WO2020047993A1 - 一种安检设备及其成像方法 - Google Patents

一种安检设备及其成像方法 Download PDF

Info

Publication number
WO2020047993A1
WO2020047993A1 PCT/CN2018/114432 CN2018114432W WO2020047993A1 WO 2020047993 A1 WO2020047993 A1 WO 2020047993A1 CN 2018114432 W CN2018114432 W CN 2018114432W WO 2020047993 A1 WO2020047993 A1 WO 2020047993A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
point cloud
cloud data
inspected
security inspection
Prior art date
Application number
PCT/CN2018/114432
Other languages
English (en)
French (fr)
Inventor
张智胜
祁春超
向志华
黄雄伟
Original Assignee
深圳市华讯方舟太赫兹科技有限公司
华讯方舟科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市华讯方舟太赫兹科技有限公司, 华讯方舟科技有限公司 filed Critical 深圳市华讯方舟太赫兹科技有限公司
Publication of WO2020047993A1 publication Critical patent/WO2020047993A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V8/00Prospecting or detecting by optical means
    • G01V8/10Detecting, e.g. by using light barriers

Definitions

  • the present application relates to the technical field of security inspection, and in particular, to a security inspection device and an imaging method thereof.
  • the security checker is a detection device that detects the presence or absence of prohibited items in the personnel to be inspected. It is widely used in airports, stations, large conferences and other public places with a large number of people. Commonly used security devices are metal security devices, X-ray scanners, and millimeter-wave imaging security devices.
  • Millimeter waves are electromagnetic waves with a wavelength between microwave and light waves. They are widely used in communications, radar imaging, and military fields. In recent years, due to the urgent needs of security inspection, millimeter wave imaging technology has been applied to the field of human body security detection, by measuring the radiation information and reflection information of the human body in the millimeter wave band.
  • the inventor of the present application has found during a long-term research and development process that although the existing security inspection device can detect and image a human body, it can usually only detect the contour information of the human body, and the imaging clarity is not high.
  • the technical problem mainly solved by the present application is to provide a security inspection device and an imaging method thereof, so as to improve the sharpness of imaging of an object to be inspected.
  • a technical solution adopted in the present application is to provide a security inspection device including: a first image acquisition device for scanning an object to be inspected to obtain a global image of the object to be inspected; Two image acquisition devices are used to scan a preset area of the object to be inspected to obtain a partial image of the object to be inspected, where the partial image is a three-dimensional image of the preset area; the processor is respectively connected with the first image acquisition device and the first The two image acquisition devices are coupled for fusing the local image with the global image to obtain the security image of the object to be inspected; wherein the resolution of the local image is greater than that of the global image; the security inspection device further includes: a main frame, a An image acquisition device includes: an antenna array and a scan driver.
  • the antenna array is arranged on the main body frame and is coupled to the scan driver.
  • the scan driver controls the antenna array to scan the object to be inspected to obtain a global image.
  • the second image acquisition device includes a three-dimensional image acquisition device.
  • a scanner, a three-dimensional scanner is coupled to the processor.
  • the first image acquisition device further includes a controller coupled to the antenna array.
  • the second image acquisition device is disposed on the antenna array.
  • the controller controls the rotation of the antenna array.
  • the antenna array drives the second image acquisition device to be inspected from different angles. The preset area of the subject is scanned.
  • the security inspection device further includes: a rotating disk, which is arranged on the bottom surface of the main body frame, and the rotating disk is coupled to the controller.
  • the controller controls the rotating disk to rotate, and the rotating direction of the rotating disk is different from that of the antenna array. The direction of rotation is reversed.
  • the three-dimensional scanner includes at least any one of a depth camera, a structured light scanner, and a laser three-dimensional scanner.
  • the global image includes the first point cloud data
  • the local image includes the second point cloud data.
  • the processor obtains the rotation matrix of the second point cloud data to the first point cloud data, and multiplies the second point cloud data by the rotation matrix.
  • the processor deletes the fourth point cloud data from the first point cloud data, where the fourth point cloud data and The first subregion of the overlapping region of the global image and the local image corresponds;
  • the processor deletes the fifth point cloud data from the third point cloud data, wherein the fifth point cloud data and the second region of the overlapping region of the global image and the local image The sub-region corresponds; the processor merges the first point cloud data after deleting the fourth point cloud data and the third point cloud data after deleting the fifth point cloud data.
  • the object to be inspected is a human body
  • the global image is a whole body image of the human body
  • the local image is a head image of the human body.
  • the difference between the vertical coordinate of the fourth point cloud data and the vertical coordinate of the highest point of the human head is smaller than the first preset value, and the difference between the vertical coordinate of the fifth point cloud data and the vertical coordinate of the highest point of the human head is greater than Or equal to the second preset value.
  • a security inspection device including: a first image acquisition device for scanning an object to be inspected to obtain a global image of the object to be inspected;
  • the second image acquisition device is configured to scan a preset area of the object to be inspected to obtain a partial image of the object to be inspected, where the partial image is a three-dimensional image of the preset area;
  • the processor is respectively connected with the first image acquisition device and
  • the second image acquisition device is coupled to fuse the local image and the global image to obtain a security image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • the security inspection device further includes a main body frame.
  • the first image acquisition device includes an antenna array and a scanning driver.
  • the antenna array is disposed on the main body frame and is coupled to the scanning driver.
  • the scanning driver controls the antenna array to scan the object to be inspected. Get the global image.
  • the first image acquisition device further includes a controller coupled to the antenna array.
  • the second image acquisition device is disposed on the antenna array.
  • the controller controls the rotation of the antenna array.
  • the antenna array drives the second image acquisition device to be inspected from different angles. The preset area of the subject is scanned.
  • the security inspection device further includes: a rotating disk, which is arranged on the bottom surface of the main body frame, and the rotating disk is coupled to the controller.
  • the controller controls the rotating disk, and the rotating direction of the rotating disk The direction of rotation is reversed.
  • the second image acquisition device includes a three-dimensional scanner, and the three-dimensional scanner is coupled to the processor.
  • the three-dimensional scanner includes at least any one of a depth camera, a structured light scanner, and a laser three-dimensional scanner.
  • the global image includes the first point cloud data
  • the local image includes the second point cloud data.
  • the processor obtains the rotation matrix of the second point cloud data to the first point cloud data, and multiplies the second point cloud data by the rotation matrix.
  • the processor deletes the fourth point cloud data from the first point cloud data, where the fourth point cloud data and The first subregion of the overlapping region of the global image and the local image corresponds;
  • the processor deletes the fifth point cloud data from the third point cloud data, wherein the fifth point cloud data and the second region of the overlapping region of the global image and the local image The sub-region corresponds; the processor merges the first point cloud data after deleting the fourth point cloud data and the third point cloud data after deleting the fifth point cloud data.
  • the object to be inspected is a human body
  • the global image is a whole body image of the human body
  • the local image is a head image of the human body.
