Abstract: An earthquake event classification method using an attention-based neural network includes: preprocessing input earthquake data by centering; extracting a feature map by nonlinearly converting the preprocessed earthquake data through a plurality of convolution layers having three or more layers; measuring importance of a learned feature of the nonlinear-converted earthquake data based on an attention technique in which interdependence of channels of the feature map is modeled; correcting a feature value of the measured importance value through element-wise multiply with the learned feature map; performing down-sampling through max-pooling based on the feature value; and classifying an earthquake event by regularizing the down-sampled feature value. Accordingly, main core features inherent in many/complex data are extracted through attention-based deep learning to overcome the limitations of the existing micro earthquake detection technology, thereby enabling earthquake detection even in low SNR environments.

Abstract: An earthquake event classification method using an attention-based neural network includes: preprocessing input earthquake data by centering; extracting a feature map by nonlinearly converting the preprocessed earthquake data through a plurality of convolution layers having three or more layers; measuring importance of a learned feature of the nonlinear-converted earthquake data based on an attention technique in which interdependence of channels of the feature map is modeled; correcting a feature value of the measured importance value through element-wise multiply with the learned feature map; performing down-sampling through max-pooling based on the feature value; and classifying an earthquake event by regularizing the down-sampled feature value. Accordingly, main core features inherent in many/complex data are extracted through attention-based deep learning to overcome the limitations of the existing micro earthquake detection technology, thereby enabling earthquake detection even in low SNR environments.

Abstract: Provided is a method of merging or fusing a visible image captured by a visible camera and an infrared (IR) image captured by an IR camera. The method includes: providing a first image of a subject captured by a first camera and a second image of the subject captured by a second camera; converting brightness of the second image based on brightness of the first image; and merging the first image and the second image having the converted brightness.

Abstract: An image processing method of separating an input image into a foreground image and a background image, the method including determining a pixel of the input image as a pixel of the foreground image if a foreground probability value of the pixel of the foreground image determined by using the Gaussian mixture model or the pixel determined to be included in a motion region is greater than a setting threshold.

Abstract: Provided is a method of merging or fusing a visible image captured by a visible camera and an infrared (IR) image captured by an IR camera. The method includes: providing a first image of a subject captured by a first camera and a second image of the subject captured by a second camera; converting brightness of the second image based on brightness of the first image; and merging the first image and the second image having the converted brightness.

Abstract: A method and system of generating a super-resolution image is provided. fusing The method includes inputting an image; and generating an estimated high-resolution image of a current time by fusing an input image and an estimated high-resolution image of a previous time corresponding to the input image.

Abstract: An image processing method of separating an input image into a foreground image and a background image, the method including determining a pixel of the input image as a pixel of the foreground image if a foreground probability value of the pixel of the foreground image determined by using the Gaussian mixture model or the pixel determined to be included in a motion region is greater than a setting threshold.

Abstract: A method and system of generating a super-resolution image is provided. fusing The method includes inputting an image; and generating an estimated high-resolution image of a current time by fusing an input image and an estimated high-resolution image of a previous time corresponding to the input image.