CN102697503B - Human detection method based on millimeter wave imaging - Google Patents
Human detection method based on millimeter wave imaging Download PDFInfo
- Publication number
- CN102697503B CN102697503B CN201210049549.0A CN201210049549A CN102697503B CN 102697503 B CN102697503 B CN 102697503B CN 201210049549 A CN201210049549 A CN 201210049549A CN 102697503 B CN102697503 B CN 102697503B
- Authority
- CN
- China
- Prior art keywords
- human body
- image
- original image
- human
- module
- 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
Abstract
The invention discloses a human detection method based on millimeter wave imaging. The method comprises the following steps of: performing millimeter wave scanning on a detected person to acquire an original image; adjusting the original image to acquire a target image; partitioning and positioning parts of the body according to the target image; and generating a human model. By the human detection method based on the millimeter wave imaging, the parts of the body in the millimeter wave image are identified and processed, so that a foundation is provided for technologies of checking concealed articles and protecting privacy.
Description
Technical field
The present invention relates to the detection method of field of safety check, more specifically, the present invention relates to a kind of human body detecting method based on mm-wave imaging.
Background technology
In field of safety check, for human body and the detection of hiding article thereof, there is following various ways: metal detector, x-ray fluoroscopy, infrared detection and millimeter wave detection etc.Metal detector is realized by electromagnetic induction, can only judge the presence or absence of metal object, can not imaging or determine object space.X-ray fluoroscopy equipment has very strong penetrance, is generally used for the detection for luggage and articles, as directly can be comparatively large to people's danger to human detection, be therefore generally rarely used in human detection in safety check.Infrared detection utilizes the thermal radiation property of object to carry out imaging, can be used for the detection to human body in safety check.The brightness of the object in infrared image depends primarily on the surface emissivity characteristic of the temperature of object and the heat of radiation and object, be characterized in there is no significant corner angle, marginal information, its edge lines are round and smooth, and grey scale change is slow, to the shape details of object and small attitudes vibration insensitive.These features make to detect the human body in infrared image to have certain difficulty.
Millimeter wave (3GHz-300GHz) is a kind of electromagnetic wave between light wave and radio wave.Millimeter wave can penetrate all medicated clothing clothes, and the millimeter wave energy of human body radiation comparatively metal, pottery, plastic explosive, powder type explosive and medicated clothing, insulant etc. be eager to excel, utilize active/passive millimeter-wave technology to detect to be hidden in the prohibited items such as various cutters, gun, explosive of human body surface.Due to stronger than metal detection technical capability, more safer than ray technology, over nearly 10 years, human body millimeter wave safety check technology is rapidly developed.The focal plane arrays (FPA) scanning technique of passive-type, multi-beam frequency-scan technique and active 3D hologram millimeter-wave technology obtain test and application in succession.Utilize active MMW rays safety detection apparatus to after human body imaging, the various article that characteristics of human body and human body carry in image, can be shown more clearly.
First, in millimeter wave safety check, the analysis of human body image is important composition link.After human body mm-wave imaging, how carrying out detection to human body image and analyze, is the basis that safe examination system realize target detects automatization, is to the concealment sign of article position on human body and the basis to human body image secret protection in subsequent treatment.
Secondly, how concealment article are detected after mm-wave imaging and sign on human body, it is the method by manual analysis in prior art, wherein image enhancement technique and multiframe comparison techniques are applied in manual analysis, but need the interpretive analysis by professional person, the identification to concealment article and location can be realized.Although attempted based on the image Segmentation Technology of the methods such as gray scale multi thresholds, Boundary Extraction, rim detection, region segmentation, wavelet transformation, morphology, fuzzy mathematics, genetic algorithm, neutral net, comentropy and applied in the automatic detection of concealment article, but owing to disconnecting mutually with human vision mechanism, only utilize gray scale in image and spatial information to Image Segmentation Using, still can produce the situation inconsistent with human vision.And based on the method for positioning analyzing of human body prior model, be applied in the motion tracking of human body, reduce the complexity of tracking, wherein mainly comprise the stick model etc. of bar band model as shown in figure 32, Figure 33, but because stick model only comprises human body contour outline information, as structure, shape, attitude etc., and stick model only comprises each articulare of human body, all can only be limited to the detection of human body, still directly can not solve the automatic detection and Identification problem of concealment article at human body.
3rd, pass through millimeter wave scanning imaging, can concealment Item Information in human body, but exposure and the display of human body privacy (as face and privacy places) can be caused simultaneously, how to carry out analyzing and processing to image after mm-wave imaging, before display concealment article, the privacy information of shielding human body is also the technical problem needing in safe examination system to solve.
Summary of the invention
The object of the invention is to provide a kind of human body detecting method based on mm-wave imaging and device, realizes in millimeter wave scanning the identification of partes corporis humani position and location.
The method comprises the following steps: carry out millimeter wave scanning to tested personnel and obtain original image; Adjustment is carried out to described original image and obtains target image; Segmentation and the location of human body is carried out according to described target image; Generate anthropometric dummy.
Further, described according to described target image carry out human body segmentation and location also comprise following sub-step: the vertical centrage determining human body; Determine the coordinate of each key point of described target image human body and the horizontal division line obtained between partes corporis humani position; Determine width and the slope of partes corporis humani position.
Further, described generation anthropometric dummy comprises: according to the coordinate of described each key point, the width of described partes corporis humani position and slope, obtains the anthropometric dummy with rectangle and/or parallelogram composition.
Further, described to described original image carry out adjustment obtain target image also comprise following sub-step: pretreatment is carried out to described original image and obtains preliminary denoising image; Binaryzation is carried out to described preliminary denoising image and obtains preliminary bianry image; Reprocessing is carried out to described preliminary bianry image and obtains described target image.
Further, describedly pretreatment is carried out to described original image obtain preliminary denoising image and comprise following sub-step further: described original image and background image gray value carry out difference operation; Picture smooth treatment; Linear gradation converts.
Further, describedly binaryzation is carried out to described preliminary denoising image to obtain preliminary bianry image be utilize Pulse Coupled Neural Network algorithm to be with entropy the threshold value that criterion chooses binaryzation to the maximum.
Further, describedly reprocessing is carried out to described preliminary bianry image to obtain described target image be pass through morphologic filtering.
Further, describedly to be comprised by morphologic filtering: use the length of side be 5 square structure element carry out erosion operation and eliminate bright noise spot outside human body; Use the length of side be 4 square structure element carry out eliminating while opening operation keeps image size isolated area and the burr at human body edge; Use the length of side be 4 square structure element carry out the minuscule hole of filling while closed operation keeps image size in human body, and the edge of level and smooth human body; Use the length of side be 5 square structure element carry out dilation operation and make Postprocessing technique arrive life size.
