TW202004377A - Image analysis apparatus for industrial plants and industrial plant monitoring control system - Google Patents

Abstract

An image analysis apparatus for industrial plants and an industrial plant monitoring control system have the following configurations. A moving image data collecting unit (21) collects moving image data obtained by shooting an equipment constituting an industrial plant and materials to be processed by the equipment in real time. An image processing treatment unit (22) extracts an image from the moving image data for each constant period, and binarizes the image by converting specified color into first color while converting color other than the specified color into second color. An image quantifying unit (23) quantifies the binarized image on the basis of the number of pixels converted into the first color. A numerical value output unit (24) outputs the quantified data.

Description

Industrial factory image analysis device and industrial factory monitoring and control system

The invention relates to an image analysis device for industrial factories and an industrial factory monitoring and control system.

Industrial plants (steel plants, power plants, petroleum plants, chemical plants, etc.) known to produce materials and resources required for industrial activities are known. The factory monitoring and control system of an industrial factory is equipped with an input/output device (I/O) connected to a large number of field devices (including actuators and sensors) constituting the factory via a control network, and can control a large number of field devices Programming logic controllers (hereinafter referred to as PLCs) are connected to each other.

In addition, the process data of the I/O signals as PLC and I/O devices are collected in the data collection device with the data collection function and the data playback function. The data collection device displays the collected process data, which the operator uses to grasp the status of the industrial plant.

As an example of a sensor that outputs process data, Patent Document 1 has disclosed an HMD (Hot Metal Detector) disposed in a steel plant. The HMD is provided at a predetermined height directly above the roller path downstream of the roll, and the detection direction is set in a direction substantially perpendicular to the roll and toward the horizontal direction. The HMD is a laser sensor with a narrow field of view, and outputs an ON signal if thermal mass is detected in the field of view, and an OFF signal if thermal mass is not detected.

[Prior Technical Literature] [Patent Literature]

Patent Literature 1: Japanese Patent Laid-Open No. 2016-87652

Patent Literature 2: International Publication No. 2014/002176

As described in Patent Document 1, the upward warpage of the thermal mass (rolled material) can be detected by arranging sensors. However, the sensor is expensive and its installation location is limited. In addition, the sensor only outputs an ON signal or an OFF signal, and the state (shape, position, etc.) of the rolled material cannot be grasped in detail.

In order to solve the above-mentioned shortcomings, the inventor of the present invention conducted intensive research and developed a dynamic image data of a subject photographed with a general camera as a sensor. The use of a camera can provide advantages such as reduced cost, a wider shooting range than the above sensor, a high degree of freedom in the installation location, and more information than the sensor output.

On the other hand, when confirming the state of the subject photographed with the camera, simply observing the dynamic image data with the naked eye is also only a judgment by visual inspection, and the accuracy of confirmation is low. Therefore, it is desired to improve the accuracy of confirmation.

The present invention was made to solve the above-mentioned problems, and an object is to provide an image analysis device for an industrial plant that uses dynamic image data to quantify and analyze the state of a photographed object in real time, and can support an operator who confirms the operation status of an industrial plant .

In addition, another object of the present invention is to provide an industrial factory monitoring and control system that uses data quantified by an image analysis device for an industrial factory to achieve appropriate control according to the state of a photographed object.

In order to achieve the above object, the image analysis device for an industrial plant of this embodiment is configured as follows. The image analysis device for an industrial factory includes a dynamic image data collection unit, an image processing unit, an image quantization unit, and a numerical output unit.

The dynamic image data collection department is a real-time collection of dynamic image data obtained by photographing the machines constituting the industrial factory and the materials processed on the machines. Real-time does not necessarily refer to the moment of shooting, including data collection that will be delayed due to communication paths and data processing, or data collection at regular intervals.

The image processing processing unit extracts an image from the dynamic image data every predetermined period, converts the specified color to the first color, converts the color other than the specified color to the second color, and binarizes the image. The certain period is preferably as short as possible, and more ideally is immediate. Portrait refers to a frame of portraits extracted from dynamic image data. The specified color is not only a single color, but also includes the specified range of colors.

