WO2017006581A1 - Image processing device and traffic management system provided with same, and image processing method - Google Patents

Abstract

This image processing device (10) is provided with an image acquiring unit (13), a signal detecting unit (16), a color determining unit (17) and a color setting unit (18). The image acquiring unit (13) acquires an infrared image from a camera (103) which captures images in the vicinity of a traffic light. The signal detecting unit (16) detects a light-emitting position of the traffic light included in the acquired infrared image. The color determining unit (17) acquires information relating to the detected light-emitting position, and with reference to the design layout of the traffic light, determines the color of the traffic light included in a monochrome image acquired by the image acquiring unit (13). The color setting unit (18) outputs an image in which the region of the traffic light has been colored, by performing color processing in the region of the light-emitting position of the traffic light included in the detected infrared image, in such a way that said region is set to the color of the traffic light as determined by the color determining unit (17).

Description

Image processing apparatus, traffic management system including the same, and image processing method

The present invention relates to an image processing apparatus, a traffic management system including the same, and an image processing method.

2. Description of the Related Art Conventionally, a vehicle recognition device that discriminates a vehicle, a driver, and the like using a captured image of the vehicle captured by an imaging device such as a camera has been proposed. Such a vehicle recognition device is considered to be effective for the control of traffic violations and the handling of accidents.
In general, as such a captured image, an infrared image obtained by irradiating a subject such as a vehicle with near infrared light and capturing the reflected light is used. This is because an image can be acquired even in a dark situation such as at night.

Here, since infrared rays are not visible rays, an infrared image is a monochrome image. Therefore, in accident response and crime investigation, there is a possibility that sufficient information such as the color of the vehicle and the vehicle number cannot be obtained in the black and white image.
For example, Patent Document 1 discloses a technique for irradiating a subject with infrared light having a plurality of different wavelengths, performing color estimation using reflection characteristics of each wavelength from the subject, and colorizing an infrared image. Yes.

However, when the conventional technique is applied to detection of traffic violations, there are the following problems.
That is, in the image processing device disclosed in the above publication, a subject is irradiated with a plurality of infrared rays having different wavelengths, and each color is assigned according to the reflection intensity of the infrared rays having those wavelengths to estimate the color. The color setting is only an estimate, and the actual color reproducibility may be low.

Especially, when verifying traffic violations and traffic accidents, the color of traffic lights must be accurately reproduced, and there are limits to verifying traffic violations and traffic accidents based on the estimated colors.

JP 2011-50049 A JP 2014-236371 A JP 2002-171519 A JP 2005-45559 A JP 2001-36916 A JP 2012-65312 A JP 2003-242440 A JP-A-8-55296 JP 2008-299645 A JP 2014-115799 A

An object of the present invention is to provide an image processing device capable of accurately reproducing the color of a traffic signal included in a captured image around the traffic signal, a traffic management system including the image processing device, and an image processing method.
An image processing apparatus according to a first aspect includes an image acquisition unit, a signal detection unit, a color determination unit, and a color setting unit. The image acquisition unit acquires a monochrome image from an imaging device that images the periphery of the traffic light. The signal detection unit detects the light emission position of the traffic light included in the monochrome image acquired by the image acquisition unit. The color determination unit acquires information on the light emission position detected by the signal detection unit, refers to the design layout of the traffic signal, and determines the color of the traffic signal included in the monochrome image acquired by the image acquisition unit. The color setting section performs color arrangement processing on the area of the light emission position of the traffic light included in the monochrome image detected by the signal detection section so that the color of the traffic light determined by the color determination section is obtained, and the traffic light area is colored. Output the image.

Here, for example, a plurality of infrared images (an example of a monochrome image) captured by an imaging device that captures reflected infrared light emitted to a subject including a vehicle or a pedestrian traveling at an intersection where a traffic signal is installed. ) Is acquired. Then, the light emission position of the traffic light included in the monochrome image such as the infrared image is detected, and based on the information on the design layout of the traffic light, the color arrangement processing is performed on the area of the light emission position of the traffic light in the monochrome image, and the actual traffic light A color image that reproduces the color is output.

Here, since the traffic signal included in the monochrome image is a monochrome image, it is difficult to accurately determine three or two colors. On the other hand, identification of the light emitting position is relatively easy because the reflected intensity of infrared rays appears as a large difference from the non-light emitting position. The design layout of the traffic lights is determined by the country, region, and installation location. For example, in the case of a horizontally long traffic light that is generally used in Japan, they are arranged in order of red, yellow, and blue from the right. In addition, in a vertically long traffic light used in a snowy country in Japan, they are arranged in the order of red, yellow, and blue from the top. Furthermore, in the case of a pedestrian traffic light, they are arranged in the order of red and blue from the top.

In addition, the monochrome image acquired by the imaging device may be an image captured intermittently at a predetermined time interval, or may be an image captured continuously like moving image shooting. In addition, the monochrome image subjected to the color arrangement process may be all the monochrome images acquired by the image acquisition unit or a part of the monochrome images selected based on a predetermined condition.

And the color arrangement processing for the area of the light emission position of the traffic light in the monochrome image is based on the light emission position of the traffic light in the monochrome image and the design layout information of the traffic light, and performs the color arrangement processing on the light emission position of the traffic light in the monochrome image, It means a process for forming a color image.
Thereby, for example, when carrying out traffic violation control at a police station or when a traffic accident occurs, it is possible to obtain a color image that accurately reproduces the actual color of the traffic light at that time.

As a result, the traffic light and the traffic accident can be verified by accurately reproducing the color of the traffic light included in the captured image around the traffic light.
An image processing device according to a second invention is the image processing device according to the first invention, wherein the color setting unit, based on a predetermined condition, from a plurality of monochrome images acquired by the image acquisition unit. The image processing apparatus further includes a selection unit that selects a monochrome image to be subjected to color arrangement processing.

Here, a monochrome image selected according to a predetermined condition from a plurality of monochrome images acquired by the image acquisition unit is used as a monochrome image to be reproduced with the color of the traffic light included in the monochrome image.
Here, the selection condition of the monochrome image to be color-coded for reproducing the color of the traffic light includes, for example, that the image is a monochrome image captured at the date and time when the traffic violation or traffic accident occurred.

As a result, only monochrome images related to traffic violations and traffic accidents are subject to coloration processing, reducing the amount of data processing compared to applying coloration processing to the traffic light areas included in all monochrome images. However, the color of the actual traffic light can be accurately reproduced.
An image processing apparatus according to a third aspect of the present invention is the image processing apparatus according to the second aspect of the present invention, further comprising a violation detection unit that detects the presence or absence of a traffic violation of the vehicle included in the monochrome image. When the violation detection unit detects that the monochrome image includes a violation vehicle that is subject to traffic violation control, the color setting unit displays the traffic light emission position area included in the monochrome image selected by the selection unit. A color arrangement process is performed on the image.

Here, the selection condition of the monochrome image that is color-coded to reproduce the color of the traffic light includes that the image is a monochrome image captured at the date and time when the traffic violation is detected by the violation detector.
As a result, only monochrome images related to traffic violations such as signal ignorance are targeted for color arrangement processing, so that the amount of data processing can be reduced compared to the case where color arrangement processing is performed on the areas of traffic lights included in all monochrome images. While reducing, it is possible to accurately reproduce the color of the actual traffic light, which is important information when implementing traffic violation control.

An image processing apparatus according to a fourth aspect is the image processing apparatus according to the third aspect, wherein the violation detection unit is a sensor that detects a state of a vehicle that is subject to traffic violation control.
Here, information on whether or not a traffic violation has occurred is acquired from a sensor for detecting the traffic violation.
Thereby, for example, when a sensor detects a traveling vehicle in a traffic light with a red lane, it can be immediately determined that a traffic violation has occurred. Then, it is possible to select one or a plurality of monochrome images picked up in a time zone in which the ignoring vehicle that ignores the signal has passed, and to perform a color arrangement process on the area of the light emission position of the traffic light.

