EMPTY CONTAINER IDENTIFICATION METHOD AND SYSTEM

    公开(公告)号:US20200210785A1

    公开(公告)日:2020-07-02

    申请号:US16725926

    申请日:2019-12-23

    Abstract: 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.

    SCANNING IMAGING SYSTEM FOR SECURITY INSPECTION OF AN OBJECT AND IMAGING METHOD THEREOF

    公开(公告)号:US20190094407A1

    公开(公告)日:2019-03-28

    申请号:US16037810

    申请日:2018-07-17

    Abstract: 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.

    IMAGE PROCESSING METHOD, IMAGE PROCESSING DEVICE AND STORAGE MEDIUM

    公开(公告)号:US20190206095A1

    公开(公告)日:2019-07-04

    申请号:US16235882

    申请日:2018-12-28

    CPC classification number: G06T11/003

    Abstract: 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.

    METHODS AND DEVICES FOR LOCATING OBJECT IN CT IMAGING
    8.
    发明申请
    METHODS AND DEVICES FOR LOCATING OBJECT IN CT IMAGING 有权
    用于定位CT成像对象的方法和设备

    公开(公告)号:US20140093152A1

    公开(公告)日:2014-04-03

    申请号:US14037236

    申请日:2013-09-25

    Abstract: The present disclosure provides methods and devices for locating a plurality of interested objects in CT imaging. Location of the interested objects in the three-dimensional space can be determined by using three projection images that are substantially perpendicular to each other. The method can rapidly locate interested objects in a CT image without pre-reconstruction of the CT image even if there are a plurality of interested objects in the field of view. The algorithm does not involve interactive steps. The method is rapid and effective, and thus applicable to industrial applications.

    Abstract translation: 本公开提供了用于在CT成像中定位多个感兴趣对象的方法和装置。 可以通过使用基本上彼此垂直的三个投影图像来确定兴趣对象在三维空间中的位置。 即使在视野中存在多个感兴趣的对象,该方法也可以快速定位CT图像中的感兴趣的对象,而无需对CT图像进行预重建。 该算法不涉及交互式步骤。 该方法快速有效,适用于工业应用。

Patent Agency Ranking