The portrait quantization unit quantizes the binarized portrait based on the number of pixels converted into the first color. In one form, the image quantization unit calculates the ratio of the first color in each band-shaped region obtained by dividing the binarized image parallel to the conveyance direction of the material. In another form, the image quantization unit calculates the proportion of the first color in each lattice-shaped area that divides the binary image into a lattice.

The numerical output unit outputs the aforementioned quantized data.

In order to achieve the above object, the industrial factory monitoring and control system of this embodiment is constructed as follows. The industrial plant monitoring and control system is equipped with the above-mentioned industrial plant image analysis device and a programmable logic controller that controls the aforementioned devices.

The aforementioned machine includes a pair of rolls for rolling the rolled material as the aforementioned material. The image processing processing unit binarizes the image of the rolled material viewed from the width direction.

In one form, the image quantization unit and the programmable logic controller are constructed as follows.

The image quantization unit makes the binarized image parallel to the conveying direction of the rolled material, divides it into at least a first area and a second area adjacent to the first area, and calculates the area occupied by the first color in each area proportion.

The programmable logic controller outputs a warning when the difference between the increase in the proportion of the first color in the second area and the decrease in the proportion of the first color in the first area is greater than the critical value At least one of a signal and a control signal that changes the rotation speed of the pair of rolls to suppress the upward warpage of the rolled material. For example, the control signal is a signal to stop the aforementioned pair of rolls, or a signal to make the rotation speed of the lower roll slower than that of the upper roll.

In another form, the image quantization unit and the programmable logic controller are configured as follows.

The image quantization unit divides the binarized image into at least a first region in a lattice shape, a second region adjacent to the first region in the lateral direction, a third region adjacent to the first region, and an adjacent second region The fourth area above the area and adjacent to the lateral direction of the third area, and calculate the proportion of the aforementioned first color in each area.

The programmable logic controller increases the proportion of the first color in the order of the first area and the second area, and the proportion of the first color in the fourth area is based on the first When the proportion of the color decreases and increases, at least one of a warning signal and a control signal is output. The control signal changes the rotation speed of the pair of rolls to suppress the upward warpage of the rolled material. For example, the control signal is a signal to stop the aforementioned pair of rolls or a signal to make the rotation speed of the lower roll slower than that of the upper roll.

According to the image analysis device for an industrial plant of the present invention, dynamic image data can be used to quantify and analyze the state of the subject in real time, and an operator who confirms the operation status of the industrial plant can be supported. In addition, according to the industrial factory monitoring and control system of the present invention, it is possible to achieve appropriate control using data quantified by the image analysis device for industrial factories.

1‧‧‧Image analysis device

2‧‧‧The first surveillance camera

3‧‧‧Second surveillance camera

4‧‧‧Picture data converter

5‧‧‧Picture signal line

6‧‧‧Internet for dynamic images

7‧‧‧Data collection device

8‧‧‧Human-machine interface

9‧‧‧Programmable logic controller

10‧‧‧Control network

21‧‧‧Motion Picture Information Collection Department

22‧‧‧Image Processing Department

23‧‧‧ Quantification Department

24‧‧‧Numerical output unit

31‧‧‧Left window

32‧‧‧Central window

33‧‧‧Right window

41‧‧‧Color filter

42‧‧‧Binarization Department

43‧‧‧Image Processing Department

50‧‧‧ Strip quantization processing department

51‧‧‧Zone A

52‧‧‧Zone B

53‧‧‧Zone C

54‧‧‧Zone D

60‧‧‧Grid quantization processing unit

61‧‧‧Grid area A

62‧‧‧Grid area B

63‧‧‧Grid area C

64‧‧‧Grid area D

65‧‧‧Grid area E

66‧‧‧Grid area F

67‧‧‧Grid area G

68‧‧‧Grid area H

69‧‧‧Grid area I

70‧‧‧Grid area J

71‧‧‧Grid area K

72‧‧‧Lattice area L

111‧‧‧CPU

112‧‧‧Memory

113‧‧‧Storage

113a‧‧‧Program Memory Department

113b‧‧‧Data Memory Department

114‧‧‧External Machine Interface Department

115a‧‧‧Control network interface

115b‧‧‧Web interface for dynamic images

116‧‧‧Internal bus

117‧‧‧Monitor

118‧‧‧ keyboard

119‧‧‧Mouse

311‧‧‧Rolled material

312‧‧‧Roll

313‧‧‧Handling roller

321‧‧‧ indicates the part of rolled material

322‧‧‧Other parts

Fig. 1 is a schematic diagram showing the structure of a factory monitoring and control system of the industrial factory according to the first embodiment.

