-
公开(公告)号：US20200074158A1
公开(公告)日：2020-03-05
申请号：US16213833
申请日：2018-12-07
Inventor： Do-Hyung KIM , Jin-Hyeok JANG , Jae-Hong KIM , Sung-Woong SHIN , Jae-Yeon LEE , Min-Su JANG
Abstract: Disclosed herein are a human behavior recognition apparatus and method. The human behavior recognition apparatus includes a multimodal sensor unit for generating at least one of image information, sound information, location information, and Internet-of-Things (IoT) information of a person using a multimodal sensor, a contextual information extraction unit for extracting contextual information for recognizing actions of the person from the at least one piece of generated information, a human behavior recognition unit for generating behavior recognition information by recognizing the actions of the person using the contextual information and recognizing a final action of the person using the behavior recognition information and behavior intention information, and a behavior intention inference unit for generating the behavior intention information based on context of action occurrence related to each of the actions of the person included in the behavior recognition information.
-
公开(公告)号：US20160156834A1
公开(公告)日：2016-06-02
申请号：US14952992
申请日：2015-11-26
Inventor： Do-Hyung KIM , Seong-Jin PARK , Il-Kyu PARK , Chang-Joon PARK , Jin-Sung CHOI
CPC classification number: H04N9/045 , G03B35/10 , H04N5/2254 , H04N5/23229
Abstract: An apparatus and method for capturing a light field image. The light field image capture apparatus includes a mirror array or a micro-lens array. An activated mirror selected from among the multiple mirrors of the mirror array provides light to the multiple elements of an image sensor. An activated lens, selected from among the multiple lenses of the micro-lens array, provides light to the multiple elements of the image sensor. Based on timesharing, the mirror, selected as the activated mirror from among the multiple mirrors, is changed, and the lens, selected as the activated lens from among the multiple lenses, is changed.
Abstract translation: 一种用于捕获光场图像的装置和方法。 光场图像捕获装置包括反射镜阵列或微透镜阵列。 从镜阵列的多个反射镜中选择的激活反射镜向图像传感器的多个元件提供光。 从微透镜阵列的多个透镜中选择的激活透镜向图像传感器的多个元件提供光。 基于分时，改变从多个反射镜中选择为激活反射镜的反射镜，并且从多个透镜中选择为被激活的透镜的透镜被改变。
-
3.发明申请APPARATUS AND METHOD FOR PROVIDING ACTIVITY RECOGNITION BASED APPLICATION SERVICE 有权提供基于活动识别的应用服务的装置和方法公开(公告)号：US20150092981A1
公开(公告)日：2015-04-02
申请号：US14162177
申请日：2014-01-23
Inventor： Do-Hyung KIM , Jae Hong KIM , Kye Kyung KIM , Youngwoo YOON , Woo han YUN , Ho sub YOON , Jae Yeon LEE , SUYOUNG CHI , Young-Jo CHO , Kyu-Dae BAN , Jong-Hyun PARK
CPC classification number: G06K9/00342 , G06K9/6269 , G06K2009/4666
Abstract: An apparatus includes an image receiving module configured to collect a depth image provided from a camera, a human body detection module configured to detect a human body from the collected depth image, and an activity recognition module configured to recognize an action of the human body on the basis of a 3-dimensional action volume extracted from the human body and a previously learned action model.
Abstract translation: 一种装置，包括图像接收模块，被配置为收集从相机提供的深度图像，人体检测模块，被配置为从所收集的深度图像中检测人体;以及活动识别模块，被配置为识别人体的动作 从人体提取的三维动作体的基础和先前学习的动作模型。
-
公开(公告)号：US20140348380A1
公开(公告)日：2014-11-27
申请号：US14163265
申请日：2014-01-24
Inventor： Youngwoo YOON , Woo han YUN , Ho sub YOON , Jae Yeon LEE , Do-Hyung KIM , Jae Hong KIM , Jong-Hyun PARK
IPC: G06K9/00
CPC classification number: G06K9/32 , G06K2009/3291 , G06T7/246 , G06T2207/10024 , G06T2207/10028 , G06T2207/30196 , G06T2207/30232
Abstract: A method for tracking an object in an object tracking apparatus includes receiving an image frame of an image; and detecting a target, a depth analogous obstacle and an appearance analogous obstacle; tracking the target, the depth analogous obstacle and the appearance analogous obstacle; when the detected target overlaps the depth analogous obstacle, comparing the variation of tracking score of the target with that of the depth analogous obstacle. Further, the method includes continuously tracking the target when the variation of tracking score of the target is below that of the depth analogous obstacle and processing a next frame when the variation of tracking score of the target is above that of the depth analogous obstacle; and re-detecting the target.