An image processing apparatus according to a fifth aspect is the image processing apparatus according to the third aspect, wherein the violation detection unit is an imaging apparatus that captures an image of a vehicle subject to traffic violation control.
Here, information on the presence or absence of the traffic violation is acquired from an imaging device such as a camera for detecting the traffic violation.
Note that the imaging device that detects the traffic violation may be the same as or different from the imaging device that captures the monochrome image.

Thereby, for example, when it is detected that a traveling vehicle is included in an image captured by the imaging device in a traffic lane in which the traffic light is red, it can be determined that a traffic violation has occurred. Then, it is possible to select one or a plurality of monochrome images picked up in a time zone in which the ignoring vehicle that ignores the signal has passed, and to perform a color arrangement process on the area of the light emission position of the traffic light.
An image processing device according to a sixth invention is the image processing device according to the second invention, and when the monochrome image includes a vehicle or a pedestrian related to a traffic accident, the color setting unit is Color arrangement processing is performed on the area of the light emission position of the traffic light included in the selected monochrome image.

Here, as a condition for selecting a monochrome image to be color-coded to reproduce the color of the traffic light, it is a monochrome image obtained by capturing a vehicle, a pedestrian, or the like related to the traffic accident at the date and time when the traffic accident occurred. included.
By doing this, only the monochrome images including vehicles and pedestrians before and after the occurrence of the traffic accident are subject to the color arrangement processing, and the color arrangement processing is performed on the areas of the light emitting positions of the traffic lights included in all the monochrome images. In comparison, it is possible to accurately reproduce the color of an actual traffic signal, which is important information when verifying a traffic accident, while reducing the data processing amount.

An image processing device according to a seventh invention is the image processing device according to any one of the second to sixth inventions, wherein the selection unit includes an object reflected in a monochrome image, a subject, contents, Based on the sharpness, a monochrome image that satisfies the conditions necessary for identifying a traffic violation or traffic accident is selected.
Here, when selecting a monochrome image in the selection unit, for example, a monochrome image suitable for detection of a traffic violation or a traffic accident such as a clearness of an image including a vehicle or a pedestrian related to a traffic violation or a traffic accident is selected. Extract.

As a result, by obtaining a color image that accurately reproduces the color of the traffic light when a traffic violation or traffic accident occurs, it is possible to effectively verify the traffic violation or traffic accident.
An image processing apparatus according to an eighth aspect of the present invention is the image processing apparatus according to any one of the first to seventh aspects, further comprising a first storage unit that stores information relating to a design layout of the traffic light. Yes.

Here, the information regarding the design layout of the traffic light used when the color determination unit determines what color the position corresponding to the light emission position is stored in the first storage unit.
Accordingly, the color determination unit can easily determine the color of the light emission position by specifying the light emission position of the traffic light included in the monochrome image and referring to the information related to the design layout of the traffic light from the first storage unit. Can do.

As a result, by obtaining a color image that accurately reproduces the color of the traffic light when a traffic violation or traffic accident occurs, it is possible to effectively verify the traffic violation or traffic accident.
An image processing apparatus according to a ninth invention is the image processing apparatus according to any one of the first to eighth inventions, wherein a color setting process is performed on the area of the light emission position of the traffic light in the color setting unit. And a second storage unit that stores the correlated image or the monochrome image subjected to the color arrangement process in the color setting unit and the color information determined in the color determination unit in association with each other.

Here, in order to detect traffic violations or verify traffic accidents later, a color image in which the color scheme is applied to the area of the light emission position of the traffic light, or a monochrome image in which the color scheme is applied in the color setting unit. The image is stored in association with the color information determined by the color determination unit.
As a result, at a police station or the like, using a color image stored in the second storage unit or a monochrome image and color information stored in association with this as evidence, a traffic violation or traffic accident is verified later. Can be implemented.

In addition, as described above, when the color arrangement processing is performed on the minimum number selected from a large number of monochrome images or only a part of one image, the second storage unit An increase in capacity can be avoided.
An image processing apparatus according to a tenth aspect of the present invention is the image processing apparatus according to the second aspect of the present invention, further comprising a third storage unit that stores a monochrome image selection condition in the selection unit.

Here, conditions necessary for selecting a monochrome image to be subjected to the color arrangement process selected by the selection unit are stored in the third storage unit.
Here, the condition necessary for selecting a monochrome image is, for example, an image including a vehicle traveling in a red lane when the traffic violation is a signal ignorance, and in the case of a traffic accident, The image includes a vehicle, a pedestrian, and the like related to the accident.

Thereby, based on the conditions stored in the third storage unit, by selecting a monochrome image to be subjected to color arrangement processing in the area of the light emission position of the traffic light and forming a color image, traffic violations and traffic accidents are formed. It is possible to obtain a color image that accurately reproduces the color of a traffic light that is important information during verification.
An image processing device according to an eleventh aspect of the invention is the image processing device according to any one of the first to tenth aspects of the invention, wherein the imaging device is installed around a traffic light installed at an intersection.

Here, an imaging device that captures a monochrome image is installed around the traffic light at the intersection.
Thereby, it is possible to accurately reproduce the color of the traffic light included in the monochrome image captured at the intersection where traffic violations and traffic accidents are likely to occur.
An image processing device according to a twelfth invention is the image processing device according to any one of the first to eleventh inventions, and the monochrome image includes an infrared image.

Here, an infrared image is used as a monochrome image acquired by an imaging device such as a camera.
As a result, for example, by implementing color arrangement processing on infrared images obtained by imaging near-infrared reflected light with an infrared camera or the like, it is possible to effectively control traffic violations and reduce the amount of data processing Thus, the processing burden can be reduced.

A traffic management system according to a thirteenth invention includes an image processing device according to any one of the first to twelfth inventions, an illumination unit that irradiates infrared light onto a subject, and an illumination area of the illumination unit. An imaging device for imaging.
Here, a traffic management system including the above-described image processing device, an illumination unit that irradiates infrared light onto the subject, and an imaging device that captures reflected light of the infrared light is constructed.

Here, the illumination unit and the imaging device may be installed in a place where traffic violations and traffic accidents are likely to occur, such as intersections and straight roads. On the other hand, the image processing apparatus may be installed, for example, in a police station that controls traffic violations, or a part of the image processing apparatus (such as an image acquisition unit) may be installed outdoors where an imaging apparatus or the like is installed. May be installed.
Thus, the traffic management system can efficiently carry out traffic violation control and traffic accident verification by accurately reproducing the color of the traffic light at the time of imaging.

The image processing method according to the fourteenth aspect includes an image acquisition step, a signal detection step, a color determination step, and a color setting step. In the image acquisition step, a monochrome image is acquired from an imaging device that images the periphery of the traffic light. In the signal detection step, the light emission position of the traffic light included in the monochrome image acquired in the image acquisition step is detected. In the color determination step, information on the light emission position detected in the signal detection step is acquired, and the color of the traffic light included in the monochrome image acquired in the image acquisition step is determined with reference to the design layout of the traffic light. In the color setting step, a color arrangement process is performed on the area of the light emission position of the traffic light included in the monochrome image detected in the signal detection step so that the color of the traffic light determined in the color determination step is obtained, and the traffic light area is colored. Output the image.

Here, for example, a plurality of infrared images (an example of a monochrome image) captured by an imaging device that captures reflected infrared light emitted to a subject including a vehicle or a pedestrian traveling at an intersection where a traffic signal is installed. ) Is acquired. Then, the light emission position of the traffic light included in the monochrome image such as the infrared image is detected, and based on the information on the design layout of the traffic light, the color arrangement processing is performed on the area of the light emission position of the traffic light in the monochrome image, and the actual traffic light A color image that reproduces the color is output.