Fig. 2 is a block diagram of the image analysis device of the first embodiment.

Fig. 3 is an example of screen display of the image analysis device of the first embodiment.

FIG. 4 is a block diagram showing an example of the hardware configuration of the processing circuit included in the image analysis device.

Fig. 5 is a block diagram of the image analysis device according to the second embodiment.

Fig. 6 is an analysis example of the image analysis device of the second embodiment.

Fig. 7 is a block diagram of the image analysis device according to the third embodiment.

Fig. 8 is an analysis example of the image analysis device of the third embodiment.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In addition, the same reference numerals are given to the common elements in the drawings, and repeated explanations are omitted.

Embodiment 1

(System Components)

Fig. 1 is a schematic diagram showing the structure of a factory monitoring and control system of the industrial factory according to the first embodiment.

A steel factory is an industrial factory that produces materials and resources required for industrial activities. In hot rolling, the high-temperature slab (rolled material) heated by the heating furnace is conveyed by the conveying roller, and is thinly extended to the required thickness by the roughing mill and the finishing mill, and processed to the required width at the same time, and finally used Coiler winding.

The factory monitoring and control system is connected to the image analysis device 1, the first monitoring camera 2, the second monitoring camera 3, the data collection device 7, the HMI (HUMAN MACHINE INTERFACE) 8, the PLC 9 and the equipment constituting the industrial factory (omitted (Illustration) etc.

The first surveillance camera 2 and the second surveillance camera 3 are arranged so as to include machines constituting the industrial factory and materials processed by the machines in the shooting range. The first monitoring camera 2 is connected to the image data converter 4 via the image signal line 5. The image output of the first monitoring camera 2 is converted into a signal capable of network communication by the image data converter 4 and transmitted to the image analysis device 1 via the network 6 for dynamic images. The second monitoring camera 3 is a network camera, and the captured moving image data is transmitted to the image analyzing device 1 via the moving image network 6.

The image analysis device 1 is connected to a programmable logic controller (PLC) 9 that controls devices (including actuators and sensors) that constitute an industrial plant via a control network 10, as a general operation of an operator in an industrial plant or Human-machine interface (HMI) 8 and data collection device 7 of the monitoring control device used in monitoring. In addition, there are cases where the image analysis device 1 is incorporated into the data collection device 7.

The control network 10 includes a plurality of nodes having a common memory, and the data on the common memory is synchronized by periodically broadcasting and transmitting between the plurality of nodes. As a result, the virtual memory space is shared between the image analysis device 1, the PLC 9, and the HMI 8. The memory area (address) of each data is allocated in the common memory. Devices connected to each node can send and receive data by writing to and reading from common memory.

(Picture analysis device)

The image analysis device 1 includes a dynamic image data collection unit 21, an image processing processing unit 22, an image quantization unit 23, and a numerical output unit 24.

The dynamic image data collection unit 21 collects and captures dynamic image data of the machines constituting the industrial factory and the materials processed on the machines in real time. Real-time does not necessarily refer to the moment of shooting, but also includes data collection accompanied by delays or data collection at regular intervals due to communication paths and data processing. Specifically, the moving image data collection unit 21 collects moving image data from the first monitoring camera 2 and the second monitoring camera 3 via the moving image network 6 at regular intervals. The dynamic image data collection unit 21 outputs the dynamic image data to the image processing processing unit 22. The moving image data collection unit 21 stores the collected moving images in the data storage unit 113b of the storage 113.

The image processing processing unit 22 extracts an image from the dynamic image data every predetermined period, converts the specified color to the first color, converts the color other than the specified color to the second color, and binarizes the image. The certain period is preferably as short as possible, and more ideally is immediate. Portrait refers to a frame of portraits extracted from dynamic image data. The specified color is not only a single color, but also includes the specified range of colors.

Specifically, the image processing unit 22 uses the color filter unit 41, the binarization unit 42, and the image processing unit 43 shown in FIG. 2 to process the image, and then outputs the processed image to the image quantization unit 23.

