Tsinghua University

Nuctech Company Limited

Nutech Company Limited

Beijing Friendship Hospital, Capital Medical University

Yuxiang Xing

Zhiqiang Chen

Li Ni Zhang

Ziran Zhao

Yuanjing Li

Yinong Liu

Kejun Kang

Liang Li

Yongshun Xiao

Haifeng Hu

Le Shen

Jianmin Li

Hu Tang

Hewei Gao

Jinyu Zhang

Li Zhang

Xuewu Wang

Yumin Yi

Jianping Gu

Xin Jin

Qingping Huang

Jianping Cheng

Qiang Li

Yan Zhang

Yunda Sun

Yuanyuan Liu

Wei Li

Jing Li

Yaohong Liu

Juan Zheng

Jie Shi

Yulan Li

Lan Zhang

Ming Chang

Bicheng Liu

Lijun Wang

Pengfei Zhao

Hui Ding

Jinning Liang

Mingzhi Hong

Hongxin Wu

Zhifeng Huang

Xinhui Duan

Zhi Guo Deng

Tiao Zhao

Gang Fu

Zhiming Wang

Yingxin Wang

Han Lv

Fanhua Meng

Qian Yi

Zhenchang Wang

Jia Hao

Qi Shen

Hongxia Yin

Fei Ding

Tianyi Yang Dai

Zhengyu Zhang

Hongkai Yang

Siyuan Zhang

Qianlu Ren

Gnowei Zhang

Guowei Zhang

Yanjie Yao

Zhiqing Chen

Yongchun Liu

Wubin Wu

Kaichao Liang

Xiaoyue Guo

Ruizhe Li

Huayu Zhang

Yuanji Li

Chuqing Feng

Meng Cao

Qingli Wang

Zhentian Wang

Li Zhnag

Kaixin Huang

Provided is a method of verifying an authenticity of declaration information. The method includes: acquiring a machine-detected radiation image obtained by scanning a container loaded with an article; acquiring a declaration information for declaring the article in the container; performing an identification on an image information of the article in the machine-detected radiation image to obtain an image feature corresponding to the machine-detected radiation image; performing an identification on a text information of the article in the declaration information to obtain a text feature corresponding to the declaration information; screening a declaration category of the article in the container by taking the image feature as an input information and the text feature as an external introduction feature; and determining that the declaration information is in doubt when a declaration category of at least one article in the container does not belong to a declaration category in the declaration information.

Method and system of verifying authenticity of declaration information, device and medium

A method of inspecting a vehicle includes: acquiring a to-be-inspected image of an inspected vehicle (S); acquiring a visual feature of the to-be-inspected image using a first neural network model (S); retrieving a template image from a vehicle template library based on the visual feature of the to-be-inspected image (S); determining a variation region between the to-be-inspected image and the template image (S); and presenting the variation region to a user (S). The system of inspecting a vehicle includes a radiation imaging device (), a display device (), an image processor (), and a storage device (). The present disclosure further includes a computer-readable storage medium.

Method and system of inspecting vehicle

Provided are a CT scanning method and system, an electronic device, and a computer-readable storage medium. The method includes: determining a first coordinate of a mark point of a part to be imaged in a dual-camera coordinate system; converting the first coordinate into a second coordinate of the mark point in a CT coordinate system according to coordinate system transformation parameters; generating first locating information according to the second coordinate to drive a scanning table to move to a first location designated by the first locating information; obtaining projection images of the part to be scanned; determining second locating information and scanning information of the part to be scanned according to the projection images; and driving the scanning table to move to a second location designated by the second locating information according to the second locating information and performing CT scanning according to the scanning information.

CT scanning method and system, electronic device, and computer-readable storage medium

A semantic-based method and apparatus for retrieving a perspective image, an electronic device and a computer-readable storage medium are provided. An method includes obtaining a perspective image for a space containing an inspected object therein. A semantic division on the perspective image is performed using a first method, to obtain a plurality of semantic region units. A feature extraction network is constructed using a second method. Based on the perspective image and each of the plurality of semantic region units, a feature of each semantic region unit is extracted using the feature extraction network. Based on the feature of each semantic region unit, an image most similar to the semantic region unit is retrieved from an image feature database, to assist in determining an inspected object in the semantic region unit.

Semantic-based method and apparatus for retrieving perspective image

Embodiments of the present disclosure provide a Bayesian image denoising method based on a distribution constraint of noiseless images from a distribution of noisy images. The method includes: determining a distribution constraint of noiseless images from a distribution of noisy images; and performing Bayesian denoising on noisy images based on the distribution constraint of noiseless images.