Here, since the traffic signal included in the monochrome image is a monochrome image, it is difficult to accurately determine three or two colors. On the other hand, since the reflected intensity of infrared rays appears as a large difference compared to the non-light emitting position, it is relatively easy to specify the light emitting position. The design layout of the traffic lights is determined by the country, region, and installation location. For example, in the case of a horizontally long traffic light that is generally used in Japan, they are arranged in order of red, yellow, and blue from the right. In addition, in a vertically long traffic light used in a snowy country in Japan, they are arranged in the order of red, yellow, and blue from the top. Furthermore, in the case of a pedestrian traffic light, they are arranged in the order of red and blue from the top.

In addition, the monochrome image acquired by the imaging device may be an image captured intermittently at a predetermined time interval, or may be an image captured continuously like moving image shooting. In addition, the monochrome image subjected to the color arrangement process may be all the monochrome images acquired in the image acquisition step, or may be a part of the monochrome images selected based on a predetermined condition.

And the color arrangement processing for the area of the light emission position of the traffic light in the monochrome image is based on the light emission position of the traffic light in the monochrome image and the design layout information of the traffic light, and performs the color arrangement processing on the light emission position of the traffic light in the monochrome image, It means a process for forming a color image.
Thereby, for example, when carrying out traffic violation control at a police station or when a traffic accident occurs, it is possible to obtain a color image that accurately reproduces the actual color of the traffic light at that time.

As a result, the traffic light and the traffic accident can be verified by accurately reproducing the color of the traffic light included in the captured image around the traffic light.
(The invention's effect)
With the image processing apparatus according to the present invention, it is possible to accurately reproduce the color of a traffic light included in a captured image around the traffic light.

The figure which shows the structure of the traffic management system containing the image processing apparatus which concerns on one Embodiment of this invention. The figure which shows the installation position in the intersection of a camera, a sensor, a signal control apparatus, etc. which are included in the traffic management system of FIG. The block diagram which shows the processing content in the violation detection part of the image processing apparatus contained in the traffic management system of FIG. The block diagram which shows the processing content in the selection part of the image processing apparatus contained in the traffic management system of FIG. The block diagram which shows the processing content in the color determination part of the image processing apparatus contained in the traffic management system of FIG. The figure which shows the layout information of the traffic signal used when performing the color determination of the traffic signal in the color determination part of FIG. The block diagram which shows the processing content in the color setting part of the image processing apparatus contained in the traffic management system of FIG. The figure which shows the area | region of the infrared image color-coded by the color setting part of FIG. The figure which shows the display mode of the traffic violation containing the color image displayed on the display part of the image processing apparatus contained in the traffic management system of FIG. The flowchart which shows the flow of the color scheme process with respect to the area | region of the traffic signal included in the infrared image by the traffic management system of FIG. The figure which shows the structure of the traffic management system containing the image processing apparatus which concerns on other embodiment of this invention. The figure which shows the structure of the traffic management system containing the image processing apparatus which concerns on further another embodiment of this invention. The figure which shows the structure of the traffic management system containing the image processing apparatus which concerns on further another embodiment of this invention. The figure which shows the structural example of the traffic management system which concerns on further another embodiment of this invention.

(Embodiment 1)
An image processing apparatus according to an embodiment of the present invention will be described below with reference to FIGS.
In the traffic management system 100 according to the present embodiment, the near-infrared reflection component irradiated to the vehicles A1 and A2 passing through the intersection is imaged using a camera (imaging device) 103, and a traffic violation occurs at a police station or the like. Conduct control and verification of traffic accidents.

<Configuration of traffic management system 100>
As illustrated in FIG. 1, the traffic management system 100 includes a sensor 101, an illumination unit 102, a camera (imaging device) 103, and an image processing device 10.
The sensor 101 is, for example, a sensor that detects traffic violations of the vehicles A <b> 1 and A <b> 2 that travel within an intersection, and transmits a traffic violation detection result to the violation detection unit 11 included in the image processing apparatus 10. And the sensor 101 is attached to the support | pillar 111 installed in the intersection, for example, as shown in FIG.

The illumination unit 102 is, for example, a device that emits near-infrared rays, and is attached to a column 111 installed at an intersection as shown in FIG. And the illumination part 102 irradiates near infrared rays with respect to vehicle A1, A2, etc. which become the object of traffic violation. The illumination unit 102 is controlled in irradiation timing and the like by an illumination control unit 12 included in the image processing apparatus 10.

In the present embodiment, the near infrared ray irradiated from the illumination unit 102 means an electromagnetic wave having a wavelength of 0.7 to 2.5 μm that is close to red visible light. Here, the near infrared ray is used for an infrared camera or the like by utilizing the property close to visible light.
The camera 103 images near-infrared reflection irradiated from the illumination unit 102 to the vehicle A1, the traffic light 110, and the like. And the camera 103 is attached to the support | pillar 111 installed in the intersection as shown in FIG. 2 similarly to the sensor 101 and the illumination part 102, for example.

Note that the camera 103 may be switched to acquire an image including visible light during a bright time period and to capture an image including near infrared light during a dark time period. Moreover, the imaging of images by the camera 103 may be performed continuously, or may be performed as needed when a traffic violation is detected.
In this embodiment, an infrared image is used as a monochrome image acquired by the camera 103, but another monochrome image may be used.

<Configuration of Image Processing Device 10>
The image processing apparatus 10 selects an image to be subjected to color arrangement processing from monochrome infrared images (a type of monochrome image) captured by the camera 103, and performs color arrangement processing on the traffic signal area of the selected image. To generate a color image. The image processing apparatus 10 is installed in, for example, a police station that controls traffic violations. Further, as shown in FIG. 1, the image processing apparatus 10 includes a violation detection unit 11, an illumination control unit 12, an image acquisition unit 13, a selection unit 14, a third storage unit 15, a signal detection unit 16, a color determination unit 17, A color setting unit 18, a second storage unit 19, and a display unit 20 are provided.

The violation detection unit 11 receives the detection result of the sensor 101 that detects the traveling state of the traveling vehicles A1 and A2 installed at the intersection or the like, and detects whether there is a traffic violation.
Specifically, the violation detection unit 11 includes a DB (database) 11a and a determination unit 11b, as shown in FIG.
The DB 11a stores information related to the traffic violation verification conditions. As the verification condition, for example, in the case of ignoring the signal, information such as signal switching timing at the intersection where the sensor 101 is installed is included. It should be noted that the DB 11a only needs to store information on conditions and the like necessary for verifying each traffic violation in accordance with the contents of various traffic violations that control other traffic violations.

The determining unit 11b refers to the various traffic violation verification conditions stored in the DB 11a and the detection result (sensor output) received from the sensor 101 to determine whether or not a traffic violation has occurred. For example, when the signal is ignored, it is determined that a traffic violation has occurred when the sensor 101 detects the vehicles A1 and A2 that have entered the intersection of the red light.
And the determination means 11b outputs violation detection information with respect to the illumination control part 12 and the selection part 14 that there exists generation | occurrence | production of the traffic violation of signal ignorance.

The illumination control unit 12 controls the illumination unit 102 that irradiates the vehicles A1 and A2 with near infrared rays. Specifically, when the violation detection information is received from the determination unit 11b of the violation detection unit 11, the illumination unit is configured to immediately irradiate near-infrared rays to the traveling vehicle A1 or the like that is subject to the traffic violation. 102 is controlled.
The image acquisition unit 13 acquires a plurality of infrared images captured by the camera 103. And the image acquisition part 13 will receive the violation detection information from the determination means 11b of the violation detection part 11, and the image containing reflection of the near infrared rays irradiated with respect to the running vehicle A1 etc. which are the object of the traffic violation An imaging command is transmitted to the camera 103 so as to capture the image. Then, the image acquisition unit 13 receives, from the camera 103, a continuously captured image such as an infrared image related to a traffic violation captured in response to a capturing command or a continuously captured moving image.

