JP2012109732A - Object identification apparatus and object identification method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an object identification apparatus that, when a moving object is included in a predetermined imaging area, can accurately identify whether or not the moving object is a human.SOLUTION: A monitoring apparatus 3 as an object identification apparatus includes: an acquisition section 21 for, when a moving object is included in a pickup image 200 imaging a predetermined monitored area 4, acquiring an enlarged image 300 of the moving object, which includes a visible area and an infrared area; an analysis section 22 for detecting spectra of a plurality of particular wavelengths in the infrared region on the basis of the enlarged image 300, and analyzing the material of the moving object on the basis of the results of the detection; and an identification section 23 for identifying the type of the moving object on the basis of the result of analysis by the analysis section 22.

Description

  The present invention relates to a target identification device and a target identification method, and more particularly, to a target identification device and a target identification method for identifying whether or not a moving object included in a predetermined imaging area is a human being.

  A monitoring device that detects an intruder into a monitoring area by photographing a predetermined monitoring area with a monitoring camera has been widely put into practical use. In such a monitoring apparatus, for example, by preparing a plurality of template images related to the appearance of a human in advance and performing pattern matching using the template image, whether a human (intruder) is included in the captured image It is determined whether or not.

  Patent Document 1 below discloses a monitoring device that monitors intruders indoors. The monitoring apparatus captures indoors with a camera, extracts a change area based on a difference image between frames, and detects a moving object (intruder) by performing pattern matching on the change area.

Japanese Patent No. 3423861

  However, the method for determining the presence or absence of a person by pattern matching using a template image has the following problems. That is, when monitoring an intruder into a specific facility such as a communication base station installed in a mountain, it is difficult to accurately distinguish an animal (eg, a monkey) whose appearance is similar to a human and a human. Therefore, when an animal approaches the monitoring area of a specific facility, there is a high possibility that the animal is erroneously detected as an intruder.

  In addition, when the entire surveillance area of the specific facility is photographed with a wide-angle surveillance camera, the size of the target object included in the photographed image is reduced, so that the possibility of erroneous detection due to pattern matching is further increased.

  The present invention has been made to solve such a problem. When a moving object is included in a predetermined imaging area, it is possible to accurately identify whether or not the moving object is a human. The object is to obtain a target identification device and a target identification method.

  The object identification device according to the first aspect of the present invention acquires an enlarged image of a moving object including a visible region and an infrared region when a moving object is included in a captured image obtained by capturing a predetermined capturing area. An acquiring unit that detects a spectrum of a plurality of wavelengths in the infrared region based on the enlarged image, and analyzes the material of the moving object based on the detection result, and the analysis by the analyzing unit And identifying means for identifying the type of the moving object based on the result.

  According to the object identification device according to the first aspect, the identification unit identifies the type of the moving object included in the imaging area based on the result of the material analysis by the analysis unit. Therefore, when human skin, chemical fiber, or the like is included as a result of material analysis, the moving object can be identified as a human. In addition, the acquisition unit acquires an enlarged image of the moving object, and the analysis unit performs material analysis based on the enlarged image. Therefore, the influence of the background area unrelated to the moving object can be eliminated, and the material analysis of the moving object can be performed with high accuracy. As a result, when a moving object is included in a predetermined imaging area, it is possible to accurately identify whether the moving object is a human being or an animal other than that.

  The object identification device according to a second aspect of the present invention is the object identification device according to the first aspect, in particular, the acquisition means includes a first camera with a relatively wide angle of view that images the entire imaging area. , When the moving object is included in the image captured by the first camera, the specifying means for specifying the position of the moving object in the shooting area, and the position specified by the specifying means And a second camera having a relatively narrow angle of view to obtain the enlarged image.

  According to the object identification device according to the second aspect, the acquisition unit captures the entire imaging area with the first camera having a relatively wide angle of view, and the captured image includes a moving object. An enlarged image of the moving object is obtained by photographing the moving object with the second camera having a relatively narrow angle of view. Accordingly, it is possible to perform detailed imaging of a moving object with the second camera while imaging the entire imaging area widely with the first camera. In addition, the specifying unit specifies the position of the moving object in the shooting area when the moving image is included in the captured image of the first camera, and the second camera determines the position specified by the specifying unit. Take a picture. Accordingly, since it is not necessary to search for a moving object with the second camera having a narrow angle of view, the moving object photographing operation by the second camera can be started without delay.