  • the difference between the vertical coordinate of the fourth point cloud data and the vertical coordinate of the highest point of the human head is smaller than the first preset value, and the difference between the vertical coordinate of the fifth point cloud data and the vertical coordinate of the highest point of the human head is greater than Or equal to the second preset value.
  • the security inspection device includes a first image acquisition unit, a second image acquisition unit, and a processor.
  • the method includes: a first image acquisition device scans an object to be inspected and acquires a global image of the object to be inspected; a second image acquisition device scans a preset region of the object to be inspected, and acquires a partial image of the object to be inspected, wherein The image is a three-dimensional image of a preset area; the processor fuses the local image with the global image and obtains the security inspection image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • the security inspection device of the embodiment of the present application includes: a first image acquisition device for scanning an object to be inspected to obtain a global image of the object to be inspected; and a second image acquisition A device for scanning a preset area of an object to be inspected to obtain a partial image of the object to be inspected, wherein the partial image is a three-dimensional image of the preset area; and the processor is respectively connected with the first image acquisition device and the second image acquisition device The device is coupled and used for fusing the local image with the global image to obtain the security inspection image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • This application fuses a local image with a higher resolution collected by a second image acquisition device and a global image with a lower resolution collected by a first image acquisition device to improve a preset area corresponding to the local image in the global image Therefore, in this way, while ensuring the imaging integrity of the object to be inspected, the imaging clarity of a preset region of the object to be inspected can be improved, thereby improving the image clarity of the object to be inspected.
  • FIG. 1 is a schematic structural diagram of a first embodiment of a security inspection device of the present application
  • FIG. 2 is a schematic structural diagram of a second embodiment of a security inspection device of the present application.
  • FIG. 3A is a schematic diagram of a first state where a local image and a global image are fused in a security inspection device of the present application;
  • 3B is a schematic diagram of a second state where a local image and a global image are fused in the security inspection device of the present application;
  • FIG. 3C is a schematic diagram of a third state where a local image and a global image are fused in the security inspection device of the present application;
  • 3D is a schematic diagram of a fourth state in which a local image and a global image are fused in the security inspection device of the present application;
  • 3E is a schematic structural diagram of a security check image in a security check device of the present application.
  • FIG. 4 is a schematic flowchart of an embodiment of an imaging method of a security inspection device of the present application
  • FIG. 5 is a schematic flowchart of step S402 in the imaging method of the security inspection device in the embodiment of FIG. 4 of the present application.
  • FIG. 1 is a schematic structural diagram of an embodiment of the security inspection device of the present application.
  • the security inspection device 101 in this embodiment includes a first image acquisition device 102, a second image acquisition device 103, and a processor 104.
  • the first image acquisition device 102 is configured to scan an object to be inspected to obtain a global image of the object to be inspected;
  • the second image acquisition device 103 is configured to scan a preset area of the object to be inspected to obtain a partial image of the object to be inspected, where the partial image is a three-dimensional image of the preset area; the processor 104 and the first image acquisition device 102 respectively
  • the second image acquisition device 103 is coupled to fuse the local image and the global image to obtain a security image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • the existing security inspection equipment usually can only detect the contour information of the object to be inspected, the imaging clarity is not high, and some detailed information of the object to be inspected cannot be obtained, resulting in its limited use range. For example, criminal suspects usually take transportation at various traffic barriers. Traffic barriers are usually provided with security equipment. The lack of detailed images obtained by existing security equipment cannot be used as a basis for tracing or monitoring criminal suspects.
  • the security inspection device 101 in this embodiment can collect a partial image of a preset region of the object to be inspected with higher resolution through the second image acquisition device 103, and then collect the object to be inspected with the first image acquisition device 102.
  • the global image is fused to obtain a high-resolution image of the object to be inspected.
  • the full body image of the criminal suspect is obtained through the first image acquisition device 102
  • the head image of the suspect is obtained through the second image acquisition device 103
  • the full body image of the criminal suspect and the head image are fused to Obtain a security inspection image of the criminal suspect.
  • the security inspection image includes at least the whole body contour information of the criminal suspect and detailed information of the head. Therefore, the staff can more easily identify the criminal suspect through the security inspection image.
  • the security inspection device 101 in this embodiment can also be applied to other application scenarios, which are not listed here one by one.
  • the security inspection device 101 in this embodiment fuses a local image with a higher resolution collected by the second image acquisition device 103 and a global image with a lower resolution collected by the first image acquisition device 102 to improve the
  • the image resolution of the preset region corresponding to the local image in the global image therefore, while ensuring the integrity of the imaging of the object to be inspected, the imaging clarity of the predetermined region of the object to be inspected can be improved, thereby improving the object to be inspected.
  • the security inspection device 201 of this embodiment is different from the security inspection device 101 of the foregoing embodiment in that the security inspection device 201 of this embodiment further includes a main frame 203 and a first image.
  • the acquisition device 202 includes an antenna array 204 and a scanning driver 205.
  • the antenna array 204 is disposed on the main body frame 203 and is coupled to the scanning driver 205.
  • the scanning driver 205 controls the antenna array 205 to scan the object 206 to be inspected to obtain the object 206 global image.
  • the antenna array 205 of this embodiment may acquire a global image of the object 206 to be inspected by using a millimeter wave imaging technology.
  • millimeter-wave imaging technology can be divided into two types: passive millimeter-wave imaging and active millimeter-wave imaging.
  • the antenna array 205 receives millimeter wave signals radiated from the object 206 to be inspected, and the processor (not shown) of the security inspection device 201 converts the millimeter wave signals into level signals
  • the magnitude of the level signal has a positive correlation with the temperature of the detected object 206.
  • the brightness temperature information of the detected object 206 can be obtained to obtain a global image that realizes the object 206.
  • the antenna array 205 transmits millimeter waves of a certain power to the detection area at different times and different positions, and the antenna array 205 receives
  • the millimeter-wave signal transmitted by the object 206 is reconstructed by the processor according to the intensity and phase information of the millimeter-wave signal using an information reconstruction algorithm to obtain a three-dimensional global image of the object 206 to be inspected.
  • the first image acquisition device 202 of this embodiment further includes a controller 208, the controller 208 is coupled to the antenna array 204, the second image acquisition device 207 is disposed on the antenna array 204, and the controller 208 controls the antenna array 204 rotates, and the antenna array 204 drives the second image acquisition device 207 to scan preset areas of the object to be inspected 206 from different angles.
  • the second image acquisition device 207 in this embodiment includes a three-dimensional scanner 207, and the three-dimensional scanner 207 is coupled to the processor.
