-
公开(公告)号：US20210039726A1
公开(公告)日：2021-02-11
申请号：US16976922
申请日：2018-12-31
Inventor： Jinguo LIU , Xing LI , Jian DING , Yuwang LIU
IPC: B62D55/075 , B62D55/065 , B62D55/125 , B62D55/08
Abstract: A reconfigurable joint track compound mobile robot has a main vehicle body, yaw joints and an auxiliary track module. The main vehicle body has a main track, and a clutch brake and a first wheel joint arranged in a main track driving wheel. A second wheel joint is arranged in a main track driven wheel. The main vehicle body is provided with main track driving mechanisms and a wheel joint driving mechanism. The main track driving wheel is driven to rotate by the main track driving mechanisms, which are connected with the clutch brake. The second wheel joint is driven to rotate by the wheel joint driving mechanism. Each wheel joint is correspondingly connected with the yaw joints, which are rotatably connected with the auxiliary track module. A yaw driving mechanism that drives the auxiliary track module to swing is arranged in each yaw joint.
-
公开(公告)号：US10915815B1
公开(公告)日：2021-02-09
申请号：US16971691
申请日：2019-04-19
Inventor： Guanxiong Zeng , Yang Chen , Shan Yu
Abstract: An information processing method based on contextual signals and a prefrontal cortex-like network includes: selecting a feature vector extractor based on obtained information to perform feature extraction to obtain an information feature vector; inputting the information feature vector into the prefrontal cortex-like network, and performing dimensional matching between the information feature vector and each contextual signal in an input contextual signal set to obtain contextual feature vectors to constitute a contextual feature vector set; and classifying each feature vector in the contextual feature vector set by a feature vector classifier to obtain classification information of the each feature vector to constitute a classification information set. An information processing system based on contextual signals and a prefrontal cortex-like network includes an acquisition module, a feature extraction module, a dimensional matching module, a classification module and an output module.
-
公开(公告)号：US10818311B2
公开(公告)日：2020-10-27
申请号：US16632373
申请日：2018-11-14
Inventor： Jiaming Xu , Jing Shi , Bo Xu
IPC: G10L21/00 , G10L21/0272 , G06F17/16 , G06N3/04 , G10L25/30
Abstract: An auditory selection method based on a memory and attention model, including: step S1, encoding an original speech signal into a time-frequency matrix; step S2, encoding and transforming the time-frequency matrix to convert the matrix into a speech vector; step S3, using a long-term memory unit to store a speaker and a speech vector corresponding to the speaker; step S4, obtaining a speech vector corresponding to a target speaker, and separating a target speech from the original speech signal through an attention selection model. A storage device includes a plurality of programs stored in the storage device. The plurality of programs are configured to be loaded by a processor and execute the auditory selection method based on the memory and attention model. A processing unit includes the processor and the storage device.
-
公开(公告)号：US10596056B2
公开(公告)日：2020-03-24
申请号：US15326132
申请日：2014-07-15
Inventor： Zengguang Hou , Liang Peng , Weiqun Wang , Long Cheng , Guibin Bian , Xiaoliang Xie
IPC: A61H1/00 , A63B23/12 , A63B24/00 , A63B21/00 , A63B21/005 , A61H1/02 , A63B23/035 , A63B71/06 , G09B5/02
Abstract: The present invention discloses an upper limb rehabilitation robot system comprising a computer (8) and a rehabilitation robot (7), wherein the computer (8) is used for performing information interaction (11) with the rehabilitation robot (7), recording training information, sending control command to the rehabilitation robot (7), showing the virtual training environment, providing rehabilitation training visual feedback (14), and showing the control interface and rehabilitation training information; wherein the rehabilitation robot (7), acting as a system actuator, is connected to the computer (8) for receiving the control command from the computer (8) to complete the motion control and terminal force output, and sending sensor data to the computer (8) at the same time. The upper limb rehabilitation robot system according to the present invention may provide a various ways of active and passive training of upper limb rehabilitation, which can enhance enthusiasm for trainings of a patient and increase the efficiency of rehabilitation.
-
公开(公告)号：US10564103B2
公开(公告)日：2020-02-18
申请号：US15534882
申请日：2014-12-10
Inventor： Jie Tian , Yamin Mao , Chongwei Chi , Xin Yang
IPC: A62B1/04 , G01N21/64 , H04N5/33 , H04N5/247 , H04N5/232 , G01N21/25 , G02B23/24 , G01N21/359 , H04N5/372 , H04N5/225 , G02B23/26
Abstract: A dual-mode optical molecular imaging navigation apparatus with a switchable field of view, and an imaging method thereof, are provided in the embodiments of the disclosure, the apparatus including: a camera module configured to perform a color imaging and a fluorescence imaging; a switching module configured to switch between an open imaging mode and an endoscopic imaging mode as per imaging requirements; an open imaging module configured to perform observation and imaging with a large field of view; an endoscopic imaging module configured to perform observation and imaging with a deep field of view; a data processing module configured to provide a camera control software and image capturing, processing and display method; and a support module configured to support and connect the navigation apparatus.
