CN109544521B - Registration method of passive millimeter wave image and visible light image in human body security check - Google Patents
Registration method of passive millimeter wave image and visible light image in human body security check Download PDFInfo
- Publication number
- CN109544521B CN109544521B CN201811339446.1A CN201811339446A CN109544521B CN 109544521 B CN109544521 B CN 109544521B CN 201811339446 A CN201811339446 A CN 201811339446A CN 109544521 B CN109544521 B CN 109544521B
- Authority
- CN
- China
- Prior art keywords
- millimeter wave
- image
- visible light
- passive millimeter
- meters
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a registration method of a passive millimeter wave image and a visible light image in human body security check, which is used for registering a visible light image and a passive millimeter wave image in millimeter wave rapid security check, and the registration relation determination step is as follows: firstly, determining a visual field boundary of a visible light image and a passive millimeter wave image by a handheld calibration light source at a specific distance, and storing a calibration point image; then, the difference of the field angle ranges of the visible light and the passive millimeter wave image is comprehensively considered, and the calibration point is optimized; and finally, taking the visible light image as a reference, completing perspective transformation and translation transformation of the passive millimeter wave image, and storing the registration parameters. Meanwhile, the calibration distances are limited to four distances of 2.0,2.5,3.0 and 3.5 meters. In practical application, a proper registration parameter is selected according to the distance information, and finally real-time registration output of the visible light and the passive millimeter wave image is completed. The invention can realize the real-time registration output of the visible light and the passive millimeter wave image in the millimeter wave rapid security inspection system.
Description
Technical Field
The invention relates to a registration method according to a passive millimeter wave image and a visible light image, in particular to an image registration method facing a millimeter wave rapid security inspection system, which belongs to the technical field of computer graphics and is mainly applied to registration of a passive millimeter wave image and a visible light image in millimeter wave human body security inspection.
Background
With the development of millimeter wave detection technology, the security inspection system based on millimeter wave fast imaging can quickly and accurately detect hidden contraband carried by non-cooperative targets, so that the security inspection system is widely researched and applied, especially to security inspection in airports, railway stations and large-scale venues.
The traditional security inspection system mainly comprises a metal detection door, a handheld metal detector, an X-ray security inspection system and the like, but the metal detection system comprising the metal detection door and the handheld metal detector can only detect whether a non-cooperative target carries metal objects or not and cannot detect non-metals, drugs, other explosives and the like; the X-ray detection system can detect metal, nonmetal, drugs, explosives and the like, but can cause serious radiation damage to human bodies if subjected to X-ray radiation for a long time, so that the X-ray detection system mainly detects luggage, articles and the like at present.
The millimeter wave is electromagnetic wave between light wave and microwave, can effectively penetrate through clothes and shielding of some insulators, can be applied to a security inspection system to detect and identify hidden contraband carried by a human target, and has no radiation damage to a human body compared with X-ray. However, due to the difference of the imaging principles, the visible light image and the passive millimeter wave image have difference in the field of view, and meanwhile, compared with the non-cooperative target in the visible light image, the non-cooperative target in the passive millimeter wave image has certain morphological deformation.
Therefore, when a concealed anomaly is detected in the passive millimeter wave image, the positioning coordinates of the concealed anomaly cannot be directly marked in the visible light image, and the passive millimeter wave image and the visible light image need to be registered.
Researchers have been trying to solve the registration problem of visible light and millimeter wave image registration methods. The problem of poor Registration effect caused by poor Millimeter Wave Image quality under long-distance imaging is solved by a Super-Resolution reconstruction algorithm in Quanliang Huang (refer to Huang Q, Sun K, Liu S.A New Method for Passive Millimeter Wave Image Registration by Applying Super Resolution [ C ]// Sixth International Conference on Image and graphics IEEE Computer Society,2011:685 and 690). A method for fusing visible light and millimeter wave radiation images [ J ] laser and infrared, 2004,34(5):386-388 ] and the like proposes an image fusion method based on wavelet transformation aiming at the problem of registration and fusion of millimeter wave radiation images and visible light images of foundation or partial airborne imaging. Pramod K.Varshney (refer to Varshney P K, Chen H M, Ramac L C, et al. registration and fusion of acquired and millimeter wave images for coherent web detection [ C ]// International Conference on Image Processing,1999.ICIP 99.proceedings. IEEE,1999: 532-. Although the existing research results obtain a better registration result aiming at the registration problem of the visible light image and the millimeter wave image in respective application scenes, the millimeter wave image has certain deformation characteristics under different imaging distances.
