公开(公告)号：US20180268559A1

公开(公告)日：2018-09-20

申请号：US15817432

申请日：2017-11-20

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jae-Yeong LEE

IPC: G06T7/246 ,  G06T5/40 ,  G06T7/90 ,  G06T7/73 ,  G06T7/60

CPC classification number: G06T7/251 ,  G06T5/40 ,  G06T7/248 ,  G06T7/60 ,  G06T7/74 ,  G06T7/75 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20104

Abstract: Disclosed herein are a method for tracking object in video in real time in consideration of both color and shape and an apparatus for the same. The apparatus may generate at least one of a correlation filter model and a color probability density model based on an input image, determine an initial position and an initial size of a target to be tracked based on a correlation filter response value calculated by applying the correlation filter model to the input image, calculate a joint probability based on the correlation filter response value and a color object probability that is calculated based on the color probability density model, and update an object model corresponding to the target to be tracked based on a final position and a final size of the target to be tracked, which are determined by applying the joint probability to the initial position and the initial size.

公开(公告)号：US20130202210A1

公开(公告)日：2013-08-08

申请号：US13654077

申请日：2012-10-17

Applicant: Electronics And Telecommunications Research Institute

Inventor： Michael Sahngwon RYOO ,  Jae-Yeong LEE ,  Wonpil YU

IPC: G06K9/46

CPC classification number: G06K9/00771 ,  G06K9/4642

Abstract: A method for human activity prediction from streaming videos includes extracting space-time local features from video streams containing video information related to human activities; and clustering the extracted space-time local features into multiple visual words based on the appearance of the features. Further, the method for the human activity prediction includes computing an activity likelihood value by modeling each activity as an integral histogram of the visual words; and predicting the human activity based on the computed activity likelihood value.

Abstract translation: 从流式视频中预测人类活动的方法包括从包含与人类活动相关的视频信息的视频流中提取时空局部特征; 并且基于特征的外观将提取的时空局部特征聚类成多个视觉词。 此外，人类活动预测的方法包括通过将每个活动建模为视觉词的整体直方图来计算活动似然度值; 并基于计算的活动似然值预测人类活动。

公开(公告)号：US20150269734A1

公开(公告)日：2015-09-24

申请号：US14663938

申请日：2015-03-20

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jae-Yeong LEE ,  Myung-Chan ROH

IPC: G06T7/00 ,  G06K9/48 ,  G06K9/00

CPC classification number: G06K9/00798 ,  G01C21/3602 ,  G06K9/00671 ,  G06T7/73 ,  G06T2207/30204 ,  G06T2207/30244 ,  G06T2207/30252

Abstract: Disclosed herein is an apparatus and method for recognizing the location of an object, which recognize the location of an object using an artificial landmark that is easily identifiable in an outdoor environment and that minimizes visual resistance. The presented apparatus includes an image acquisition unit for acquiring an image of an artificial landmark implemented using at least one of a first-type mark and a second-type mark, an artificial landmark detection unit for processing the image acquired by the image acquisition unit and detecting the artificial landmark from the image, a pose calculation unit for calculating a pose of the object based on an image coordinate and a world coordinate of the artificial landmark detected by the artificial landmark detection unit, and a pose verification unit for verifying whether the pose of the object calculated by the pose calculation unit are within an effective range.

Abstract translation: 本文公开了一种用于识别物体的位置的装置和方法，其使用在室外环境中容易识别并使视觉阻力最小化的人造地标来识别对象的位置。 所提出的装置包括：图像获取单元，用于获取使用第一类型标记和第二类型标记中的至少一个实现的人造地标的图像;人造地标检测单元，用于处理由图像获取单元获取的图像;以及 从图像中检测人造地标;姿势计算单元，用于基于由人造地标检测单元检测到的人造地标的图像坐标和世界坐标来计算物体的姿态;姿态验证单元，用于验证姿态 由姿态计算单元计算的对象在有效范围内。

公开(公告)号：US20140119609A1

公开(公告)日：2014-05-01

申请号：US13892872

申请日：2013-05-13

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jae-Yeong LEE ,  Wonpil YU

IPC: G06K9/62

CPC classification number: G06K9/6215 ,  G06K9/00785 ,  G06K9/00805

Abstract: An image recognizing apparatus includes a sample image acquiring unit configured to acquire a sample image having one or more target objects therein from a camera; and a reference range setting unit configured to calculate image locations and image heights for the respective target objects from the sample image and set a reference range of the image heights depending on the image positions. Further, the image recognizing apparatus includes a selection unit configured to determine whether a candidate area of each target object in the sample image acquired by the camera falls within the reference range to select an effective candidate area.

Abstract translation: 图像识别装置包括：样本图像获取单元，被配置为从相机获取其中具有一个或多个目标对象的样本图像; 以及参考范围设定单元，被配置为从样本图像计算各个目标对象的图像位置和图像高度，并且根据图像位置设置图像高度的参考范围。 此外，图像识别装置包括：选择单元，被配置为确定由相机获取的样本图像中的每个目标对象的候选区域是否落入参考范围内以选择有效候选区域。