The color filter unit 41 extracts a specified color related to the machine and material in the image. As for the designated color, for example, the color of the hot material is set in advance, and the color indicating the abnormal temperature of the machine or the material is set.

The binarization unit 42 converts the designated color into the first color (for example, white), converts colors other than the designated color into the second color (for example: black), and binarizes the portrait. This can reduce the amount of data, reduce the calculation load of image processing and quantization, and ensure real-time.

The image processing unit 43 converts an image when the first surveillance camera 2 or the second surveillance camera 3 shoots a subject diagonally, and converts it into a portrait viewed from the side or above. As a result, the camera has a high degree of flexibility in setting, not only when the camera cannot be installed above or beside the subject, but also in an environment where it is difficult to install a sensor near the subject. Also. When the camera can be installed above or beside the subject, it is not necessary to execute the processing of the image processing unit 43.

The portrait quantization unit 23 quantizes the binarized portrait based on the number of pixels converted into the first color. For example, the proportion of the first color in the image is calculated based on the number of pixels converted into the first color (for example, white) by the image processing unit 22. The portrait quantization unit 23 outputs the quantized data to the numerical output unit 24.

The numerical output unit 24 outputs the quantized data to the data collection device 7, the HMI 8, and the PLC 9 via the control network 10.

FIG. 3 is a diagram showing a display example displayed on the display 117 (see FIG. 4) by the image analysis device 1. The portrait analysis device 1 displays the collected dynamic portrait data in real time on the left window 31. In the example of FIG. 3, the shooting range includes a pair of rolls 312 (rough rolling mills or finishing mills) and conveying rollers 313 that roll a rolled material 311 as a material. The rolled material 311 is conveyed from left to right and is paired The state of the roll 312 rolling. In addition, the image analysis device 1 displays an image that binarizes the image displayed on the left window 31 in the center window 32. The portion 321 representing the rolled material is displayed in white, and the other portion 322 is displayed in black. In addition, the image analysis device 1 displays a graph showing the time change of the proportion of white in the binarized image in the right window 33. In the example of FIG. 6, a graph showing the time change of the proportion of white in each area divided in the horizontal direction is displayed.

The data collection device 7 collects process data from PLC 9 and HMI 8. Process data includes various data related to the machines that make up industrial plants and the materials processed by the machines. Examples include control values of actuators, detection values of sensors, and material specifications. Large-scale factories such as iron and steel factories have input and output points of thousands and tens of thousands, and various process data exist. These process data are collected in a data collection device 7 with a data collection function and a data playback function, and are used for data analysis during testing, adjustment, operation, and failure.

In addition, the data collection device 7 receives quantized data from the image analysis device 1 and synchronizes with the process data and collects and stores at the same time. In addition, the data collection device 7 receives the necessary data from the image analysis device 1 and can realize the display similar to FIG. 3.

The HMI 8 will display the process data received from the PLC 9 as values, texts and lights. In addition, the HMI 8 is equipped with operation buttons for sending button input signals and numerical input signals, and outputs signals for controlling the PLC 9 according to the pressed operation buttons. Furthermore, the HMI 8 receives quantitative data from the image analysis device 1 and can display its value, or can issue an alarm when its value exceeds a predetermined threshold.

The PLC 9 is calculated based on input from sensors in industrial plants and outputs signals to actuators such as valves and motors to control industrial plants. In addition, the data output from the image analysis device 1 is received and calculated in the same manner as the input from the sensor, and a signal is output to actuators such as valves and motors to control industrial plants. In addition, an alarm is issued when the calculation result exceeds a critical value.

As described above, according to the image analysis device 1 of the first embodiment, by quantifying the dynamic image collected from the monitoring camera in real time, it is possible to grasp the degree to which the subject enters the shooting range. Therefore, the image analysis device 1 can quantitatively analyze the position and shape of the machine and the material in real time, and can support the operator to confirm the operation status of the operation. In addition, since no special sensor is used, the cost is low. For example, it is possible to reduce the installation cost of the sensor when detecting the warpage of the hot-rolled steel strip and the thick plate. In addition, compared with the sensor, the shooting range is wide and the degree of freedom of the installation place is high, so the state of the subject can be grasped in various environments.