Disclosure of Invention
The technical problem of the invention is solved: the difference of the field ranges of the passive millimeter wave image and the visible light image in the rapid millimeter wave security inspection system is overcome, and the method for registering the passive millimeter wave image and the visible light image in the human body security inspection is provided, so that the detection result of the passive millimeter wave image is marked at the corresponding position in the visible light image in real time, and the problem of deformation of the passive millimeter wave image under different distances can be effectively solved.
The technical solution of the invention is as follows: a registration method of a passive millimeter wave image and a visible light image in human body security inspection comprises the following registration steps:
firstly, measuring the boundary of a calibration point by a handheld luminous source at a fixed distance;
secondly, under the current distance, the visible light and passive millimeter wave calibration point images of all different calibration points are stored;
thirdly, due to the difference of the field angle range between the passive millimeter wave image and the visible light image, the boundary position of the calibration point in the visible light image and the passive millimeter wave image is comprehensively considered to complete the optimization of the calibration point;
fourthly, completing perspective transformation of the passive millimeter wave image by taking the visible light image as a reference through the coordinate relation of the optimized calibration point in the passive millimeter wave image and the visible light image;
fifthly, taking the non-cooperative target in the visible light and the passive millimeter wave image as a matching target, and carrying out translation transformation on the passive millimeter wave image after perspective transformation to ensure that the non-cooperative target in the two images is overlapped and complete registration at the current distance;
and sixthly, storing the perspective transformation parameters and the matching translation transformation parameters under the current distance.
In order to calculate perspective transformation parameters and matching translation transformation parameters under different distances, the steps are repeated under different distances, the distances are respectively 3.5 meters, 3.0 meters, 2.5 meters and 2.0 meters, and finally registration parameters under all the distances are calculated.
In the actual rapid security check process, the registration step of the passive millimeter wave image and the visible light image is as follows:
(1) reading the passive millimeter wave image and the visible light image in real time, and acquiring distance information corresponding to the current frame according to the distance sensor;
(2) selecting perspective transformation parameters corresponding to the current distance according to the current distance information, and carrying out perspective transformation on the passive millimeter wave image;
(3) and selecting matching translation transformation parameters corresponding to the current distance according to the current distance information, and performing translation transformation on the passive millimeter wave image, so as to realize real-time registration output of the passive millimeter wave image and the visible light image.
In the practical application process, the distance information measured by the distance sensor is not a fixed numerical value, so that the registration parameters under different pre-calculated distances can be effectively utilized, and the method for selecting the perspective transformation parameters and the matching translation transformation matrix according to the distance information comprises the following steps:
when the distance is larger than 3.25 meters and smaller than 3.5 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.5 meters;
when the distance is greater than 2.75 meters and less than or equal to 3.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.0 meters;
when the distance is greater than 2.25 meters and less than or equal to 2.75 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.5 meters;
and when the distance is greater than 2.0 meters and less than or equal to 2.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.0 meters.