Bayesian image denoising method based on distribution constraint of noisy images

An image-guided radiation therapy apparatus comprises: a high-energy ray source configured for radiation therapy of an object; and a KV ray source, a first and second PET detectors, and a CT detector for KV CT and PET imaging for guiding the radiation therapy. The KV ray source is placed on, or at an inner or outer side of the first PET detector; the second PET detector and the CT detector are configured to receive the KV ray to perform KV CT imaging; the PET detectors are further configured to receive gamma ray emitted by the object to perform PET imaging.

Tomographic imaging and image-guided radiation therapy apparatus

Empty container identification method and system are disclosed. The method includes: obtaining customs declaration information, and finding out an vehicle declared as an empty container or an empty vehicle from the customs declaration information; performing X-ray inspection on the vehicle to acquire a transmission image of the vehicle; inputting the transmission image into an empty container identification model obtained by pre-training, so that the empty container identification model determines candidate regions of the transmission image, and performs post-processing analysis on the candidate regions to obtain an image identification result; and comparing the image identification result with the corresponding customs declaration information to determine whether or not the image identification result is consistent with the customs declaration information.

Empty container identification method and system

A low-angle self-swinging type computed tomography (CT) device is provided, having an X-ray accelerator and a plurality of rows of detectors and includes a slip ring, such that the slip ring with the accelerator and the detectors thereon is capable of performing a single-pendulum reciprocating movement while an object to be inspected passes through the slip ring, a three-dimensional CT image of the object is displayed, thereby achieving accurate inspection for large-scale objects, such as van containers.

Low-angle self-swinging, large-scale multi-slice spiral computed tomography apparatus and inspection method

An image processing method, comprising: acquiring, by a CT scanning system, projection data of an object; and processing, by using a convolutional neural network, the projection data, to acquire an estimated image of the object. The convolutional neural network comprises: a projection domain network for processing input projection data to obtain estimated projection data; an analytical reconstruction network layer for performing analytical reconstruction to obtain a reconstructed image; an image domain network for processing the reconstructed image to obtain an estimated image, a projection layer for performing a projection operation by using a system projection matrix of the CT scanning system, to obtain a projection result of the estimated image; and a statistical model layer for determining consistency among the input projection data, the estimated projection data, and the projection result of the estimated image based on a statistical model.

Image processing method using convolutional neural network, image processing device and storage medium

The present disclosure discloses a ray transmission and fluorescence CT imaging system and method. The system comprises: a ray source configured to emit a beam of rays; a rotational scanning device configured to perform rotational CT scanning on an object to be inspected; a transmission CT detector configured to receive the beam of rays which has passed through the object; a fluorescence CT detector configured to receive fluorescent photons excited by irradiation of the beam of rays on the object; a data acquisition unit configured to acquire a transmission data signal and a fluorescence data signal respectively; and a control and data processing unit configured to control the ray source to emit the beam of rays, control the rotational scanning device to perform the rotational CT scanning, and obtain a transmission CT image and a fluorescence CT image simultaneously based on the transmission data signal and the fluorescence data signal.

Ray transmission and fluorescence CT imaging system and method

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.

Method and device for reconstructing CT image and storage medium

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 on a first scale. Projection data on a plurality of other scales is generated from the projection data on the first scale. Projection data on each scale is processed on the corresponding scale by using a first convolutional neural network to obtain processed projection data, and a back-projection operation is performed on the processed projection data to obtain a CT image on the corresponding scale. CT images on the plurality of scales are fused to obtain a reconstructed image of the object to be inspected.

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.

X-ray detection method and X-ray detector

A method and apparatus for reconstructing an incident energy spectrum for a detector are disclosed. In this method, an object to be inspected is illuminated with rays, and then rays transmitted through the object to be inspected are received by the detector to convert the received rays into data of a detected energy spectrum. The incident energy spectrum for the detector is reconstructed based on the data of the energy spectrum using a statistical iterative algorithm with a pre-established detector response function. With the above solution of the embodiments, the incident energy spectrum for the detector can be more accurately acquired, thereby reducing a distortion of the incident energy spectrum caused by the detector.

Methods and apparatuses for reconstructing incident energy spectrum for a detector

The disclosure provides a scanning imaging system for security inspection of an object and an imaging method thereof, the system comprising: a conveying unit configured for bringing the object to move along a conveying direction; a plurality of radiographic sources at one side of the conveying unit, being arranged successively in a direction vertical to a plane, in which the conveying unit is located, and configured for alternately emitting ray beams to form a scanning area; a linear detector array at the other side of the conveying unit, being configured for detecting first projection images, which are formed after the ray beams emitted by the plurality of radiographic sources penetrate through the object, in the process of the object passing through the scanning area; an imaging unit configured for obtaining a first reconstructed image of the object based on the first projection images of the plurality of radiographic sources.

Scanning imaging system for security inspection of an object and imaging method thereof

Growing community of inventors

Beijing, China

Yuxiang Xing