-
公开(公告)号：US10410326B2
公开(公告)日：2019-09-10
申请号：US15557081
申请日：2015-04-16
Inventor： Ruoshan Guo , Rui Han , Renjun Tang
Abstract: The present invention discloses an image anti-aliasing system, which comprises an edge detection unit, a directional filter, a low-angle directional filter, a directional filtering fusion unit and a result fusion unit; the edge detection unit outputs the edge direction and edge confidence according to an input image, the directional filter outputs a directional filtering result based on the input image and the edge direction, the low-angle directional filter outputs a low-angle directional filtering result according to the input image and the edge direction; the directional filtering fusion unit weights and combines the result output from the directional filter and the result output from the low-angle directional filter according to the edge direction, and outputs a result of weighted combination of two directional filtering results; the result fusion unit outputs an optimized image according to the edge confidence, the input image and the result of the directional filtering fusion unit. The present invention can well handle directional filtering in any direction and it has good effect to low-angle aliasing.
-
公开(公告)号：US10278333B2
公开(公告)日：2019-05-07
申请号：US15314068
申请日：2014-05-26
Inventor： Zhen Shen , Mengzhen Kang , Jiantong Li , Feiyue Wang
Abstract: A pruning robot system, which comprises: a signal tag device (2) for detecting and storing information of trees and crops and positioning information, and assisting positioning; a robot (1) comprising a central processing device (10) for storing and analyzing data information of each part of the robot (1) and issuing action instructions to each part of the robot (1), and a positioning and navigating device (11) for positioning and navigating the robot (1), and for planning a path and providing obstacle-avoiding navigation for the robot (1) according to an electronic map; a cloud platform terminal (3), which is in connection and communication with the central processing device (10) of the robot (1) and is used for storing data of trees and crops as well as detection data of the robot (1), and for planning a path for the robot (1) through computing and experimenting according to the information data; a map building device (4) for building a three-dimensional electronic map corresponding to the plantation through field-detection by the robot (1). The pruning robot system realizes positioning in the plantation, robot (1) path planning, pruning information collection and automatic pruning.
-
133.发明授权公开(公告)号：US10261502B2
公开(公告)日：2019-04-16
申请号：US15527208
申请日：2014-12-30
Inventor： Wenli Shang , Jianming Zhao , Ming Wan , Peng Zeng , Haibin Yu
IPC: H04L29/06 , G05B19/418 , H04L12/40
Abstract: Proposed is an anomaly detection method for communication behaviors in an industrial control system based on an OCSVM algorithm. According to the present invention, a normal behavior profile model and an abnormal behavior profile model, i.e. a dual-outline model, of communication behaviors in an industrial control system are established, parameter optimization is performed by means of a particle swarm optimization (PSO) algorithm, an optimal intrusion detection model is obtained, and abnormal Modbus TCP communication traffic is identified. According to the present invention, the false alarm rate is reduced by means of cooperative discrimination of the dual-outline detection model, the efficiency and reliability of anomaly detection are improved, and the method is more applicable to practical applications.
-
134.发明授权公开(公告)号：US10252029B2
公开(公告)日：2019-04-09
申请号：US14770232
申请日：2013-06-25
Inventor： Zengguang Hou , Guibin Bian , Xiaoliang Xie , Long Cheng , Min Tan , Zhenqiu Feng , Xiaohu Zhou
Abstract: A catheter or guide wire manipulating device with two-point-clamping for vascular intervention is provided, comprising a thumb component (3), a forefinger component (4), a driving component (1) and a catheter/guide wire support component (2); the thumb component (3) comprises a pair of rollers (9, 10) configured to advance or retreat the catheter/guide wire; the thumb component (3) is configured to drive the catheter/guide wire to rotate clockwise or counterclockwise through a combination motion of the components; the forefinger component (4) is configured to implement the rotation and the advancement of the catheter/guide wire by moving manually away from the thumb component (3), and returning by a pull force of a spring (27) after being released; the driving component (2) is configured to drive the thumb component (3) and the forefinger component (4); the catheter/guide wire support component comprises a Y adapter fixation configured to install a Y adapter and an entry support configured to support and guide the catheter/guide wire into a mechanism.
-
公开(公告)号：US10223780B2
公开(公告)日：2019-03-05
申请号：US15557080
申请日：2015-04-15
Inventor： Tieniu Tan , Jing Dong , Wei Wang , Yinlong Qian
Abstract: The present invention provides a method for detecting image steganography based on deep learning, which comprises: filtering images having steganographic class label or true class label in a training set with a high-pass filter to obtain a training set including steganographic class residual images and true class residual images; training a deep network model on said training set to obtain a trained deep model for steganalysis; filtering the image to be detected with said high-pass filter to obtain a residual image to be detected; detecting said residual image to be detected on said deep model so as to determine whether said residual image to be detected is a steganographic image. The method for detecting image steganography in the present invention can create an automatic blind steganalysis model through feature learning and can identify steganographic images accurately.