Compared with the prior art, the invention has the advantages that: although the existing research results obtain a better registration result aiming at the registration problem of the visible light image and the millimeter wave image in respective application scenes, the millimeter wave image has certain deformation characteristics under different imaging distances. In order to better solve the deformation difference between the passive millimeter wave image and the visible light image under different distances, the invention collects the calibration point images of the passive millimeter waves and the visible light at the positions of 2.0 meters, 2.5 meters, 3.0 meters and 3.5 meters by a handheld light source calibration method, then uses the visible light image as a reference image, performs perspective transformation parameter calculation on the optimized 6 calibration points by using a perspective transformation method to realize the perspective transformation of the passive millimeter wave image, and finally performs translation transformation on the passive millimeter wave image after the perspective transformation, thereby finally realizing the registration of the passive millimeter wave image and the visible light image. The registration results of the passive millimeter wave images and the visible light images at 2.0 meters, 2.5 meters, 3.0 meters and 3.5 meters in fig. 6,7,8 and 9(d) respectively show the effectiveness and efficiency of the registration method disclosed by the invention, and compared with the passive millimeter wave images after perspective transformation shown in fig. 6,7,8 and 9(c), it can be obviously seen that the passive millimeter wave images at different distances have different deformation characteristics.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a plot of a visible light and passive millimeter wave image captured at 2.0 meters in accordance with the present invention; (a) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the visible light image, (b) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the passive millimeter wave image;
FIG. 3 is a calibration point image of visible light and passive millimeter wave images collected at 2.5 meters in accordance with the present invention; (a) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the visible light image, (b) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the passive millimeter wave image;
FIG. 4 is a calibration point image of visible light and passive millimeter wave images collected at 3.0 meters in accordance with the present invention; (a) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the visible light image, (b) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the passive millimeter wave image;
FIG. 5 is a calibration point image of visible light and passive millimeter wave images collected at 3.5 meters in accordance with the present invention; (a) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the visible light image, (b) the preferred index points of the boundaries of the upper left, middle left, sitting, upper right, middle right and lower right fields in the passive millimeter wave image;
FIG. 6 shows the visible light and passive millimeter wave images of all the preferred calibration points at different distances according to the present invention, wherein the images of the visible light and passive millimeter wave calibration points collected at positions (a), (b), (c), and (d) are 2.0 m, 2.5 m, 3.0 m, and 3.5 m, respectively;
fig. 7,8, 9, and 10 are the registration results of the visible light and passive millimeter wave images, respectively, in which: (a) the method comprises the following steps of (a) obtaining two visible light images to be registered, (b) obtaining two passive millimeter wave images corresponding to the visible light images, (c) obtaining a result after perspective transformation is carried out on the passive millimeter wave images according to a calibration point, and (d) obtaining a final registration result.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and examples.
The invention relates to a registration method of a passive millimeter wave image and a visible light image in human body security check, which is used for registering a visible light image and a passive millimeter wave image in millimeter wave rapid security check, and the registration relation determination step is as follows: (1) under a specific distance, respectively determining the visual field boundaries of the visible light image and the passive millimeter wave image by using the handheld calibration light source; (2) storing the visible light and passive millimeter wave calibration point images at the current distance; (3) due to the difference of the visible light image and the passive millimeter wave image in the field angle range, the boundary position of the calibration point in the visible light image and the passive millimeter wave image is comprehensively considered so as to complete the optimization of the calibration point; (4) the perspective transformation of the passive millimeter wave image is completed by taking the visible light image as a reference according to the coordinate relation of the optimized calibration point in the visible light and the passive millimeter wave image; (5) taking a non-cooperative target in the visible light and the passive millimeter wave image as a matching target, and carrying out translation transformation on the passive millimeter wave image after perspective transformation to ensure that the non-cooperative target in the two images is overlapped and complete registration under the current distance; (6) saving perspective transformation parameters and matching translation transformation parameters under the current distance; (7) and finishing the registration of the visible light and the passive millimeter wave images at different distances by the same step, and simultaneously saving the perspective transformation parameters and the matching translation parameters. In practical application, firstly, the distance sensor acquires the distance information of the non-cooperative target, the registration parameters at the current distance which are pre-measured are selected according to the distance information, and finally, the real-time registration output of the visible light and the passive millimeter wave image is completed. The invention can realize the real-time registration output of the visible light and the passive millimeter wave image in the millimeter wave rapid security inspection system, ensures that the detection result based on the passive millimeter wave image is displayed in the visible light image in real time, and improves the positioning accuracy of the hidden prohibited object.