  The object identification device according to a third aspect of the present invention is the object identification device according to the second aspect, in particular, the second camera transmits the reflected light from the first light receiving element portion and the moving object. A first optical system that guides light onto the first light receiving element unit, and the analysis means includes a second light receiving element unit, the first light receiving element unit, and the first optical system. Between the first optical system and the first light receiving element portion, and branching means for branching the reflected light from the first optical system to the first light receiving element portion, and the reflected light branched by the branching means on the second light receiving element portion And a second optical system for guiding light.

  According to the object identification device according to the third aspect, the branching means is disposed between the first light receiving element portion and the first optical system, and the reflection is directed from the first optical system toward the first light receiving element portion. The light is branched toward the second optical system by the branching unit. Thereby, the reflected light common to the reflected light guided to the first light receiving element portion by the first optical system can be guided to the second light receiving element portion by the second optical system. . As a result, the analysis means can accurately perform material analysis based on the enlarged image obtained by the second camera. In addition, since it is not necessary to provide a dedicated camera for performing material analysis separately from the second camera, the apparatus can be reduced in size, and the operation of the dedicated camera and the operation of the second camera to obtain a common enlarged image. The control which synchronizes is also unnecessary.

  The object identification device according to a fourth aspect of the present invention is the object identification device according to any one of the first to third aspects, in particular, the analysis means divides the entire area of the enlarged image and the enlarged image. The material analysis is performed on at least one of the plurality of small regions and a circular or elliptical region included in the enlarged image.

  According to the object identification device according to the fourth aspect, the analysis means includes at least one of the entire area of the enlarged image, a plurality of small areas obtained by dividing the enlarged image, and a circular or elliptical area included in the enlarged image. Material analysis is performed on the target. By using the entire area of the enlarged image as an analysis target, material analysis can be easily performed. By using a plurality of small regions obtained by dividing the enlarged image as an analysis target, it is possible to perform a highly accurate analysis as compared with a case where the entire region is an analysis target. By using a circular or elliptical area included in the enlarged image as the analysis target, when a face is included in the enlarged image, material analysis can be performed for that face, so moving objects It is possible to identify with high accuracy whether the person is a human or other animal.

  In the object identification method according to the fifth aspect of the present invention, (A) when a moving object is included in a photographed image obtained by photographing a predetermined photographing area, the moving object including the visible region and the infrared region is enlarged. (B) detecting a spectrum of a plurality of specific wavelengths in the infrared region based on the enlarged image, and analyzing the material of the moving object based on the detection result; C) identifying the type of the moving object based on the result of the analysis in step (B).

  According to the object identification method according to the fifth aspect, in step (C), the type of the moving object included in the imaging area is identified based on the result of the material analysis in step (B). Therefore, when human skin, chemical fiber, or the like is included as a result of material analysis, the moving object can be identified as a human. Moreover, in step (A), an enlarged image of the moving object is acquired, and in step (B), material analysis is performed based on the enlarged image. Therefore, the influence of the background area unrelated to the moving object can be eliminated, and the material analysis of the moving object can be performed with high accuracy. As a result, when a moving object is included in a predetermined imaging area, it is possible to accurately identify whether the moving object is a human being or an animal other than that.

  According to the present invention, there is provided a target identification device and a target identification method capable of accurately identifying whether or not a moving object is a human when the predetermined photographing area includes the moving object. Obtainable.

It is a figure which shows an example of the usage condition of the monitoring apparatus as an object identification apparatus which concerns on embodiment of this invention. It is a figure which shows typically the external appearance of a monitoring apparatus. It is a block diagram which shows the function of a monitoring apparatus roughly. It is a block diagram which shows the structure of an acquisition part roughly. It is a flowchart which shows the whole operation | movement of a monitoring apparatus roughly. It is a figure which shows typically an example of the picked-up image image | photographed with the monitoring apparatus. It is a figure which shows schematically the internal structure of a telephoto camera. It is a figure which shows the structure of an optical system. It is a top view which shows the light-receiving surface of a light-receiving element part. It is a figure which shows roughly an example of the optical path in the orthogonal | vertical direction of the reflected light which injected into the optical system. It is a figure which shows roughly an example of the optical path in the horizontal direction of the light which injected into the optical system. It is a block diagram which shows the structure of a calculating part. It is a flowchart which shows the identification process of the target object by an identification part. It is a flowchart which shows the identification process of the target object by an identification part. It is a figure which shows the other example of a setting of an analysis object range.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In addition, the element which attached | subjected the same code | symbol in different drawing shall show the same or corresponding element.