-
Patent Agency Ranking
36.发明申请公开(公告)号：US20200026941A1
公开(公告)日：2020-01-23
申请号：US16488600
申请日：2017-06-23
Inventor： Tieniu TAN , Jing DONG , Wei WANG , Bo PENG
Abstract: A perspective distortion characteristic based facial image authentication method and storage and processing device thereof are proposed. The method includes: S1: recognizing key points and a contour in a 2D facial image; S2: acquiring key points in a corresponding 3D model; S3: calculating camera parameters based on a correspondence between the key points in the 2D image and the key points in the 3D model; S4: optimizing the camera parameters based on the contour in the 2D image; S5: sampling the key points in the two-dimensional facial image by multiple times to obtain a camera intrinsic parameter estimation point cloud; and S6: calculating the inconsistency between the camera intrinsic parameter estimation point cloud and the camera nominal intrinsic parameters, and determining the authenticity of the facial image. The present disclosure can effectively authenticate the 2D image and has a relatively higher accuracy.
-
公开(公告)号：US10540768B2
公开(公告)日：2020-01-21
申请号：US15217141
申请日：2016-07-22
Inventor： Byungin Yoo , Jungbae Kim , Chang Kyu Choi , Jaejoon Han , Yongzhen Huang , Liang Wang
IPC: G06T7/11
Abstract: A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.
-
38.发明申请公开(公告)号：US20180247180A1
公开(公告)日：2018-08-30
申请号：US15753520
申请日：2015-08-21
Inventor： Jian Cheng , Jiaxiang Wu , Cong Leng , Hanqing Lu
CPC classification number: G06N3/04 , G06F17/16 , G06K9/4628 , G06K9/6243 , G06K9/6274 , G06N3/0454 , G06N3/08 , G06N20/00
Abstract: An acceleration and compression method for a deep convolutional neural network based on quantization of a parameter provided by the present application comprises: quantizing the parameter of the deep convolutional neural network to obtain a plurality of subcode books and respective corresponding index values of the plurality of subcode books; acquiring an output feature map of the deep convolutional neural network according to the plurality of subcode books and respective corresponding index values of the plurality of subcode books. The present application may implement the acceleration and compression for a deep convolutional neural network.
-
公开(公告)号：US20180133088A1
公开(公告)日：2018-05-17
申请号：US15559819
申请日：2015-03-20
Inventor： Zengguang Hou , Weiqun Wang , Long Peng , Xu Liang , Liang Peng , Long Cheng , Xiaoliang Xie , Guibin Bian , Min Tan , Lincong Luo
IPC: A61H1/02 , A63B21/00 , A63B21/005
Abstract: The application presents a multi-posture lower limb rehabilitation robot, which includes a robot base and a training bed. The training bed comprises two sets of leg mechanisms, a seat, a seat width adjustment mechanism, a mechanism for adjusting the gravity center of human body, a back cushion, a weight support system and a mechanism for adjusting the back cushion angle. The robot base comprises a mechanism for adjusting the bed angle. The mechanisms for adjusting the angles of bed and back cushion can be used together to provide paralysis patients with multiple training modes of lying, sitting, and standing postures. Each leg mechanism comprises hip, knee, and ankle joints, which are driven by electric motors; angle and force sensors are installed on each joint, and can be used to identify patients' motion intention to provide patients with active and assistant training. The mechanism for adjusting the gravity center of human body, the leg mechanisms, and the weight support system can be used together to implement human natural walking gait to improve the training effect.
-
公开(公告)号：US20180061014A1
公开(公告)日：2018-03-01
申请号：US15557082
申请日：2015-04-16
Inventor： Ruoshan GUO , Lu YE , Rui HAN , Renjun TANG , Yang LUO , Fengli YAN , Xiaoli TANG
CPC classification number: G06T5/002 , G06T5/20 , G06T7/20 , G06T2207/20182 , G06T2207/20201 , H04N5/21
Abstract: The present invention discloses a contrast adaptive video denoising system, which comprises a frame memory for buffering the filtered frame; an inter-frame difference calculating module for inter-frame difference of the current input frame of the video and a previous filtered frame in the frame memory; a contrast calculating module for calculating the local contrast of the current input frame and inputting it into a low-contrast region detection module, a calculated low-contrast region confidence together with the inter-frame difference are input into a motion detection module to calculate the motion probability for each pixel. The motion adaptive temporal filtering module performs motion adaptive temporal filtering by using the current input frame of the video and the previous filtered frame in the frame memory as well as the motion probability of each pixel, and finally outputs the current filtered frame to store in the frame memory. Said system can solve the problems of motion tailing and blurring caused by conventional video denoising systems when processing low-contrast motion videos.
-
-
-
-
-
-
-
-
-
Search Results
243
records
(took 0.027 seconds)