  • the three-dimensional scanner 207 may acquire a three-dimensional image of the object 206 to be inspected by using an existing image processing algorithm. Image processing algorithms are not described here.
  • the three-dimensional scanner 207 of this embodiment works under the driving of another scanning driver, which may be integrated with the scanning driver 205, or the three-dimensional scanner 207 shares the scanning driver 205 with the first image acquisition device 202.
  • the specific number and specific installation positions of the three-dimensional scanner 207 are not limited.
  • the three-dimensional scanner 207 in this embodiment includes at least any one of a depth camera, a structured light scanner, and a laser three-dimensional scanner.
  • the object to be inspected 206 in this embodiment is a human body 206
  • the global image is a whole body image of the human body 206
  • the preset area is a head area of the human body 206
  • the local image is a head image of the human body 206.
  • the second image acquisition device 207 and the head region of the human body 206 are equal in height, or the height difference between the two is within a threshold range.
  • the security inspection device 201 in this embodiment further includes a rotating disk 209, which is disposed on the bottom surface of the main body frame 203.
  • the rotating disk 209 is coupled to the controller 208.
  • control The controller 208 controls the rotation of the rotating disk 209, and the rotating direction of the rotating disk 209 is opposite to that of the antenna array 204.
  • the scanning cycle of the antenna array 204 and the second image acquisition device 207 can be set according to the rotation speed or rotation angle of the rotating disk 209 and / or the antenna array 204.
  • the relative positional relationship between the antenna array, the controller, the scan driver, the second image acquisition device, and the main body frame and the object to be inspected is not limited.
  • This application does not limit the security inspection equipment to the above structure.
  • the global image of the object 206 includes the first point cloud data
  • the local image of the object 206 includes the second point cloud data
  • the processor obtains the rotation of the second point cloud data to the first point cloud data.
  • Matrix and multiply the second point cloud data with the rotation matrix to obtain the third point cloud data of the second point cloud data in the coordinate system corresponding to the first point cloud data; the processor further obtains the third point cloud data from the first point cloud data
  • the fourth point cloud data is deleted, wherein the fourth point cloud data corresponds to the first sub-region of the overlapping area of the global image and the local image, and the fifth point cloud data is deleted from the third point cloud data, where the fifth The point cloud data corresponds to the second sub-region of the overlapping area of the global image and the local image; the processor further combines the first point cloud data with the third point cloud data.
  • the object to be inspected 206 is a human body 206
  • the global image is a whole body image of the human body 206
  • the local image is an image of the head of the human body 206.
  • the first point cloud data A includes three-dimensional coordinates, color information, and reflection intensity information of the whole body image of the human body 206
  • the second point cloud data B includes three-dimensional coordinates, color information, and reflection intensity information of the head image of the human body 206.
  • the processor obtains a rotation matrix from the second point cloud data A to the first point cloud data B.
  • the processor obtains at least 3 first image points from the first point cloud data A, and from the second point cloud data Get at least 3 second image points in B, where the first image point corresponds to the second image point, that is, the same image point of the human body, the processor uses the SVD method to obtain the rotation matrix; then, the processor converts the second point cloud Data B is multiplied with the rotation matrix to obtain the third point cloud data C of the second point cloud data B in the corresponding coordinate system of the first point cloud data A, that is, the second point cloud data B is converted to the first point Cloud data A is in the same coordinate system (as shown in FIG. 3B); then, the processor deletes the fourth point cloud data D from the first point cloud data A (as shown in FIG. 3B and FIG.
  • the fourth point cloud The data D corresponds to the first sub-region of the overlapping area of the global image and the local image
  • the processor deletes the fifth point cloud data E from the third point cloud data C (as shown in FIG. 3C and FIG. 3D), where: The fifth point cloud data E corresponds to S2 of the second sub-region of the overlapping region of the global image and the local image; finally, After the first A point cloud point cloud data and the fifth E deleted after deleting the fourth processor of the third D point cloud data merge point cloud data C (FIG. 3E). In this way, a security inspection image of the object to be inspected 206 can be acquired.
  • the difference between the vertical coordinate of the fourth point cloud data D (coordinates with the height direction of the human body 206) and the vertical coordinate of the highest point of the head of the human body 206 is smaller than the first preset value.
  • the difference between the vertical coordinates of the highest point of the head of the human body 206 is greater than or equal to a second preset value.
  • the first preset value and the second preset value in this embodiment are the same, both being 25CM.
  • the first preset value is different from the second preset value, and may be set according to actual conditions.
  • image processing methods may also be used to fuse the global image and the local image of the object to be inspected to obtain a security image with a higher definition.
  • FIG. 4 is a schematic flowchart of an embodiment of the imaging method of the present application.
  • the method of this embodiment is applied to the above security inspection equipment.
  • the method of this embodiment specifically includes the following steps:
  • Step S401 the first image acquisition device scans the object to be inspected and acquires a global image of the object to be inspected; the second image acquisition device scans a preset region of the object to be inspected, and acquires a partial image of the object to be inspected, where The image is a three-dimensional image of a preset area.
  • Step S402 The processor fuses the local image with the global image, and obtains the security inspection image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • step S402 can be implemented by using the method shown in FIG.
  • the method of the embodiment includes the following steps:
  • Step S501 The processor obtains a rotation matrix from the second point cloud data to the first point cloud data, and multiplies the second point cloud data by the rotation matrix to obtain the second point cloud data corresponding to the first point cloud data.
  • the third point cloud data in the coordinate system.
  • Step S502 The processor deletes the fourth point cloud data from the first point cloud data, where the fourth point cloud data corresponds to the first sub-region of the overlapping area of the global image and the local image, and is removed from the third point cloud data.
  • the fifth point cloud data is deleted, where the fifth point cloud data corresponds to a second sub-region of the overlapping region of the global image and the local image.
  • Step S503 The processor further merges the first point cloud data with the third point cloud data.
  • the security inspection device in the embodiment of the present application includes: a first image acquisition device for scanning an object to be inspected to obtain a global image of the object to be inspected; and a second image acquisition device for predicting the object to be inspected Set the area to scan to obtain a partial image of the object to be inspected, where the partial image is a three-dimensional image of a preset area; the processor is coupled to the first image acquisition device and the second image acquisition device, respectively, and is configured to connect the partial image Fusion with the global image to obtain the security image of the object to be inspected; wherein the resolution of the local image is greater than the resolution of the global image.
  • This application fuses a local image with a higher resolution collected by a second image acquisition device and a global image with a lower resolution collected by a first image acquisition device to improve a preset area corresponding to the local image in the global image Therefore, in this way, while ensuring the imaging integrity of the object to be inspected, the imaging clarity of a preset region of the object to be inspected can be improved, thereby improving the image clarity of the object to be inspected.