In the first embodiment described above, the number of pixels converted to the first color is calculated for the entire portrait, but it is not limited to this. You can also specify a partial area of the portrait and calculate the number of pixels converted to the first color in that area. By specifying areas to be noted in the portrait, noise can be reduced and detection accuracy can be improved.

In addition, by using the image analysis device 1 and the data collection device 7 of the first embodiment described above, the dynamic image data can be displayed on the data collection device 7 in real time, and the data stored in the data collection device 7 can be played back from any specified time. Collect the dynamic portrait data of the device 7. It makes it easy to grasp the location and size of past phenomena, and can improve the accuracy of the location and size confirmation. In addition, you can also stop, fast forward, and rewind the moving image. In addition, the above content is also the same in the following embodiments.

In addition, although the image analysis device 1 of the first embodiment described above does not include the display 117, the keyboard 118, and the mouse 119 shown in FIG. 4 described later, the image analysis device 1 may include such equipment. In addition, the above content is also the same in the following embodiments.

In addition, in the first embodiment, although the steel plant is taken as an example to describe the industrial system, it is not limited to this. The industrial system also includes power generation plants, petroleum plants, chemical plants, etc.

(Example of hardware configuration)

The hardware configuration of the image analysis device 1 will be described with reference to FIG. 4. FIG. 4 is a block diagram showing an example of the hardware configuration of the processing circuit included in the image analysis device 1. Each part of the image analysis device 1 shown in FIG. 2 shows a part of the functions of the image analysis device 1, and each function is realized by a processing circuit. For example, the processing circuit is connected to the CPU 113, the memory 112, the storage 113 such as HDD or mass storage, the external device interface (I/F) unit 114, the control network interface unit 115a, the dynamic image via the internal bus 116 It is constituted by the network interface section 115b. In addition, the data collection device 7 has the same structure.

The CPU 111 realizes the functions of each part of the image analysis device 1 by executing various programs stored in the program memory section 113a of the memory 113.

The memory 112 is used as a calculation area for temporarily storing or expanding data when the CPU 111 executes various programs.

The memory 113 has a program memory 113a and a data memory 113b. The program memory 113a stores an OS (OPERATING SYSTEM, operating system) and various programs. In addition, the data storage unit 113b stores the collected process data and dynamic image data at each time.

In the example shown in FIG. 4, although the program memory 113a and the data memory 113b are provided in one memory 113, the program memory 113a and the data memory 113b may be provided separately in a plurality of memories.

The external device interface 114 is an interface for connecting an external device such as a display 117, a keyboard 118, a mouse 119, and the image analysis device 1.

The control network interface section 115a is an interface for connecting the control network 10 and the image analysis device 1. The network interface 115b for moving images is an interface for connecting the network 6 for moving images and the image analyzing device 1.

Embodiment 2

Next, Embodiment 2 will be described with reference to FIGS. 5 and 6. In the first embodiment described above, the ratio of the first color to the overall portrait was calculated. On the other hand, in the second embodiment, the ratio of the first color in each band-shaped region that divides the image into bands is calculated, and the change in the ratio of the first color in each band-shaped region is compared. Analyze the state of the subject.

Fig. 5 is a block diagram of the image analysis device 1 of the second embodiment. The configuration shown in FIG. 5 is the same as that in FIG. 2 except that the image quantization unit 23 includes the band-shaped quantization processing unit 50, and therefore description of the configuration that is common to them is omitted or simplified.

The image processing unit 22 binarizes the image of the material viewed in the width direction.

The band quantization processing unit 50 calculates the first color (for example, white) for each band region obtained by dividing the image binarized by the image processing processing unit 22 in parallel with the conveying direction of the material proportion. In the example of FIG. 5, the binary image system is divided into four regions in the horizontal direction. The four divided regions are referred to as a band-shaped region A51, a band-shaped region B52, a band-shaped region C53, and a band-shaped region D54 from bottom to top. The band quantization processing unit 50 calculates the ratio of the number of white pixels in each band region.

Real-time calculation of the proportion of the first color in each strip-shaped area divided into layers (hereinafter referred to as the first color ratio), and the position of the subject can be quantitatively grasped by confirming the change in the first color ratio , Shape changes.