The selection unit 14 selects one or a plurality of infrared images that satisfy the conditions necessary for detecting a traffic violation for the plurality of infrared images acquired by the image acquisition unit 13.
Specifically, as illustrated in FIG. 4, the selection unit 14 first relates to a traffic violation based on a plurality of infrared images received from the image acquisition unit 13 and violation detection information (presence or absence of traffic violation). Select the infrared image to be used. Next, the selection unit 14 further selects an optimal infrared image as a traffic violation evidence image based on the selection condition stored in the third storage unit 15.

Here, the 2nd memory | storage part 15 explained in full detail in the back | latter stage has memorize | stored the conditions of the image suitable as an evidence image of a traffic violation. For example, the contents (signals, license plates, etc.) that must be reflected in the infrared image may be stored in association with the type of traffic violation.
In addition, the infrared image selected in the selection part 14 may be one sheet, or may combine several sheets according to the kind of traffic violation, the state of an infrared image, etc.

And the selection part 14 outputs the information of the selected infrared image. In addition to the selected infrared image, the remaining non-selected infrared images may be output as the infrared image output from the selection unit 14.
The third storage unit 15 stores information such as image conditions necessary for detecting traffic violations.
Here, the image conditions necessary for detecting traffic violations stored in the third storage unit 15 include, for example, an image including a traffic light and a vehicle in which the signal is ignored when the traffic violation is signal ignorance. There are things. The captured object is clearly imaged and can be used for license plate character recognition, driver face recognition, and the like.

The signal detection unit 16 first detects a traffic signal area included in the infrared image selected by the selection unit 14. Specifically, the signal detection unit 16 detects a traffic signal from the shape of an object included in the infrared image. Next, the signal detection unit 16 detects a light emission position that is turned on at the time of imaging in the traffic light area, and sets this area as a color arrangement area. And the signal detection part 16 outputs the information regarding the area | region of the light emission position of the signal apparatus in the image with the selected infrared image information.

Here, for example, in the case of a traffic signal for a vehicle, the color arrangement area is three circular regions arranged in the horizontal direction or the vertical direction, and in the case of a traffic signal for pedestrians, two color arrangement areas are arranged in the vertical direction. It is a humanoid area. In the case of a traffic signal for a vehicle, the color arrangement region may be represented by an arrow.
Since these color arrangement regions may differ depending on the country or region, the external shape of the traffic light or the color arrangement region may be stored in advance in accordance with the shape of the traffic light to be imaged.

In addition, when the camera 103 is fixedly arranged and the same area is always imaged, the signal detection unit 16 assumes that there is a traffic signal in a specific area in the infrared image, and detects the traffic signal in that area. May be.
Furthermore, the detection of the light emission position by the signal detector 16 can be easily determined by detecting the difference in the reflection intensity of infrared rays. That is, the light emission position of the traffic light tends to be displayed brighter on the infrared image than the area of the other non-light emission positions of the traffic light. Therefore, the determination of the light emission position of the traffic light included in the infrared image may be made by selecting and setting the brightest area.

In addition, the detection of the light emission position of the traffic light by the signal detection unit 16 may be performed using another method.
The color determination unit 17 is based on information on the light emission position area in the traffic light included in the infrared image detected by the signal detection unit 16 and the traffic light layout information stored in the first storage unit 17a. The actual emission color of the traffic light is determined.

Specifically, as illustrated in FIG. 5, the color determination unit 17 acquires information on the infrared image selected by the selection unit 14 and signal region information indicating the light emission position of the traffic light from the signal detection unit 16. . Then, the color determination unit 17 refers to the traffic light layout information stored in the first storage unit 17a to determine the color of the light emission position.
Here, the traffic light layout information is information indicating the arrangement of three or two light emitting areas of the traffic light included in the infrared image.

The order of the light emitting areas of red, yellow, blue, etc. is determined for each country or region, and the first storage unit 17a stores the light emitting area arrangement information (layout information) of the traffic light to be imaged. Is saved.
For example, in the case of a horizontally long traffic light that is generally used in Japan, they are arranged in order of red, yellow, and blue from the right.

Accordingly, the color determination unit 17 can determine which color the light emission position is lit by receiving information on the light emission position from the signal detection unit 16. That is, it is possible to accurately determine the color of the traffic light when an infrared image is captured.
For example, as described above, in the case of a horizontally long traffic signal, the left side of the infrared image is detected as the light emission position as shown in FIG. 6 because the signals are arranged in the order of red, yellow, and blue from the right. Then, the color determination unit 17 determines the color of the traffic light as “blue”. When the center on the infrared image is detected as the light emission position, the color determination unit 17 determines the color of the traffic light as “yellow”. Further, when the right side on the infrared image is detected as the light emission position, the color determination unit 17 determines the color of the traffic light as “red”.

Thereafter, the color determination unit 17 outputs information on the selected infrared image, information on the light emission position of the traffic light in the image, and information on the actual color of the traffic light at the imaging date and time.
The first storage unit 17a for storing the traffic signal layout information need not be provided in the image processing apparatus 10, and may be configured to provide layout information to the image processing apparatus 10 as an external input. Good.

As shown in FIG. 7, the color setting unit 18 receives information on the selected infrared image, information on the detected light emission position of the traffic signal, and information on the color of the determined traffic signal from the color determination unit 17. The color arrangement process is performed on the traffic light area C1 (see FIG. 8) of the selected infrared image.
Specifically, the color setting unit 18 sets a light emitting position region for performing color arrangement processing on the received infrared image based on information on the traffic light region C1, and based on the color information of the traffic light, sets the light emission position region. A color (for example, any one of red, yellow, and blue) to be arranged in the area is set.

Then, as shown in FIG. 7, the color setting unit 18 transmits the color image subjected to the color arrangement processing to the traffic signal area C1 to the second storage unit 19 to be stored. The color setting unit 18 also outputs the color image that has been subjected to the color arrangement processing to the traffic signal area C1 to the display unit 20 such as a liquid crystal display.
Here, the color setting process in the color setting unit 18 is not limited to only the traffic signal area C1 shown in FIG. 8, but using another color arrangement processing technique, the vehicle area C2 and the vehicle number area C3. The entire image including the driver area C4 and the background area C5 may be used. Alternatively, in addition to the traffic light area C1, for example, the area C2 of the vehicle related to a traffic violation or a traffic accident, the area C3 of the vehicle number, the area C4 of the driver's face, etc. Good.

In addition, as another color arrangement processing technique, for example, a known method such as a method disclosed in Japanese Patent Application Laid-Open No. 2011-50049 can be used. The technique for converting a monochrome infrared image into a color image is not limited to this method, and other known techniques may be used (see Patent Documents 2 to 6).
The second storage unit 19 receives from the color setting unit 18 a color image in which the area C1 of the traffic light is subjected to color arrangement processing and stores it. Then, the color image stored in the second storage unit 19 is taken out and used when a traffic violation control, a traffic accident verification, or the like is performed later at a police station or the like.

The display unit 20 is, for example, a liquid crystal display or a PC monitor installed in a police station or the like that controls traffic violations. Then, the display unit 20 receives the color image subjected to the color arrangement processing in the color setting unit 18 and displays the color image together with information on traffic violation.
<Display Mode on Display Unit 20>
In the traffic management system 100 according to the present embodiment, a color image obtained by performing color arrangement processing on the traffic signal area C1 in the following display mode on the display unit 20 installed in a police station or the like that controls traffic violations. Display various information about traffic violations, including

(When signal is ignored)
When the traffic violation is signal ignorance, as shown in FIG. 9, all the information related to one traffic violation is displayed in one screen on the display screen S1.
As shown in FIG. 9, the display screen S <b> 1 has three display areas: a violation content display area 31, a specifying image display area 32, and a person information display area 33.