Abstract

一种安检设备(101),包括:第一图像采集装置(102),用于对待检对象(206)进行扫描,以获取待检对象(206)的全局图像;第二图像采集装置(103),用于对待检对象(206)的预设区域进行扫描,以获取待检对象(206)的局部图像,其中,局部图像为预设区域的三维图像;处理器(104),分别与第一图像采集装置(102)及第二图像采集装置(103)耦接,用于将局部图像与全局图像进行融合,以获取待检对象(206)的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。通过这种方式能够提高待检对象(206)的清晰度。还提供一种安检设备的成像方法。

Description

一种安检设备及其成像方法 【技术领域】
本申请涉及安检技术领域,特别是涉及到一种安检设备及其成像方法。
【背景技术】
安检仪是一种检测待检人员有无携带违禁物品的探测装置,其广泛应用于机场、车站、大型会议等人流较大的公共场所。常用的安检仪有金属安检仪、X光扫描仪以及毫米波成像安检仪等。
毫米波是波长介于微波与光波之间的电磁波,被广泛应用于通讯、雷达成像及军事领域。近年来,由于安检的迫切需求,毫米波成像技术被应用于人体安检探测领域,通过测量人体在毫米波波段的辐射信息和反射信息成像。
本申请的发明人在长期的研发过程中发现,现有的安检仪虽然可以探测到人体并成像,但通常只能探测到人体的轮廓信息,成像清晰度不高。
【发明内容】
本申请主要解决的技术问题是提供一种安检设备及其成像方法,以提高待检对象成像的清晰度。
为解决上述技术问题,本申请采用的一个技术方案是:提供一种安检设备,该安检设备包括:第一图像采集装置,用于对待检对象进行扫描,以获取待检对象的全局图像;第二图像采集装置,用于对待检对象的预设区域进行扫描,以获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器,分别与第一图像采集装置及第二图像采集装置耦接,用于将局部图像与全局图像进行融合,以获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率;安检设备进一步包括:主体框架,第一图像采集装置包括:天线阵列及扫描驱动器,天线阵列设置在主体框架上,并与扫描驱动器耦接,扫描驱动器控制天线阵列对待检对象进行扫描,以得到全局图像;第二图像采集装置包括三维扫描仪,三维扫描仪与处理器耦接。
其中,第一图像采集装置进一步包括:控制器,与天线阵列耦接,第二图像采集装置设置在天线阵列上,控制器控制天线阵列旋转,天线阵列带动第二 图像采集装置从不同角度对待检对象的预设区域进行扫描。
其中,安检设备进一步包括:旋转盘,设置在主体框架的底面,旋转盘与控制器耦接,当待检对象在旋转盘上,控制器控制旋转盘旋转,旋转盘的旋转方向与天线阵列的旋转方向相反。
其中,三维扫描仪至少包括深度相机、结构光扫描仪、激光三维扫描仪中的任一种。
其中,全局图像包括第一点云数据,局部图像包括第二点云数据;处理器获取第二点云数据到第一点云数据的旋转矩阵,并将第二点云数据与旋转矩阵相乘,以获取第二点云数据在第一点云数据对应的坐标系下的第三点云数据;处理器从第一点云数据中删除第四点云数据,其中,第四点云数据与全局图像和局部图像的重叠区域的第一子区域对应;处理器从第三点云数据中删除第五点云数据,其中,第五点云数据与全局图像和局部图像的重叠区域的第二子区域对应;处理器将删除第四点云数据后的第一点云数据与删除第五点云数据后的第三点云数据进行合并。
其中,待检对象为人体,全局图像为人体的全身图像,局部图像为人体的头部图像。
其中,第四点云数据的垂直坐标与人体头部最高点的垂直坐标的差值小于第一预设值,第五点云数据的垂直坐标与人体头部最高点的垂直坐标的差值大于或等于第二预设值。
为解决上述技术问题,本申请采用的另一技术方案是:提供一种安检设备,该安检设备包括:第一图像采集装置,用于对待检对象进行扫描,以获取待检对象的全局图像;第二图像采集装置,用于对待检对象的预设区域进行扫描,以获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器,分别与第一图像采集装置及第二图像采集装置耦接,用于将局部图像与全局图像进行融合,以获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。
其中,安检设备进一步包括:主体框架,第一图像采集装置包括:天线阵列及扫描驱动器,天线阵列设置在主体框架上,并与扫描驱动器耦接,扫描驱动器控制天线阵列对待检对象进行扫描,以得到全局图像。
其中,第一图像采集装置进一步包括:控制器,与天线阵列耦接,第二图像采集装置设置在天线阵列上,控制器控制天线阵列旋转,天线阵列带动第二 图像采集装置从不同角度对待检对象的预设区域进行扫描。
其中,安检设备进一步包括:旋转盘,设置在主体框架的底面,旋转盘与控制器耦接,当待检对象在旋转盘上,控制器控制旋转盘旋转,旋转盘的旋转方向与天线阵列的旋转方向相反。
其中,第二图像采集装置包括三维扫描仪,三维扫描仪与处理器耦接。
其中,三维扫描仪至少包括深度相机、结构光扫描仪、激光三维扫描仪中的任一种。
其中,全局图像包括第一点云数据,局部图像包括第二点云数据;处理器获取第二点云数据到第一点云数据的旋转矩阵,并将第二点云数据与旋转矩阵相乘,以获取第二点云数据在第一点云数据对应的坐标系下的第三点云数据;处理器从第一点云数据中删除第四点云数据,其中,第四点云数据与全局图像和局部图像的重叠区域的第一子区域对应;处理器从第三点云数据中删除第五点云数据,其中,第五点云数据与全局图像和局部图像的重叠区域的第二子区域对应;处理器将删除第四点云数据后的第一点云数据与删除第五点云数据后的第三点云数据进行合并。
其中,待检对象为人体,全局图像为人体的全身图像,局部图像为人体的头部图像。
其中,第四点云数据的垂直坐标与人体头部最高点的垂直坐标的差值小于第一预设值,第五点云数据的垂直坐标与人体头部最高点的垂直坐标的差值大于或等于第二预设值。
为解决上述技术问题,本申请采用的又一个技术方案是:提供一种案件设备的成像方法,应用于安检设备,该安检设备包括第一图像采集单元、第二图像采集单元及处理器,该方法包括:第一图像采集装置对待检对象进行扫描,并获取待检对象的全局图像;第二图像采集装置对待检对象的预设区域进行扫描,并获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器将局部图像与全局图像进行融合,并获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。