  FIG. 1 is a diagram illustrating an example of a usage state of a monitoring device 3 as a target identification device according to an embodiment of the present invention. A communication base station 1 is installed in the mountains, and the communication base station 1 is surrounded by a fence 2. In this example, the monitoring device 3 is used for the purpose of monitoring an intruder trying to get over the fence 2 and enter the communication base station 1 by shooting the monitoring area 4 including the fence 2 as a predetermined shooting area. Is done. In the example of FIG. 1, only one monitoring device 3 is installed in the communication base station 1, but a plurality of monitoring devices 3 may be installed in order to monitor the surroundings of the communication base station 1 without blind spots. .

  FIG. 2 is a diagram schematically illustrating the appearance of the monitoring device 3. A pair of wide-angle cameras 11 </ b> A and 11 </ b> B functioning as a stereo camera, a telephoto camera 12, and a control device 13 are attached to the frame 10. The wide-angle cameras 11A and 11B have a fixed field of view so that the entire monitoring area 4 can be photographed. The telephoto camera 12 is, for example, a PTZ camera equipped with a pan / tilt function and a zoom function. The wide-angle cameras 11A and 11B and the telephoto camera 12 capture the object by receiving reflected sunlight from the object. However, the monitoring device 3 may be provided with a light irradiator for irradiating the monitoring area 4 with halogen light or infrared light so as to enable photographing at night.

  FIG. 3 is a block diagram schematically showing functions of the monitoring device 3. The monitoring device 3 includes an acquisition unit 21, an analysis unit 22, and an identification unit 23. When the captured image obtained by capturing the monitoring area 4 includes a moving object, the acquiring unit 21 acquires an enlarged image of the moving object including the visible region and the infrared region. The analysis unit 22 detects a spectrum of specific wavelengths in the infrared region based on the enlarged image acquired by the acquisition unit 21, and analyzes the material of the moving object based on the detection result. The identification unit 23 identifies the type of the moving object based on the analysis result by the analysis unit 22.

  FIG. 4 is a block diagram schematically showing the configuration of the acquisition unit 21. The acquisition unit 21 includes wide-angle cameras 11A and 11B, a telephoto camera 12, and a position specifying unit 31. FIG. 5 is a flowchart schematically showing the overall operation of the monitoring device 3. FIG. 6 is a diagram schematically illustrating an example of a captured image captured by the monitoring device 3. 6A shows captured images 200 of the wide-angle cameras 11A and 11B, and FIG. 6B shows an enlarged image 300 captured by the telephoto camera 12. FIG.

  4 to 6, the wide-angle cameras 11A and 11B always shoot the entire monitoring area 4, and a captured image 200 is thereby obtained (step P11). If any moving object is detected in the monitoring area 4 based on the captured images 200 of the wide-angle cameras 11A and 11B (the determination result in step P12 is “YES”), the position specifying unit 31 may select the wide-angle cameras 11A and 11B. The position of the moving object in the monitoring area 4 (for example, the center position 201) is specified based on the distance between them and the positional relationship of the moving object in the captured images 200 of the wide-angle cameras 11A and 11B (step P13). In the example of the present embodiment, it is assumed that the monitoring device 3 is used for monitoring an intruder trying to get over the fence 2 and enter the communication base station 1. Since it is necessary to consider the amount of movement in the vertical direction, a stereo camera is configured using the two wide-angle cameras 11A and 11B. However, when it is not necessary to consider the amount of movement in the height direction, it is not always necessary to use a stereo camera, and the position of a moving object can be specified using only one wide-angle camera.

  Next, the acquisition unit 21 acquires an enlarged image 300 of the moving object including the visible region and the infrared region by performing imaging with the telephoto camera 12 with the position of the moving object specified by the position specifying unit 31 as the center of the visual field. (Step P14). Next, the analysis unit 22 performs material analysis of the moving object using the hyperspectral analysis technique on the enlarged image 300 acquired by the acquisition unit 21 (step P15). Next, the identification unit 23 determines whether or not the moving object is a human based on the result of the analysis by the analysis unit 22 (step P16).

