-
1.
公开(公告)号:US20180144478A1
公开(公告)日:2018-05-24
申请号:US15857551
申请日:2017-12-28
Applicant: SHENZHEN UNIVERSITY
Inventor: Jihong Pei , Lixia Wang , Weixin Xie , Xuan Yang
CPC classification number: G06T7/194 , G06K9/0063 , G06K9/522 , G06K9/6267 , G06T5/20 , G06T7/11 , G06T7/143 , G06T7/168 , G06T2207/10032 , G06T2207/20021 , G06T2207/20056 , G06T2207/20076 , G06T2207/30181 , G06T2207/30236
Abstract: The disclosure provides a method for sea background modeling and suppression on high-resolution remote sensing sea images, the method comprises steps of segmentation, classification, calculation, modeling and suppression. The disclosure also provides a system for sea background modeling and suppression on high-resolution remote sensing sea images. The technical solution of the disclosure is provided in such way as to perform sea background suppression first and then detect the target, leading to large improvement of detection accuracy and reduction of false alarm.
-
公开(公告)号:US20180174274A1
公开(公告)日:2018-06-21
申请号:US15838404
申请日:2017-12-12
Applicant: SHENZHEN UNIVERSITY
Inventor: Jihong Pei , Mi Zou , Weixin Xie , Xuan Yang
CPC classification number: G06T5/002 , G06T2207/10048 , H04N5/217 , H04N5/33 , H04N5/3658
Abstract: A method of eliminating stripe noise for infrared images including: selecting a specific row of data from an to-be-filtered image Aim, and obtaining a stripe width N1 from information of a frequency spectrum of the data; intercepting (N1+1) new sequences of different lengths from a specific row sequence of the image according to the stripe width N1, and obtaining an optimal interception length N by analyzing information of amplitude spectrum of each new sequence; splitting the to-be-filtered image Aim with a size of M×Nn into a pair of optimum to-be-filtered sub-images Bim and Cim with a size of M×N according to the length N; obtaining two sub-images Bimf and Cimf after using a notch-comb filter to filter the two optimum to-be-filtered sub-images Bim and Cim; carrying out a brightness adjustment and a combination process to the two sub-image Bimf and Cimf to obtain an image Aimf.
-
公开(公告)号:US10935653B2
公开(公告)日:2021-03-02
申请号:US16236603
申请日:2018-12-30
Applicant: SHENZHEN UNIVERSITY
Inventor: Zongxiang Liu , Liangqun Li , Weixin Xie
IPC: G01S13/72 , G01S13/538
Abstract: A multi-target tracking method applicable to a cluttered environment includes a prediction step, a classification step, an updating step, a pruning and extracting step, a generation step, a supplement step and a combining step. A multi-target tracking system applicable to a cluttered environment is also provided. The present invention has the characteristic of a fast processing speed, and at the same time, effectively solves the problem that the existing method fails to provide state estimation for a new target in the initial few moments after the new target appears.
-
公开(公告)号:US20170169736A1
公开(公告)日:2017-06-15
申请号:US15444308
申请日:2017-02-27
Applicant: SHENZHEN UNIVERSITY
Inventor: Dongning Zhao , Yong Zhang , Weixin Xie , Yanshan Li , Jianping Yu , Jianyong Chen
IPC: G09C1/00
CPC classification number: G09C1/00 , G09C5/00 , H04L2209/16
Abstract: The invention relates to the technical field of data hiding, in particular to a data hiding method and a data hiding system. An image is used as a data carrier; after secret data is converted into a bit sequence by a sending end, the values of each bit in the bit sequence are hidden in the image; the image hidden with the secret data is obtained and is sent to a receiving end; and the receiving end can extract the hidden secret data from the image according to a corresponding secret key. During data hiding, each square image block can hide two-bit data through inverse number odd-even properties of a pixel gray value sequence of two diagonal lines of each square image block, so that the volume of data hidden in the image is twice of the number of the image blocks split by the image.
-
5.
公开(公告)号:US20210358133A1
公开(公告)日:2021-11-18
申请号:US17278972
申请日:2020-09-07
Applicant: Shenzhen University
Inventor: Jihong Pei , Kaiwen Liao , Weixin Xie , Xuan Yang
Abstract: The present application provides a method and a device for estimating background motion of infrared image sequences and a storage medium. The method comprises: determining regions to be matched according to the maximum displacement of two adjacent frames of images in background motion, dividing the region to be matched into T sub-regions, and generating M groups of sub-window sets in the sub-regions randomly, and computing the background motion displacement corresponding to these sub-window sets by synchronous mutual information matching, then calculating the background motion displacement between two adjacent frames of images by a potential function voting method according to the background motion displacement corresponding to these sub-window sets. The method in the present application is based on image block matching, and does not depend on feature point extraction, so it has high robustness for background motion estimation of infrared image sequences with few feature points and noise interference.