As shown in fig. 1, the registration process of the passive millimeter wave image and the visible light image of the invention specifically comprises the following steps:
1. index point boundary measurement at specific distances
Under the set distance, one of the distances of 2.0 meters, 2.5 meters, 3.0 meters and 3.5 meters, the handheld luminous source continuously carries out boundary measurement of the calibration point under the current distance, and the maximum outer boundary of the visible light image and the passive millimeter wave image is preliminarily determined. The invention collects the images of the calibration points at 2.0 m, 2.5 m, 3.0 m and 3.5 m respectively.
2. Image acquisition of different calibration points
At the current distance, the visible light and passive millimeter wave index point images are saved as much as possible, especially the index point images close to the boundary of the field of view range, including the visible light and passive millimeter wave index point images at the four boundaries of the upper, lower, left and right.
3. Preference of index point image
Because the passive millimeter wave image and the visible light image have a difference in the field angle range, and the calibration point at the boundary of the visible light image is not necessarily located at the boundary of the field of view, the boundary position of the calibration point in the visible light image and the passive millimeter wave image needs to be considered comprehensively, such as the preferred boundary calibration point shown in fig. 2,3, 4, and 5, which not only ensures that the 6 preferred calibration points exist in the passive millimeter wave image and the visible light image at the same time, but also satisfies that the calibration point is the maximum boundary between the two. Taking fig. 2 as an example, (a) shows a preferable visible light image field boundary calibration point image at a distance of 2.0 meters; (b) the figure shows the preferred passive millimeter wave image view field boundary fixed point images at a distance of 2.0 meters, namely, the upper left landmark fixed point image, the middle left landmark fixed point image, the lower left landmark fixed point image, the upper right landmark fixed point image, the middle right landmark fixed point image and the lower right landmark fixed point image. Fig. 3,4 and 5 are similar to fig. 2, except that the images of the index points are at distances of 2.5 meters, 3.0 meters and 3.5 meters, respectively. Fig. 6 shows all preferred index point images at 4 different distances, where (a), (b), (c), and (d) are all preferred index point images at 2.0 meters, 2.5 meters, 3.0 meters, and 3.5 meters, respectively, with the first row showing the top left, middle left, bottom left, top right, middle right, and bottom right border preferred index points in the visible image, and the second row showing the top left, middle left, bottom left, top right, middle right, and bottom right border preferred index points in the passive millimeter wave image.
4. Perspective transformation of passive millimeter wave images
In order to accurately register the passive millimeter wave image and the visible light image, the method takes the visible light image as a reference, and completes perspective transformation of the passive millimeter wave image according to the coordinate relationship of the optimized passive millimeter wave image and the visible light image calibration point.
Let IvAnd ImRespectively visible light image and passive millimeter wave image, (x)i,yi)∈Iv1,2,3, 6 denote 6 preferred index points in the visible light image, (u)j,vj)∈ImJ ═ 1,2, 3.., 6 denotes the corresponding 6 preferred index points in the passive millimetre wave image. According to the definition of perspective transformation, with one of the index points (u)1,v1) For example, the passive millimeter wave image may be labeled byCarrying out perspective projection transformation on fixed points:
the following can be obtained from the above formula:
the corresponding index point (x) in the visible light image1,y1) Can be obtained by the following formula:
finishing to obtain:
let X1=(u1,v1,1,0,0,0,-x1u1,-x1v1,-x1),Y1=(0,0,0,u1,v1,1,-y1u1,-y1v1,-y1),H=(h1,h2,h3,h4,h5,h6,h7,h8,h9)TThen equation (4) can be expressed as:
A1H=[X1 Y1]TH=0 (5)
the invention uses the optimized 6 calibration points to perform the projection transformation of the passive millimeter wave image, and then the formula (5) is further expressed as:
AH=[X1 Y1 X2 Y2 X3 Y3 X4 Y4 X5 Y5 X6 Y6]TH=0 (6)
then, the present invention decomposes a using singular-value decomposition (SVD) theory to obtain:
A=UΣVT (7)
u and V represent two orthogonal matrices, and Σ represents a diagonal matrix, respectively. From equation (6), the size of matrix a is 12 × 9, and from SVD decomposition theory, the sizes of matrices U, Σ, V are 12 × 12, 12 × 9, 9 × 9, respectively. Therefore, the last column of the right feature matrix V in equation (7) is converted into a 3 × 3 matrix, and the perspective transformation matrix H is the 3 × 3 matrix.