  If the moving object is not a human (the determination result in Step P16 is “NO”), the process returns to Step P11 and the same operation as described above is repeated. On the other hand, when the moving object is a human (that is, an intruder) (the determination result in Step P16 is “YES”), the intruder is warned by sound or light, and the telephoto camera 12 detects the intruder. The captured image is tracked and the captured image is recorded (step P17). Drive control of the telephoto camera 12 for tracking an intruder is performed by the control unit 13 shown in FIG. However, by mounting an FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) storing a predetermined control program for tracking in the telephoto camera 12, tracking of the intruder can be performed by controlling the telephoto camera 12 itself. You may go. If the intruder leaves the monitoring area 4 as a result of tracking the intruder (the determination result in step P18 is “YES”), the process returns to step P11 and the same operation as described above is repeated.

  FIG. 7 is a diagram schematically showing the internal structure of the telephoto camera 12. The telephoto camera 12 includes an optical system 41 including a zoom lens and a light receiving element unit 42 such as a CCD. Reflected light (including visible light and infrared light) from the moving object is guided onto the light receiving element unit 42 by the optical system 41. Each light receiving element constituting the light receiving element unit 42 outputs an electrical signal having a magnitude corresponding to the received light intensity of the reflected light in the visible light wavelength region. The enlarged image 300 taken by the telephoto camera 12 is displayed on a display unit 43 such as a liquid crystal display installed in the communication base station 1 or a remote monitoring center.

  As illustrated in FIG. 7, the analysis unit 22 includes a branching unit 51, an optical system 52, a light receiving element unit 53, and a calculation unit 54. The branching unit 51 is a prism or a half mirror, and is disposed between the optical system 41 and the light receiving element unit 42. The reflected light traveling from the optical system 41 toward the light receiving element unit 42 is branched by the branching unit 51 toward the optical system 52. The branched reflected light is guided onto the light receiving element portion 53 by the optical system 52. Each light receiving element constituting the light receiving element unit 53 outputs an electric signal having a magnitude corresponding to the received light intensity of the reflected light in the wavelength range of infrared light. The electrical signal output from the light receiving element unit 53 is input to the calculation unit 54. The signal output from the calculation unit 54 is input to the identification unit 23.

  Instead of using a prism or a half mirror, an insertable / retractable reflecting mirror may be disposed between the optical system 41 and the light receiving element portion 42. At the first timing, the reflecting mirror is retracted from the optical path between the optical system 41 and the light receiving element unit 42. Thereby, the reflected light from the moving object is guided onto the light receiving element portion 42. Further, at the second timing, the reflecting mirror is inserted on the optical path between the optical system 41 and the light receiving element portion 42. The reflected light from the optical system 41 toward the light receiving element unit 42 is reflected toward the optical system 52 by the reflecting mirror. Thereby, the reflected light from the moving object is guided onto the light receiving element portion 53. The first and second timings are alternately repeated at predetermined minute time intervals.

  FIG. 8 is a diagram illustrating a configuration of the optical system 52. The optical system 52 includes a diffusing unit 61, a condensing unit 62, and a selective transmission unit 63. The X direction shown in the figure indicates the horizontal direction, the Y direction indicates the vertical direction, and the Z direction indicates a direction orthogonal to both the X direction and the Y direction. The diffusing unit 61, the light collecting unit 62, and the selective transmission unit 63 are arranged so as to overlap each other in the Z direction.

  The diffusing unit 61 is a lenticular lens having a structure in which a plurality of cylindrical lenses 64 extending along the X direction are arranged in parallel along the Y direction. The diffusion part 61 is made of a transparent material such as glass. The diffusion unit 61 diffuses the reflected light from the incident moving object in the Y direction.

  The condensing part 62 has the cylindrical lens 65 formed with transparent materials, such as glass. The condensing unit 62 condenses the reflected light diffused in the Y direction by the diffusing unit 61 in the X direction.

  The selective transmission unit 63 has a structure in which a plurality of wavelength selection filters 661 to 665 extending along the X direction are arranged in parallel along the Y direction. In the example of the present embodiment, the wavelength selection filters 661, 662, 663, 664, and 665 are the 1100 nm band, the 1200 nm band, the 1300 nm band, the 1500 nm band, and the 1600 nm band of the light incident from the light collecting unit 62, respectively. Only the wavelength component is transmitted.