本申请实施例的有益效果是:区别于现有技术,本申请实施例安检设备包括:第一图像采集装置,用于对待检对象进行扫描,以获取待检对象的全局图像;第二图像采集装置,用于对待检对象的预设区域进行扫描,以获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器,分别与第一 图像采集装置及第二图像采集装置耦接,用于将局部图像与全局图像进行融合,以获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。本申请将第二图像采集装置采集的分辨率较大的局部图像与第一图像采集装置采集的分辨率较小的全局图像进行融合,以提高该全局图像中与该局部图像对应的预设区域的图像分辨率,因此,通过这种方式,在保证待检对象成像的完整性性的同时,能够提高待检对象预设区域的成像清晰度,从而提高待检对象成像的清晰度。
【附图说明】
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本申请安检设备第一实施例的结构示意图;
图2是本申请安检设备第二实施例的结构示意图;
图3A是本申请安检设备中局部图像与全局图像进行融合的第一状态示意图;
图3B是本申请安检设备中局部图像与全局图像进行融合的第二状态示意图;
图3C是本申请安检设备中局部图像与全局图像进行融合的第三状态示意图;
图3D是本申请安检设备中局部图像与全局图像进行融合的第四状态示意图;
图3E是本申请安检设备中安检图像的结构示意图;
图4是本申请安检设备的成像方法一实施例的流程示意图;
图5是本申请图4实施例安检设备的成像方法中步骤S402的具体流程示意图。
【具体实施方式】
下面结合附图和实施例,对本申请作进一步的详细描述。特别指出的是, 以下实施例仅用于说明本申请,但不对本申请的范围进行限定。同样的,以下实施例仅为本申请的部分实施例而非全部实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“内”、“外”等指示的方位或者位置关系为基于附图所示的方位或者位置关系,或者是该申请产品使用时惯常摆放的方位或者位置关系,仅是为了方便描述本申请合简化描述,而不是指示或者暗示所指的装置或者元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本申请的限制。
此外,本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含。
本申请首先提出一种安检设备,如图1所示,图1是本申请安检设备一实施例的结构示意图。本实施例安检设备101包括第一图像采集装置102、第二图像采集装置103及处理器104,其中,第一图像采集装置102用于对待检对象进行扫描,以获取待检对象的全局图像;第二图像采集装置103用于对待检对象的预设区域进行扫描,以获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器104分别与第一图像采集装置102及第二图像采集装置103耦接,用于将局部图像与全局图像进行融合,以获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。
由于现有的安检设备通常只能探测到待检对象的轮廓信息,成像清晰度不高,不能获取待检对象的一些细节信息,导致其使用范围有限。例如,犯罪嫌疑人通常会在各种交通关口乘坐交通工具转移,交通关口通常设置有安检设备,现有的安检设备获取的缺乏细节的图像并不能作为追查或监控犯罪嫌疑人的依据。
为解决上述问题,本实施例安检设备101能够通过第二图像采集装置103采集分辨率较高的待检对象的预设区域的局部图像,然后与第一图像采集装置102采集的该待检对象的全局图像进行融合,以获取清晰度较高的待检对象的成像。例如,通过第一图像采集装置102获取犯罪嫌疑人的全身图像,通过第二 图像采集装置103获取该犯罪嫌疑人的头部图像,然后将犯罪嫌疑人的全身图像与头部图像进行融合,以获取犯罪嫌疑人的安检图像,该安检图像至少包括犯罪嫌疑人的全身轮廓信息及头部的细节信息,因此,工作人员通过该安检图像较容易识别犯罪嫌疑人。
当然,本实施例安检设备101还可以应用于其它的应用场景,这里不一一列举。
区别于现有技术,本实施例安检设备101将第二图像采集装置采集103的分辨率较大的局部图像与第一图像采集装置102采集的分辨率较小的全局图像进行融合,以提高该全局图像中与该局部图像对应的预设区域的图像分辨率,因此,能够在保证待检对象成像的完整性性的同时,提高待检对象预设区域的成像清晰度,从而能够提高待检对象成像的清晰度。
本申请进一步提出第二实施例的安检设备,如图2所示,本实施例安检设备201与上述实施例安检设备101是区别在于:本实施例安检设备201进一步包括主体框架203,第一图像采集装置202包括:天线阵列204及扫描驱动器205,天线阵列204设置在主体框架203上,并与扫描驱动器205耦接,扫描驱动器205控制天线阵列205对待检对象206进行扫描,以得到待检对象206的全局图像。
本实施例的天线阵列205可采用毫米波成像技术获取待检对象206的全局图像。根据成像机制的不同,毫米波成像技术可以分为被动式毫米波成像和主动式毫米波成像两种技术。
在一个应用场景中,采用被动式毫米波成像技术时,天线阵列205接收待检对象206向外辐射的毫米波信号,安检设备201的处理器(图未示)将毫米波信号转化为电平信号,该电平信号的大小和被检测待检对象206的温度呈正相关,通过测量该电平信号就能获得被检测待检对象206的亮温信息,以获取实现待检对象206的全局图像。
在另一应用场景中,采用主动式毫米波成像技术时,天线阵列205在不同时刻、不同的位置,以不同的频率向检测区发射出一定功率的毫米波,同时天线阵列205接收从待检对象206发射回来的毫米波信号,处理器根据毫米波信号的强度和相位信息,利用信息重建的算法对该强度和相位信息进行重建,以得到待检对象206的三维全局图像。
可选地,本实施例的第一图像采集装置202进一步包括:控制器208,控制 器208与天线阵列204耦接,第二图像采集装置207设置在天线阵列204上,控制器208控制天线阵列204旋转,天线阵列204带动第二图像采集装置207从不同角度对待检对象206的预设区域进行扫描。