-
公开(公告)号:US10334166B2
公开(公告)日:2019-06-25
申请号:US15828403
申请日:2017-11-30
Applicant: SHENZHEN UNIVERSITY
Inventor: Jihong Pei , Kai Sun , Xuan Yang , Weixin Xie
IPC: H04N5/228 , H04N5/232 , H04N7/18 , G06T7/80 , G06T7/30 , G03B37/04 , H04N5/247 , H04N21/218 , H04N21/2365 , G08B13/196
Abstract: The present disclosure relates to a distributed video panoramic display system. The present disclosure collects video images of different areas through an existing camera network; the video images collected by each camera are converted into the same coordinate system by each video splitting node in a video splitting module; a plurality of paths of video image data are subjected to parallel splitting processing, so that a display area of each split video image block in a panoramic display unit respectively corresponds to a separate display screen; and each video reorganization node in a video reorganization module is used to perform reorganization processing on each received video image block, then each path of video image formed after the processing is output to the corresponding display screen of the panoramic display unit, and a panoramic video image is formed.
-
公开(公告)号:US10311757B2
公开(公告)日:2019-06-04
申请号:US15444308
申请日:2017-02-27
Applicant: SHENZHEN UNIVERSITY
Inventor: Dongning Zhao , Yong Zhang , Weixin Xie , Yanshan Li , Jianping Yu , Jianyong Chen
Abstract: The invention relates to the technical field of data hiding, in particular to a data hiding method and a data hiding system. An image is used as a data carrier; after secret data is converted into a bit sequence by a sending end, the values of each bit in the bit sequence are hidden in the image; the image hidden with the secret data is obtained and is sent to a receiving end; and the receiving end can extract the hidden secret data from the image according to a corresponding secret key. During data hiding, each square image block can hide two-bit data through inverse number odd-even properties of a pixel gray value sequence of two diagonal lines of each square image block, so that the volume of data hidden in the image is twice of the number of the image blocks split by the image.
-
8.
公开(公告)号:US11669978B2
公开(公告)日:2023-06-06
申请号:US17278972
申请日:2020-09-07
Applicant: Shenzhen University
Inventor: Jihong Pei , Kaiwen Liao , Weixin Xie , Xuan Yang
CPC classification number: G06T7/223 , G06T7/248 , G06T2207/10016 , G06T2207/10048 , G06T2207/20021
Abstract: The present application provides a method and a device for estimating background motion of infrared image sequences and a storage medium. The method comprises: determining regions to be matched according to the maximum displacement of two adjacent frames of images in background motion, dividing the region to be matched into T sub-regions, and generating M groups of sub-window sets in the sub-regions randomly, and computing the background motion displacement corresponding to these sub-window sets by synchronous mutual information matching, then calculating the background motion displacement between two adjacent frames of images by a potential function voting method according to the background motion displacement corresponding to these sub-window sets. The method in the present application is based on image block matching, and does not depend on feature point extraction, so it has high robustness for background motion estimation of infrared image sequences with few feature points and noise interference.
-
公开(公告)号:US10282824B2
公开(公告)日:2019-05-07
申请号:US15838404
申请日:2017-12-12
Applicant: SHENZHEN UNIVERSITY
Inventor: Jihong Pei , Mi Zou , Weixin Xie , Xuan Yang
Abstract: A method of eliminating stripe noise for infrared images including: selecting a specific row of data from an to-be-filtered image Aim, and obtaining a stripe width N1 from information of a frequency spectrum of the data; intercepting (N1+1) new sequences of different lengths from a specific row sequence of the image according to the stripe width N1, and obtaining an optimal interception length N by analyzing information of amplitude spectrum of each new sequence; splitting the to-be-filtered image Aim with a size of M×Nn into a pair of optimum to-be-filtered sub-images Bim and Cim with a size of M×N according to the length N; obtaining two sub-images Bimf and Cimf after using a notch-comb filter to filter the two optimum to-be-filtered sub-images Bim and Cim; carrying out a brightness adjustment and a combination process to the two sub-image Bimf and Cimf to obtain an image Aimf.
-
公开(公告)号:US20180091736A1
公开(公告)日:2018-03-29
申请号:US15828403
申请日:2017-11-30
Applicant: SHENZHEN UNIVERSITY
Inventor: Jihong Pei , Kai Sun , Xuan Yang , Weixin Xie
CPC classification number: H04N5/23238 , G03B37/04 , G06T7/30 , G06T7/80 , G06T2207/30232 , G08B13/19645 , G08B13/19682 , H04N5/247 , H04N7/18 , H04N7/181 , H04N21/21805 , H04N21/2365
Abstract: The present disclosure relates to a distributed video panoramic display system. The present disclosure collects video images of different areas through an existing camera network; the video images collected by each camera are converted into the same coordinate system by each video splitting node in a video splitting module; a plurality of paths of video image data are subjected to parallel splitting processing, so that a display area of each split video image block in a panoramic display unit respectively corresponds to a separate display screen; and each video reorganization node in a video reorganization module is used to perform reorganization processing on each received video image block, then each path of video image formed after the processing is output to the corresponding display screen of the panoramic display unit, and a panoramic video image is formed.
-
-
-
-
-
-
-
-
-