  As a modification, five wavelength selective filters that transmit only the wavelength components in the 1100 nm band, the 1200 nm band, the 1300 nm band, the 1500 nm band, and the 1600 nm band are prepared, and the five wavelengths are used at the second timing. By arranging the selection filter in order in the optical system 41 (see FIG. 6), the arrangement of the selective transmission part 63 can be omitted.

  Referring to FIG. 8, the light receiving element portion 53 is disposed in the vicinity of the transmission surface of the selective transmission portion 63. The size of the light receiving surface of the light receiving element unit 53 is substantially equal to the size of the transmission surface of the selective transmission unit 63. The light receiving element portion 53 has a structure in which a plurality of light receiving elements using InGaAs or the like are arranged in a matrix. Each light receiving element outputs an electrical signal having a magnitude corresponding to the received light intensity. In addition, by arranging a projection lens between the selective transmission unit 63 and the light receiving element unit 53, the size of the light receiving surface of the light receiving element unit 53 can be made smaller than the size of the transmission surface of the selective transmission unit 63. it can.

  FIG. 9 is a plan view showing a light receiving surface of the light receiving element portion 53. The light receiving surface of the light receiving element portion 53 has light receiving regions 71, 72, 73, 74, 75 corresponding to the transmission surfaces of the wavelength selection filters 661, 662, 663, 664, 665, respectively.

  FIG. 10 is a diagram schematically illustrating an example of an optical path in the vertical direction (Y direction) of the reflected light incident on the optical system 52. When the columnar target object 100 is present in front of the monitoring device 3, the reflected light from the target object 100 is branched toward the optical system 52 by the branching part 51 and then enters the diffusion part 61. The reflected light incident on the diffusing unit 61 is refracted by the cylindrical lens 64 according to the incident angle in the Y direction, and is dispersed in the Y direction. The reflected light dispersed by the dispersion unit 61 is incident on the light receiving surface of the light receiving element unit 53 by passing through the light collecting unit 62 and then selectively passing through the selective transmission unit 63 according to the wavelength.

  Here, the formation pitch of the cylindrical lenses 64 on the surface of the diffusion part 61 is sufficiently smaller than the distance between the diffusion part 61 and the object 100. Therefore, the reflected light from the object 100 is also incident on the other cylindrical lenses 64, and is refracted in various directions in each cylindrical lens 64 according to the incident angle. Therefore, the reflected light from the object 100 is diffused by the diffusing unit 61 and passes through all the wavelength selection filters 661 to 665 of the selective transmission unit 63 according to the wavelength.

  FIG. 11 is a diagram schematically illustrating an example of an optical path in the horizontal direction (X direction) of light incident on the optical system 52. The reflected light from the object 100 is branched toward the optical system 52 by the branching unit 51, then passes through the diffusion unit 61 and enters the light collecting unit 62. The condensing unit 62 condenses the incident reflected light at different positions in the X direction on the light receiving surface of the light receiving element unit 53 according to the position of the object 100 in the X direction. At that time, the reflected light traveling from the light collecting unit 62 toward the light receiving element unit 53 selectively transmits through the selective transmission unit 63 according to the wavelength as described above.

  12 is a block diagram showing a configuration of the calculation unit 54 shown in FIG. The calculation unit 54 includes a reflectance calculation unit 91, a normalization index calculation unit 92, and a secondary differential value calculation unit 93.

  As described above, each light receiving element constituting the light receiving element unit 53 outputs an electrical signal having a magnitude corresponding to the received light intensity of the reflected light. The electrical signal is input to the reflectance calculation unit 91 from each light receiving element.

  Based on the electrical signal input from the light receiving element unit 53, the reflectance calculation unit 91 reflects the reflectances R1100, R1200, R1300, and R1500 for each wavelength component in the 1100 nm band, 1200 nm band, 1300 nm band, 1500 nm band, and 1600 nm band. , R1600.