其中,本实施例的第二图像采集装置207包括三维扫描仪207,三维扫描仪207与处理器耦接。
三维扫描仪207可以采用现有的图像处理算法获取待检对象206的三维图像。关于图像处理算法这里不进行介绍。
当然,本实施例的三维扫描仪207在另一扫描驱动器的驱动下工作,该扫描驱动器可与扫描驱动器205集成,或者三维扫描仪207与第一图像采集装置202共用扫描驱动器205。
在其它实施例中,不限定三维扫描仪207的具体数量及具体设置位置。
其中,本实施例的三维扫描仪207至少包括深度相机、结构光扫描仪、激光三维扫描仪中的任一种。
本实施例的待检对象206为人体206,全局图像为人体206的全身图像,预设区域为人体206的头部区域,局部图像为人体206的头部图像。
其中,本实施例的第二图像采集装置207与人体206的头部区域等高,或者二者的高度差在阈值范围内。
可选地,本实施例安检设备201进一步包括:旋转盘209,旋转盘209设置在主体框架203的底面,旋转盘209与控制器208耦接,当待检对象206在旋转盘209上,控制器208控制旋转盘209旋转,旋转盘209的旋转方向与天线阵列204的旋转方向相反。
其中,可以根据旋转盘209和/或天线阵列204的旋转速度或旋转角度来设置天线阵列204及第二图像采集装置207对待检对象206的扫描周期。
在其它实施例中,不限定天线阵列、控制器、扫描驱动器及第二图像采集装置等与主体框架及待检对象的相对位置关系。
本申请不限定安检设备为上述结构。
在一个应用场景中,待检对象206的全局图像包括第一点云数据,待检对象206的局部图像包括第二点云数据,处理器获取第二点云数据到第一点云数据的旋转矩阵,并将第二点云数据与该旋转矩阵相乘,以获取第二点云数据在第一点云数据对应的坐标系下的第三点云数据;处理器进一步从第一点云数据中删除第四点云数据,其中,第四点云数据与全局图像和局部图像的重叠区域 的第一子区域对应,并从第三点云数据中删除第五点云数据,其中,第五点云数据与全局图像和局部图像的重叠区域的第二子区域对应;处理器进一步将第一点云数据与第三点云数据进行合并。
具体地,如图3A所示,待检对象206为人体206,全局图像为人体206的全身图像,局部图像为人体206的头部图像。第一点云数据A包括人体206的全身图像的三维坐标、颜色信息及反射强度信息等,第二点云数据B包括人体206的头部图像的三维坐标、颜色信息及反射强度信息等。首先,处理器获取第二点云数据A到第一点云数据B的旋转矩阵,具体地,处理器从第一点云数据A中获取最少3个第一图像点,从第二点云数据B中获取最少3个第二图像点,其中第一图像点与第二图像点对应,即人体的同一个图像点,处理器采用SVD方法获取该旋转矩阵;接着,处理器将第二点云数据B与该旋转矩阵相乘,以获取第二点云数据B在第一点云数据A的对应坐标系下的第三点云数据C,即将第二点云数据B转换到与第一点云数据A同一坐标系(如图3B所示);然后,处理器从第一点云数据A中删除第四点云数据D(如图3B及图3C所示),其中,第四点云数据D与全局图像和局部图像的重叠区域的第一子区域对应S1,且处理器从第三点云数据C中删除第五点云数据E(如图3C及图3D所示),其中,第五点云数据E与全局图像和局部图像的重叠区域的第二子区域对应S2;最后,处理器将删除第四点云数据D后的第一点云数据A与删除第五点云数据E后的第三点云数据C进行合并(如图3E所示)。通过这种方式,能够获取待检对象206的安检图像。
其中,第四点云数据D的垂直坐标(与人体206身高方向坐标)与人体206的头部最高点的垂直坐标的差值小于第一预设值,第五点云数据E的垂直坐标与人体206的头部最高点的垂直坐标的差值大于或等于第二预设值。
其中,本实施例的第一预设值与第二预设值相同,均为25CM。当然,在其它实施例中,第一预设值与第二预设值不同,且可以根据实际情况设定。
当然,在其它实施例中,还可以采用其它图像处理方法融合待检对象的全局图像及局部图像,以获取清晰度较高的安检图像。
本申请进一步提出一种成像方法,如图4所示,图4是本申请成像方法一实施例的流程示意图。本实施例的方法应用于上述安检设备,本实施例的方法具体包括以下步骤:
步骤S401:第一图像采集装置对待检对象进行扫描,并获取待检对象的全局图像;第二图像采集装置对待检对象的预设区域进行扫描,并获取待检对象的局部图像,其中,局部图像为预设区域的三维图像。
步骤S402:处理器将局部图像与全局图像进行融合,并获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。
可选地,待检对象的全局图像包括第一点云数据,待检对象的局部图像包括第二点云数据,本实施例可以通过如图5所示的方法实现步骤S402,具体地,本实施例的方法包括以下步骤:
步骤S501:处理器获取第二点云数据到第一点云数据的旋转矩阵,并将第二点云数据与该旋转矩阵相乘,以获取第二点云数据在第一点云数据对应的坐标系下的第三点云数据。
步骤S502:处理器从第一点云数据中删除第四点云数据,其中,第四点云数据与全局图像和局部图像的重叠区域的第一子区域对应,并从第三点云数据中删除第五点云数据,其中,第五点云数据与全局图像和局部图像的重叠区域的第二子区域对应。
步骤S503:处理器进一步将第一点云数据与第三点云数据进行合并。
关于安检设备的其它结构及其它控制方法、工作原理这里不赘述。
区别于现有技术,本申请实施例安检设备包括:第一图像采集装置,用于对待检对象进行扫描,以获取待检对象的全局图像;第二图像采集装置,用于对待检对象的预设区域进行扫描,以获取待检对象的局部图像,其中,局部图像为预设区域的三维图像;处理器,分别与第一图像采集装置及第二图像采集装置耦接,用于将局部图像与全局图像进行融合,以获取待检对象的安检图像;其中,局部图像的分辨率大于全局图像的分辨率。本申请将第二图像采集装置采集的分辨率较大的局部图像与第一图像采集装置采集的分辨率较小的全局图像进行融合,以提高该全局图像中与该局部图像对应的预设区域的图像分辨率,因此,通过这种方式,在保证待检对象成像的完整性性的同时,能够提高待检对象预设区域的成像清晰度,从而提高待检对象成像的清晰度。
以上所述仅为本申请的实施方式,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (17)

