mining tasks like inspection, mapping, and surveying. Drones offer a precision advantage over traditional satellite methods. To this end, we have created a dataset consisting of 373 aerial images captured by a DJI Phantom 4 drone, which depict a mining site in the Benslimane region of Western Morocco. These images, with a ground resolution of 2.5 cm per pixel, are the basis of our research. Our study aims to address the challenges posed by traditional mining techniques and to leverage technological innovations to improve segmentation and classification. The proposed approach includes new methodologies, particularly the combination of K-Means clustering and mathematical morphology, to overcome limitations and deliver better segmentation results. Our findings represent a significant step forward in advancing mining operations through the effective use of modern technologies.

show abstract

Section: Analysis Of Accuracy and Calibration Coefficientsmentioning

confidence: 99%

An improved mining image segmentation with K-Means and morphology using drone dataset

Haqiq,

Zaim,

Sbihi

et al. 2024

IJECE

View full text Add to dashboard Cite

show abstract

“…• FID (Fréchet Inception Distance) [32] • PSNR (Peak Signal-to-Noise Ratio) [33] • SCC (Spatial Correlation Coefficient) [34] • SSIM (Structural Similarity Index) [35] • VIF (Visual Information Fidelity) [36] • File size…”

Section: F Metric Measurements Definitionmentioning

confidence: 99%

Adaptive Lightweight License Plate Image Recovery Using Deep Learning Based on Generative Adversarial Network

Sereethavekul

Ekpanyapong

2023

IEEE Access

View full text Add to dashboard Cite

Many Convolutional Neural Networks (CNNs) methods have already surpassed traditional approaches to image restoration tasks. Those CNNs models were usually designed to enhance single tasks such as an image resolution (super-resolution) or image denoising, but we came up with unconventional goals, that is, multiple recovery tasks from a single network design. Although the Transformer design has recently gained attention in image recovery task but they are too slow. In order to work with license plate images from a traffic camera stream, the system has to be fast. So, we proposed a lightweight deep learningbased data recovery system using a Generative Adversarial Network (GAN) principle named License Plate Recovery GAN (LPRGAN). The design has a proposed encoder-decoder style inspired by an autoencoder aided by dual classification networks. This style is suitable for problem-characteristic learning because strong contextual information retrieves from the down-scaled representations. This proposed system has three main features, identifying a problem, data recovery, and a fail-safe mechanism. The data recovery unit (LPRGAN) is used to recover license plate images from multiple degraded input images. Most existing image restoration systems do not have self-awareness, leading to an inefficiency problem. Unlike existing works, this system has anomaly detection and will only process on a degraded input, reducing workload overhead and improving efficiency as well as a fail-safe feature to prevent an unexpected bad output. Hence, it is a light and efficient system so it could be possible to deploy on a low-power machine such as edge computing devices, opening up new possibilities in on-device computing. Our proposed research can recover several degraded problems up to 720p resolution at 15 frames per second on a single graphic card, 256x128 resolution at 17 frames per second on a CPU-only workstation machine, or 7 frames per second on an ultra-low-power tablet PC.

show abstract

“…It is known that the CC-based loss function has performed better than error-based loss functions: mean squared error, mean absolute error, etc. (Vallejos et al 2020;Atmaja & Akagi 2021). We use Lin's concordance CC, which takes bios into Pearson's CC (Lawrence & Lin 1989).…”

Section: Deep-learning Modelmentioning

confidence: 99%

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Jeong

Moon

Park

et al. 2022

ApJS

View full text Add to dashboard Cite

Here we greatly improve artificial intelligence (AI)–generated solar farside magnetograms using data sets from the Solar Terrestrial Relations Observatory (STEREO) and Solar Dynamics Observatory (SDO). We modify our previous deep-learning model and configuration of input data sets to generate more realistic magnetograms than before. First, our model, which is called Pix2PixCC, uses updated objective functions, which include correlation coefficients (CCs) between the real and generated data. Second, we construct input data sets of our model: solar farside STEREO extreme-ultraviolet (EUV) observations together with nearest frontside SDO data pairs of EUV observations and magnetograms. We expect that the frontside data pairs provide historic information on magnetic field polarity distributions. We demonstrate that magnetic field distributions generated by our model are more consistent with the real ones than previously, in consideration of several metrics. The averaged pixel-to-pixel CC for full disk, active regions, and quiet regions between real and AI-generated magnetograms with 8 × 8 binning are 0.88, 0.91, and 0.70, respectively. Total unsigned magnetic flux and net magnetic flux of the AI-generated magnetograms are consistent with those of real ones for the test data sets. It is interesting to note that our farside magnetograms produce polar field strengths and magnetic field polarities consistent with those of nearby frontside magnetograms for solar cycles 24 and 25. Now we can monitor the temporal evolution of active regions using solar farside magnetograms by the model together with the frontside ones. Our AI-generated solar farside magnetograms are now publicly available at the Korean Data Center for SDO (http://sdo.kasi.re.kr).

show abstract

A spatial concordance correlation coefficient with an application to image analysis

Cited by 6 publications

References 35 publications

An improved mining image segmentation with K-Means and morphology using drone dataset

An improved mining image segmentation with K-Means and morphology using drone dataset

Adaptive Lightweight License Plate Image Recovery Using Deep Learning Based on Generative Adversarial Network

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Contact Info

Product

Resources

About