Further, describedly pretreatment is carried out to described original image obtain preliminary denoising image and also comprise following sub-step: image enhaucament is carried out to described original image.
Correspondingly, the human body detection device based on mm-wave imaging of the present invention, comprising: scanning means, obtains original image for carrying out millimeter wave scanning to tested personnel; Adjusting module, obtains target image for carrying out adjustment to described original image; Segmentation locating module, for carrying out segmentation and the location of human body according to described target image; Anthropometric dummy generation module, for generating anthropometric dummy.
Further, described segmentation locating module also comprises following submodule: vertically centrage module, for determining the vertical centrage of human body; Coordinate horizontal line module, for determining the coordinate of each key point of described target image human body and the horizontal division line obtained between partes corporis humani position; Width slope module, for determining width and the slope of partes corporis humani position.
Further, described anthropometric dummy generation module is further used for the coordinate according to described each key point, the width of described partes corporis humani position and slope, obtains the anthropometric dummy with rectangle and/or parallelogram composition.
Further, described adjusting module also comprises following submodule: pretreatment module, obtains preliminary denoising image for carrying out pretreatment to described original image; Binarization block, obtains preliminary bianry image for carrying out binaryzation to described preliminary denoising image; Reprocessing module, obtains described target image for carrying out reprocessing to described preliminary bianry image.
Further, described pretreatment module comprises further with lower unit:
Difference operation unit, for carrying out difference operation by described original image and background image gray value; Smoothing processing unit, for carrying out picture smooth treatment; Linear change unit, for carrying out linear gradation conversion.
Further, described binarization block utilizes Pulse Coupled Neural Network algorithm to be with entropy the threshold value that criterion chooses binaryzation to the maximum further.
Further, described reprocessing module carries out reprocessing further by morphologic filtering.
Further, describedly to be comprised by morphologic filtering: use the length of side be 5 square structure element carry out erosion operation and eliminate bright noise spot outside human body; Use the length of side be 4 square structure element carry out eliminating while opening operation keeps image size isolated area and the burr at human body edge; Use the length of side be 4 square structure element carry out the minuscule hole of filling while closed operation keeps image size in human body, and the edge of level and smooth human body; Use the length of side be 5 square structure element carry out dilation operation and make Postprocessing technique arrive life size.
Further, described pretreatment module also comprises: image enhancing unit, for carrying out image enhaucament to described original image.
By the human body detecting method based on mm-wave imaging of the present invention and device, achieve in millimeter-wave image to the identification of human body parts and process, for subsequent survey concealment article and secret protection provide the foundation.
The location that the object of the invention is also to provide a kind of automatic detection and Identification method and apparatus hiding article to realize distributing on human body to concealment article in millimeter wave scanning and identifying from manually becoming automatically, reduces the instructions for use of personnel.
The automatic detection and Identification method of described concealment article, comprises the following steps: carry out millimeter wave scanning to tested personnel and obtain original image; Adjustment is carried out to described original image and obtains target image; Segmentation and the location of human body is carried out according to described target image; Generate bar rod combination model; According to described original image, non-human target is detected, obtain non-human target distribution original image; Described bar rod combination model is utilized to obtain the location distribution information of described non-human target distribution original image relative to human body; Classification identification is carried out to described non-human target and shows the location distribution information of concealment article relative to human body.
Further, described generation bar rod combination model comprises following sub-step: generate the stick model providing each key point of human body; Generate the bar band model that human body contour outline information is provided; In conjunction with described stick model and described bar band model, generate bar rod combination model.
Further, describedly according to described original image, non-human target to be detected, obtain non-human target distribution original image and comprise following sub-step: rim detection is carried out to described original image, tentatively identify non-human target; Non-human target distribution region is highlighted by mathematical morphological operation; Choose minimum circumscribed rectangle according to the border in described non-human target distribution region and obtain non-human goal rule regional distribution chart; Merge described non-human goal rule regional distribution chart and described original image, obtain described non-human target original image.
Further, the described described non-human target distribution original image of described bar rod combination model acquisition that utilizes is by being input to by described non-human target distribution original image on described bar rod combination model relative to the location distribution information of human body.
Further, described to described non-human target carry out classification identification and display concealment article comprise following sub-step relative to the location distribution information of human body: the exposed position of human body is positioned; The non-human target be distributed on the exposed position of human body is defined as non-concealment article, the non-human target be distributed in outside the exposed position of human body is defined as hide article; Reject the original image of described non-concealment article and show the distributed intelligence of concealment article original image on described bar rod combination model.
Correspondingly, the automatic detection and Identification device of concealment article of the present invention, comprising: scanning means, obtains original image for carrying out millimeter wave scanning to tested personnel; Adjusting module, obtains target image for carrying out adjustment to described original image; Segmentation locating module, for carrying out segmentation and the location of human body according to described target image; Bar rod combination model generation module, for generating bar rod combination model; Non-human target Preliminary detection module, for detecting non-human target according to described original image, obtains non-human target distribution original image; Non-human target distribution module, obtains the location distribution information of described non-human target distribution original image relative to human body for utilizing described bar rod combination model; Classification recognition module, for carrying out classification identification and showing the location distribution information of concealment article relative to human body to described non-human target.
Further, described bar rod combination model generation module comprises following submodule: stick model generation module, for generating the stick model providing each key point of human body; Band model generation module, for generating the bar band model providing human body contour outline information; Binding modules, in conjunction with described stick model and described bar band model.
Further, described non-human target Preliminary detection module comprises following submodule: edge detection module, for carrying out rim detection to described original image, and the non-human target of preliminary identification; Highlight module, for being highlighted non-human target distribution region by mathematical morphological operation; Regularization module, obtains non-human goal rule regional distribution chart for choosing minimum circumscribed rectangle according to the border in described non-human target distribution region; Fusion Module, for merging described non-human goal rule regional distribution chart and described original image, obtains described non-human target original image.
Further, described non-human target distribution module is by being input to by described non-human target distribution original image on described bar rod combination model.
Further, described classification recognition module comprises following submodule: exposed spots localization module, for positioning the exposed position of human body; Sort module, for the non-human target be distributed on the exposed position of human body is defined as non-concealment article, is defined as the non-human target be distributed in outside the exposed position of human body hiding article; Display module, for rejecting the original image of described non-concealment article and showing the distributed intelligence of concealment article original image on described bar rod combination model.
By the method and apparatus of the automatic detection and Identification of concealment article of the present invention, achieving the detection and Identification of concealment article automatic from manually becoming, reducing the instructions for use of personnel, reducing personal error, shorten and detect the interpretation time.
The object of the invention is also to provide a kind of method for secret protection based on mm-wave imaging and device, achieves the secret protection to tested personnel in millimeter wave scanning.