Based on the reflectances R1100, R1200, R1300, R1500, and R1600 calculated by the reflectance calculation unit 91, the normalization index calculation unit 92 calculates normalization indexes ND1 to ND4 defined by the following expressions.
ND1: (R1500-R1300) / (R1500 + R1300)
ND2: (R1500-R1200) / (R1500 + R1200)
ND3: (R1600-R1300) / (R1600 + R1300)
ND4: (R1300-R1100) / (R1300 + R1100)

Moreover, the secondary differential value calculation part 93 calculates the secondary differential value of the function of the said reflectance and a wavelength. In the example of the present embodiment, the second derivative calculation unit 93 is an approximation defined by the following formula based on the reflectances R1100, R1200, R1300, R1500, and R1600 calculated by the reflectance calculation unit 91. to calculate the specific secondary differential value ² nd ^der1,2 nd ^der2.
2 ^nd der1:
[{(R1500-R1300) / (R1500 + R1300)} / 200]
-[{(R1300-R1200) / (R1300 + R1200)} / 100]
2 ^nd der2:
[{(R1500-R1200) / (R1500 + R1200)} / 300]
-[{(R1200-R1100) / (R1200 + R1100)} / 100]

The reflectances R1100, R1200, R1300, R1500, R1600, the normalization indices ND1 to ND4, and the second derivative values 2 ^nd der1 and ^nd der2 are input from the calculation unit 54 to the identification unit 23.

  The identification unit 23 identifies the type of the target (that is, the moving object included in the monitoring area 4) based on the information input from the calculation unit 54.

  FIGS. 13 and 14 are flowcharts showing the object identifying process by the identifying unit 23. First, in step P21, the identification unit 23 determines whether or not the values of the reflectances R1100, R1200, R1300, R1500, and R1600 are approximately zero. For example, when the reflectance value is less than a predetermined value (for example, 0.02), the reflectance is determined to be approximately 0, and when the reflectance value is greater than or equal to the predetermined value, It is determined that the reflectance is not approximately 0. When the values of all the reflectances R1100, R1200, R1300, R1500, R1600 are approximately 0 (that is, when the determination result in step P21 is “YES”), the identification unit 23 is within the analysis target range. It is determined that the window glass exists in the entire area of the enlarged image 300 in this example.

On the other hand, if any of the reflectances R1100, R1200, R1300, R1500, R1600 is not approximately 0 (that is, if the determination result in step P21 is “NO”), then in step P22, the identification unit 23 determines whether a value “2 ^nd der1 × (ND1 + ND3)” obtained by multiplying the secondary differential value 2 ^nd der1 by the sum of the normalization indices ND1 and ND3 is less than a predetermined threshold Th11.

When the value of “2 ^nd der1 × (ND1 + ND3)” is equal to or greater than the threshold Th11 (that is, when the determination result in Step P22 is “NO”), in Step P23, the identifying unit 23 then performs the normalization index ND2. It is determined whether the value of is greater than a predetermined threshold Th12.

  When the value of the normalization index ND2 is larger than the threshold Th12 (that is, when the determination result in Step P23 is “YES”), the identification unit 23 determines that there is an animal or cloth within the analysis target range.

On the other hand, when the value of the normalization index ND2 is equal to or less than the threshold Th12 (that is, when the determination result in Step P23 is “NO”), in Step P24, the identification unit 23 then determines the second derivative value 2 ^nd der2 It is determined whether the value of is less than a predetermined threshold value Th13.

When the value of the secondary differential value 2 ^nd der2 is less than the threshold Th13 (that is, when the determination result in Step P24 is “YES”), the identification unit 23 determines that a plant exists in the analysis target range. .

On the other hand, when the value of the second derivative 2 ^nd der2 is equal to or greater than the threshold Th13 (that is, when the determination result in Step P24 is “NO”), the identification unit 23 has human skin within the analysis target range. Judge that.

If the value of “2 ^nd der1 × (ND1 + ND3)” is greater than or equal to the threshold Th11 in the determination in step P22 (that is, if the determination result in step P22 is “NO”), then in step P25, the identification unit 23 determines whether the value of the normalization index ND3 is less than a predetermined threshold Th14.

  If the value of the normalized index ND3 is less than the threshold Th14 (that is, if the determination result in Step P25 is “YES”), then in Step P26, the identifying unit 23 determines that the value of the normalized index ND4 is a predetermined value. It is determined whether or not the threshold value is less than Th15.

  When the value of the normalization index ND4 is less than the threshold Th15 (that is, when the determination result in Step P26 is “YES”), the identification unit 23 determines that the metal exists within the analysis target range.