The violation content display area 31 displays the violation content (for example, ignoring a red signal), the violation location, and the image shooting date and time. In this embodiment, as shown in FIG. 9, since a traffic violation is verified using one color image and two monochrome images, an infrared image that is the basis of the color image and the monochrome image is captured. It will be written up to the date.
In the specifying image display area 32, a color image is displayed in which the color arrangement processing is performed on the traffic signal area C1 in order to verify the violation content displayed in the violation content display area 31. In this embodiment, as shown in FIG. 9, one violation specifying color image P1 and two monochrome person specifying images P2 and P3 are displayed.

The violation specifying color image P1 shows a state in which the target vehicle is traveling in the intersection in a state where the signal of the oncoming lane is a red signal. Usually, the signal of the opposite lane and the signal of the lane in which the target vehicle is traveling are displayed in synchronism with each other. For this reason, this color image is extracted as a violation specifying color image P1 which is determined to be able to prove the violation.
The person specifying image P2 displays an enlarged vehicle number (number plate) portion of the front image of the violating vehicle determined to be ignored in the violation specifying color image P1 by image processing. By identifying the vehicle number of the violating vehicle from this image, it is possible to identify the name of the owner of the violating vehicle or the name of the user (company) by referring to pre-registered vehicle inspection information or the like. .

The person specifying image P3 is an enlarged image of the vicinity of the driver's seat by image processing among the images of the front side of the violating vehicle determined to ignore the signal in the violation specifying color image P1. By identifying the driver's face and the passenger's face with this image, refer to the face photo information etc. of the license registered in advance, and specify the name of the driver and passenger's name of the violating vehicle Can do.
In the person information display area 33, information related to the person (driver, owner, user, etc.) specified using the person specifying images P2, P3 displayed in the specifying image display area 32 is displayed. For example, the displayed driver information includes data such as the driver's name, address, license number, violation history, and deduction points.

Here, in the traffic management system 100 of the present embodiment, as described above, the traffic signal area is selectively selected from the large amount of infrared images received from the image acquisition unit 13 with respect to an image that is optimal for detecting a traffic violation. A color scheme is being implemented.
As a result, the burden of data processing required for the color arrangement process can be greatly reduced as compared with the case where the color arrangement process is performed on the traffic light areas of all infrared images.

Finally, the second storage unit 19 in which the color image is stored can significantly reduce the storage capacity compared to the case of storing the color image in which the color arrangement processing is performed on all infrared images. it can.
Further, in the present embodiment, since the color arrangement processing is performed by focusing on the traffic signal area C1 included in the selected infrared image, the data processing amount can be reduced more effectively, and the storage capacity of the second storage unit 19 can be reduced. An increase can be avoided.

<Color scheme processing flow of this embodiment>
In the traffic management system 100 according to the present embodiment, the image processing apparatus 10 according to the flowchart shown in FIG. 10, conditions necessary for detecting traffic violations and traffic accidents, specifying vehicles, etc. from the infrared image acquired by the camera 103. An infrared image satisfying the condition is selected and color arrangement processing is performed.

Specifically, as shown in FIG. 10, first, in step S11, the sensor 101 detects a vehicle having a traffic violation speed such as signal ignorance. Then, the sensor 101 transmits violation detection information to the violation detection unit 11 of the image processing apparatus 10.
Next, in step S12, the violation detector 11 determines whether or not a traffic violation has been detected with reference to various conditions stored in the DB 11a.

If it is determined that a traffic violation has occurred, the process proceeds to step S13. On the other hand, if it is determined that no traffic violation has occurred, the process returns to step S11 again.
Next, in step S <b> 13, the illumination control unit 12 that has received the violation detection information from the violation detection unit 11 issues an illumination command to the illumination unit 102.
Next, in step S14, the illumination unit 102 that has received the illumination command from the illumination control unit 12 irradiates the offending vehicle with near infrared rays.

Next, in step S <b> 15, the camera 103 acquires one or a plurality of infrared images including the violating vehicle in synchronization with the timing at which near-infrared rays are emitted from the illumination unit 102.
Next, in step S <b> 16, conditions necessary for the verification of the traffic violation stored in the third storage unit 15 by the selection unit 14 from the plurality of infrared images captured by the camera 103 and acquired by the image acquisition unit 13. , Etc., one or a plurality of infrared images that are equivalent to the color arrangement processing are selected.

Next, in step S17, the traffic light region C1 (see FIG. 8) and the light emission position (see FIG. 6) in the infrared image selected in step S16 are detected.
Here, the signal area C1 may be detected by detecting the signal from the shape of the object included in the infrared image and setting three or two areas corresponding to the light emitting portion as candidate areas to be colored.

In addition, the light emitting part is detected by utilizing the difference in infrared reflection intensity between the light emitting part and the non-light emitting part, and the lightest part (lightest) of the three or two color scheme candidate areas in the traffic light is selected as the light emitting part. Can be set as
Next, in step S18, based on the light emission position of the traffic signal included in the infrared image selected by the selection unit 14 and the layout information (arrangement of the light emission position) of the traffic signal, the actual traffic signal at the time of imaging the infrared image. Set the color information.

Next, in step S19, a color arrangement process is performed so that the color information set in step S18 is reflected on the light emission position in the traffic signal area C1 set in step S17.
Next, in step S <b> 20, the color image generated by the color setting unit 18 is stored in the second storage unit 19. When a traffic violation control, a traffic accident verification, or the like is performed at a police station or the like, a color image is output to the display unit 20 installed at the police station.

In the traffic management system 100 of the present embodiment, as described above, traffic is detected from a plurality of infrared images captured continuously or intermittently at a police station or the like that conducts traffic violation control or traffic accident verification. Select important images that provide evidence to identify violations, vehicles, drivers, etc. Then, a color image is formed by performing a color arrangement process on the area of the traffic signal included in the selected one or more infrared images.

As a result, it is possible to obtain an image that accurately reproduces the color of the traffic light, which is important information when carrying out traffic violation control and traffic accident verification. Therefore, it is possible to efficiently identify whether there is a traffic violation or to grasp the situation in a traffic accident.
In addition, when extracting the minimum necessary infrared image and performing the color arrangement process only on the traffic signal area included therein, the color arrangement process is performed on the signal area of all infrared images acquired by the camera 103. Compared with, the data processing amount can be significantly reduced.
In addition, even for selected infrared images that are subject to color schemes, traffic color enforcement is performed while further reducing the amount of data processing by implementing color schemes only on traffic signal areas that are important for identifying traffic violations. Efficiency can be improved.

(Embodiment 2)
The traffic management system 200 and the image processing apparatus 210 according to the present embodiment will be described as follows with reference to FIG.

Note that the traffic management system 200 of the present embodiment is different from the first embodiment in that a traffic violation is detected using an infrared image captured by the camera 103 instead of a sensor. Other configurations have the same functions as the configurations described in the first embodiment, and therefore the same reference numerals are given here, and detailed descriptions thereof are omitted.
In the traffic management system 200 of the present embodiment, near-infrared irradiation by the illumination unit 102 and imaging by the camera 103 are continuously performed.

Then, the image acquisition unit 13 receives infrared images continuously captured by the camera 103 and transmits them to the violation detection unit 11 and the selection unit 14.
The violation detection unit 11 determines whether there is a traffic violation of the vehicle included in the infrared image, and transmits the determination result to the selection unit 14.
The violation detection in the violation detection unit 11 is performed by the determination unit 11b with reference to various conditions stored in the DB 11a, as in the first embodiment.

When the selection unit 14 receives the determination result that the traffic violation has been detected from the violation detection unit 11, the infrared image that satisfies the conditions necessary for the verification of the traffic violation is selected from the infrared images used when the traffic violation is detected. An image is selected and transmitted to the signal detector 16.
Note that the conditions necessary for verifying the traffic violation in the selection unit 14 are stored in the third storage unit 15 as in the first embodiment.