Method for secret protection based on mm-wave imaging of the present invention, comprises the following steps: carry out millimeter wave scanning to tested personnel and obtain original image; Human detection and concealment Articles detecting is carried out according to described original image; Determine the privacy places of human body; The privacy places of human body is shielded and indicates the concealment Item Information on human body.
Further, describedly determine that the privacy places of human body comprises: the sex judging tested personnel, when tested personnel are male, the region of head zone and the downward torso width 1/2 of human body waist is defined as privacy places, when tested personnel are women, the region of human body head region, the downward torso width 1/2 of human body waist and trunk are privacy places from trunk upper end down to the region of trunk height 1/2.
Further, the described privacy places to human body shields and the concealment Item Information indicated on human body comprises: on described original image, carry out Fuzzy processing forming section obfuscation original image to privacy places; Described concealment article sign frame marks by described obscure portions original image.
Further, the described privacy places to human body shields and the concealment Item Information indicated on human body comprises: select the object image in described human detection; Judge to hide the privacy places whether article are in human body, if so, then use the color blocks different from human body color to represent and hide article and indicate on described object image; If not, then the original image of concealment article is presented on described object image.
Further, the described privacy places to human body shields and the concealment Item Information indicated on human body comprises: on described original image, carry out whole Fuzzy processing to human body form whole obfuscation original image; Judge to hide the privacy places whether article are in human body, if so, then use the color blocks different from human body color to represent and hide article and indicate on described whole obfuscation original image; If not, then the original image of concealment article is presented on described whole obfuscation original image.
Further, the described privacy places to human body shields and the concealment Item Information indicated on human body comprises: select the anthropometric dummy in described human detection; Use the color blocks different from anthropometric dummy color to represent hide article and indicate in described anthropometric dummy.
Correspondingly, the privacy protection device based on mm-wave imaging of the present invention comprises: scanning means, obtains original image for carrying out millimeter wave scanning to tested personnel; Checkout gear, for carrying out human detection and concealment Articles detecting according to described original image; Privacy places determination module, for determining the privacy places of human body; Privacy mask module, for shielding the privacy places of human body and indicating the concealment Item Information on human body.
Further, described privacy places determination module is further used for: the sex judging tested personnel, when tested personnel are male, the region of head zone and the downward torso width 1/2 of human body waist is defined as privacy places, when tested personnel are women, the region of human body head region, the downward torso width 1/2 of human body waist and trunk are privacy places from trunk upper end down to the region of trunk height 1/2.
Further, described privacy mask module comprises following submodule further: obscure portions module, for carrying out Fuzzy processing forming section obfuscation original image to privacy places on described original image; First indicates module, for being marked by described concealment article sign frame on described obscure portions original image.
Further, described privacy mask module comprises further: select object image module, for selecting the object image in described human detection; Second indicates module, hides for judging the privacy places whether article are in human body, if so, then uses the color blocks different from human body color to represent and hides article and indicate on described object image; If not, then the original image of concealment article is presented on described object image.
Further, described privacy mask module comprises further: all obfuscation modules, form whole obfuscation original image for carrying out whole Fuzzy processing to human body on described original image; 3rd indicates module, hides for judging the privacy places whether article are in human body, if so, then uses the color blocks different from human body color to represent and hides article and indicate on described whole obfuscation original image; If not, then the original image of concealment article is presented on described whole obfuscation original image.
Further, described privacy mask module comprises further: preference pattern module, for selecting the anthropometric dummy in described human detection; 4th indicates module, represents hide article and indicate in described anthropometric dummy for using the color blocks different from anthropometric dummy color.
By the method for secret protection based on mm-wave imaging of the present invention and device, avoid the exposure to human body privacy when detecting concealment article, achieve the available protecting to privacy places of human body.
Accompanying drawing explanation
Below with reference to accompanying drawings and the present invention is specifically described in conjunction with the embodiments.
Fig. 1 is the human body detecting method basic flow sheet based on mm-wave imaging;
Fig. 2 is the human body detection device basic block diagram based on mm-wave imaging;
Fig. 3 is original image;
Fig. 4 is preliminary denoising image;
Fig. 5 is preliminary bianry image;
Fig. 6 is the flow chart of step S2 in the human body detecting method based on mm-wave imaging;
Fig. 7 is the structural representation of adjusting module in the human body detection device based on mm-wave imaging;
Image for the purpose of Fig. 8;
Fig. 9 is human body backbone figure;
Figure 10 is human body segmentation effect figure;
Figure 11 is the flow chart of step S3 in the human body detecting method based on mm-wave imaging;
Figure 12 is the structural representation splitting locating module in the human body detection device based on mm-wave imaging;
Figure 13 is the anthropometric dummy figure based on obtaining in the human body detecting method of mm-wave imaging and device;
Figure 14 is anthropometric dummy figure and the corresponding design sketch of original image;
Figure 15 is the basic flow sheet of the automatic detection and Identification method of concealment article;
Figure 16 is the flow chart of step S5 in the automatic detection and Identification method of concealment article;
Figure 17 is bar rod combination model figure;
Figure 18 is the flow chart of step S6 in the automatic detection and Identification method of concealment article;
Figure 19 is the non-human target image of preliminary identification;
Figure 20 is non-human target distribution administrative division map;
Figure 21 is non-human goal rule regional distribution chart;
Figure 22 is non-human target original image;
Figure 23 is the scattergram of non-human target original image on bar rod combination model;
Figure 24 is the scattergram of concealment article original image on bar rod combination model;
Figure 25 is the flow chart of step S8 in the automatic detection and Identification method of concealment article;
Figure 26 is the basic flow sheet of the method for secret protection based on mm-wave imaging;
Figure 27 is the structural representation of the privacy protection device based on mm-wave imaging;
Figure 28 is the design sketch of the first embodiment of privacy mask;
Figure 29 is the design sketch of the second embodiment of privacy mask;
Figure 30 is the design sketch of the third embodiment of privacy mask;
Figure 31 is the design sketch of the 4th kind of embodiment of privacy mask;
Figure 32 is the band model schematic in background technology;
Figure 33 is the stick model schematic diagram in background technology.
Detailed description of the invention
With reference to the accompanying drawings and by embodiments of the invention, technical scheme of the present invention is described in detail.
A kind of human body detecting method based on mm-wave imaging in the present invention, comprises the following steps: S1, tested personnel are carried out to millimeter wave scanning and obtain original image; S2, described original image carried out to adjustment and obtain target image; S3, carry out segmentation and the location of human body according to described target image; S4, generation anthropometric dummy.As shown in Figure 1.