5. Translation registration of passive millimeter wave image and visible light image after perspective transformation
Once the perspective transformation matrix is calculated, perspective transformation of the passive millimeter wave image can be realized. As shown in (c) of fig. 7,8, 9, and 10, the non-cooperative target in the passive millimeter wave image and the non-cooperative target in the visible light image basically keep the same shape, and only the passive millimeter wave image after perspective transformation needs to be subjected to translation operation, so as to ensure that the passive millimeter wave image and the non-cooperative target in the visible light image are overlapped, thereby achieving the best matching effect.
6. Preserving registration parameters
The registration of the passive millimeter wave image and the visible light image at a specific distance can be completed through the steps, and for the convenience of direct calling in practical application, registration parameters at the distance need to be stored, including perspective transformation matrix and translation transformation parameters.
The registration method of the passive millimeter wave image and the visible light image provided by the invention is used for acquiring the calibration point image and calculating the registration parameters at the positions of 2.0 meters, 2.5 meters, 3.0 meters and 3.5 meters respectively. According to the registration parameters which are calculated and stored, the practical application steps of the passive millimeter wave image and the visible light image are as follows:
(1) reading the passive millimeter wave image and the visible light image in real time, and acquiring distance information corresponding to the current frame according to the distance sensor;
(2) selecting perspective transformation parameters corresponding to the current distance according to the current distance information, and carrying out perspective transformation on the passive millimeter wave image;
(3) and selecting matching translation transformation parameters corresponding to the current distance according to the current distance information, and performing translation transformation on the passive millimeter wave image, thereby realizing the registration application of the passive millimeter wave image and the visible light image in real time.
The method for selecting the perspective transformation parameters and the matching translation transformation parameters according to the distance information comprises the following steps:
when the distance is larger than 3.25 meters and smaller than 3.5 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.5 meters;
when the distance is greater than 2.75 meters and less than or equal to 3.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.0 meters;
when the distance is greater than 2.25 meters and less than or equal to 2.75 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.5 meters;
and when the distance is greater than 2.0 meters and less than or equal to 2.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.0 meters.
As shown in (d) of fig. 7,8, 9 and 10, as a result of the registration of the passive millimeter wave image and the visible light image at different distances, the non-cooperative human target achieves better registration.
Claims (3)
1. A registration method of a passive millimeter wave image and a visible light image in human body security inspection is characterized by comprising the following steps:
firstly, respectively determining a visible light image view field boundary and a passive millimeter wave image view field boundary by a handheld calibration light source at a set distance;
secondly, under the set distance, storing all different calibration points in the visible light image and the passive millimeter wave image;
thirdly, determining the boundary position of the calibration point in the visible light image and the passive millimeter wave image based on the visual field boundary of the visible light image and the visual field boundary of the passive millimeter wave image determined in the first step according to the difference of the visual field angle ranges of the visible light image and the passive millimeter wave image, and obtaining the optimal calibration point in the visible light image and the passive millimeter wave image;
fourthly, according to the coordinate relation of the optimal calibration point in the passive millimeter wave image and the visible light image, taking the visible light image as a reference, completing perspective transformation of the passive millimeter wave image to obtain a transformed passive millimeter wave image;
fifthly, taking a non-cooperative target in the visible light image and the passive millimeter wave image as a matching target, performing translation transformation on the passive millimeter wave image transformed in the fourth step to ensure that the visible light image and the non-cooperative target in the passive millimeter wave image are overlapped, completing registration under the current set distance, and obtaining registration parameters by registration, wherein the registration parameters comprise perspective transformation parameters and matching translation transformation parameters;