  1. 一种安检设备,其中,所述安检设备包括:
    第一图像采集装置,用于对待检对象进行扫描,以获取所述待检对象的全局图像;
    第二图像采集装置,用于对所述待检对象的预设区域进行扫描,以获取所述待检对象的局部图像,其中,所述局部图像为所述预设区域的三维图像;
    处理器,分别与所述第一图像采集装置及所述第二图像采集装置耦接,用于将所述局部图像与所述全局图像进行融合,以获取所述待检对象的安检图像;
    其中,所述局部图像的分辨率大于所述全局图像的分辨率;
    所述安检设备进一步包括:主体框架,所述第一图像采集装置包括:天线阵列及扫描驱动器,所述天线阵列设置在所述主体框架上,并与所述扫描驱动器耦接,所述扫描驱动器控制所述天线阵列对所述待检对象进行扫描,以得到所述全局图像;
    所述第二图像采集装置包括三维扫描仪,所述三维扫描仪与所述处理器耦接。
  2. 根据权利要求1所述的安检设备,其中,所述第一图像采集装置进一步包括:控制器,与所述天线阵列耦接,所述第二图像采集装置设置在所述天线阵列上,所述控制器用于控制所述天线阵列旋转,所述天线阵列带动所述第二图像采集装置从不同角度对所述待检对象的预设区域进行扫描。
  3. 根据权利要求1所述的安检设备,其中,所述安检设备进一步包括:旋转盘,设置在所述主体框架的底面,所述旋转盘与所述控制器耦接,当所述待检对象在所述旋转盘上,所述控制器控制旋转盘旋转,所述旋转盘的旋转方向与所述天线阵列的旋转方向相反。
  4. 根据权利要求1所述的安检设备,其中,所述三维扫描仪至少包括深度相机、结构光扫描仪、激光三维扫描仪中的任一种。
  5. 根据权利要求1所述的安检设备,其中,所述全局图像包括第一点云数据,所述局部图像包括第二点云数据;
    所述处理器获取所述第二点云数据到所述第一点云数据的旋转矩阵,并将所述第二点云数据与所述旋转矩阵相乘,以获取所述第二点云数据在所述第一点云数据对应的坐标系下的第三点云数据;
    所述处理器从所述第一点云数据中删除第四点云数据,其中,所述第四点云数据与所述全局图像和所述局部图像的重叠区域的第一子区域对应;
    所述处理器从所述第三点云数据中删除第五点云数据,其中,所述第五点云数据与所述全局图像和所述局部图像的重叠区域的第二子区域对应;
    所述处理器将删除所述第四点云数据后的第一点云数据与删除所述第五点云数据后的第三点云数据进行合并。
  6. 根据权利要求5所述的安检设备,其中,所述待检对象为人体,所述全局图像为所述人体的全身图像,所述局部图像为所述人体的头部图像。
  7. 根据权利要求6所述的安检设备,其中,所述第四点云数据的垂直坐标与所述人体头部最高点的垂直坐标的差值小于第一预设值,所述第五点云数据的垂直坐标与所述人体头部最高点的垂直坐标的差值大于或等于第二预设值。
  8. 一种安检设备,其特征在于,所述安检设备包括:
    第一图像采集装置,用于对待检对象进行扫描,以获取所述待检对象的全局图像;
    第二图像采集装置,用于对所述待检对象的预设区域进行扫描,以获取所述待检对象的局部图像,其中,所述局部图像为所述预设区域的三维图像;
    处理器,分别与所述第一图像采集装置及所述第二图像采集装置耦接,用于将所述局部图像与所述全局图像进行融合,以获取所述待检对象的安检图像;
    其中,所述局部图像的分辨率大于所述全局图像的分辨率。
  9. 根据权利要求8所述的安检设备,其中,所述安检设备进一步包括:主体框架,所述第一图像采集装置包括:天线阵列及扫描驱动器,所述天线阵列设 置在所述主体框架上,并与所述扫描驱动器耦接,所述扫描驱动器控制所述天线阵列对所述待检对象进行扫描,以得到所述全局图像。
  10. 根据权利要求9所述的安检设备,其中,所述第一图像采集装置进一步包括:控制器,与所述天线阵列耦接,所述第二图像采集装置设置在所述天线阵列上,所述控制器用于控制所述天线阵列旋转,所述天线阵列带动所述第二图像采集装置从不同角度对所述待检对象的预设区域进行扫描。
  11. 根据权利要求9所述的安检设备,其中,所述安检设备进一步包括:旋转盘,设置在所述主体框架的底面,所述旋转盘与所述控制器耦接,当所述待检对象在所述旋转盘上,所述控制器控制旋转盘旋转,所述旋转盘的旋转方向与所述天线阵列的旋转方向相反。
  12. 根据权利要求8所述的安检设备,其中,所述第二图像采集装置包括三维扫描仪,所述三维扫描仪与所述处理器耦接。
  13. 根据权利要求12所述的安检设备,其中,所述三维扫描仪至少包括深度相机、结构光扫描仪、激光三维扫描仪中的任一种。
  14. 根据权利要求8所述的安检设备,其中,所述全局图像包括第一点云数据,所述局部图像包括第二点云数据;
    所述处理器获取所述第二点云数据到所述第一点云数据的旋转矩阵,并将所述第二点云数据与所述旋转矩阵相乘,以获取所述第二点云数据在所述第一点云数据对应的坐标系下的第三点云数据;
    所述处理器从所述第一点云数据中删除第四点云数据,其中,所述第四点云数据与所述全局图像和所述局部图像的重叠区域的第一子区域对应;
    所述处理器从所述第三点云数据中删除第五点云数据,其中,所述第五点云数据与所述全局图像和所述局部图像的重叠区域的第二子区域对应;
    所述处理器将删除所述第四点云数据后的第一点云数据与删除所述第五点云数据后的第三点云数据进行合并。
  15. 根据权利要求14所述的安检设备,其中,所述待检对象为人体,所述全 局图像为所述人体的全身图像,所述局部图像为所述人体的头部图像。
  16. 根据权利要求15所述的安检设备,其中,所述第四点云数据的垂直坐标与所述人体头部最高点的垂直坐标的差值小于第一预设值,所述第五点云数据的垂直坐标与所述人体头部最高点的垂直坐标的差值大于或等于第二预设值。
  17. 一种安检设备的成像方法,其特征在于,应用于安检设备,所述安检设备包括第一图像采集单元、第二图像采集单元及处理器,所述方法包括:
    第一图像采集装置对待检对象进行扫描,并获取所述待检对象的全局图像;
    第二图像采集装置对所述待检对象的预设区域进行扫描,并获取所述待检对象的局部图像,其中,所述局部图像为所述预设区域的三维图像;
    处理器将所述局部图像与所述全局图像进行融合,并获取所述待检对象的安检图像;
    其中,所述局部图像的分辨率大于所述全局图像的分辨率。
PCT/CN2018/114432 2018-09-03 2018-11-07 一种安检设备及其成像方法 WO2020047993A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811022886.4 2018-09-03
CN201811022886.4A CN109116433B (zh) 2018-09-03 2018-09-03 一种安检设备及其成像方法