For example, the rolled material 311 (refer to FIG. 3) as a material may jump on the conveying roller 313 (refer to FIG. 3) of the steel plant. At this time, the subject (rolled material) is moved in parallel from the strip-shaped area A51 to the strip-shaped area B52. Therefore, by confirming that the increase amount of the first color ratio of the band-shaped area B52 is equal to the decrease amount of the first color ratio of the band-shaped area A51, it can be confirmed that the subject has moved in parallel.

On the other hand, the shape of the subject may be deformed. For example, hot rolling lines and thick plate lines in steel plants may warp upwards in the rolled material 311 (see FIG. 3) due to rolling. An example of image analysis will be described with reference to FIG. 6. t1 is the shape of the rolled material in the previous cycle, and t2 is the shape of the rolled material in the current cycle. The strip quantization processing unit 50 divides the binarized image into at least a strip region A51 and a strip region B52 adjacent to the strip region A51 in parallel with the rolling material conveying direction, and calculates the number of each region. One color ratio. The boundary between the strip-shaped area A51 and the strip-shaped area B52 is set between the upper and lower surfaces of the rolled material.

The operator confirms the change in the proportion of the first color in each band-shaped region accompanying the change in t1 to t2. By confirming the magnitude of the difference between the increase in the first color ratio in the band-shaped region B52 and the decrease in the first color ratio in the band-shaped region A51, the upward warpage of the rolled material can be quantitatively grasped.

The image analysis device 1 can support the operator's confirmation operation by displaying a graph showing the time change of the first color ratio in each band-like region as illustrated in the right window 33 of FIG. 3.

The PLC 9 receives the data output by the numerical output unit 24 (the first color ratio in each band area). PLC9 can control the position of the subject, the amount of movement of the subject, and the shape of the subject (e.g., the amount of upward warping) from the first color ratio in each banded area .

The control according to the upward warpage amount will be described with reference to the above-mentioned FIG. 6. When the difference between the increase in the first color ratio in the strip area B52 and the decrease in the first color ratio in the strip area A51 is greater than the critical value, the PLC 9 outputs at least one of a warning signal and a control signal. The signal changes the rotation speed of the pair of rollers 312 to suppress the upward warpage of the rolled material. For example, the control signal is a signal to stop the pair of rolls 312, or a signal to make the rotation speed of the lower roll lower than that of the upper roll.

In addition, when the difference between the increase in the first color ratio in the strip-shaped area B52 and the decrease in the first color ratio in the strip-shaped area A51 is greater than the first critical value, the output of the PLC 9 makes the rotation speed of the lower roll higher than The signal that the rotation speed of the roll is slow, and when the difference is greater than the second critical value (larger than the first critical value), a signal to stop the pair of rolls 312 may also be output.

In addition, PLC9 may output a warning signal with high urgency when the difference becomes larger.

As described above, according to the system of the present embodiment provided with the band-shaped quantization processing unit 50, it is possible to more accurately support the operator's work of confirming the position or size of the machine and material as compared with the first embodiment. In addition, the PLC 9 uses the data quantized by the band quantization processing section 50 to achieve appropriate control according to the state of the subject. For example, changing the control value allows the machine as the subject to move to an appropriate position, or changing the control value to prevent the rolling material of the subject from colliding with sensors and machinery.

In addition, the system of Embodiment 2 described above can be combined with the system of Embodiment 1. This point is the same in the following embodiments.

In addition, although the band-shaped quantization processing unit 50 of the second embodiment described above sets the band-shaped region in the horizontal direction, it may set the band-shaped region in the vertical direction or the oblique direction.

In addition, the band quantization processing unit 50 of the second embodiment described above divides the screen into four, but it may be divided into two, three, or more than five.

Embodiment 3

Next, Embodiment 3 will be described with reference to FIGS. 7 and 8. In the first embodiment described above, the ratio of the first color to the overall portrait was calculated. On the other hand, in the third embodiment, the ratio of the first color in each grid-shaped area that divides the image into grids is calculated, and the change in the ratio of the first color in each grid-shaped area is compared, and more detailed Analyze the state of the subject.