-
Patent Agency Ranking
136.发明授权公开(公告)号：US10121535B2
公开(公告)日：2018-11-06
申请号：US15551008
申请日：2015-03-27
Inventor： Jingqiu Wang , Liang Chen , Li Liu
IPC: G11C11/34 , G11C11/417 , H01L27/11 , G11C11/412
Abstract: The memory cell of static random access memory based on resistance-capacitance reinforcement, which comprises a latch circuit and a bit selection circuit, the latch circuit consists of two PMOS transistors P1 and P2, two NMOS transistors N1 and N2, a first resistance-capacitance network and a second resistance-capacitance network; the bit selection circuit consists of NMOS transistors N5 and N6; the latch circuit forms four storage nodes X1, X1B, X2, X2B, among which a coupling capacitor C is provided between a pair of complementary data storage nodes. Compared to the conventional memory cell of 6T structure, a resistance-capacitance network and a coupling capacitor are added, so that without changing the original read operation circuit and without obviously increasing complexity, the memory cell is prevented from having single event upset merely at a cost of increasing a small amount of area, thus ensuring correctness of data.
-
公开(公告)号：US10026202B2
公开(公告)日：2018-07-17
申请号：US15289535
申请日：2016-10-10
Inventor： Jie Tian , Kunshan He , Chongwei Chi , Xin Yang
CPC classification number: G06T11/003 , A61B5/0075 , A61B5/6803 , G01B11/00 , G01B11/24 , H04N5/2256 , H04N5/2258 , H04N5/332
Abstract: The invention discloses a wearable molecular imaging navigation system comprising: a multi-spectral light transceiver configured to transmit a multi-spectral light to a detected subject in a detection region and acquire an emitting light regarding the detected subject and acquire a reflecting light regarding the detected subject; an image processor configured to receive the reflecting light and the emitting light from the multi-spectral light transceiver, execute a three-dimensional reconstruction and fusion process on the reflecting light and the emitting light to obtain a fusion image; a wireless signal processor configured to enable a wireless communication; and a wearable device, configured to receive the fusion image from the image processor via the wireless signal processor, display the fusion image and control the multi-spectral light transceiver and the image processor based on instructions received.
-
公开(公告)号：US20180174648A1
公开(公告)日：2018-06-21
申请号：US15551024
申请日：2015-03-27
Inventor： Li Liu , Jingqiu Wang , Liang Chen
IPC: G11C11/419 , H01L27/11 , G06F3/06
CPC classification number: G11C11/419 , G06F3/0619 , G11C11/4125 , G11C29/74 , H01L27/11
Abstract: The present invention provides a memory cell of a static random access memory based on DICE structure, which comprises a redundant information latch circuit and a redundant bit selection circuit; the redundant information latch circuit is formed by four MOS transistors and includes four data storage nodes; the redundant bit selection circuit is also formed by four MOS transistors M0, M1, M2 and M3, with their drains connected to the four data storage nodes X0, X1, X2 and X3; wherein sources of M0 and M2 are connected to each other and are connected to a bit line BL, sources of M1 and M3 are connected to each other and are connected to a bit line BLB; and gates of the four MOS transistors are connected to each other and are connected to a word line WL. By means of the present invention, without obviously increasing complexity and merely increasing a small amount of area, the memory cell can be prevented from having a state reversal when hit by particles, thus ensuring correctness of data.
-
公开(公告)号：US09996939B2
公开(公告)日：2018-06-12
申请号：US15307805
申请日：2014-04-30
Inventor： Kaiqi Huang , Lijun Cao , Weihua Chen
CPC classification number: G06T7/246 , G06K9/00771 , G06K9/4642 , G06K9/4652 , G06K9/6212 , G06K9/6215 , G06T7/215 , G06T7/277 , G06T7/292 , G06T2207/30241
Abstract: The present invention relates to a large-range-first cross-camera visual target re-identification method. The method comprises: step S1, obtaining initial single-camera tracks of targets; step S2, calculating a piecewise major color spectrum histogram feature of each track, and obtaining a track feature representation; step S3, obtaining a calculation formula of the similarity between any two tracks by using a minimum uncertainty method, so as to obtain the similarity between any two tracks; and step S4, performing global data association on all the tracks by using a maximum posterior probability method, so as to obtain a cross-camera tracking result. The target re-identification method of the present invention achieves high correct identification accuracy.
-
公开(公告)号：US20180061013A1
公开(公告)日：2018-03-01
申请号：US15557081
申请日：2015-04-16
Inventor： Ruoshan GUO , Rui HAN , Renjun TANG
CPC classification number: G06T5/002 , G06T5/20 , G06T7/13 , G06T11/60 , G06T2207/20192
Abstract: The present invention discloses an image anti-aliasing system, which comprises an edge detection unit, a directional filter, a low-angle directional filter, a directional filtering fusion unit and a result fusion unit; the edge detection unit outputs the edge direction and edge confidence according to an input image, the directional filter outputs a directional filtering result based on the input image and the edge direction, the low-angle directional filter outputs a low-angle directional filtering result according to the input image and the edge direction; the directional filtering fusion unit weights and combines the result output from the directional filter and the result output from the low-angle directional filter according to the edge direction, and outputs a result of weighted combination of two directional filtering results; the result fusion unit outputs an optimized image according to the edge confidence, the input image and the result of the directional filtering fusion unit. The present invention can well handle directional filtering in any direction and it has good effect to low-angle aliasing.
-
-
-
-
-
-
-
-
-
Search Results
243
records
(took 0.026 seconds)