  On the other hand, when the value of the normalization index ND4 is equal to or greater than the threshold Th15 (that is, when the determination result in Step P26 is “NO”), the identification unit 23 determines that concrete or stone exists within the analysis target range. To do.

  If the value of the normalization index ND3 is equal to or greater than the threshold value Th14 in the determination in step P25 (that is, if the determination result in step P25 is “NO”), then in step P27, the identification unit 23 performs normalization. It is determined whether or not the value of the index ND2 is less than a predetermined threshold Th16.

  When the value of the normalization index ND2 is less than the threshold Th16 (that is, when the determination result in Step P27 is “YES”), the identification unit 23 determines that asphalt exists within the analysis target range.

  On the other hand, when the value of the normalization index ND2 is equal to or greater than the threshold Th16 (that is, when the determination result in Step P27 is “NO”), the identification unit 23 determines that concrete or stone exists within the analysis target range. To do.

  In addition, each threshold value Th11 to Th16 is an appropriate value that can accurately identify a target by setting a measurement region for a known target such as metal or human skin in advance and performing the identification flow by the identification unit 23. Set to a value.

  As a result, when the identification unit 23 determines that human skin exists within the analysis target range, the identification unit 23 identifies that the type of the moving object included in the monitoring area 4 is human. On the other hand, in other cases, the type of the moving object included in the monitoring area 4 is identified as not being human. For example, when it is determined that a window glass or metal exists within the analysis target range, the type of the moving object included in the monitoring area 4 is identified as a car.

  In addition, the situation where the intruder into the monitoring area 4 does not expose human skin by wearing a cover or gloves is also assumed. Therefore, if it is determined that a chemical fiber is present in the analysis target range by setting an identification flow that can detect a material such as a chemical fiber worn only by humans, the movement included in the monitoring area 4 The object type may be identified as human.

  In the above description, the analysis target range in which material analysis is performed is set in the entire area of the enlarged image 300. However, a different area can be set as the analysis target range. FIG. 15 is a diagram illustrating another setting example of the analysis target range. By dividing the entire area of the enlarged image 300 into a plurality of small areas 301 and sequentially setting each small area 301 as an analysis target range, material analysis on each small area 301 is sequentially executed. When it is determined that human skin (or chemical fiber) exists in at least one of the plurality of small regions 301, the identification unit 23 determines that the type of the moving object included in the monitoring area 4 is human. Identify it. As another example, paying attention to the human head having a circular or elliptical shape, a circular or elliptical region 302 included in the enlarged image 300 is extracted by pattern matching or the like, and the region 302 is analyzed. By setting the target range, the material analysis regarding the region 302 is executed. When it is determined that human skin (or chemical fiber) is present in the region 302, the identification unit 23 identifies that the type of the moving object included in the monitoring area 4 is human. A method for setting the entire region of the enlarged image 300 as an analysis target range, a method for sequentially setting a plurality of small regions 301 as an analysis target range, and a method for setting a circular or elliptical region 302 as an analysis target range are as follows. These can be applied in combination with each other, and the identification accuracy can be improved by combining a plurality of methods.

  As described above, according to the monitoring device 3 according to the present embodiment, the identification unit 23 identifies the type of the moving object included in the monitoring area 4 based on the result of the material analysis by the analysis unit 22. Therefore, when human skin, chemical fiber, or the like is included as a result of material analysis, the moving object can be identified as a human. Moreover, the acquisition unit 21 acquires the enlarged image 300 of the moving object, and the analysis unit 22 performs material analysis based on the enlarged image 300. Therefore, the influence of the background area unrelated to the moving object can be eliminated, and the material analysis of the moving object can be performed with high accuracy. As a result, when a moving object is included in the predetermined monitoring area 4, it is possible to accurately identify whether the moving object is a human being or an animal other than that.

  Moreover, according to the monitoring device 3 according to the present embodiment, the acquisition unit 21 captures the entire monitoring area 4 with the wide-angle cameras 11A and 11B, and when the captured image 200 includes a moving object, By capturing a moving object with the telephoto camera 12, an enlarged image 300 of the moving object is obtained. Accordingly, it is possible to take a detailed picture of a moving object with the telephoto camera 12 while photographing the entire monitoring area 4 widely with the wide-angle cameras 11A and 11B. Moreover, the position specifying unit 31 specifies the position of the moving object in the monitoring area 4 when the captured images 200 of the wide-angle cameras 11A and 11B include the moving object, and the telephoto camera 12 includes the position specifying unit 31. Shoots the position specified from. Accordingly, since it is not necessary to search for a moving object with the telephoto camera 12, the moving object photographing operation by the telephoto camera 12 can be started without delay.