Fig. 7 is a block diagram of the image analysis device 1 of the third embodiment. The configuration shown in FIG. 7 is the same as that in FIG. 2 or FIG. 5 except that the image quantization unit 23 includes a lattice-like quantization processing unit 60, and therefore description of the configuration that is common to them is omitted or simplified.

The image processing unit 22 binarizes the image viewed from the width direction of the material.

The lattice-shaped quantization processing unit 60 calculates the proportion of the first color (for example, white) in each lattice-shaped region obtained by dividing the image obtained by the image processing processing unit 22 into a lattice-shaped region. In the example of FIG. 7, the binarized image system is divided into 4 areas in the horizontal direction and 3 areas in the vertical direction, and the total is divided into 12 areas. The divided regions are referred to as a lattice region A61, a lattice region B62, a lattice region C63, a lattice region D64, a lattice region E65, a lattice region F66, a lattice region G67, a lattice region H68, a lattice region I69, The grid-like area J70, the grid-like area K71, and the grid-like area L72. The grid-like quantization processing unit 60 calculates the ratio of the number of white pixels in each grid-like area.

Real-time calculation of the proportion of the first color in each grid-like area divided into a grid (hereinafter referred to as the first color ratio), and the position of the subject can be quantitatively grasped by confirming the change in the first color ratio , Shape changes.

For example, there may be a case where the rolled material 311 (refer to FIG. 3) as a material bounces on the conveying roller 313 (refer to FIG. 3) of the steel plant. At this time, the subject (rolled material) is moved in parallel from the lattice-shaped area A61 to the lattice-shaped area B62. Therefore, by confirming that the increase amount of the first color ratio of the grid-like area A61 is equal to the decrease amount of the first color ratio of the grid-like area B62, it can be confirmed that the photographic subject moves in parallel.

In addition, when the subject extends obliquely and extends from the lattice-shaped region A61 to the lattice-shaped region F66, the first color ratio of the lattice-shaped region A61 is saturated, and the first color ratio of the lattice-shaped region F66 increases. The increase and decrease of the first color ratio of the adjacent lattice-shaped area B62 and the increase and decrease of the first color ratio of the lattice-shaped area E65 can confirm whether the subject extends without horizontal shaking.

In addition, the shape of the subject may be deformed. For example, hot rolling lines and thick plate lines in steel plants may warp upwards in the rolled material 311 (see FIG. 3) due to rolling. An example of image analysis will be described with reference to FIG. 8. t3 is the shape of the rolled material in the previous cycle, and t4 is the shape of the rolled material in the current cycle. The lattice-like quantization processing unit 60 divides the binary image into at least a lattice-like region F66, a lattice-like region J70 adjacent to the lattice-like region F66, and a lattice-like region adjacent to the lattice-like region F66. G67. A lattice-shaped region K71 adjacent to the upper side of the lattice-shaped region J70 and adjacent to the transverse direction of the lattice-shaped region G67, and calculating the first color ratio of each region. The boundary between the lattice-like region F66 and the lattice-like region G67 is set above the rolled material.

The operator confirms the change in the proportion of the first color in each grid-like area accompanying the change in t3 to t4. By confirming that the first color ratio increases in the order of the grid region F66 and the grid region J70, and the first color ratio in the grid region K71 increases according to the decrease in the first color ratio in the grid region G67, it can be quantified Way to grasp the upward warpage of rolled material.

The PLC 9 receives the data output by the numerical output unit 24 (the first color ratio in each grid-like area). PLC9 can perform control based on the position of the subject, control based on the amount of movement of the subject, and control based on the shape of the subject from the first color ratio in each grid-like area (for example, control based on the amount of upward warpage) .

The control according to the upward warpage amount will be described with reference to the above-mentioned FIG. 8. PLC9 outputs a warning when the first color ratio increases in the order of grid area F66 and grid area J70, and the first color ratio in grid area K71 increases according to the decrease of the first color ratio in grid area G67 At least one of a signal and a control signal that changes the rotational speed of a pair of rolls 312 to suppress the upward warpage of the rolled material. For example, the control signal is a signal to stop the pair of rolls 312, or a signal to make the rotation speed of the lower roll lower than that of the upper roll.

As described above, according to the system of the present embodiment provided with the lattice-shaped quantization processing unit 60, it is possible to more accurately support the operator's work of confirming the position or size of the machine and material as compared with the first embodiment. In addition, the PLC 9 uses data quantized by the lattice-like quantization processing unit 60 to realize appropriate control according to the state of the subject.