The signal detection unit 16 detects a traffic light area and a light emission position area included in the infrared image selected by the selection unit 14. And the signal detection part 16 outputs the information regarding the light emission position of the traffic light in the image with the selected infrared image information.
Based on the light emission position of the traffic signal included in the infrared image selected by the selection unit 14 and the layout information (light emission position arrangement) of the traffic signal stored in the first storage unit 17a, the color determination unit 17 Information on the color of the actual traffic light when the image is captured is set.

The color setting unit 18 performs a color arrangement process on the region of the light emission position of the traffic light of the infrared image selected by the selection unit 14 to generate a color image. Then, the color setting unit 18 stores the generated color image in the second storage unit 19 and outputs it to the display unit 20.
According to the traffic management system 200 of the present embodiment, the color of the traffic light at that time is accurately determined when the traffic violation is controlled or the traffic accident is verified without using a sensor or the like for detecting the traffic violation. The same effect as in the first embodiment can be obtained that a reflected color image can be obtained.

When the violation detection unit 11 needs to detect the color of the traffic light, the same detection method as the determination of the color of the traffic light in the color determination unit 17 and the first storage unit 17a may be used.
In addition, since only the minimum necessary infrared image is extracted and the color arrangement process is performed, the data processing amount is significantly reduced compared to the case where the color arrangement process is performed on all infrared images acquired by the camera 103. There is also an effect that it can be done.
In addition, even in selected infrared images that are subjected to color scheme processing, data processing is performed by performing color scheme processing only in the area of the light emission position of the traffic light in order to reflect the color of the traffic light important for identifying traffic violations, etc. While reducing the amount, the efficiency of traffic violation control can be improved.

(Embodiment 3)
The traffic management system 300 and the image processing apparatus 310 according to the present embodiment will be described as follows with reference to FIG.

The traffic management system 300 of the present embodiment is different from the first and second embodiments in that the fourth storage unit 21 temporarily stores all infrared images continuously captured by the camera 103. Is different.
Further, the present embodiment is common to the second embodiment in that a traffic violation is detected using an infrared image captured by the camera 103 instead of a sensor.

Other configurations have the same functions as the configurations described in the first and second embodiments, and thus are denoted by the same reference numerals and detailed description thereof is omitted.
In the traffic management system 300 of the present embodiment, near-infrared irradiation by the illumination unit 102 and imaging by the camera 103 are continuously performed as in the second embodiment.
And the image acquisition part 13 receives the infrared image continuously imaged in the camera 103, and transmits to the 4th memory | storage part 21 which once preserve | saves all the infrared images.

The violation detection unit 11 uses the infrared image continuously acquired from the fourth storage unit 21 when conducting a traffic violation control at a police station or the like, and subsequently determines whether there is a vehicle traffic violation. And the determination result is transmitted to the selection unit 14.
At this time, the infrared image stored in the fourth storage unit 21 is also transmitted to the selection unit 14.

Here, violation detection in the violation detection unit 11 is performed by the determination unit 11b with reference to various conditions stored in the DB 11a, as in the first and second embodiments.
When the selection unit 14 receives the determination result that the traffic violation has been detected from the violation detection unit 11, the infrared image that satisfies the conditions necessary for the verification of the traffic violation is selected from the infrared images used when the traffic violation is detected. An image is selected and transmitted to the signal detector 16.

Note that the conditions necessary for verifying the traffic violation in the selection unit 14 are stored in the third storage unit 15 as in the first and second embodiments.
The signal detection unit 16 detects a traffic light area and a light emission position area included in the infrared image selected by the selection unit 14. And the signal detection part 16 outputs the information regarding the light emission position of the traffic light in the image with the selected infrared image information.

Based on the light emission position of the traffic signal included in the infrared image selected by the selection unit 14 and the layout information (light emission position arrangement) of the traffic signal stored in the first storage unit 17a, the color determination unit 17 Information on the color of the actual traffic light when the image is captured is set.
The color setting unit 18 performs a color arrangement process on the region of the light emission position of the traffic light of the infrared image selected by the selection unit 14 to generate a color image. Then, the color setting unit 18 stores the generated color image in the second storage unit 19 and outputs it to the display unit 20.

According to the traffic management system 300 of the present embodiment, the color of the traffic light at that time is accurately determined when the traffic violation is controlled or the traffic accident is verified without using a sensor for detecting the traffic violation. The same effect as in the first and second embodiments can be obtained that a reflected color image can be obtained.
In addition, since only the minimum necessary infrared image is extracted and the color arrangement process is performed, the data processing amount is significantly reduced compared to the case where the color arrangement process is performed on all infrared images acquired by the camera 103. There is also an effect that it can be done.
Furthermore, even in the selected infrared image to be subjected to the color scheme, the data processing amount can be further increased by performing the color scheme only on the traffic signal area in order to reflect the color of the traffic signal important for identifying traffic violations. While reducing, it is possible to improve the efficiency of traffic violation control.

(Embodiment 4)
The traffic management system 400 and the image processing apparatus 410 according to the present embodiment will be described as follows with reference to FIG.

Note that the traffic management system 400 of this embodiment is common to the first embodiment in that a traffic violation is detected using the sensor 101. Unlike the first and second embodiments, in common with the third embodiment, the fourth storage unit 21 temporarily stores all infrared images continuously captured by the camera 103. Yes.
Other configurations have the same functions as the configurations described in the first to third embodiments, and therefore, the same reference numerals are given here, and detailed descriptions thereof are omitted.

In the traffic management system 400 of this embodiment, the sensor 101 detects the presence or absence of a traffic violation.
Near-infrared irradiation by the illumination unit 102 and imaging of an infrared image by the camera 103 are continuously performed as in the second and third embodiments.
The image acquisition unit 13 receives the infrared images continuously captured by the camera 103 regardless of whether or not the traffic violation is detected by the violation detection unit 11, and temporarily stores all the infrared images. Send to.

The violation detection unit 11 continuously acquired from the fourth storage unit 21 with reference to the time when the traffic violation was detected by the sensor 101 when the traffic violation was subsequently controlled at a police station or the like. A part of the infrared image is used to determine whether or not the vehicle has a traffic violation, and the determination result is transmitted to the selection unit 14.
At this time, the infrared image stored in the fourth storage unit 21 is also transmitted to the selection unit 14.

Here, violation detection in the violation detection unit 11 is performed by the determination unit 11b with reference to various conditions stored in the DB 11a, as in the first to third embodiments.
When the selection unit 14 receives the determination result that the traffic violation has been detected from the violation detection unit 11, the infrared image that satisfies the conditions necessary for the verification of the traffic violation is selected from the infrared images used when the traffic violation is detected. An image is selected and transmitted to the signal detector 16.

The conditions necessary for verifying the traffic violation in the selection unit 14 are stored in the third storage unit 15 as in the first to third embodiments.
The signal detection unit 16 detects a traffic light area and a light emission position area included in the infrared image selected by the selection unit 14. And the signal detection part 16 outputs the information regarding the light emission position of the traffic light in the image with the selected infrared image information.

Based on the light emission position of the traffic signal included in the infrared image selected by the selection unit 14 and the layout information (light emission position arrangement) of the traffic signal stored in the first storage unit 17a, the color determination unit 17 Information on the color of the actual traffic light when the image is captured is set.
The color setting unit 18 performs a color arrangement process on the region of the light emission position of the traffic light of the infrared image selected by the selection unit 14 to generate a color image. Then, the color setting unit 18 stores the generated color image in the second storage unit 19 and outputs it to the display unit 20.

In the traffic management system 400 of the present embodiment, it is possible to detect in real time whether or not a traffic violation has occurred using a sensor or the like for detecting a traffic violation. Then, when conducting traffic violation control after the fact, it is the most proof of traffic violation from among a plurality of infrared images and infrared videos taken in the time zone when the traffic violation was detected by the sensor 101. A suitable infrared image or the like is taken out and a color arrangement process is performed.

