-
公开(公告)号:US10896527B2
公开(公告)日:2021-01-19
申请号:US16045303
申请日:2018-07-25
Applicant: Tsinghua University , NUCTECH COMPANY LIMITED
Inventor: Yuxiang Xing , Li Zhang , Jianmin Li , Zhiqiang Chen , Jianping Gu
Abstract: A method and device for reconstructing a CT image and a storage medium are disclosed. CT scanning is performed on an object to be inspected to obtain projection data. The projection data is processed using a first convolutional neural network to obtain processed projection data. The first convolutional neural network comprises a plurality of convolutional layers. A back-projection operation is performed on the processed projection data to obtain a reconstructed image.
-
公开(公告)号:US10795050B2
公开(公告)日:2020-10-06
申请号:US16233387
申请日:2018-12-27
Applicant: TSINGHUA UNIVERSITY , Nuctech Company Limited
Inventor: Ying Li , Jianmin Li , Jinguo Cao , Yuan Ma , Yulan Li , Yuan He , Yuanjing Li , Hui Meng , Zhiqiang Chen , Yiwei Guo , Li Zhang
Abstract: A vehicle detection system includes a transverse detector arm, two vertical detector arms, a radiation source, a plurality of transverse detectors, and a plurality of vertical detectors. The transverse detector arm may be disposed on the ground. Two vertical detector arms are disposed at both ends of the transverse detector arm. The radiation source is located above the transverse detector arm. A plurality of transverse detectors are disposed within the transverse detector arm and are laid along a length direction of the transverse detector arm for receiving ray emitted by the radiation source. The plurality of vertical detectors are symmetrically disposed on the two vertical detector arms, and each of the vertical detectors is disposed towards a center point of the radiation source for receiving ray emitted by the radiation source.
-
公开(公告)号:US10724969B2
公开(公告)日:2020-07-28
申请号:US16175796
申请日:2018-10-30
Applicant: Tsinghua University , Nuctech Company Limited
Inventor: Yuxiang Xing , Xiaoyue Guo , Zhi Deng , Le Shen , Li Zhang , Zhiqiang Chen , Liang Li
IPC: G01N23/04 , A61B6/00 , G01N23/046 , A61B6/03
Abstract: An X-ray detection method and an X-ray detector are provided. The X-ray detection method according to embodiments of the present disclosure includes: dividing an energy range of photons emitted by an X-ray source into a number N of energy windows, where N is an integer greater than 0; obtaining a weighting factor for each of the number N of energy windows based on linear attenuation coefficients of a substance of interest and a background substance of an imaging target; obtaining a weighting factor matrix for M output channels of an X-ray detector based on the weighting factor for each of the number N of energy windows, where M is an integer greater than 0; and obtaining output results of the M output channels based on the weighting factor matrix and numbers of photons having an energy range falling into individual energy windows of the number N of energy windows.
-
公开(公告)号:US10607483B2
公开(公告)日:2020-03-31
申请号:US15300947
申请日:2015-12-23
Applicant: Nuctech Company Limited , Tsinghua University
Inventor: Zhiqiang Chen , Li Zhang , Jianmin Li , Ziran Zhao , Yaohong Liu , Qiang Li , Zheng Hu , Jianping Gu , Ying Li
Abstract: Disclosed is a vehicle identification method and system. The method includes: acquiring appearance information of an inspected vehicle; obtaining external features of the vehicle based on the appearance information; acquiring a transmission image of the vehicle and obtaining internal features of the vehicle from the transmission image; forming descriptions on the vehicle at least based on the external features and the internal features; and determining a vehicle model of the vehicle from a vehicle model databased by utilizing the descriptions. This method merges various types of modality information, especially introducing the transmission image, and combines the internal structure information with the appearance information, so that the present disclosure can identify a vehicle model more practically.
-
公开(公告)号:US10448904B2
公开(公告)日:2019-10-22
申请号:US16232072
申请日:2018-12-26
Applicant: TSINGHUA UNIVERSITY , NUCTECH COMPANY LIMITED
Inventor: Liang Li , Zhiqiang Chen , Kejun Kang , Ziran Zhao , Li Zhang , Yuxiang Xing , Tiao Zhao , Jianmin Li , Bicheng Liu , Qian Yi
Abstract: The present disclosure provides a decomposition method based on basis material combination. In the present disclosure, a scanned object is divided into a plurality of regions, the basis material combinations used in each of the divided regions are different each other, and the scanned object is re-divided according to the re-determined equivalent atomic number of its each point until the change on decomposition coefficient meets certain conditions. Thereby, a decomposition method based on dynamic basis material combinations is realized, which reduces a decomposition error caused by improper selection of the basis material combination and improves the accuracy of the decomposition and substance identification of the multi-energy CT.