  Further, according to the monitoring device 3 according to the present embodiment, the branching unit 51 is arranged between the light receiving element unit 42 and the optical system 41, and the reflected light traveling from the optical system 41 toward the light receiving element unit 42 is separated from the branching unit 51. Branches 51 toward the optical system 52. Accordingly, the reflected light that is common to the reflected light guided onto the light receiving element unit 42 by the optical system 41 can be guided onto the light receiving element unit 53 by the optical system 52. As a result, the analysis unit 22 can accurately perform spectrum analysis on the enlarged image 300 obtained by the telephoto camera 12. In addition, since it is not necessary to provide a dedicated camera (hyperspectral camera) for performing spectrum analysis separately from the telephoto camera 12, the apparatus can be downsized and the operation of the dedicated camera and the telephoto camera 12 to obtain a common enlarged image. Control to synchronize with the operation is also unnecessary.

  Further, according to the monitoring device 3 according to the present embodiment, the analysis unit 22 includes the entire area of the enlarged image 300, a plurality of small areas 301 obtained by dividing the enlarged image 300, and a circle or an ellipse included in the enlarged image 300. Spectral analysis is performed on at least one of the regions 302 of the shape. By using the entire area of the enlarged image 300 as an analysis target, spectrum analysis can be easily performed. By using a plurality of small regions 301 obtained by dividing the enlarged image 300 as analysis targets, it is possible to perform analysis with higher accuracy than when the entire region is set as an analysis target. Since a circular or elliptical region 302 included in the enlarged image 300 is set as an analysis target, when a face is included in the enlarged image 300, spectrum analysis can be performed on the face. It becomes possible to identify with high accuracy whether the moving object is a human being or an animal other than that.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined not by the above-mentioned meaning but by the scope of claims for patent, and is intended to include all modifications within the scope and meaning equivalent to the scope of claims for patent.

DESCRIPTION OF SYMBOLS 3 Monitoring apparatus 4 Monitoring area 11A, 11B Wide angle camera 12 Telephoto camera 21 Acquisition part 22 Analysis part 23 Identification part 31 Position specification part 41,52 Optical system 42,53 Light receiving element part 51 Branch part 54 Operation part 300 Enlarged image 301 Small area 302 area

Claims (5)

An acquisition means for acquiring an enlarged image of the moving object including a visible region and an infrared region when a moving object is included in a captured image obtained by capturing a predetermined capturing area;
Analyzing means for detecting a spectrum of a plurality of specific wavelengths in the infrared region based on the enlarged image, and analyzing the material of the moving object based on the detection result;
Identification means for identifying the type of the moving object based on the result of analysis by the analysis means;
An object identification device comprising: The acquisition means includes
A first camera with a relatively wide angle of view that captures the entire imaging area;
A specifying means for specifying a position of the moving object in the shooting area when the moving object is included in an image captured by the first camera;
A second camera with a relatively narrow angle of view that obtains the enlarged image by photographing the position specified by the specifying means;
The object identification device according to claim 1, comprising: The second camera is
A first light receiving element portion;
A first optical system for guiding reflected light from the moving object onto the first light receiving element unit;
Have
The analysis means includes
A second light receiving element portion;
A branching unit that is disposed between the first light receiving element unit and the first optical system and branches reflected light from the first optical system toward the first light receiving element unit;
A second optical system that guides the reflected light branched by the branching unit onto the second light receiving element unit;
The object identification device according to claim 2, comprising: The analysis means includes
The entire area of the enlarged image,
4. The spectrum analysis according to claim 1, wherein the spectrum analysis is performed on at least one of a plurality of small regions obtained by dividing the enlarged image and a circular or elliptical region included in the enlarged image. Object identification device. (A) acquiring a magnified image of the moving object including a visible region and an infrared region when a moving object is included in a captured image obtained by capturing a predetermined capturing area;
(B) detecting a spectrum of a plurality of specific wavelengths in the infrared region based on the enlarged image, and analyzing the material of the moving object based on the detection result;
(C) identifying the type of the moving object based on the result of the analysis in step (B);
An object identification method comprising:

Images