Correspondingly, as shown in Figure 2, the present invention also provides a kind of human body detection device based on mm-wave imaging, comprising:
Scanning means 1, for performing step S1, carrying out millimeter wave scanning to tested personnel and obtaining original image;
Adjusting module 2, for performing step S2, carrying out adjustment to described original image and obtaining target image;
Segmentation locating module 3, for performing step S3, carries out segmentation and the location of human body according to described target image;
Anthropometric dummy generation module 4, for performing step S4, generates anthropometric dummy.
In step sl, require that tested personnel enter millimeter wave scan test section, after carrying out Scanning Detction by the mode of scanning means 1 millimeter wave active/passive, obtain original image as shown in Figure 3.Original image after scanning generally has following features: integral image is clear not, comprises much noise.
Therefore need adjusting module 2 to carry out step S2, adjust original image thus obtain the target image being suitable for carrying out image operation and segmentation, as Fig. 6, step S2 comprises following sub-step: S21, carry out pretreatment obtain preliminary denoising image to original image; S22, binaryzation is carried out to preliminary denoising image obtain preliminary bianry image; S23, reprocessing is carried out to preliminary bianry image obtain described target image.
Correspondingly, as Fig. 7, adjusting module 2 also comprises following submodule:
Pretreatment module 21, for performing step S21, carrying out pretreatment to described original image and obtaining preliminary denoising image;
Binarization block 22, for performing step S22, carrying out binaryzation to described preliminary denoising image and obtaining preliminary bianry image;
Reprocessing module 23, for performing step S23, carrying out reprocessing to described preliminary bianry image and obtaining described target image.
Further, pretreatment module 21 also comprises image enhancing unit, difference operation unit, smoothing processing unit, linear change unit.Pretreatment module 21 performs step S21 to be needed to carry out following sub-step:
Image enhancing unit is used for carrying out image enhaucament to original image makes the contrast of human region and background area in original image increase, and improves image visual effect.
The gray value that difference operation unit is used for being undertaken by the gray value of original image and empty background image difference operation original image and empty background image in other words subtracts each other, thus elimination system noise.Empty background image carries out scanning formed image when being exactly and not having tested personnel in millimeter wave scan test section.
Smoothing processing unit removes the random noise in image for the smoothing processing of carrying out image, by using in this unit
Operator carries out low-pass filtering to image and realizes smooth operation.
Linear change unit is used for carrying out gray scale stretching to image or claiming subregion linear transformation, the tonal range of background area uninterested in image is compressed, human region tonal range is expanded, thus outstanding human body parts, make human body parts entirety clear, finally obtain preliminary denoising image, as shown in Figure 4.
Further, step S22 performed by binarization block 22, preliminary denoising image being carried out to binaryzation, to obtain preliminary bianry image be utilize Pulse Coupled Neural Network (PCNN) algorithm to be with entropy the threshold value that criterion chooses binaryzation to the maximum, utilize this threshold value that the gray-scale map of preliminary denoising image is converted to the image of binaryzation, thus realize the segmentation of human region and background area in image.
How human body and background more completely being carried out splitting by selected threshold is accurately the key of problem, here comparatively ripe Pulse Coupled Neural Network (PCNN) technology is used, PCNN be the nineties Eckhom etc. based on the mammiferous visual characteristics such as cat research and propose based on Pulse-coupled Neural Network Model, the iterative process that the threshold value that this model is used for image is chosen, iterative formula is as follows:
F is exactly i-th, a j neuronic n feed back input F
i, j[n], I
i, j[n] for input stimulus signal (in the matrix formed for image pixel here i-th, the gray value of a j pixel), β be coefficient of connection, L
i, j[n] connects item, T
i, j[n] is dynamic threshold, i.e. required threshold value, the Y separated in the present invention
i, j[n] is PCNN pulse output valve, U
i, j[n] is internal activity item.The wherein M of inner connection matrix M, W (general W=M)
i, j, k, l, W
i, j, k, lbe respectively F
i, j[n], L
i, jy in [n]
i, jthe weight coefficient of [n], α
f, α
l, α
tbe respectively F
i, j[n], L
i, j[n], T
i, jthe damping time constant of [n], V
f, V
l, V
tbe respectively F
i, j[n], L
i, j[n], T
i, jintrinsic electromotive force in [n].
Entropy is a kind of form of expression of image statistics, reflects the size that image comprises quantity of information.For image, after general segmentation, Image entropy is larger, obtains quantity of information larger after segmentation is described from former figure, and segmentation image detail is abundanter, and thus overall segmentation effect also should be better.The criterion that the criterion that this patent use entropy is to the maximum terminates as PCNN iteration.The computing formula of entropy is:
H
1(P)＝-P
1×log
2P
1-P
0×log
2P
0。
Wherein, P
1, P
0represent that pulse output valve Y [n] is 1, is the probability of 0 respectively.The present invention passes through the very large iterations n of setting one, as n=100, uses PCNN algorithm to carry out interative computation, obtains corresponding entropy H after each computing terminates
1(P), then compare the entropy that n computing obtains, obtain the value H that wherein entropy is maximum
1max(P) iterations N time
max.Iterations is N
maxtime obtain threshold value T [N
max], the Y [N of now PCNN output
max] constitute under other parameters one stable condition of PCNN, the bianry image of overall segmentation effect the best.Wherein Y [N
max] be 1 part be background parts, Y [N
max] be 0 part be human body parts.
The span being adapted to each parameter in the PCNN formula of above-mentioned computational process is:
| α F | α L | α T | V F | V L | V T | β |
| 0.1～0.6 | 1～10 | 0.1～0.6 | 0.1～0.5 | 0.1～0.5 | 2～10 | 0.1～0.6 |
W, M two operators can use 1/r or 1//r
2element form form matrix, r represents the matrix length of side of operator.
Preferably, the present invention can get following parameter value: α
f=0.2, α
l=2, α
t=0.1, V
f=0.1, V
l=0.5, V
t=20, β=0.5,
Calculate, the preliminary bianry image of the optimum efficiency of acquisition as shown in Figure 5.
Further, the step S23 performed by reprocessing module 23, carrying out reprocessing obtain described target image to described preliminary bianry image, is pass through morphologic filtering.Because Threshold segmentation can cause picture noise, the isolated bright noise spot of this noise mainly outside human body parts or the isolated dark noise point in human body.In order to remove these noises, the method that the present invention uses carries out filtering and conversion to preliminary bianry image applied mathematics morphology operations method, obtain one and there is the image of the binaryzation of clear level and smooth profile and described target image, as shown in Figure 8, thus be beneficial to follow-up process.
Mathematical morphological operation method mainly comprises erosion operation, dilation operation, opening operation and closed operation.
Erosion operation can weaken even elimination and be less than structural element bright areas, thus can be used for effectively removing rough projection on isolated noise point border.
Dilation operation is the process be incorporated into by all background dots contacted with target object in object, can filling cavity and formed together with rough female on territory and flat image boundary.