This makes it possible to obtain a color image that accurately reflects the color of the traffic lights at the time when carrying out traffic violation control, traffic accident verification, etc., without using sensors for detecting traffic violations. The same effect as the first to third embodiments can be obtained.
In addition, since only the minimum necessary infrared image is extracted and the color arrangement process is performed, the data processing amount is significantly reduced compared to the case where the color arrangement process is performed on all infrared images acquired by the camera 103. There is also an effect that it can be done.
Furthermore, even in the selected infrared image to be subjected to the color scheme, the data processing amount can be further increased by performing the color scheme only on the traffic signal area in order to reflect the color of the traffic signal important for identifying traffic violations. While reducing, it is possible to improve the efficiency of traffic violation control.

[Other Embodiments]
As mentioned above, although one Embodiment of this invention was described, this invention is not limited to the said embodiment, A various change is possible in the range which does not deviate from the summary of invention.

(A)
The traffic management system 500 and the image processing apparatus 510 according to another embodiment of the present invention may have a configuration as shown in FIG. 14, for example.
Specifically, as shown in FIG. 14, the traffic management system 500 is connected to an external traffic violation control device (camera 103) via a network N such as the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network). Is done. The traffic management system 500 is connected to the storage device 160.

The traffic management system 500 includes a computer terminal, and includes a CPU (Central Processing Unit) 150, a RAM (Random Access Memory) 151, an output unit 152, a communication unit 153, an input unit 154, an image processing device 510, and the like. .
The CPU 150 executes various arithmetic processes and the like, and executes a predetermined control program that is read into the RAM 151 and expanded. With this control program, the functions of the components included in the traffic management system 500 are executed.

The RAM 151 is configured by a memory element such as SRAM (Static RAM) or DRAM (Dynamic RAM), and stores data generated during the processing of the CPU 150.
The output unit 152 has a connection terminal for connecting a cable or the like for transmitting an analog signal such as an image and sound or a digital signal. And the output part 152 is connected to the display part 20 of each embodiment mentioned above via these cables. The output unit 152 converts various types of information read from the storage device 160 into image signals in accordance with instructions from a display control unit (not shown), and outputs the image signals to the display unit 20 via a cable.

The communication unit 153 has a connection terminal or a wireless communication interface for connecting a communication cable, and is connected to the network N. The communication unit 153 transmits / receives data to / from a traffic violation control apparatus (sensor 101, camera 103, etc.) connected to the network N.
The input unit 154 includes (a mouse, a keyboard, a touch panel operated on a screen, etc.). The input unit 154 accepts input of information by user operation, menu selection, and the like, and notifies the CPU 150 of the accepted operation content.

The storage device 160 includes a semiconductor memory, a magnetic recording medium, an optical recording medium, and the like. In addition, the 1st memory | storage part 17a, the 2nd memory | storage part 19, the 3rd memory | storage part 15, and the 4th memory | storage part 21 of each embodiment mentioned above may be contained in this memory | storage device 160, or are connected separately. It may be a large capacity storage device. Further, the storage device 160 may be connected to the traffic management system 500 via a network.

(B)
In the above-described embodiment, an example has been described in which after an occurrence of a traffic violation is detected, an infrared image related to the verification of the traffic violation is selected, and a color arrangement process is performed on the traffic light area on the image. However, the present invention is not limited to this.
For example, the color arrangement processing may be performed on the areas of traffic signals of all infrared images captured continuously or intermittently regardless of whether or not a traffic violation occurs. That is, a configuration without the selection unit 14 of each of the first to fourth embodiments described above may be used.

In this case, since color arrangement processing is performed on all of the acquired infrared images, it is possible to obtain a color image that reproduces the actual colors at the time of imaging of the traffic lights included in all the infrared images.
Here, in this embodiment, the target area of the color arrangement process is limited to the area of the traffic light. For this reason, even when color arrangement processing is performed on all acquired infrared images, an increase in the amount of data processing can be minimized.

(C)
In the said embodiment, the image processing apparatus 10 gave and demonstrated the example provided with the violation detection part 11 which detects the presence or absence of a traffic violation. However, the present invention is not limited to this.
As the scope of application of the present invention, since the occurrence of traffic violation is not essential, an image processing device having no violation detection unit and a traffic management system including the image processing device may be used.
In this case, by obtaining an image that accurately reproduces the color of the traffic light when a traffic accident occurs, it can be used effectively for verification of the traffic accident.

(D)
In the said embodiment, as shown in FIG. 6, it demonstrated taking the case of the horizontally long traffic signal generally used in Japan. However, the present invention is not limited to this.

For example, the present invention can be similarly applied to a vertically long three-color traffic light or a pedestrian two-color traffic light.
Specifically, in a vertically long traffic light used in a snowy country in Japan, three colors are arranged in the order of red, yellow, and blue from the top. Furthermore, in the case of a pedestrian traffic light, two colors are arranged in the order of red and blue from the top.
As described above, the color of the light emitting position is determined accurately and easily by using the layout information of the traffic light installed in the country or region where the traffic management system and the image processing apparatus of the present invention are introduced. An image that reproduces the color of the traffic light can be obtained.

(E)
In the above-described embodiment, an example in which a plurality of infrared images are acquired by the camera 103 in accordance with the infrared irradiation timing when a traffic violation is detected has been described. However, the present invention is not limited to this.

For example, as in moving image shooting, a plurality of infrared images obtained by continuously capturing the situation in the intersection may be acquired by the camera.
In this case, a large number of infrared images that are not directly related to traffic violations are acquired. For this reason, when the present invention is applied, the effect of reducing the amount of data processing is greater and the increase in the storage capacity of the second storage unit 19 can be suppressed as compared with the case where color processing is performed on all infrared images. This is more preferable.

(F)
In the above embodiment, using an infrared image captured from the front of the traveling vehicle by the camera 103, an infrared image that satisfies the conditions necessary for specifying the content of the traffic violation, the violation vehicle, the driver, and the like is selected. In the above, an example of performing color arrangement processing on the traffic signal area has been described. However, the present invention is not limited to this.

For example, using an infrared image acquired by installing a camera in the direction of imaging the rear of the traveling vehicle, an infrared image that satisfies the conditions necessary for identifying the content of the traffic violation, the offending vehicle, and the owner of the offending vehicle May be selected.
In this case, since the driver of the violating vehicle cannot be specified from the image, the owner may be specified from the vehicle number of the violating vehicle.

Further, when the camera is installed in the direction in which the rear portion of the traveling vehicle is imaged, it is possible to capture so that the front of the traffic light 110 and the offending vehicle are included in one image. In this case, there is a possibility that the violating vehicle ignoring the signal and its owner can be identified from the single image.
Therefore, when the identification of the driver is not an indispensable condition for certifying as a traffic violation, the camera may be installed in a direction in which the rear portion of the traveling vehicle is imaged.

(G)
In the said embodiment, the traffic management system 100,200,300,400 demonstrated and demonstrated the structure containing the display parts 20, such as a liquid crystal display, as an example. However, the present invention is not limited to this.
For example, the traffic management system and the image processing apparatus of the present invention may be configured as a system that does not include a display unit such as a liquid crystal display.
In this case, by using a display means such as a liquid crystal display as an external device, it is possible to obtain the same effect as described above that it is possible to efficiently control traffic violations with a simple configuration.

(H)
In the above embodiment, as illustrated in FIG. 2, an example in which one sensor 101, a camera 103, and the like are installed for one lane to detect a traffic violation and acquire an infrared image has been described. However, the present invention is not limited to this.

For example, one sensor or camera may be installed for a plurality of lanes, and an image for specifying the violation content may be acquired.
In this case, by installing a camera having a field-of-view range and resolution that covers a plurality of lanes, a violation vehicle can be effectively detected from the target vehicles traveling in the plurality of lanes. Therefore, the system configuration can be further simplified.

