-
公开(公告)号：US11947061B2
公开(公告)日：2024-04-02
申请号：US16992246
申请日：2020-08-13
Inventor： Hanseok Ko , Bon Hwa Ku
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.
-
Patent Agency Ranking
公开(公告)号：US10923126B2
公开(公告)日：2021-02-16
申请号：US15557378
申请日：2015-03-19
Inventor： Hanseok Ko , Sung-soo Kim , Taeyup Song , Kyungsun Lee , Jae-won Lee
Abstract: Provided is a method of detecting a voice section, including detecting from at least one image an area where lips exist, obtaining a feature value of movement of the lips in the detected area based on a difference between pixel values of pixels included in the detected area, and detecting the voice section from the at least one image based on the feature value.
-
公开(公告)号：US09842382B2
公开(公告)日：2017-12-12
申请号：US14888852
申请日：2014-04-11
Inventor： Dubok Park , Hanseok Ko
CPC classification number: G06T5/001 , G06T5/003 , G06T2207/10016 , G06T2207/20192 , H04N5/361 , H04N5/3651
Abstract: The present invention provides a method for removing a haze in a single image. In the present invention, a transmission is estimated by using a dark channel prior obtained from a hazy input image. The estimated transmission includes a block artifact. In an exemplary embodiment of the present invention, in order to preserve an edge and remove the block artifact, a refined transmission value is obtained by performing WLS filtering by using an estimated transmission value and a morphologically-processed input image, the image is restored based on the refined transmission value, and then multi-scale tone manipulation image processing is performed.
-
公开(公告)号：US09451214B2
公开(公告)日：2016-09-20
申请号：US13667804
申请日：2012-11-02
Inventor： Hanseok Ko , Younghyun Lee , Kwangyoun Kim , Bonhwa Ku , Taeyup Song , Hanjun Kim
CPC classification number: H04N7/18 , G06K9/00771 , G06K9/6277 , G06T7/11 , G06T7/194 , G06T2207/30232
Abstract: A surveillance system and method are provided. The surveillance system includes an audio processing device which extracts an audio feature of an audio signal, and determines whether an abnormal event has occurred in a monitoring region, based on the audio feature; a video processing device which extracts a foreground region from a video signal, and determines whether an abnormal event has occurred in the monitoring region, based on motion information of the foreground region; and a context awareness device which calculates an audio abnormal probability and a video abnormal probability by respectively accumulating results of abnormal event occurrence/non-occurrence determinations performed on audio signals and results of abnormal event occurrence/non-occurrence determinations performed on video signals for a certain period of time, and finally determines whether an abnormal situation has occurred in the monitoring region, by using respective combined probability distribution models for a normal situation and the abnormal situation.
Abstract translation: 提供了一种监视系统和方法。 监视系统包括音频处理装置，其提取音频信号的音频特征，并且基于音频特征确定监视区域中是否发生异常事件; 视频处理装置，从视频信号中提取前景区域，根据前景区域的运动信息，判定监视区域是否发生异常事件; 以及上下文感知装置，其通过分别累积对音频信号执行的异常事件发生/不存在确定的结果以及对视频信号执行的异常事件发生/不存在确定的结果来计算音频异常概率和视频异常概率 通过对正常情况和异常情况使用各自的组合概率分布模型，最终确定监控区域是否发生异常情况。
-
公开(公告)号：US10410638B2
公开(公告)日：2019-09-10
申请号：US15553819
申请日：2015-02-27
Inventor： Hanseok Ko , Sung-soo Kim , Jinsang Rho , Suwon Shon , Jae-won Lee
Abstract: A method of converting a feature vector includes extracting a feature sequence from an audio signal including utterance of a user; extracting a feature vector from the feature sequence; acquiring a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values; and converting the feature vector by using the conversion matrix.
-
公开(公告)号：US11830272B2
公开(公告)日：2023-11-28
申请号：US17279661
申请日：2019-04-18
Inventor： Hanseok Ko , Sangwook Park , Kyung-Deuk Ko , Donghyeon Kim
CPC classification number: G06V40/10 , G06F18/217 , G06F18/254 , G06N3/02 , G10L17/26
Abstract: Disclosed are a method and an apparatus for identifying animal species by using audiovisual information. A method for identifying animal species, according to one embodiment of the present invention, may include: a step of receiving an input signal for an object to be identified; a step of processing image information and acoustic information based on the input signal, wherein a processing result of the image information and a processing result of the acoustic information are represented by class-specific scores; a step of determining whether the image information processing result and the acoustic information processing result corresponding to the input signal exist; and a final result derivation step of fusing the image information processing result and the acoustic information processing result according to the determination result and classifying the object to be identified as a certain animal species by using the fused processing result.
-
-
-
-
-
Search Results
6
records
(took 0.014 seconds)