Opening operation first carries out erosion operation to image to carry out dilation operation again, the isolated area in image and burr can be got rid of, utilization can eliminate the noise spot that shape is less than structural element, according to the feature of target noise, select suitable structural element, just can reject target noise, and background is remained.
Closed operation first carries out dilation operation to image to carry out erosion operation again, can minuscule hole in filler body, connects contiguous thing and level and smooth object boundary.
Wherein, structural element is the basic operator of mathematical morphological operation, and the structural element of choice for use is mainly the shape and size of structural element.
Preferably, the morphology operations that this method uses can be following processing procedure: (1) use the length of side be 5 square structure element carry out in erosion operation removal of images outside human body to image bright noise spot; (2) use the length of side be 4 square structure element opening operation is carried out to image, keep image size to eliminate isolated area and the burr at human body edge simultaneously; (3) use the length of side be 4 square structure element closed operation is carried out to image, fill the minuscule hole in human body while keeping image size, and the border of level and smooth human body; (4) use the length of side be 5 square structure element expansive working carried out to image make Postprocessing technique arrive life size.By this process can remove long and wide be all less than 5 noise, fill up on human body long and wide be all less than 5 cavity, processed in the target image of rear formation and comprised one and be similar to complete human body parts, made characteristics of human body more obvious.
In addition, if also have the White lnterfere region that area is not eliminated comparatively greatly in image, by the area of each connected region in computed image, the region that area is less can be removed.
Further, as Figure 11, step S3, the segmentation carrying out human body according to described target image and location also comprise following sub-step: S31, determine the vertical centrage of human body; S32, determine each key point of described target image human body coordinate and the horizontal division line obtained between partes corporis humani position; S33, the width determining partes corporis humani position and slope.
Correspondingly, as shown in figure 12, split locating module 3 and also comprise following submodule:
Vertical centrage module 31, for performing step 31, determining the vertical centrage of human body;
Coordinate horizontal line module 32, for performing step 32, determining the coordinate of each key point of described target image human body and the horizontal division line obtained between partes corporis humani position;
Width slope module 33, for performing step 33, determining width and the slope of partes corporis humani position.
When vertical centrage module 31 performs in step S31 the position of the vertical centrage determining people, because the human region in target image has bilateral symmetry, therefore calculate the total pixel of the image of this human region and, as with S
0represent, then from human region left side edge by the row of image calculate from left to right human body parts image pixel and, as with S
1represent, work as S
1for S
01/2 time, when prostatitis is the vertical centrage of human body.
Perform in step S32 in coordinate horizontal line module 32, the coordinate of each key point of human body is exactly the position coordinates of partes corporis humani position, as the coordinate etc. of marginal end point coordinates, central point, human body comprises: the crown, sole, neck, trunk upper end, trunk lower end (waist), crotch, knee, finger tip and ancon.Horizontal division line between the coordinate of each key point of human body and each position is the process mutually calculated, specific as follows:
Vertical centrage along human body is downward from image top, the first man body region boundary point found, continue to have downwards continuously and length is not less than 1/10 same gray value of picture altitude from this point if judge, then determine that this point is the crown central point of human body, this horizontal line residing for point is the crown horizontal line H2 of human body.
And the position of human foot is fixing position in the picture, therefore can determine that sole coordinate and residing horizontal line are H9.Because the position of people's standing, which is fixing during imaging, the height H of people can be obtained with the vertical coordinate that the vertical coordinate on the crown deducts sole.
Judge according to human anatomy, head part accounts for 15% of height, can determine the coordinate of neck upper end and residing horizontal line H4.The height of neck accounts for 45% of height of head, therefore can determine the coordinate of the edge end points of trunk upper end and residing horizontal line H5.
Refinement is carried out to target image represented by Fig. 8 and can also obtain human body backbone figure, as shown in Figure 9.
In the key figure of Fig. 9 human body, the cross point of trunk and two lower limbs is as the position of trunk lower end, and its place horizontal line, as stringcourse H6, is the long H of lower limb along this line to the horizontal distance definition of foot
leg.
Judge according to human anatomy, the ratio of human calf and thigh is about 1: 1.2, therefore can determine that the horizontal level of knee is from foot upwards H
legthe position of × 5/11, therefore obtains knee horizontal line H8.
On the target image shown in Fig. 8, from image base along vertical centrage upwards, with first position of intersecting point of human body image as crotch, thus obtain human body crotch horizontal line H7.
With vertical centrage for the image of human region is divided into left and right two halves by cut-off rule, the peak of left one side of something and the position of left hand finger tip, on image right, the peak of human body is exactly the position of right hand finger tip, thus obtains finger tip horizontal line H0.In the present invention, the difference in height between two finger tips is ignored.
Due to before scanning tested personnel, require that its two-arm is outwards opened, the width therefore on target image between two elbows is the widest position of human body, therefore finds the position of the human region leftmost side to be exactly the left elbow of health, the rightmost side is exactly the right elbow of health, thus obtains elbow lever line H3.In the present invention, the difference in height between two elbows is ignored.
According to human dissection theory, general human body hands is 7: 9 with the length ratio of upper arm, therefore can determine the position of wrist according to hands point and the position of elbow, thus also obtain wrist horizontal line H1.
Human body segmentation's design sketch as shown in Figure 10.
In step S33 performed by width slope module 33, according to the width of determining partes corporis humani position crossing with each horizontal division line of partes corporis humani position in the target image of Fig. 8, key point (two central points as the two ends up and down of a part) coordinate of recycling partes corporis humani position calculates the slope at this position.
Further, step S4 performed by anthropometric dummy generation module 4 generates anthropometric dummy and comprises respectively according to the coordinate of each position key point, width and slope, each position is represented with rectangle or parallelogram, all positions are linked together, namely an anthropometric dummy formed with rectangle and/or parallelogram is obtained, as shown in figure 13.This human body can carry out proportional corresponding with the human region in original image, and effect as shown in figure 14.
It should be noted that the anthropometric dummy generated in the description of this method is the explanation carried out for bar band model.Carry out the segmentation of human body according to target image and can also stick model be generated after locating.Further, bar band model and stick model all can be applied following a kind of concealment in the automatic detection and Identification method of article.
On the other hand, the present invention also provides a kind of and hides the automatic detection and Identification method of article and a kind of automatic detection and Identification device hiding article, and one is extract characteristics of human body and locate, and two is identify non-human target.The process wherein extracted characteristics of human body and locate mainly is not limited to this human body detecting method and device based on the aforesaid human body detecting method in mm-wave imaging and device.