Further, the shooting direction of the camera is not limited to a direction along the road traveling direction.
For example, a camera is installed on a support post at the corner of an intersection, and the entire intersection is photographed. Using the image, the contents of the traffic violation, the vehicle in violation, the driver and owner of the vehicle in violation are identified. May be.

Alternatively, a camera is installed on the traffic light pole provided at the corner of the intersection and the entire intersection is photographed, and the image of the traffic violation, the violation vehicle, the driver and owner of the violation vehicle, etc. are used. You may specify.
In this case, since the camera can capture the entire intersection, there is a possibility that the violating vehicle that committed the violation of prohibition of turning right and left, the driver, and the like can be identified.

(I)
In the above embodiment, the example of traffic violation detected and managed in this system has been described in detail mainly by ignoring signal as an example. However, the present invention is not limited to this.
For example, in this system, in addition to the traffic violations exemplified in the above embodiment, traffic violations and traffic accidents that can be detected by sensors, cameras, etc., and various traffic violations stipulated by laws and regulations established in each country And traffic accidents can be detected and managed.

(J)
In the above-described embodiment, an example in which the sensor 101, the camera 103, the signal control device 104, and the like are installed at an intersection has been described as a place for carrying out traffic violation control. However, the present invention is not limited to this.
For example, when enforcement of red light ignoring control is performed, a sensor, a camera, or the like may be installed on a straight road or the like where the line of sight is good and the traveling speed is likely to increase.
Similarly, for other traffic violations, it is possible to improve the efficiency of the control by installing sensors, cameras, etc. around the roads where the traffic violation is likely to occur.

(K)
In the above-described embodiment, an example in which the present invention is applied to a traffic management system that controls traffic violations of vehicles has been described. However, the present invention is not limited to this.

For example, the present invention may be applied to a traffic management system for controlling traffic violations of bicycles and pedestrians.
Even in this case, as in the above embodiments, traffic violations such as ignoring red traffic lights by bicycles and pedestrians can be efficiently controlled by accurately reproducing the color of traffic lights when traffic violations are detected or when a traffic accident occurs. be able to.

(L)
In the above-described embodiment, an example in which the present invention is applied to a traffic management system that controls traffic violations of vehicles has been described. However, the present invention is not limited to this.
For example, the image processing apparatus of the present invention may form a color image that accurately reproduces the color of a traffic light at the time of occurrence of a traffic accident, in addition to being used for traffic violation control.
Even in this case, since the color information of the traffic light at the time when the traffic accident occurred can be accurately reproduced, the traffic accident can be effectively verified.

(M)
In the above-described embodiment, an example in which one or a plurality of infrared images satisfying a predetermined condition is selected from a plurality of infrared images captured by the camera and the color arrangement process is performed has been described. However, the present invention is not limited to this.

For example, when shooting a movie with a camera, only a part of the movie satisfying a predetermined condition is cut out, and a plurality of infrared images constituting the part of the movie are selected to perform color arrangement processing. Also good.
In this case, for example, it is possible to generate a part of the video related to the detection of traffic violations and traffic accidents as a color image in which the color of traffic lights is accurately reproduced. Can be implemented effectively.

The image processing apparatus according to the present invention has an effect of accurately reproducing the color of a traffic signal included in a captured image around the traffic signal, and thus can be widely applied to various apparatuses that acquire a monochrome image.

10 Image Processing Device 11 Violation Detection Unit 11a DB
11b determination means 12 illumination control unit 13 image acquisition unit 14 selection unit 15 third storage unit 16 signal detection unit 17 color determination unit 17a first storage unit 18 color setting unit 19 second storage unit 20 display unit 21 fourth storage unit 31 Violation content display area 32 Image display area for identification 33 Person information display area 100 Traffic management system 101 Sensor 102 Illumination unit 103 Camera (imaging device)
110 traffic light 111 post 150 CPU (Central Processing Unit)
151 RAM (Random Access Memory)
152 output unit 153 communication unit 154 input unit 160 storage device 200 traffic management system 210 image processing device 300 traffic management system 310 image processing device 400 traffic management system 410 image processing device 500 traffic management system 510 image processing devices A1, A2 vehicle C1 traffic light Area C2, C3, C4 area (non-colored area)
P1 Violation specifying color image P2, P3 Person specifying image S1 screen

Claims (14)

1. An image acquisition unit that acquires a monochrome image from an imaging device that images the periphery of the traffic light;
   A signal detection unit for detecting a light emission position of a traffic light included in the monochrome image acquired by the image acquisition unit;
   A color determination unit that acquires information on the light emission position detected in the signal detection unit, refers to a design layout of the traffic signal, and determines a color of the traffic signal included in the monochrome image acquired in the image acquisition unit;
   A color arrangement process is performed on the area of the light emission position of the traffic light included in the monochrome image detected by the signal detection section so as to be the color of the traffic light determined by the color determination section. A color setting unit for outputting the converted image;
   An image processing apparatus.
2. A selection unit configured to select the monochrome image to be subjected to color arrangement processing in the color setting unit from a plurality of monochrome images acquired in the image acquisition unit based on a predetermined condition; Yes,
   The image processing apparatus according to claim 1.
3. A violation detection unit for detecting the presence or absence of traffic violation of the vehicle included in the monochrome image is further provided,
   When the violation detection unit detects that the monochrome image includes a violation vehicle subject to traffic violation control,
   The color setting unit performs a color arrangement process on an area of a light emission position of the traffic light included in the monochrome image selected by the selection unit.
   The image processing apparatus according to claim 2.
4. The violation detection unit is a sensor that detects a state of the vehicle that is subject to traffic violation control.
   The image processing apparatus according to claim 3.
5. The violation detector is an imaging device that images the vehicle that is subject to traffic violation control.
   The image processing apparatus according to claim 3.
6. When the monochrome image includes vehicles or pedestrians related to traffic accidents,
   The color setting unit performs a color arrangement process on an area of a light emission position of the traffic light included in the monochrome image selected by the selection unit.
   The image processing apparatus according to claim 2.
7. The selection unit selects a monochrome image that satisfies a condition necessary for specifying a traffic violation or a traffic accident based on an object, a subject, contents, and clarity reflected in the monochrome image.
   The image processing apparatus according to claim 2.
8. A first storage for storing information relating to the design layout of the traffic light;
   In addition,
   The image processing apparatus according to claim 1.
9. In the color setting unit, the colorized image that has been subjected to color arrangement processing in the area of the light emission position of the traffic light, or the monochrome image that is subjected to color arrangement processing in the color setting unit and the color determination unit are determined. A second storage unit for storing the color information in association with
   In addition,
   The image processing apparatus according to claim 1.
10. A third storage unit storing the selection condition of the monochrome image in the selection unit;
    In addition,
    The image processing apparatus according to claim 2.
11. The imaging device is installed around the traffic light installed at an intersection,
    The image processing apparatus according to claim 1.
12. The monochrome image includes an infrared image,
    The image processing apparatus according to claim 1.
13. The image processing apparatus according to any one of claims 1 to 12,
    An illumination unit that irradiates the subject with infrared light;
    An imaging device for imaging an illumination area of the illumination unit;
    Traffic management system with
14. An image acquisition step of acquiring a monochrome image from an imaging device that images the periphery of the traffic light;
    A signal detection step of detecting a light emission position of a traffic light included in the monochrome image acquired in the image acquisition step;
    Obtaining information on the light emission position detected in the signal detection step, referring to the design layout of the traffic light, and determining the color of the traffic light included in the monochrome image acquired in the image acquisition step; and
    Color distribution processing is performed on the area of the light emission position of the traffic light included in the monochrome image detected in the signal detection step so as to be the color of the traffic light determined by the color determination unit. Color setting step for outputting a digitized image;
    An image processing method comprising:

Images