Abstract translation: 一种用于跟踪对象跟踪装置中的对象的方法包括：接收图像的图像帧; 并且检测目标，深度类似障碍物和外观类似障碍物; 跟踪目标，深度类似障碍和外观类似障碍; 当检测到的目标与深度类似障碍物重叠时，将目标的跟踪得分的变化与深度类似障碍物的变化进行比较。 此外，当目标的跟踪得分的变化低于深度类似障碍物的跟踪得分的变化并且当目标的跟踪得分的变化高于深度类似障碍物的变化时处理下一帧，该方法包括连续跟踪目标; 并重新检测目标。
-
5.发明申请APPARATUS AND METHOD FOR INFORMING BUS DRIVER OF INTENTION TO GET ON OR OFF BUS 审中-公开用于通知总线驱动器以接通或关闭总线的装置和方法公开(公告)号：US20140210650A1
公开(公告)日：2014-07-31
申请号：US13958344
申请日：2013-08-02
Inventor： Do-Hyung KIM , Jae-Ho Lee , Choong-Bum Park , Jin-Suk Ma , Cheol Ryu , Seok-Jin Yoon , Hyung-Seok Lee
IPC: G08G1/123
CPC classification number: G08G1/133
Abstract: Disclosed herein are an apparatus and method for informing a bus driver of a user's intention to get on or off a bus. The apparatus for informing a bus driver of a user's intention to get on or off a bus includes a getting-on information collection device. The getting-on information collection device includes a getting-on information reception unit, an arrival-expected bus identification unit, and a transmission information transmission unit. The getting-on information reception unit receives getting-on information entered by a passenger who desires to get on a bus at a bus stop via a getting-on information transfer device of the bus stop. The arrival-expected bus identification unit identifies a bus expected to arrive having the earliest expected arrival time at the bus stop based on a bus number. The transmission information transmission unit transmits the transmission information to the getting-on information notification device of the bus expected to arrive.
Abstract translation: 这里公开了一种用于向总线驱动程序通知用户打开或关闭总线的设备和方法。 用于向总线驱动器通知用户打开或关闭总线的装置包括上载信息收集装置。 上载信息收集装置包括上载信息接收单元，到达预期总线识别单元和发送信息发送单元。 接收信息接收单元接收乘客希望通过公共汽车站的上传信息传送装置在公共汽车站上乘坐公共汽车输入的接入信息。 到达预期的公共汽车识别单元基于总线号来识别预期在公共汽车站处有最早预期到达时间的预期的公共汽车。 发送信息发送单元将发送信息发送到预期到达的总线的接通信息通知装置。
-
Patent Agency Ranking
公开(公告)号：US20240127587A1
公开(公告)日：2024-04-18
申请号：US18479499
申请日：2023-10-02
Inventor： Do-Hyung KIM , Ho-Beom JEON , Hyung-Min KIM , Jae-Hong KIM , Jeong-Dan CHOI
Abstract: Disclosed herein is a method for integrated anomaly detection. The method includes detecting a thing object and a human object in input video using a first neural network, and tracking the human object, and detecting an anomalous situation based on an object detection result and a human object tracking result.
-
公开(公告)号：US20220024046A1
公开(公告)日：2022-01-27
申请号：US17082843
申请日：2020-10-28
Inventor： Min-Su JANG , Do-Hyung KIM , Jae-Hong KIM , Jae-Yeon LEE
Abstract: Disclosed herein are an apparatus and method for determining a modality of interaction between a user and a robot. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform recognizing a user state and an environment state by sensing circumstances around a robot, determining an interaction capability state associated with interaction with a user based on the recognized user state and environment state, and determining the interaction behavior of the robot for the interaction with the user based on the user state, the environment state, and the interaction capability state.