Therefore, as Figure 15, a kind of automatic detection and Identification method of hiding article comprises the following steps: S1, tested personnel are carried out to millimeter wave scanning and obtain original image; S2, described original image carried out to adjustment and obtain target image; S3, carry out segmentation and the location of human body according to described target image; S5, generation bar rod combination model; S6, according to described original image, non-human target to be detected, obtain non-human target distribution original image; S7, described bar rod combination model is utilized to obtain described non-human target distribution original image relative to the location distribution information of human body; S8, described non-human target carried out to classification identification and display concealment article relative to the location distribution information of human body.
Correspondingly, a kind of automatic detection and Identification device hiding article, comprising:
Scanning means 1, for performing step S1, carrying out millimeter wave scanning to tested personnel and obtaining original image;
Adjusting module 2, for performing step S2, carrying out adjustment to described original image and obtaining target image;
Segmentation locating module 3, for performing step S3, carries out segmentation and the location of human body according to described target image;
Bar rod combination model generation module, for performing step S5, generates bar rod combination model;
Non-human target Preliminary detection module, for performing step S6, detects non-human target according to described original image, obtains non-human target distribution original image;
Non-human target distribution module, for performing step S7, utilizes described bar rod combination model to obtain the location distribution information of described non-human target distribution original image relative to human body;
Classification recognition module, for performing step S8, carrying out classification identification to described non-human target and showing the location distribution information of concealment article relative to human body.
Wherein step S1, S2 and S3 a kind of based in the human body detecting method of mm-wave imaging, scanning means 1, adjusting module 2, segmentation locating module 3 a kind of based on the human body detection device of mm-wave imaging in be described, repeat no more herein.
According to Figure 16, step S5 comprises following sub-step further: S51, generate and provide the stick model of each key point of human body; S52, generate the bar band model of human body contour outline information is provided; S53, in conjunction with described stick model and described bar band model, thus generate bar rod combination model.
Correspondingly, the bar rod combination model generation module performing step S5 comprises following submodule:
Stick model generation module, for performing step S51, generates the stick model providing each key point of human body;
Band model generation module, for performing step S52, generates the bar band model providing human body contour outline information;
Binding modules, for performing step S53, in conjunction with described stick model and described bar band model.
Wherein, step S51 performed by stick model generation module is by a kind of step S32 of the human body detecting method based on mm-wave imaging, the coordinate determining each key point of described target image human body obtain the step of the horizontal division line between partes corporis humani position, utilize each key point of human body wherein to obtain each articulare building stick model, then connect each articulare with straight line and just can generate stick model.
The process generating bar band model in step S52 performed by band model generation module with a kind of based on the human body detecting method of mm-wave imaging in S4 to generate the process of anthropometric dummy identical.
Step S53 performed by binding modules is in conjunction with described stick model and described bar band model, generate bar rod combination model as shown in figure 17, thus complete extraction and the location of characteristics of human body in this method, articulare when circular node in Figure 17 represents that characteristics of human body extracts, can also add the sequence of extraction of each articulare of digitized representation in these articulares.
Further, the non-human target Preliminary detection module of the step S6 of execution also comprises: edge detection module, highlight module, regularization module and Fusion Module.Correspondingly, as shown in figure 18, step S6, according to described original image, non-human target to be detected, obtains non-human target distribution original image and also comprise following sub-step:
S61, edge detection module carry out rim detection to described original image, such as, make use of Sobel (Sobel) operator and carry out rim detection, tentatively identify non-human target, as shown in figure 19;
S62, highlight module and highlight non-human target distribution region by mathematical morphological operation, such as, first erosion operation is carried out to Figure 19, then carry out dilation operation.Wherein burn into dilation operation use respectively the length of side be 2 and 4 square structure element, thus the non-human target distribution administrative division map highlighted, as Figure 20;
S63, regularization module choose minimum circumscribed rectangle according to the border in described non-human target distribution region, make the irregular regioinvertions in Figure 20 be non-human goal rule regional distribution chart in Figure 21;
S64, module merge Figure 21 and merge non-human goal rule regional distribution chart and described original image Fig. 3, and obtain the non-human target original image of Figure 22, this image also show the human body parts of non-human target position certainly.
Because stick model only comprises human body contour outline information, there is no concrete articulare information, stick model only comprises articulare information, mask the position of non-human target on human body contour outline, so further, step S7 performed by non-human target distribution module is by being input to by described non-human target distribution original image on described bar rod combination model, the non-human target of human body contour outline information acquisition that bar rod combination model discal patch band model provides so both can have been utilized in the intramarginal distribution of human body contour outline, the human synovial dot position information that provides of stick model in bar rod combination model is further utilized to obtain the relative position relation between non-human target and articulare, therefore bar rod combination model is utilized, non-human target is provided with on this object of reference of human body locate more accurately, the scattergram of target original image as non-human in Figure 23 on bar rod combination model.
Further, classification recognition module comprises following submodule: exposed spots localization module, sort module and display module.Be respectively used to perform step S8 carry out class of risk identification to described non-human target and show concealment article relative to each sub-steps in the location distribution information of human body, as Figure 25:
S81, exposed spots localization module position the exposed position of human body, as head, wrist, palm etc., can carry out spots localization so more targetedly in the segmentation of aforesaid human body and location;
S82, sort module are classified to non-human target, and the non-human target be distributed on the exposed position of human body is defined as non-concealment article, as glasses, button, wrist-watch, ring etc.; Owing to there being medicated clothing to hide, the non-human target outside the exposed position of human body cannot directly be checked by security staff, the non-human target be distributed in outside the exposed position of human body is defined as hiding article, therefore needs to pay close attention to;
S83, display module reject the original image of described non-concealment article and the distributed intelligence of display concealment article original image on described bar rod combination model, as Figure 24 be eliminate the original image of the wrist-watch of wrist in Figure 23 after the design sketch that shows again.
By the automatic detection and Identification method and apparatus of concealment article of the present invention, the instructions for use of personnel can be reduced, reduce personal error, shorten the interpretation time that human body concealment dangerous materials check.
On the other hand, after human body mm-wave imaging, because original image is more clear, by the aforesaid human body detecting method based on mm-wave imaging and the automatic detection and Identification method of hiding article, can identify and show the concealment article on human body and/or human body, but the exposure of privacy places of human body can be caused simultaneously.
In order to protect privacy, the present invention also provides a kind of method for secret protection based on mm-wave imaging, as Figure 26, comprising: S1, tested personnel are carried out to millimeter wave scanning and obtain original image; A, to carry out human detection and concealment Articles detecting according to described original image; B, determine the privacy places of human body; C, the privacy places of human body shielded and indicates the concealment Item Information on human body.
Correspondingly, as shown in figure 27, the present invention also provides a kind of privacy protection device based on mm-wave imaging, comprising:
Scanning means 1, obtains original image for carrying out millimeter wave scanning to tested personnel;
Checkout gear, for performing steps A, carries out human detection and concealment Articles detecting according to described original image;
Privacy places determination module, for performing step B, determines the privacy places of human body;
Privacy mask module, for performing step C, shielding the privacy places of human body and indicating the concealment Item Information on human body.