sixthly, saving perspective transformation parameters and matching translation transformation parameters under the current set distance;
seventhly, repeating the first step to the sixth step under different set distances, and finally calculating registration parameters of the visible light images and the passive millimeter wave images under all the set distances, wherein the registration parameters comprise perspective transformation parameters and matching translation transformation parameters;
in the seventh step, the application steps of the registration parameters of the visible light image and the passive millimeter wave image at all the set distances are as follows:
(1) reading the passive millimeter wave image and the visible light image in real time, and acquiring distance information corresponding to the current frame according to the distance sensor;
(2) selecting perspective transformation parameters corresponding to the current distance according to the current distance information, and carrying out perspective transformation on the passive millimeter wave image;
(3) selecting matching translation transformation parameters corresponding to the current distance according to the current distance information, and carrying out translation transformation on the passive millimeter wave image, so as to realize real-time registration of the passive millimeter wave image and the visible light image;
in the steps (2) and (3), the method for selecting the perspective transformation parameter corresponding to the current distance and the method for matching the translation transformation parameter according to the current distance information comprises the following steps:
when the distance is larger than 3.25 meters and smaller than 3.5 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.5 meters;
when the distance is greater than 2.75 meters and less than or equal to 3.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 3.0 meters;
when the distance is greater than 2.25 meters and less than or equal to 2.75 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.5 meters;
and when the distance is greater than 2.0 meters and less than or equal to 2.25 meters, the registration parameters select perspective transformation parameters and matching translation transformation parameters corresponding to 2.0 meters.
2. The method for registering the passive millimeter wave image and the visible light image in the human body security check according to claim 1, characterized in that: in the first step, 4 distances are set, which are respectively 2.0 meters, 2.5 meters, 3.0 meters and 3.5 meters.
3. The method for registering the passive millimeter wave image and the visible light image in the human body security check according to claim 1, characterized in that: in the third step, the preferable number of the index points is 6, and the number represents the upper left, upper right, middle left, middle right, lower left, and lower right boundaries of the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811339446.1A CN109544521B (en) | 2018-11-12 | 2018-11-12 | Registration method of passive millimeter wave image and visible light image in human body security check |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811339446.1A CN109544521B (en) | 2018-11-12 | 2018-11-12 | Registration method of passive millimeter wave image and visible light image in human body security check |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109544521A CN109544521A (en) | 2019-03-29 |
CN109544521B true CN109544521B (en) | 2021-08-17 |
Family
ID=65846782
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811339446.1A Active CN109544521B (en) | 2018-11-12 | 2018-11-12 | Registration method of passive millimeter wave image and visible light image in human body security check |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109544521B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112381748A (en) * | 2020-11-16 | 2021-02-19 | 上海亨临光电科技有限公司 | Terahertz and visible light image registration method and device based on texture feature points |
CN113284128B (en) * | 2021-06-11 | 2023-05-16 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Image fusion display method and device based on power equipment and computer equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102938146A (en) * | 2012-08-14 | 2013-02-20 | 中山大学 | Automatic registration method for multi-source remote sensing images based on J-divergences |
KR20130023930A (en) * | 2011-08-30 | 2013-03-08 | 대구대학교 산학협력단 | Registration and fusion method between passive millimeter wave image and visulal image for detecting concealed objects |
CN105607056A (en) * | 2015-12-28 | 2016-05-25 | 深圳市太赫兹科技创新研究院 | Human body security check system and method |
CN107977924A (en) * | 2016-10-21 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of image processing method based on dual sensor imaging, system |