-
公开(公告)号：US20150187061A1
公开(公告)日：2015-07-02
申请号：US14317238
申请日：2014-06-27
Inventor： Seong-Jin PARK , Bon-Ki KOO , Jin-Sung CHOI , Do-Hyung KIM , Il-Kyu PARK
CPC classification number: G06T3/0068 , G06T7/344 , G06T2207/10028 , G06T2207/20212 , G06T2207/30036
Abstract: An apparatus includes: an input/output interface configured to have a reference surface model and a floating surface model inputted thereto; a memory having instructions for registration of the reference surface model and the floating surface model stored therein; and a processor configured for registration of the reference surface model and the floating surface model according to the instructions. The instructions perform: selecting initial transformation parameters corresponding to the floating surface model by comparing depth images of the reference surface model and the floating surface model; transforming the floating surface model according to the initial transformation parameters; calculating compensation transformation parameters through a matrix calculated by applying singular value decomposition to a cross covariance matrix between the reference surface model and the floating surface model; and transforming the floating surface model according to the compensation transformation parameters, and executing registration of the reference surface model and the floating surface model.
Abstract translation: 一种装置包括：输入/输出接口，被配置为具有输入到其的参考表面模型和浮动表面模型; 存储器，其具有用于登记参考表面模型和存储在其中的浮动表面模型的指令; 以及处理器，其被配置为根据所述指令注册所述参考表面模型和所述浮动表面模型。 指令执行：通过比较参考表面模型和浮动表面模型的深度图像来选择与浮动表面模型对应的初始变换参数; 根据初始变换参数变换浮动表面模型; 通过将参考表面模型和浮动表面模型之间的交叉协方差矩阵应用奇异值分解计算出的矩阵来计算补偿变换参数; 并根据补偿变换参数变换浮动表面模型，并执行参考表面模型和浮动表面模型的注册。
-
公开(公告)号：US20140218516A1
公开(公告)日：2014-08-07
申请号：US13933074
申请日：2013-07-01
Inventor： Do-Hyung KIM , Ho sub YOON , Jae Yeon LEE , Kyu-Dae BAN , Woo han YUN , Youngwoo YOON , Jae Hong KIM , Young-Jo CHO , Suyoung CHI , Kye Kyung KIM
IPC: H04N7/18
CPC classification number: H04N7/18 , G06K9/00335 , G06K9/00369 , G06K9/00664
Abstract: A human information recognition method includes analyzing sensor data from multi-sensor resource placed in a recognition space to generate human information based on the sensor data, the human information including an identity, location and activity information of people existed in the recognition space. Further, the human information recognition method includes mixing the human information based on the sensor data with human information, the human information being acquired through interaction with the people existed in the recognition space; and storing a human model of the people existed in the recognition space depending on the mixed human information in a database unit.
Abstract translation: 一种人类信息识别方法，包括从放置在识别空间中的多传感器资源分析传感器数据，基于传感器数据生成人类信息，所述人类信息包括识别空间中存在的人的身份，位置和活动信息。 此外，人类信息识别方法包括将基于传感器数据的人类信息与人类信息进行混合，通过与存在于识别空间中的人相互作用来获取人类信息; 并且根据数据库单元中的混合人类信息，存储人的人类模型存在于识别空间中。
-
10.发明申请公开(公告)号：US20250095478A1
公开(公告)日：2025-03-20
申请号：US18676563
申请日：2024-05-29
Inventor： Byung-Ok HAN , Do-Hyung KIM , Jae-Hong KIM , Woo-Han YUN
Abstract: Disclosed herein are an apparatus and method for providing crosswalk pedestrian guidance based on an image and a beacon. The method for providing crosswalk pedestrian guidance based on an image and a beacon may include estimating a walking location based on a beacon signal corresponding to at least one traffic light and first-person view sensor information, analyzing a hazard factor around a pedestrian based on an image acquired from a camera corresponding to the traffic light, predicting a hazard around the pedestrian in combination by considering together the walking location, the hazard factor, and status information of the traffic light, and providing walking guidance to a pedestrian guidance terminal based on the predicted hazard around the pedestrian.
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.021 seconds)