Wherein steps A can be undertaken by the automatic detection and Identification method of the aforesaid human body detecting method based on mm-wave imaging and concealment article, correspondingly, checkout gear can comprise based on mm-wave imaging human body detection device and concealment article automatic detection and Identification device.
The privacy places performing the privacy places determination module determination human body of step B to be determined privacy places according to the segmentation of aforementioned human body and location and human anatomy equally and is located, comprise the sex judging tested personnel, when tested personnel are male, the region of the downward torso width 1/2 in human body head region and human body waist center is defined as privacy places, when tested personnel are women, be privacy places from trunk upper end down to the region of trunk height 1/2 by the region of the downward torso width 1/2 in human body head region and human body waist center and trunk.Be described for the mm-wave imaging of the tested personnel of male in the present invention.
The privacy mask module performing step C, to shield the privacy places of human body and indicate the concealment Item Information on human body can adopt following several detailed description of the invention to carry out the protection of privacy:
(1) privacy mask module comprises obscure portions module and the first sign module, obscure portions module carries out Fuzzy processing forming section obfuscation original image to privacy places on described original image, obfuscation can use morphology operations, use the mosaic area that the length of side is certain, or can directly use the rectangular block of solid color to cover privacy places; First indicates module marks described concealment article sign frame on described obscure portions original image, the frame of such as highlight color, as shown in figure 28.This mode is adapted to concealment article and automatically detects situation about combining with manual detection.Or,
(2) privacy mask module comprises selection object image module and the second sign module, because the image of the binaryzation of complete display can mask the Pixel Information of the privacy places of tested personnel, object image module is selected to select object image table to show human body parts so present embodiment utilizes, this object image is obtained, as Fig. 8 by the described human body detecting method based on mm-wave imaging; Before this object image shows concealment Item Information, second indicates module first judges to hide the privacy places whether article are in human body, if, then use the color blocks different from human body color to represent hide article and indicate on described object image, as used certain gray value, the grey rectangle block as 128 indicates; If not, then the direct original image by concealment article is presented on described object image.Shield the complete information of human body in original image so completely, reach again the object of secret protection, effect as shown in figure 29.Under this method is only applicable to the automatic detection mode of concealment article, do not need the situation showing complete human body figure.Or,
(3) privacy mask module comprises whole obfuscation module and the 3rd sign module.Whole obfuscation module is carried out whole Fuzzy processing to human body and is formed whole obfuscation original image on described original image, and the method for obfuscation can be identical with detailed description of the invention (1), and in present embodiment, obfuscation employs operator
Before this whole obfuscation original image showing concealment Item Information, 3rd indicates module judges to hide the privacy places whether article are in human body, if, then use the color blocks different from human body color to represent hide article and indicate on described whole obfuscation original image, as used certain gray value, the grey rectangle block as 128 indicates; If not, be then presented on described whole obfuscation original image by the original image of concealment article, design sketch is as Figure 30.Under this method is only applicable to the automatic detection mode of concealment article, do not need the situation showing complete human body figure.Or,
(4) privacy mask module comprises preference pattern module and the 4th sign module.Anthropometric dummy in human detection described in preference pattern model choice, anthropometric dummy here can be bar band model, also can be bar rod combination model; 4th indicates module uses the color blocks different from anthropometric dummy color, as redness, represents concealment article and indicates in described anthropometric dummy.So also can shield the privacy information of human body completely.The effect that bar band model shows as shown in figure 31.The complete information that this method is only applicable to not show concealment article does not need to show the situation of complete human body figure yet.
Should be appreciated that above is illustrative and not restrictive by preferred embodiment to the detailed description that technical scheme of the present invention is carried out.Those of ordinary skill in the art can modify to the technical scheme described in each embodiment on the basis of reading description of the present invention, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.Protection scope of the present invention is only limited by following claims.
Claims (7)
1. based on a human body detecting method for mm-wave imaging, it is characterized in that, comprise the following steps:
Millimeter wave scanning is carried out to tested personnel and obtains original image;
Adjustment is carried out to described original image and obtains target image;
Carry out segmentation and the location of human body according to described target image, this step comprises
Determine the vertical centrage of human body;
Determine the coordinate of each key point of described target image human body and the horizontal division line obtained between partes corporis humani position;
Determine width and the slope of partes corporis humani position;
Generate anthropometric dummy, this step comprises the coordinate according to described each key point, the width of described partes corporis humani position and slope, obtains the anthropometric dummy with rectangle and/or parallelogram composition.
2. the human body detecting method based on mm-wave imaging according to claim 1, is characterized in that, described to described original image carry out adjustment obtain target image also comprise following sub-step:
Pretreatment is carried out to described original image and obtains preliminary denoising image;
Binaryzation is carried out to described preliminary denoising image and obtains preliminary bianry image;
Reprocessing is carried out to described preliminary bianry image and obtains described target image.
3. the human body detecting method based on mm-wave imaging according to claim 2, is characterized in that, describedly carries out pretreatment to described original image and obtains preliminary denoising image and comprise following sub-step further:
Described original image and background image gray value carry out difference operation;
Picture smooth treatment;
Linear gradation converts.
4. the human body detecting method based on mm-wave imaging according to claim 2, it is characterized in that, describedly binaryzation is carried out to described preliminary denoising image to obtain preliminary bianry image be utilize Pulse Coupled Neural Network algorithm to be with entropy the threshold value that criterion chooses binaryzation to the maximum.
5. the human body detecting method based on mm-wave imaging according to claim 2, is characterized in that,
Describedly reprocessing is carried out to described preliminary bianry image to obtain described target image be pass through morphologic filtering.
6. the human body detecting method based on mm-wave imaging according to claim 5, is characterized in that, is describedly comprised by morphologic filtering:
Use the length of side be 5 square structure element carry out erosion operation and eliminate bright noise spot outside human body:
Use the length of side be 4 square structure element carry out eliminating while opening operation keeps image size isolated area and the burr at human body edge;
Use the length of side be 4 square structure element carry out the minuscule hole of filling while closed operation keeps image size in human body, and the edge of level and smooth human body;
Use the length of side be 5 square structure element carry out dilation operation and make Postprocessing technique arrive life size.
