The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A detecção de horizonte é útil no processamento de imagens marítimas para diversos fins, como estimativa da orientação da câmera, registro de quadros consecutivos e restrição da região de busca do objeto. Os métodos existentes de detecção de horizonte são baseados na extração de bordas. Para maior precisão, eles usam várias imagens, que são filtradas com diferentes tamanhos de filtro. No entanto, isso aumenta o tempo de processamento. Além disso, esses métodos não são robustos para deixar escapar. Portanto, desenvolvemos um método de detecção de horizonte sem extrair os candidatos das informações de borda, formulando o problema de detecção de horizonte como um problema de otimização global. Uma linha do horizonte em um plano de imagem foi representada por dois parâmetros, que foram otimizados por um algoritmo evolutivo (algoritmo genético). Assim, as características locais e globais de um horizonte foram utilizadas simultaneamente no processo de otimização, que foi acelerado pela aplicação de uma estratégia grosseira para fina. Como resultado, pudemos detectar a linha do horizonte em imagens marítimas de alta resolução em cerca de 50ms. O desempenho do método proposto foi testado em 49 vídeos do conjunto de dados marinhos de Cingapura e do conjunto de dados Buoy, que contêm mais de 16000 quadros em diferentes cenários. Resultados experimentais mostram que o método proposto pode atingir maior precisão do que os métodos do estado da arte.
Uuganbayar GANBOLD
Iwate University
Junya SATO
Gifu University
Takuya AKASHI
Iwate University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Uuganbayar GANBOLD, Junya SATO, Takuya AKASHI, "Coarse-to-Fine Evolutionary Method for Fast Horizon Detection in Maritime Images" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 12, pp. 2226-2236, December 2021, doi: 10.1587/transinf.2021EDP7064.
Abstract: Horizon detection is useful in maritime image processing for various purposes, such as estimation of camera orientation, registration of consecutive frames, and restriction of the object search region. Existing horizon detection methods are based on edge extraction. For accuracy, they use multiple images, which are filtered with different filter sizes. However, this increases the processing time. In addition, these methods are not robust to blurting. Therefore, we developed a horizon detection method without extracting the candidates from the edge information by formulating the horizon detection problem as a global optimization problem. A horizon line in an image plane was represented by two parameters, which were optimized by an evolutionary algorithm (genetic algorithm). Thus, the local and global features of a horizon were concurrently utilized in the optimization process, which was accelerated by applying a coarse-to-fine strategy. As a result, we could detect the horizon line on high-resolution maritime images in about 50ms. The performance of the proposed method was tested on 49 videos of the Singapore marine dataset and the Buoy dataset, which contain over 16000 frames under different scenarios. Experimental results show that the proposed method can achieve higher accuracy than state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7064/_p
Copiar
@ARTICLE{e104-d_12_2226,
author={Uuganbayar GANBOLD, Junya SATO, Takuya AKASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Coarse-to-Fine Evolutionary Method for Fast Horizon Detection in Maritime Images},
year={2021},
volume={E104-D},
number={12},
pages={2226-2236},
abstract={Horizon detection is useful in maritime image processing for various purposes, such as estimation of camera orientation, registration of consecutive frames, and restriction of the object search region. Existing horizon detection methods are based on edge extraction. For accuracy, they use multiple images, which are filtered with different filter sizes. However, this increases the processing time. In addition, these methods are not robust to blurting. Therefore, we developed a horizon detection method without extracting the candidates from the edge information by formulating the horizon detection problem as a global optimization problem. A horizon line in an image plane was represented by two parameters, which were optimized by an evolutionary algorithm (genetic algorithm). Thus, the local and global features of a horizon were concurrently utilized in the optimization process, which was accelerated by applying a coarse-to-fine strategy. As a result, we could detect the horizon line on high-resolution maritime images in about 50ms. The performance of the proposed method was tested on 49 videos of the Singapore marine dataset and the Buoy dataset, which contain over 16000 frames under different scenarios. Experimental results show that the proposed method can achieve higher accuracy than state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2021EDP7064},
ISSN={1745-1361},
month={December},}
Copiar
TY - JOUR
TI - Coarse-to-Fine Evolutionary Method for Fast Horizon Detection in Maritime Images
T2 - IEICE TRANSACTIONS on Information
SP - 2226
EP - 2236
AU - Uuganbayar GANBOLD
AU - Junya SATO
AU - Takuya AKASHI
PY - 2021
DO - 10.1587/transinf.2021EDP7064
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2021
AB - Horizon detection is useful in maritime image processing for various purposes, such as estimation of camera orientation, registration of consecutive frames, and restriction of the object search region. Existing horizon detection methods are based on edge extraction. For accuracy, they use multiple images, which are filtered with different filter sizes. However, this increases the processing time. In addition, these methods are not robust to blurting. Therefore, we developed a horizon detection method without extracting the candidates from the edge information by formulating the horizon detection problem as a global optimization problem. A horizon line in an image plane was represented by two parameters, which were optimized by an evolutionary algorithm (genetic algorithm). Thus, the local and global features of a horizon were concurrently utilized in the optimization process, which was accelerated by applying a coarse-to-fine strategy. As a result, we could detect the horizon line on high-resolution maritime images in about 50ms. The performance of the proposed method was tested on 49 videos of the Singapore marine dataset and the Buoy dataset, which contain over 16000 frames under different scenarios. Experimental results show that the proposed method can achieve higher accuracy than state-of-the-art methods.
ER -