Bayesian Inference for Post-Processing of Remote-Sensing Image Classification DOI Creative Commons
Gilberto Câmara, Renato Assunção, Alexandre Carvalho

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(23), P. 4572 - 4572

Published: Dec. 6, 2024

A key component of remote-sensing image analysis is classification, which aims to categorize images into different classes using machine-learning methods. In many applications, classifiers assign class probabilities each pixel. These serve as input for post-processing techniques that aim improve the results algorithms. This paper proposes a new algorithm based on an empirical Bayes approach. We employ non-isotropic neighborhood definitions capture impact borders between land in statistical model. By incorporating expert knowledge, improves consistency classified map. technique has proven its efficacy large-scale data processing time-series analysis. The proposed method time-first, space-based approach big Earth-observation processing. It available open source part R package sits.

Language: Английский

Preface: Advancing deep learning for remote sensing time series data analysis DOI
Hankui K. Zhang, Gustau Camps‐Valls, Shunlin Liang

et al.

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: unknown, P. 114711 - 114711

Published: March 1, 2025

Language: Английский

Citations

0
Comparative analysis of forest disturbance detection in the key state-owned forest region of the Greater Khingan Range of China based on different algorithms DOI Creative Commons
Ke Xu,

Wenshu Lin,

Ning Zhang

et al.

Geocarto International, Journal Year: 2025, Volume and Issue: 40(1)

Published: April 15, 2025

Language: Английский

Citations

0
Forest disturbance detection in Central Europe using transformers and Sentinel-2 time series DOI Creative Commons
Christopher Schiller,

Jonathan Költzow,

Selina Schwarz

et al.

Remote Sensing of Environment, Journal Year: 2024, Volume and Issue: 315, P. 114475 - 114475

Published: Oct. 24, 2024

Language: Английский

Citations

2
Bayesian Inference for Post-Processing of Remote-Sensing Image Classification DOI Creative Commons
Gilberto Câmara, Renato Assunção, Alexandre Carvalho

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(23), P. 4572 - 4572

Published: Dec. 6, 2024

A key component of remote-sensing image analysis is classification, which aims to categorize images into different classes using machine-learning methods. In many applications, classifiers assign class probabilities each pixel. These serve as input for post-processing techniques that aim improve the results algorithms. This paper proposes a new algorithm based on an empirical Bayes approach. We employ non-isotropic neighborhood definitions capture impact borders between land in statistical model. By incorporating expert knowledge, improves consistency classified map. technique has proven its efficacy large-scale data processing time-series analysis. The proposed method time-first, space-based approach big Earth-observation processing. It available open source part R package sits.

Language: Английский

Citations

0