-
公开(公告)号:US10430669B2
公开(公告)日:2019-10-01
申请号:US15719309
申请日:2017-09-28
Applicant: Nuctech Company Limited
Inventor: Hu Tang , Li Zhang , Zhiqiang Chen , Jiamin Zhang
IPC: G06K9/00 , H04N7/18 , H04N21/233 , H04L29/08 , G08B13/196
Abstract: A method, server and system for operating on security inspection data is disclosed. In one aspect, an example method performed by a server for operating on security inspection data includes receiving an operation request for target security inspection data from a client through a network. The target security inspection data is loaded from a storage server based on the operation request. Image processing on the loaded target security inspection data is performed. The processed target security inspection data or a graphic interface including the processed target security inspection data is encoded. The encoded target security inspection data or graphic interface is transmitted to the client through the network in a video stream.
-
公开(公告)号:US10371648B2
公开(公告)日:2019-08-06
申请号:US15301345
申请日:2015-12-14
Applicant: NUCTECH COMPANY LIMITED
Inventor: Li Zhang , Xin Jin , Huaping Tang , Qingping Huang , Yunda Sun , Zhiqiang Chen
IPC: G01N23/00 , G01N23/04 , G01N23/046 , G01V5/00
Abstract: The present disclosure discloses a radiography system including: a ray source, comprising a plurality of X-ray generators which are distributed on one or more planes intersected with a moving direction of an object being inspected; a detector module comprising a plurality of detection units; a data collection circuit; a controller, configured to control at least two X-ray generators of the plurality of X-ray generators in the ray source to generate X-rays alternately such that the object is scanned by the generated X-rays; and control the detector module and the data collection circuit to respectively obtain detection data corresponding to the at least two X-ray generators; and a data processing computer, configured to create images of the object being inspected in view angles of the at least two X-ray generators based on the detection data. The above embodiments may implement a multi-view-angle perspective imaging system within a single scan plane by utilizing a distributed X-ray source and reuse of the detectors.
-
公开(公告)号:US10302578B2
公开(公告)日:2019-05-28
申请号:US15494884
申请日:2017-04-24
Applicant: Tsinghua University , Nuctech Company Limited
Inventor: Liang Li , Zhiqiang Chen , Kejun Kang , Li Zhang , Ziran Zhao , Yuxiang Xing , Jianmin Li , Yulan Li , Tiao Zhao
IPC: G01N23/046 , G01N23/087
Abstract: Methods and system for decomposing a high-energy dual-energy X-ray CT material are disclosed. In the method, two types of effect such as Compton effect and electron pairing effect which dominates are reserved and the influence of the other effect such a photoelectric effect is removed so as to improve the accuracy of the material decomposition. The unique advantage of the present disclosure is to effectively remove the error of the calculated atomic number Z due to directly selecting two effects during processes of material decomposition in the conventional dual-energy CT method. This may greatly improve the accuracy of dual-energy CT identification of the material, and it is important to improve the conventional dual-use CT imaging system applications, such as clinical therapy, security inspection, industrial non-destructive testing, customs anti-smuggling and other fields.
-
公开(公告)号:US10262410B2
公开(公告)日:2019-04-16
申请号:US15279664
申请日:2016-09-29
Applicant: NUCTECH COMPANY LIMITED
Inventor: Zhiqiang Chen , Li Zhang , Ziran Zhao , Yaohong Liu , Cun Cheng , Qiang Li , Jianping Gu , Jian Zhang , Gang Fu
IPC: G06T7/00 , G06K9/00 , G06K9/46 , G06Q30/00 , G06K9/32 , G06T7/11 , G06K9/18 , G06K9/62 , G06T7/136
Abstract: The present disclosure provides a method and a system for inspecting goods. The method includes the steps of: obtaining a transmission image and a HSCODE of inspected goods; processing the transmission image to obtain a region of interest; retrieving from a model library a model created based on the HSCODE, in accordance with the HSCODE of the inspected goods; and determining whether there are any goods not registered in a customs declaration that are contained in the region of interest based on the model. With the above solution, it is possible to inspect goods in a container efficiently, so as to find out whether there are goods not indicated in the customs declaration that are concealed in the container.
-
公开(公告)号:US10217204B2
公开(公告)日:2019-02-26
申请号:US15409738
申请日:2017-01-19
Applicant: Nuctech Company Limited
Inventor: Zhiqiang Chen , Yuanjing Li , Li Zhang , Ziran Zhao , Yaohong Liu , Jianping Gu , Zhiming Wang
Abstract: A method of evaluating an image quality for an imaging system and the imaging system are provided. The method in some examples includes: acquiring an image to be evaluated which is generated by the imaging system; extracting a number of sub-images from the image; obtaining a coefficient vector indicating a degree of sparsity by applying a sparse decomposition on the sub-images based on a pre-set redundant sparse representation dictionary; and performing a linear transformation on the coefficient vector so as to obtain an evaluation value for the image quality. The sparse dictionary is learned by only using a few high quality perspective images, and then the image quality is evaluated based on the sparse degree of the image obtained by using the sparse dictionary. A convenient and rapid no-reference image quality evaluation is achieved.
-
-
-
-
-
-
-
-
-