CN108510528A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of method and device of visible light and infrared image registration fusion |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8712177B2 (en) * | 2011-01-25 | 2014-04-29 | Siemens Aktiengesellschaft | Motion compensated overlay |
US9571312B2 (en) * | 2013-11-26 | 2017-02-14 | University Of Virginia Patent Foundation | Expurgated pulse position modulation for communication |
US9684963B2 (en) * | 2014-12-31 | 2017-06-20 | Flir Systems, Inc. | Systems and methods for dynamic registration of multimodal images |
JP6446303B2 (en) * | 2015-03-19 | 2018-12-26 | パナソニック株式会社 | Wireless communication apparatus and communication control method |
US10481235B2 (en) * | 2016-07-21 | 2019-11-19 | Canon Medical Systems Corporation | Magnetic resonance imaging apparatus and image processing apparatus |
CN106447704B (en) * | 2016-10-13 | 2019-04-19 | 西北工业大学 | Visible light based on marking area feature and edge degree-infrared image method for registering |
CN107993258B (en) * | 2017-11-23 | 2021-02-02 | 浙江大华技术股份有限公司 | Image registration method and device |
CN108376395B (en) * | 2017-11-23 | 2019-01-18 | 六安同辉智能科技有限公司 | Dynamic Graph display platform based on image recognition |
-
2018
- 2018-11-12 CN CN201811339446.1A patent/CN109544521B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130023930A (en) * | 2011-08-30 | 2013-03-08 | 대구대학교 산학협력단 | Registration and fusion method between passive millimeter wave image and visulal image for detecting concealed objects |
CN102938146A (en) * | 2012-08-14 | 2013-02-20 | 中山大学 | Automatic registration method for multi-source remote sensing images based on J-divergences |
CN105607056A (en) * | 2015-12-28 | 2016-05-25 | 深圳市太赫兹科技创新研究院 | Human body security check system and method |
CN107977924A (en) * | 2016-10-21 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of image processing method based on dual sensor imaging, system |
CN108510528A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of method and device of visible light and infrared image registration fusion |
Non-Patent Citations (2)
Title |
---|
无源毫米波图像配准技术研究;孙坤;《中国优秀硕士学位论文全文数据库信息科技辑》;20130715;第I,18-19,31-39页 * |
用于人员安检的主动毫米波成像技术现状与展望;费鹏 等;《微波学报》;20150430;第31卷(第2期);第91-96页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109544521A (en) | 2019-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11244197B2 (en) | Fast and robust multimodal remote sensing image matching method and system | |
WO2017049994A1 (en) | Hyperspectral image corner detection method and system | |
CN109785371A (en) | A kind of sun image method for registering based on normalized crosscorrelation and SIFT | |
CN110044374A (en) | A kind of method and odometer of the monocular vision measurement mileage based on characteristics of image | |
CN109544521B (en) | Registration method of passive millimeter wave image and visible light image in human body security check | |
CN106772417A (en) | A kind of multiple dimensioned infrared spectrum pattern measurement method and system of moving-target various dimensions | |
Zhu et al. | Robust registration of aerial images and LiDAR data using spatial constraints and Gabor structural features | |
Gong et al. | Extrinsic calibration of a 3D LIDAR and a camera using a trihedron | |
CN113093184B (en) | Interferometric measurement method based on video synthetic aperture radar | |
Deng et al. | Line scanning thermography reconstruction algorithm for defects inspection with novel velocity estimation and image registration | |
CN107797110B (en) | System imaging method of synthetic aperture projection radiation and synthetic aperture projection radiometer | |
CN109581526B (en) | Real-time tracking imaging method applied to camera type millimeter wave human body security check instrument | |
CN106251350B (en) | A kind of RCS picture based on infinitesimal inertia and objective contour method for registering | |
CN112734683B (en) | Multi-scale SAR and infrared image fusion method based on target enhancement | |
CN106910178B (en) | Multi-angle SAR image fusion method based on tone statistical characteristic classification | |
CN110231625B (en) | Synthetic aperture imaging method based on multi-scale fusion | |
Luo et al. | Local road area extraction in CSAR imagery exploiting improved curvilinear structure detector | |
Su et al. | Obtaining obstacle information by an omnidirectional stereo vision system | |
Boerner et al. | Brute force matching between camera shots and synthetic images from point clouds | |
CN110969601A (en) | Structure rotation response non-contact type identification method based on visual feature tracking algorithm | |
CN107526079A (en) | A kind of spatial spin target wideband radar three-D imaging method based on L-type triantennary interference treatment | |
CN116125493A (en) | Target three-dimensional reconstruction method based on optical radar image projection feature fusion | |
CN111489398B (en) | Imaging equipment calibration method and device | |
CN114067064A (en) | Target three-dimensional reconstruction method based on multi-view radar image | |
CN112766032A (en) | SAR image saliency map generation method based on multi-scale and super-pixel segmentation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |