JP2013125021A - Device, method, and program for correcting contrast, and possession detection device - Google Patents

Abstract

An object of the present invention is to prevent the detection of a possessed item from being missed because there is not much difference between fine signals emitted from the human body and the possessed item and the contrast is poor.
A masking processing unit 151 detects an outer peripheral boundary of a person 10 who is an imaging target of a millimeter-wave passive imaging device 100. And the masking process part 151 cuts out the imaging target part (part of the person 10) inside the outer periphery boundary of the person 10 from the image which the millimeter wave passive imaging device 100 imaged. Then, the contrast correction unit 154 performs contrast correction by scaling only the imaging target portion cut out of the captured image.
[Selection] Figure 1

Description

  The present invention relates to a contrast correction apparatus, method, program, and belongings detection apparatus, and in particular, a fine signal emitted from an imaging target that corrects a signal output from an imaging element constituting the line sensor in an imaging apparatus that scans a line sensor. Device for detecting an object to be captured using an imaging apparatus that receives and captures a fine signal emitted from the imaging target The present invention relates to a detection device.

  2. Description of the Related Art Conventionally, there is an imaging apparatus that performs imaging by receiving a fine signal such as a millimeter wave spontaneously emitted from a subject (see, for example, Patent Document 1). For example, such a special imaging apparatus has been proposed in order to find out violations that cannot be captured by an imaging apparatus using visible light or X-rays.

JP 2010-008272 A

  However, an imaging apparatus that receives and captures a fine signal as described above must greatly amplify the signal because the received signal is fine, and the noise signal is inevitably greatly amplified. In particular, the S / N (signal / noise) ratio is deteriorated. In such an environment, if a person has possession for a long time, the temperature of the possession approaches the human body temperature, so the millimeter wave intensity emitted by the possession approximates the millimeter wave intensity emitted by the human body. As a result, there is a problem that it becomes more difficult to distinguish between people and belongings.

  The present invention has been made in view of the above points, and provides a contrast correction device, method, program, and belonging detection device capable of preventing the occurrence of detection omission of belongings due to poor contrast. The purpose is to provide.

  In the present invention, in order to solve the above-described problem, in the contrast correction device used in an imaging device that receives and captures a fine signal emitted from an imaging target, outer peripheral boundary detection that detects the outer peripheral boundary of the imaging target of the imaging device Means, an imaging target cutout means for cutting out an imaging target portion that is inside the outer peripheral boundary from an image picked up by the imaging device, and a scaling means for scaling only the cut out imaging target portion. A contrast correction apparatus is provided.

  Thereby, the outer periphery boundary detection unit detects the outer periphery boundary of the imaging target of the imaging device, and the imaging target cutout unit cuts out the imaging target portion inside the outer periphery boundary from the image captured by the imaging device, A scaling unit scales only the cut-out imaging target portion.

  According to the present invention, in the possession detection device for detecting the possession of the imaging target using the imaging device that receives and captures a fine signal emitted from the imaging target, the outer peripheral boundary of the imaging target of the imaging device is detected. An outer peripheral boundary detecting means, an imaging target cutting means for cutting out an imaging target portion inside the outer peripheral boundary from an image taken by the imaging device, and a scaling means for scaling only the extracted imaging target portion. There is provided a belonging detection device characterized by

  Thereby, the outer periphery boundary detection unit detects the outer periphery boundary of the imaging target of the imaging device, and the imaging target cutout unit cuts out the imaging target portion inside the outer periphery boundary from the image captured by the imaging device, A scaling unit scales only the cut-out imaging target portion.

  According to the present invention, in the contrast correction method used in the imaging apparatus that receives and captures a fine signal emitted from the imaging target, the outer peripheral boundary detection unit detects the outer peripheral boundary of the imaging target of the imaging apparatus; The imaging target cutting means includes a step of cutting out an imaging target portion that is inside the outer peripheral boundary from an image captured by the imaging device, and a scaling means includes a step of scaling only the cut out imaging target portion. A contrast correction method is provided.

  Thereby, the outer periphery boundary detection unit detects the outer periphery boundary of the imaging target of the imaging device, and the imaging target cutout unit cuts out the imaging target portion inside the outer periphery boundary from the image captured by the imaging device, A scaling unit scales only the cut-out imaging target portion.

  Further, in the present invention, in a contrast correction program used for an imaging apparatus that receives and captures a fine signal emitted from an imaging target, an outer boundary detection unit that detects an outer peripheral boundary of the imaging target of the imaging apparatus, A contrast correction program that functions as an imaging target cutout unit that cuts out an imaging target portion inside the outer peripheral boundary from an image captured by the imaging device, and a scaling unit that scales only the cutout imaging target portion. Is provided.

  Thereby, the outer periphery boundary detection unit detects the outer periphery boundary of the imaging target of the imaging device, and the imaging target cutout unit cuts out the imaging target portion inside the outer periphery boundary from the image captured by the imaging device, A scaling unit scales only the cut-out imaging target portion.

  According to the contrast correction device, the method, the program, and the belonging detection device of the present invention, the outer peripheral boundary of the imaging target is detected, and the imaging target portion that is inside the outer peripheral boundary is cut out from the image captured by the imaging device. Therefore, only the millimeter wave radiated only from the cut out imaging target part should be excluded, excluding the millimeter wave radiated from the part other than the person who is the subject (background part). Therefore, the millimeter wave radiated only from the cut-out imaging target part, that is, the contrast is improved even if the millimeter wave intensity emitted by the person who is the imaging target and the possession possessed by the person is fine, The detection accuracy of belongings can be improved.

It is a block diagram of the invention applied to the form of the present invention. It is a figure which shows the image data before a masking process, and its histogram. It is a figure which shows the image data after a masking process, and its histogram. 5 is a flowchart illustrating a procedure of image processing performed by the image processing unit 150 in accordance with imaging processing performed by the millimeter wave passive imaging device 100.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a block diagram of an invention applied to the embodiment of the present invention.

  As shown in FIG. 1, the millimeter wave passive imaging apparatus 100 according to the present embodiment includes a vibration reflector unit 110, a line sensor 120, a synchronization / address generation unit 130, a conversion unit 140, and an image processing unit 150.

  The vibration reflector unit 110 includes a vibration reflector 111 that performs a swing operation, and a pulse generation unit 112 that generates a horizontal synchronization pulse for transmitting the timing of the swing operation.

  The line sensor 120 receives the millimeter wave emitted by the subject such as the person 10 via the vibration reflector 111. The line sensor 120 is arranged so that the image pickup devices are arranged in the horizontal direction. When the vibration reflector 111 swings up and down, each part to be imaged such as the person 10 is scanned, and the line sensor 120 appropriately scans. A millimeter wave is received.

  A radio wave absorber 11 is provided behind a subject such as a person 10. This is to prevent the external noise from being received by the line sensor 120 by blocking the millimeter wave radiated from behind the imaging target and absorbing the millimeter wave radiated from the imaging target direction.

  When receiving the horizontal synchronization pulse from the pulse generation unit 112, the synchronization / address generation unit 130 generates and transmits a synchronization signal and a memory address to the line sensor 120 and the frame memory 142. The line sensor 120 outputs an analog voltage based on the received millimeter wave to the conversion unit 140 based on the received synchronization signal.

  The conversion unit 140 includes an A / D conversion circuit 141 and a frame memory 142, and the analog voltage output from the line sensor 120 is digitized by the A / D conversion circuit 141, and the memory address generated by the synchronization / address generation unit 130. Is stored in the frame memory 142 based on the above. Thus, the vibration reflector 111 is swung and scanned, and the data of each horizontal line captured by the line sensor 120 is stored in the frame memory 142 as two-dimensional image data.

  The image processing unit 150 includes a masking processing unit 151, a histogram creation unit 152, a table creation unit 153, a contrast correction unit 154, and an output processing unit 155.

  When new image data is stored in the frame memory 142, the masking processing unit 151 performs a masking process that masks the outer portion of the person 10 shown in the stored image data.

  When the histogram creation unit 152 receives the image data subjected to the masking process, the histogram creation unit 152 creates a histogram only from the inner part of the outer periphery of the person 10 not masked.

  The table creation unit 153 creates a contrast table from the created histogram, and the contrast correction unit 154 performs contrast correction based on the created contrast table. The contrast-corrected image data is output to the monitor 20 via the output processing unit 155 and displayed.

  As a result, image data with appropriate contrast correction is output and displayed in real time.

  Next, imaging processing performed by the millimeter-wave passive imaging device 100 and image processing performed by the image processing unit 150 associated therewith will be described.

  FIG. 2 is a diagram showing image data before masking processing and a histogram thereof, and FIG. 3 is a diagram showing image data after masking processing and a histogram thereof. FIG. 2A shows image data before the masking process, and FIG. 2B shows the whole image data before the masking process and histogram correction and contrast correction. 3A shows the image data after the masking process, and FIG. 3B shows the image data after the masking process, in which only the inner peripheral portion of the person 10 is histogrammed and contrast-corrected. is there.

  The millimeter wave intensity emitted by an object depends on the temperature of the object, and the higher the temperature, the stronger the millimeter wave intensity emitted. Therefore, the millimeter wave image data before masking processing shown in FIG. 2 is formed into three peaks, a human body part having a high temperature, a background part having a low temperature, and a belonging part having an intermediate temperature between the human body and the background, as shown in FIG.

  On the other hand, when the data of the millimeter wave image after the masking process shown in FIG. 3A is histogrammed, the background part is masked as shown in FIG. Will be formed.

  As can be seen by comparing FIG. 2 (B) and FIG. 3 (B), in the histogram including the background portion, the histogram includes data relating to the millimeter wave in the background portion. FIG. 3B is easier to distinguish between the mountain formed by such data and the mountain formed by the data related to millimeter waves of the human body part than in FIG. This means that in FIG. 3B, contrast between the portion of the person 10 and the portion of the belonging 12 is clearer in the image data than in FIG. 2A.

  Since the background portion is masked in this way, the contrast becomes clear, so that the person 10 and the belongings 12 can be easily distinguished both in the image data and in the histogram. Furthermore, since the contrast becomes clear, even when trying to automatically detect the belonging 12, the difference between the person 10 and the possession 12 becomes clear, thereby preventing false detection and detection omission, and the detection accuracy is improved. improves. Note that FIGS. 2B and 3B show histograms of millimeter wave intensities subjected to contrast correction so as to have 256 gradations.

Next, the content of the above-described image processing will be specifically described using a flowchart.
FIG. 4 is a flowchart illustrating a procedure of image processing performed by the image processing unit 150 in accordance with imaging processing performed by the millimeter wave passive imaging device 100. In the following, the process illustrated in FIG. 4 will be described in order of step number.

[Step S11] The masking processing unit 151 acquires image data of a millimeter wave image stored in the frame memory 142, and creates a binary image by performing binarization processing on the acquired image data. The threshold th used for this binarization processing is calculated using the following formulas (1) to (3).
Intraclass variance A ² = (ω1δ1 ² + ω2δ2 ² ) / (ω1 + ω2) (1)
In-class variance B ² = (ω1ω2 (m1−m2) ² )) / (ω1 + ω2) ² (2)
t = (B ² ) / (A ² ) …………………………………………………………………… (3)
A value at which the ratio of t calculated by the above formula (3) is maximized is defined as a threshold value th.

  [Step S12] The masking processing unit 151 performs a boundary line tracking process for tracking the boundary line on the outer periphery of the binarized person 10. Thereby, the outer periphery of the human figure representing the person 10 in the binary image is detected.

  [Step S13] The masking processing unit 151 creates a background mask that masks the outer part of the outer periphery of the person 10 detected by the boundary line tracking process. The reason why the outer peripheral portion of the person 10 is detected in the process of step S12 and the other boundary lines are not problematic is that the person 10 possesses the belonging 12 and the person 10 in the human figure representing the person 10 This is to prevent the hollow portion from being masked by the background mask even when the possessed portion 12 having a lower millimeter wave intensity is in the hollow portion. In other words, if the human figure that appears when binarized is masked as it is, when the person 10 possesses the possession 12, the part of the possession 12 is masked, resulting in possession. The object 12 cannot be detected. Therefore, the above boundary line processing is purposely performed to detect the outer periphery.

  [Step S14] The masking processing unit 151 performs a masking process using the created background mask, and extracts a human body portion of the person 10 that is not masked.

  [Step S15] The histogram creation unit 152 creates a histogram using only the human body portion of the person 10 cut out by the masking processing unit 151.

  [Step S16] Upon receiving the created histogram, the table creation unit 153 creates a contrast table.

  [Step S17] The contrast correction unit 154 corrects the contrast of the millimeter wave image using the created contrast table. In the contrast table used for this correction, only the humanoid part of the person 10 is targeted by the background mask, so the difference in contrast between the person 10 and the belongings 12 becomes clear. Therefore, when the person 10 possesses for a relatively long time, the temperature of the person 10 and the temperature of the possession 12 become close, and the intensity of the millimeter wave radiated from the person 10 and the possession 12 is approximate. However, since the difference in contrast becomes large, it becomes easy to distinguish.

  Through the processing as described above, the outer peripheral boundary of the imaging target is detected, the imaging target part inside the outer peripheral boundary is cut out from the image captured by the imaging device, and only the extracted imaging target part is scaled. Millimeter waves emitted from parts other than people (background parts) are excluded, and only millimeter waves emitted only from the cut-out imaging target part are scaled, so that millimeters emitted only from the cut-out imaging target part are scaled. Even if the millimeter wave intensity generated by the wave, that is, the person to be imaged and the belongings possessed by the person is fine, the contrast is improved and the detection accuracy of the belongings can be improved.

  Thus, if the detection accuracy of belongings can be improved, it is useful to apply the invention according to the present embodiment to an automatic belonging detection device, for example. That is, by performing the above-described contrast correction, the difference in contrast becomes large even when the intensities of millimeter waves radiated from the person 10 and the belongings 12 are approximated. This makes it easy to apply the above-described invention to a device for detecting the above. That is, the possessed object 12 shown in FIG. 3B radiates more than the difference between the millimeter wave intensity peak emitted by the possession 12 shown in FIG. 2B and the millimeter wave intensity peak emitted by the person 10. Since the difference between the peak of the millimeter wave intensity to be generated and the peak of the millimeter wave intensity emitted by the person 10 is clearer, when applied to the detection device for the possession 12, the probability of detection omission of the possession 12 can be significantly reduced. It becomes possible.

The above processing functions can be realized by a computer. In that case, an output correction program describing the processing content of the function that the output correction apparatus should have is provided. By executing the output correction program on a computer, the above processing functions are realized on the computer. The output correction program describing the processing content can be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory. Magnetic recording devices include HDDs, FDs, magnetic tapes, and the like. Optical discs include DVD (Digital Versatile Disc), DVD-RAM, CD-ROM, CD-R (Recordable) / RW (ReWritable), and the like. Magneto-optical recording devices include MO (Magneto
Optical disk).

  When distributing the output correction program, for example, portable recording media such as a DVD and a CD-ROM in which the output correction program is recorded are sold. It is also possible to store the program in a storage device of a server computer and transfer the output correction program from the server computer to another computer via a network.

  The computer that executes the output correction program stores, for example, the output correction program recorded on the portable recording medium or the output correction program transferred from the server computer in its own storage device. Then, the computer reads the output correction program from its own storage device and executes processing according to the output correction program. The computer can also read the output correction program directly from the portable recording medium and execute processing according to the output correction program. Further, each time the output correction program is transferred from the server computer, the computer can sequentially execute processing according to the received output correction program.

  The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present invention.

  The above merely illustrates the principle of the present invention. In addition, many modifications and changes can be made by those skilled in the art, and the present invention is not limited to the precise configuration and application shown and described above, and all corresponding modifications and equivalents may be And the equivalents thereof are considered to be within the scope of the invention.

10 people 11 radio wave absorbers 12 belongings 20 monitor 100 millimeter wave passive imaging device 110 vibration reflector unit 111 vibration reflector 112 pulse generation unit 120 line sensor 130 synchronization / address generation unit 140 conversion unit 141 A / D conversion circuit 142 frame memory 150 Image processing unit 151 Masking processing unit 152 Histogram creation unit 153 Table creation unit 154 Contrast correction unit 155 Output processing unit

Claims (6)

In a contrast correction device used for an imaging device that receives and captures a fine signal emitted from an imaging target,
An outer boundary detection unit for detecting an outer boundary of an imaging target of the imaging device;
An imaging target cutting means for cutting out an imaging target portion inside the outer peripheral boundary from an image captured by the imaging device;
Scaling means for scaling only the cut-out imaging target portion;
A contrast correction apparatus comprising: A histogram generating means for generating a histogram of the cut-out imaging target portion;
The contrast correction apparatus according to claim 1, wherein the scaling unit performs scaling using the generated histogram. Binarizing means for binarizing an image captured by the imaging device;
The contrast correction apparatus according to claim 1, wherein the outer peripheral boundary detection unit detects an outer peripheral boundary of the imaging target using the binarized image. In the possession detection apparatus for detecting the possession of the imaging target using the imaging apparatus that receives and captures a fine signal emitted from the imaging target,
An outer boundary detection unit for detecting an outer boundary of an imaging target of the imaging device;
An imaging target cutting means for cutting out an imaging target portion inside the outer peripheral boundary from an image captured by the imaging device;
Scaling means for scaling only the cut-out imaging target portion;
A possession detection apparatus comprising: In a contrast correction method used for an imaging apparatus that receives and captures a fine signal emitted from an imaging target,
A step of detecting an outer peripheral boundary of an imaging target of the imaging device;
A step of cutting out an imaging target from an image captured by the imaging device, the imaging target portion being inside the outer peripheral boundary;
A scaling means for scaling only the cut-out imaging target portion; and
A contrast correction method comprising: In a contrast correction program used for an imaging device that receives and captures a fine signal emitted from an imaging target,
Computer
An outer peripheral boundary detecting means for detecting an outer peripheral boundary of an imaging target of the imaging device;
An imaging target cutting means for cutting out an imaging target portion that is inside the outer peripheral boundary from an image picked up by the imaging device; and a scaling means for scaling only the cut out imaging target portion;
Contrast correction program characterized by functioning as

Images