Publications (1)

Publication Number Publication Date
WO2020047993A1 true WO2020047993A1 (zh) 2020-03-12

Family

ID=64860591

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/114432 WO2020047993A1 (zh) 2018-09-03 2018-11-07 一种安检设备及其成像方法

Country Status (2)

Country Link
CN (1) CN109116433B (zh)
WO (1) WO2020047993A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108845367A (zh) * 2018-05-30 2018-11-20 深圳市华讯方舟太赫兹科技有限公司 一种安检系统以及安检方法
CN109886872B (zh) * 2019-01-10 2023-05-16 深圳市重投华讯太赫兹科技有限公司 安检设备及其图像检测方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1997912A (zh) * 2004-04-14 2007-07-11 安全观察公司 增强的监视主体成像
CN1998011A (zh) * 2004-04-14 2007-07-11 安全观察公司 多传感器监视入口
US20080043102A1 (en) * 2004-04-14 2008-02-21 Safeview, Inc. Multi-source surveillance system
CN102540264A (zh) * 2011-12-30 2012-07-04 北京华航无线电测量研究所 一种人体隐私部位自动检测与遮挡的微波安检系统
CN202453516U (zh) * 2011-12-30 2012-09-26 北京华航无线电测量研究所 一种微波安检系统
CN106570836A (zh) * 2016-11-03 2017-04-19 北京航星机器制造有限公司 一种辐射图像局部增强方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103400362B (zh) * 2013-07-30 2015-11-25 中国人民解放军第三军医大学第三附属医院 事故近景图与航拍图像相融合获取清晰场景图的方法
CN105243374B (zh) * 2015-11-02 2018-11-20 湖南拓视觉信息技术有限公司 三维人脸识别方法、系统及应用其的数据处理装置
CN106296584B (zh) * 2016-08-02 2020-02-07 杭州普维光电技术有限公司 一种全景拼接图与局部视频或图像融合显示的方法
CN106713772B (zh) * 2017-03-31 2018-08-17 维沃移动通信有限公司 一种拍照方法及移动终端
CN107895345B (zh) * 2017-11-29 2020-05-26 浙江大华技术股份有限公司 一种提高人脸图像分辨率的方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1997912A (zh) * 2004-04-14 2007-07-11 安全观察公司 增强的监视主体成像
CN1998011A (zh) * 2004-04-14 2007-07-11 安全观察公司 多传感器监视入口
US20080043102A1 (en) * 2004-04-14 2008-02-21 Safeview, Inc. Multi-source surveillance system
CN102540264A (zh) * 2011-12-30 2012-07-04 北京华航无线电测量研究所 一种人体隐私部位自动检测与遮挡的微波安检系统
CN202453516U (zh) * 2011-12-30 2012-09-26 北京华航无线电测量研究所 一种微波安检系统
CN106570836A (zh) * 2016-11-03 2017-04-19 北京航星机器制造有限公司 一种辐射图像局部增强方法

Also Published As

Publication number Publication date
CN109116433B (zh) 2020-02-04
CN109116433A (zh) 2019-01-01

Similar Documents

Publication Publication Date Title
CN102809745B (zh) 混合式毫米波成像系统和方法
RU2510036C2 (ru) Адаптивная система обнаружения
CN106556873B (zh) 一种基于人体微波成像的安检方法及系统
WO2018097035A1 (ja) 画像取得装置、これを用いた画像取得方法及び照射装置
CN109691989A (zh) 一种基于红外人脸检测技术的人体温度测量方法
CN108051868A (zh) 太赫兹人体安检成像系统
EP2312336A1 (en) Image processing device
WO2020047993A1 (zh) 一种安检设备及其成像方法
WO2015010531A1 (zh) 人体安全检查方法和人体安全检查系统
TW202111384A (zh) 被搭載於移動體處之雷射掃描系統、被搭載於移動體處之雷射掃描器之雷射掃描方法及雷射掃描程式
US20210096239A1 (en) Intrusion detection system and intrusion detection method
WO2020134338A1 (zh) 毫米波太赫兹成像设备及物体识别分类方法
CN113596335A (zh) 基于图像融合的公路隧道火灾监测系统及方法
US20230082753A1 (en) Structure inspection method and structure inspection system
CN109655931A (zh) 毫米波/太赫兹波成像设备及对人体或物品的检测方法
CN106706709A (zh) 一种线扫描激励连续大面积红外热成像检测方法
CN108596862A (zh) 用于排除红外热像全景图干扰源的处理方法
CN207263664U (zh) 辐射检查系统
US11042988B2 (en) Boundary detection evaluation
CN211086647U (zh) 一种全视角太赫兹安防监控设备
US11344279B2 (en) Imaging method for obtaining human skeleton
Wang et al. Applications of artificial intelligence enhanced drones in distress pavement, pothole detection, and healthcare monitoring with service delivery
JPH09287913A (ja) 物体位置検出装置、人体検出方法
JP2006041939A (ja) 監視装置及び監視プログラム
CN209728193U (zh) 场景监控式毫米波扫描成像系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18932422

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18932422

Country of ref document: EP

Kind code of ref document: A1