In addition, the system of Embodiment 3 described above can be combined with the system of Embodiment 1 and the system of Embodiment 2.

In addition, the lattice-like quantization processing unit 60 of Embodiment 3 described above defines the regions in a lattice shape in the horizontal direction and the vertical direction, but the lattice-like regions may be set in the oblique direction.

In addition, the lattice-like quantization processing unit 60 of the above-mentioned Embodiment 3 divides the screen into twelve, and if it is an equal division, the number of divisions is not limited. Especially when shooting a subject from an oblique angle, the image is converted into a portrait shot from the side or above by image conversion. At this time, the amount of movement and deformation of the subject may become small. In this case, by increasing the number of grid-like divisions, it is possible to detect a smaller amount of movement and deformation.

The embodiments of the present invention have been described above, but the present invention is not limited to the above-mentioned embodiments, and various modifications can be made within the scope not departing from the purpose of the present invention.

1‧‧‧Image analysis device

2‧‧‧The first surveillance camera

3‧‧‧Second surveillance camera

4‧‧‧Picture data converter

5‧‧‧Picture signal line

6‧‧‧Internet for dynamic images

7‧‧‧Data collection device

8‧‧‧ Human Machine Interface (HMI)

9‧‧‧Programmable logic controller (PLC)

10‧‧‧Control network

21‧‧‧Motion Picture Information Collection Department

22‧‧‧Image Processing Department

23‧‧‧ Quantification Department

24‧‧‧Numerical output unit

Claims (5)

An image analysis device for an industrial factory is provided with: a dynamic image data collection unit that collects and captures dynamic image data of machines constituting the industrial factory and materials processed on the machine in real time; The aforementioned dynamic portrait data extracts the portrait, converts the specified color to the first color, converts the color other than the specified color to the second color, and binarizes the portrait; the portrait quantization part is based on the conversion to the first color Pixels are used to quantify the binarized portrait; and the numerical output section outputs the quantized data. The image analysis device for an industrial plant as described in item 1 of the patent application scope, wherein the image quantization unit calculates each of the band-shaped regions obtained by dividing the binarized image parallel to the conveying direction of the material The proportion of the aforementioned first color. The image analysis device for an industrial plant as described in item 1 or item 2 of the patent application scope, wherein the image quantization unit calculates the first in each grid-shaped area obtained by dividing the binarized image into a grid The proportion of a color. An industrial plant monitoring and control system comprising: an image analysis device for an industrial plant as described in item 1 of the patent application scope; and a programmable logic controller that controls the aforementioned machine; the aforementioned machine includes a rolled material that is rolled as the aforementioned material A pair of rollers; the image processing unit is to binarize the image of the rolled material viewed from the width direction; the image quantization unit is to make the binarized image parallel to the conveying direction of the rolled material, At least divided into the first area and the second area adjacent to the first area, and calculate the proportion of the first color in each area; the programmable logic controller is the first in the second area When the difference between the increase in the proportion of colors and the decrease in the proportion of the first colors in the first area is greater than the critical value, at least one of a warning signal and a control signal is output, and the control signal changes The rotation speed of the pair of rolls is to suppress the upward warpage of the rolled material. An industrial plant monitoring and control system comprising: an image analysis device for an industrial plant as described in item 1 of the patent application scope; and a programmable logic controller that controls the aforementioned machine; the aforementioned machine includes a rolled material that is rolled as the aforementioned material A pair of rollers; the image processing unit is to binarize the image of the rolled material viewed from the width direction; the image quantization unit is to divide the binarized image into at least a grid-like first region, phase The second area adjacent to the first area laterally, the third area adjacent to the first area above, the fourth area adjacent to the second area above and adjacent to the third area laterally, and calculate each The proportion of the first color in the area; the proportion of the programmable logic controller in the first color increases in the order of the first area and the second area, and the aforementioned in the fourth area When the proportion of the first color increases according to the decrease of the proportion of the first color in the third area, at least one of a warning signal and a control signal is output, and the control signal changes the rotation of the pair of rollers Speed to suppress the upward warpage of the aforementioned rolled material.

Images