Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
)Matsuda, Asahi*; Takahashi, Satoru*; Kawabata, Kuniaki; Oda, Shoji*; Kaneko, Shunichi*
Denki Gakkai Rombunshi, D, 139(4), p.424 - 432, 2019/04
Takahashi, Satoru*; Nota, Yoshiki*; Matsuda, Asahi*; Kawabata, Kuniaki; Suzuki, Tsuyoshi*; Takemura, Fumiaki*; Ogasawara, Kei*; Kaneko, Shunichi*
Journal of Signal Processing, 21(1), p.15 - 24, 2017/01
In recent years, many researchers try to observe the state of the global environment from marine information for the understanding of the global environment change. First, we introduce the recording system of underwater environment which is made by the authors. By using this system, we want to observe the change of global environment from the coral bleaching. In this paper, especially, we propose the generation method of underwater landmark which is used to measure the position of robot of oceanographic observation based on the dynamic image processing. In here, underwater landmark means the feature point in underwater image.
Matsuda, Asahi*; Takahashi, Satoru*; Kawabata, Kuniaki; Takemura, Fumiaki*; Ogasawara, Kei*
no journal, ,
In recent years, research of bleaching of coral based on change of underwater environment is important in order to know change of global environment. Currently, investigation of underwater is conducted by the diver. Therefore, several problems such as load for the diver and restriction of search area are occurred. To solve these problems, we are developing the underwater robot for investigating of coral reef for the wide and the long time. In here, to know the current situation of coral we consider the automatic extraction method of the coral based on texture analysis from image obtained by monitoring.
Matsuda, Asahi*; Okuda, Yudai*; Takahashi, Satoru*; Kawabata, Kuniaki; Ogasawara, Kei*
no journal, ,
Research of monitoring of corals plays an important role in observing the natural environment on a global scale. Identifying and detecting corals amongst other objects, including marine organisms, from an image taken undersea is a difficult task. Moreover, there are many types of corals and they cannot be easily categorized automatically. Currently, texture analysis is being pursued that solves the problem of detecting and recognizing corals from pictures taken undersea; Haralick 14 conditional equations are used to calculate the texture characteristics information based on the gray level co-occurrence matrix of 256 gradations and also to perform liner discrimination analysis on the characteristics information. In this paper, we propose one algorithm of texture analysis for discrimination of undersea objects, in order to detect the corals.
Matsuda, Asahi*; Takahashi, Satoru*; Kawabata, Kuniaki; Kaneko, Shunichi*
no journal, ,
It is important to observe Medaka behavior for biological experiment for understanding adaptivity of Medaka. This paper reported to develop a method for tracking Medaka by image processing based on rotation invariant features.
Matsuda, Asahi*; Takahashi, Satoru*; Kawabata, Kuniaki; Oda, Shoji*; Kaneko, Shunichi*
no journal, ,
Medaka (Oryzias latipes) has genetic diversity, and analyzing its behavior in a group is very important for elucidation of diversity of organisms. However, conventional method of visual measurement has some problems. For example, the time cost and human error. In this paper, we proposed a method of behavior measurement of medaka in a group based on an image instrumentation. Our proposed method consists of four processes: pre-processing, particle filter, orientation code matching using by central differences with multi-templates, and detection of target position. Finally, we examined the effectiveness of our proposed method through an experimentation.