7. the human body detecting method based on mm-wave imaging according to claim 2, is characterized in that, describedly carries out pretreatment to described original image and obtains preliminary denoising image and also comprise following sub-step:
Image enhaucament is carried out to described original image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210049549.0A CN102697503B (en) | 2012-02-29 | 2012-02-29 | Human detection method based on millimeter wave imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210049549.0A CN102697503B (en) | 2012-02-29 | 2012-02-29 | Human detection method based on millimeter wave imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102697503A CN102697503A (en) | 2012-10-03 |
| CN102697503B true CN102697503B (en) | 2015-03-18 |
Family
ID=46890779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210049549.0A Active CN102697503B (en) | 2012-02-29 | 2012-02-29 | Human detection method based on millimeter wave imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102697503B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901490B (en) * | 2012-12-27 | 2017-02-08 | 同方威视技术股份有限公司 | Human body security check device and human body security check method |
| CN103475796A (en) * | 2013-09-30 | 2013-12-25 | 吕昕炜 | Scanner for customization of gloves |
| CN103645474B (en) * | 2013-12-12 | 2016-02-24 | 北京无线电计量测试研究所 | For the formation method of the two dimensional image of millimeter wave 3-D imaging system |
| CN104537619A (en) * | 2014-12-25 | 2015-04-22 | 深圳市一体太赫兹科技有限公司 | Millimeter wave image recovery method and system |
| CN106418847A (en) * | 2015-08-04 | 2017-02-22 | 王廷金 | Human 3D size measuring method based on computer vision technology |
| CN106127732B (en) * | 2016-06-13 | 2019-01-01 | 深圳市太赫兹科技创新研究院 | Human body sex-screening method and apparatus in microwave imagery |
| US10884116B2 (en) | 2016-08-25 | 2021-01-05 | Shenzhen Cct Thz Technology Co., Ltd. | Human-body foreign-matter detection method and system based on millimetre-wave image |
| CN106371148B (en) * | 2016-09-27 | 2019-05-03 | 华讯方舟科技有限公司 | A kind of human body foreign body detection method and system based on millimeter-wave image |
| CN106447634B (en) * | 2016-09-27 | 2018-02-27 | 中国科学院上海微系统与信息技术研究所 | A kind of privacy places positioning and guard method based on active mm-wave imaging |
| CN106485077B (en) * | 2016-10-11 | 2018-12-14 | 徐州玖胜医疗器械有限公司 | A kind of supervision place medical monitoring systems |
| CN107947871A (en) * | 2017-11-21 | 2018-04-20 | 韩劝劝 | A kind of method of the amount of radiation of control router |
| CN108937869A (en) * | 2018-07-12 | 2018-12-07 | 芜湖博高光电科技股份有限公司 | A kind of the millimeter wave survival kit and operating method of hand-held perspective bone |
| CN109492592A (en) * | 2018-11-15 | 2019-03-19 | 杭州芯影科技有限公司 | Mm-wave imaging image processing method |
| CN109711330A (en) * | 2018-12-25 | 2019-05-03 | 山东雷诚电子科技有限公司 | A kind of active MMW human body imaging threat object detecting method |
| CN110799913A (en) * | 2018-12-29 | 2020-02-14 | 深圳市大疆创新科技有限公司 | Control method and device for ground remote control robot |
| CN110298797B (en) * | 2019-06-12 | 2021-07-09 | 博微太赫兹信息科技有限公司 | Millimeter wave image processing method based on convolutional neural network |
| TWI769602B (en) * | 2020-11-30 | 2022-07-01 | 群邁通訊股份有限公司 | Body posture identifying method using mmw radar and computer readable storage medium |
| CN112581391B (en) * | 2020-12-14 | 2023-04-11 | 佛山科学技术学院 | Image denoising method based on PCNN |
| CN113156429B (en) * | 2021-04-23 | 2022-05-31 | 森思泰克河北科技有限公司 | Imaging method, device and equipment based on millimeter wave and storage medium |
| CN116434289A (en) * | 2021-12-30 | 2023-07-14 | 同方威视技术股份有限公司 | Millimeter wave or terahertz wave identity verification method and device, millimeter wave or terahertz wave security inspection equipment and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7180441B2 (en) * | 2004-04-14 | 2007-02-20 | Safeview, Inc. | Multi-sensor surveillance portal |
| JP2008241352A (en) * | 2007-03-26 | 2008-10-09 | Maspro Denkoh Corp | Millimeter-wave imaging device and picked-up image display device |
| CN101614722B (en) * | 2008-06-27 | 2014-03-05 | 同方威视技术股份有限公司 | Personnel safety check system |
| CN101866018B (en) * | 2010-05-27 | 2012-09-05 | 中国科学院上海微系统与信息技术研究所 | Radio frequency receiving and transmitting front end for millimeter wave holographic imaging security check system |
-
2012
- 2012-02-29 CN CN201210049549.0A patent/CN102697503B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN102697503A (en) | 2012-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102697503B (en) | Human detection method based on millimeter wave imaging | |
| CN102629315B (en) | A kind of detection automatically hiding article and identification device | |
| CN102708372B (en) | A kind of automatic detection and Identification method of hiding article | |
| CN102708560B (en) | A kind of method for secret protection based on mm-wave imaging | |
| CN102707322B (en) | Human body detection device based on millimeter wave imaging | |
| CN102708561B (en) | A kind of secret protection device based on mm-wave imaging | |
| CN105469113B (en) | A kind of skeleton point tracking method and system in two-dimensional video stream | |
| CN107169475B (en) | A kind of face three-dimensional point cloud optimized treatment method based on kinect camera | |
| CN103810478B (en) | A kind of sitting posture detecting method and device | |
| CN106447634B (en) | A kind of privacy places positioning and guard method based on active mm-wave imaging | |
| CN110133739A (en) | A kind of X-ray rays safety detection apparatus and its drawing method is known automatically | |
| US20090174554A1 (en) | Method and system for screening luggage items, cargo containers or persons | |
| CN106327459A (en) | Visible light and infrared image fusion algorithm based on UDCT (Uniform Discrete Curvelet Transform) and PCNN (Pulse Coupled Neural Network) | |
| CN106908813A (en) | A kind of satellite remote sensor Calibration Method and device | |
| CN107726990B (en) | The acquisition of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement | |
| WO2018035814A1 (en) | Millimetre wave image-based human body foreign matter detection method and system | |
| CN110400294A (en) | A kind of Infrared Target Detection system and detection method | |
| Yan et al. | Radio frequency interference detection based on the AC-UNet model | |
| Su et al. | Enhancing concealed object detection in Active Millimeter Wave Images using wavelet transform | |
| Fitriyah et al. | Automatic measurement of human body temperature on thermal image using knowledge-based criteria | |
| CN106530389B (en) | Stereo reconstruction method based on medium-wave infrared facial image | |
| CN104361571A (en) | Infrared and low-light image fusion method based on marginal information and support degree transformation | |
| CN112907465A (en) | Deep learning-based underwater thermal disturbance image restoration system and method | |
| CN105869134A (en) | Directional diagram model based human face sketch synthesis method | |
| RU2006118700A (en) | HIDDEN DETECTION |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |