JP2021002791A - Environmental abnormality detection device - Google Patents

Abstract

To provide an environmental abnormality detection device capable of effectively suppressing false detection due to image blur and external environment such as rain and thereby capable of accurately detecting abnormalities from an image of a monitoring target.SOLUTION: An environmental abnormality detection device 10 includes: a receiving section 21 receiving an image obtained by imaging a monitoring target; a detection frame setting section 22 setting a detection frame 31 having a plurality of measurement points 32 within a predetermined range in an image; a flow acquisition section 23 acquiring a vector of an optical flow of each of the measurement points 32; and a determination section 24 which determines that the monitoring target is abnormal, when the vector of each of the measurement points 32 is biased in a specific direction, and which does not determine that the monitoring target is abnormal, when the vector is not biased in a specific direction.SELECTED DRAWING: Figure 2

Description

The present invention relates to an environmental abnormality detection device.

Conventionally, a device for detecting an abnormality based on captured image information has been known. For example, Patent Document 1 discloses this kind of technology.

In Patent Document 1, a predetermined area is set as a monitoring area and photographed by a surveillance camera, and the speed change of an object in the monitoring area is extracted from the image information obtained from the surveillance camera to detect the occurrence of a disaster such as a debris flow. The technology related to the disaster detection system is described.

Japanese Unexamined Patent Publication No. 2014-7448

When the camera is installed in a place away from the monitoring target, even a slight shaking due to wind or the like causes a large movement in the image, and there is a possibility that it is erroneously detected that a flow in a predetermined direction has occurred. In addition, when it rains, the downward flow becomes large and overlaps with the flow direction of the river, which causes false detection. The prior art shown in Patent Document 1 and the like has room for improvement from the viewpoint of reducing false positives caused by the external environment such as image blurring and rain.

An object of the present invention is to provide an environmental abnormality detection device capable of effectively suppressing false detection caused by an external environment such as image blurring and rain, and accurately detecting an abnormality from a monitored image.

The present invention is an environmental abnormality detection device that detects an abnormality from a plurality of images that are continuous in time, and has a receiving unit that receives an image of a monitored object and a plurality of measurement points in a predetermined range in the image. An abnormality occurs when the detection frame setting unit that sets the detection frame including the detection frame, the flow acquisition unit that acquires the optical flow vector of each measurement point, and the vector of each measurement point are biased in a specific direction. The present invention relates to an environmental abnormality detection device including a determination unit that determines and does not determine an abnormality if it is not biased in a specific direction.

According to the environmental abnormality detection device of the present invention, false detection caused by an external environment such as image blurring or rain can be effectively suppressed, and an abnormality can be accurately detected from an image to be monitored.

It is a figure which shows typically the disaster detection system to which the environmental abnormality detection apparatus which concerns on one Embodiment of this invention is applied. It is a block diagram of the environmental abnormality detection device of this embodiment. It is a flowchart which shows the first half of the abnormality detection processing by the environment abnormality detection apparatus of this embodiment. This is the first half of the flowchart showing the latter half of the abnormality detection process by the environmental abnormality detection device of the present embodiment. It is a schematic diagram which shows an example of the image which performs abnormality detection by the environmental abnormality detection device of this embodiment. It is a schematic diagram which shows the measurement point of the detection frame of this embodiment. It is a schematic diagram explaining the acquisition of the optical flow by the environmental abnormality detection device of this embodiment. It is a schematic diagram explaining the calculation of the frequency of measurement points by direction by the environmental abnormality detection device of this embodiment. This is an example of a graph showing the frequency distribution of measurement points for each direction measured by the environmental abnormality detection device of the present embodiment. This is an example of a graph showing the frequency distribution of measurement points for each direction measured by the environmental abnormality detection device of the present embodiment. It is a schematic diagram which shows the degree of the strength of the vector of the measurement point in a predetermined direction measured by the environmental abnormality detection device of this embodiment. It is a schematic diagram which shows the distribution of the abnormality point with respect to the measurement point measured by the environmental abnormality detection apparatus of this embodiment. This is an example of a graph showing the frequency distribution of abnormal points in each direction measured by the environmental abnormality detection device of the present embodiment. This is an example of a graph showing the frequency distribution of abnormal points in each direction measured by the environmental abnormality detection device of the present embodiment. It is a schematic diagram which shows the detection example by the difference of the vector state by the environmental abnormality detection device of this embodiment. It is a graph which compared the determination system of the environmental abnormality detection device of the Example of this invention, and the environmental abnormality detection device of a comparative example.

Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram schematically showing a disaster detection system 1 to which the environmental abnormality detection device 10 according to the embodiment of the present invention is applied.

First, the overall configuration of the disaster detection system 1 will be described. As shown in FIG. 1, the disaster detection system 1 includes a camera 2 that captures an image to be monitored, a speaker 3 that notifies the occurrence of a disaster, an information terminal 4 that receives disaster information, and a pre-registered mobile terminal 5. And an environmental abnormality detection device 10 for determining the occurrence of a disaster based on the image information acquired by the camera 2.

The camera 2 is installed at each of the points T1, T2, and T3 for detecting the occurrence of the debris flow 100. The image information acquired by each camera 2 is transmitted to the environmental abnormality detection device 10.

The speaker 3 is one of the notification units for notifying the occurrence of a disaster such as a debris flow 100 by sound. For example, when an abnormality is detected by the environmental abnormality detection device 10 described later, the user activates the speaker 3 to notify the disaster. Further, the speaker 3 may be automatically operated when an abnormality is detected by the environmental abnormality detecting device 10. As the notification unit for notifying the disaster, in addition to the speaker 3, a method of notifying the disaster by light such as lighting, a method of displaying an image on a display or the like to notify the disaster, or the like can be used.

The information terminal 4 is a computer that receives disaster information indicating the occurrence of a disaster such as a debris flow 100. The information terminal 4 that has received the disaster information executes the processing associated with the disaster information. For example, the information terminal 4 performs a process of displaying the occurrence of a disaster on a display device such as a display. The mobile terminal 5 is an electronic device such as a smartphone registered in advance in the environmental abnormality detection device 10. Disaster information is transmitted from the environmental abnormality detection device 10 to the mobile terminal 5 via a communication means such as e-mail.

The environmental abnormality detection device 10 is a computer that executes a process of detecting an abnormality of a monitoring target based on image information acquired by the camera 2. The environment abnormality detection device 10 is connected to an input device for the user to operate the environment abnormality detection device 10 and a display device for displaying the processing result of the environment abnormality detection device 10.

The image information acquired by the camera 2 is input to the environmental abnormality detection device 10. The image information is a moving image that is continuous in time. For example, the camera 2 shoots a monitoring target at a frame rate (fps) 30, and the shot moving image is transmitted to the environment abnormality detection device 10 via an internet line, a dedicated line, or the like.

Next, processing related to abnormality detection by the environmental abnormality detection device 10 will be described. FIG. 2 is a block diagram of the environmental abnormality detection device 10 of the present embodiment. As shown in FIG. 2, the environmental abnormality detection device 10 includes a reception unit 21, a detection frame setting unit 22, a flow acquisition unit 23, a determination unit 24, and a storage unit 25.

The receiving unit 21 is an interface for receiving image data captured by the camera 2 by wire or wirelessly. The detection frame setting unit 22, the flow acquisition unit 23, and the determination unit 24 are a part of the control device 26 that executes the process of detecting an abnormality. The storage unit 25 stores various information related to control and abnormality detection.

3 and 4 are flowcharts showing an example of abnormality detection processing by the environmental abnormality detection device 10 of the present embodiment.

As shown in FIG. 3, first, the detection frame setting unit 22 sets the detection frame 31 and the measurement point 32 (step S101). FIG. 5 is a schematic diagram showing an example of an image in which an abnormality is detected by the environmental abnormality detection device 10 of the present embodiment. FIG. 6 is a schematic view showing the measurement points 32 of the detection frame 31 of the present embodiment.

The detection frame setting unit 22 performs a process of setting the detection frame 31 in a predetermined area of the image. As shown in FIG. 5, the detection frame 31 is an area set for each monitoring target, and is set, for example, in the area of the river in the image. The detection frame 31 is empirically and empirically set by the user. The position of the detection frame 31 does not match for each of the points T1 to T3 having different monitoring targets and different angles of view. The detection frame 31 may be automatically set by image processing to distinguish between rivers in the image and others. In FIG. 5, an example in which six detection frames 31 are arranged in the upper range 91, five detection frames 31 are arranged in the middle range 92, and 14 detection frames 31 are arranged in the lower range 93 is shown by a broken line. It is divided. In the lower range 93, the detection frames 31 are arranged in two upper and lower lines. It should be noted that the broken line is described for the purpose of explaining the figure and may not be displayed in the actual image.

The detection frame 31 will be described. As shown on the left side of FIG. 6, the size of one detection frame 31 of the present embodiment is a square frame having a length of 10 pixels and a width of 10 pixels. As shown on the left side of FIG. 6, a plurality of measurement points 32 are set in the detection frame 31. In the present embodiment, the intersections of the grid in units of 4 pixels are the measurement points 32, and 25 measurement points 32 are set for one detection frame 31. Further, in step S101, the direction to be detected is also set. In the present embodiment, the direction to be detected is set downward based on the direction in which the debris flow flows in the image.

Return to the flow of FIG. When the setting of the detection frame 31 and the measurement point 32 is completed, the receiving unit 21 starts reading the new moving image received (step S102). The moving image is a moving image to be monitored captured by the camera 2.

Next, the flow acquisition unit 23 calculates the average value of the flow direction and flow velocity of 60 frames for each measurement point 32. As described above, since images are taken at a frame rate (fps) of 30, 60 frames are 60 images constituting a 2-second moving image (step S103).

FIG. 7 is a schematic diagram illustrating acquisition of an optical flow by the environmental abnormality detection device 10 of the present embodiment. The direction of the arrow extending from the measurement point 32 in FIG. 7 indicates the flow direction, and the length thereof indicates the flow velocity.

The flow acquisition unit 23 calculates the flow direction and the flow velocity of each of the 25 measurement points 32 by the optical flow technique based on the first image and the second image that are continuous in time. The flow direction and flow velocity for each measurement point 32 are calculated based on a pair of images that are continuous in time, such as the second image, the third image, the third image, and the fourth image. When this process is performed on 60 images, the flow direction and the flow velocity for each of the 59 measurement points 32 are calculated.

The flow acquisition unit 23 sets the averaged flow direction and flow velocity of 59 times for each measurement point 32 as the flow direction and flow velocity of each measurement point 32. In this way, the averaged flow direction and flow velocity for m-1 times from m consecutive images within a predetermined time is set as the flow direction and flow velocity for each measurement point 32.

One target measurement point 32 is set from the 25 measurement points 32 (step S104). FIG. 8 is a schematic diagram illustrating the calculation of the frequency of measurement points by direction by the environmental abnormality detection device 10 of the present embodiment. For example, as shown on the left side of FIG. 8, the measurement point 32 located at the leftmost corner is set as the target measurement point 32.

In steps S105 to S110, it is determined whether or not the measurement point 32 set in step S104 is an abnormal point based on a plurality of conditions.

First, after selecting the measurement point 32, the determination unit 24 executes a process of investigating the maximum number of appearance frequencies for each direction at the measurement point 32 (step S105). As shown on the right side of FIG. 8, the direction of the optical flow at the measurement point 32 is determined to be one of the directions P1 to P8 divided into eight directions by 45 degrees, and the directions corresponding to the number of measurement results are acquired. .. The determination unit 24 determines the maximum number of directions among the directions P1 to P8, and acquires the appearance frequency of the maximum number of directions.

The process of acquiring the maximum number of occurrence frequencies will be described with reference to FIG. FIG. 9 is an example of a graph showing the frequency distribution of the measurement points 32 in each direction measured by the environmental abnormality detection device 10 of the present embodiment. The horizontal axis of FIG. 9 shows the direction of the optical flow, and the vertical axis shows the frequency of appearance in each direction at one measurement point.

FIG. 9 shows an example of the results of 59 measurements at a certain measurement point 32. In this example, of the 59 filings, the highest number of filings is in the downward direction P5 surrounded by a broken line. The determination unit 24 sets the maximum number of directions to P5. The application frequency of this P5 is about 70%.

Return to the flow of FIG. After the process of step S105, the determination unit 24 determines whether or not the first condition is satisfied. In the present embodiment, the determination unit 24 determines whether or not the maximum number of application frequencies is 30% or more set as the threshold value (step S106). Here, if it is less than 30%, the measurement point 32 is not an abnormal point, and the process proceeds to step S104, and different measurement points 32 of the same detection frame 31 are newly set. The processing after step S105 is executed for the newly set measurement point 32.

In the process of step S105, when the maximum number of applications is 30% or more, the directions in which the maximum number of times is reached at the measurement point 32 are adjacent to each other in order to determine whether or not the measurement point 32 satisfies the second condition. A process for investigating the appearance frequency of the direction is executed (step S107). Adjacent directions are directions that are adjacent to each other in the circumferential direction.

A method of determining an abnormal point that reflects the frequency of appearance in directions adjacent to each other in the direction of the maximum number of times will be described with reference to FIG. FIG. 10 is an example of a graph showing the frequency distribution of measurement points for each direction measured by the environmental abnormality detection device of the present embodiment, and is the same graph as in FIG. As shown by the broken line in FIG. 10, P4 and P6, which are adjacent to each other in the maximum number of directions P5, are set in adjacent directions.

In the second condition, the determination unit 24 determines whether or not the appearance frequency in the three directions of the maximum number of directions P5 and the adjacent directions P4 and P6 is 50% or more set as the threshold value (step S108). .. In the example shown in FIG. 10, the maximum number of times direction P1 is about 70%, direction P4 is about 10%, direction P5 is about 10%, and the application frequency in three directions is about 90%. It will be judged that the condition of is satisfied.

Return to the flow of FIG. Here, if it is less than 50%, the measurement point 32 is not an abnormal point, and the process proceeds to step S104, and different measurement points 32 of the same detection frame 31 are newly set. The processing after step S105 is executed for the newly set measurement point 32.

In the process of step S108, when the frequency of appearance in the maximum number of directions and the adjacent directions is 50% or more, the strength of the vector at the measurement point is determined in order to determine whether or not the measurement point 32 satisfies the third condition. The process shifts to the process of investigating (step S109). In step S109, the average value of the strength of the vector is created in units of 2 seconds at one measurement point 32.

FIG. 11 is a schematic diagram showing the degree of strength of the vector of the measurement point 32 in the predetermined direction measured by the environmental abnormality detection device 10 of the present embodiment. In FIG. 11, a vector of 3 pixels is shown as the average value of the maximum number of directions P5. In the third condition, 2 pixels are set as a criterion for determining the strength of the maximum number of average vectors. In the present embodiment, the number of pixels as a threshold value is set based on the camera resolution, the distance to the camera 2, and the like.

After creating the average value of the vector of the maximum number of times in step S109, the determination unit 24 determines whether or not the average value of the vector is 2 pixels or more (step S110). Here, if the average value of the vector is less than 2 pixels, the measurement point 32 is not an abnormal point, and the process proceeds to step S104, and different measurement points 32 of the same detection frame 31 are newly set. To. The processing after step S105 is executed for the newly set measurement point 32.

In the process of step S110, when the average value of the vectors is 2 pixels or more, the measurement point 32 is set as an abnormal point, and the information is stored in the storage unit 25. Next, it is confirmed whether or not the calculation of the 25 measurement points 32 in the detection frame 31 is completed (step S111). Here, if the calculation of the 25 measurement points 32 is not completed, the process proceeds to step S104, and different measurement points 32 of the same detection frame 31 are newly set. The processing after step S105 is executed for the newly set measurement point 32.

Return to the flow of FIG. When it is determined in the process of step S111 that the calculation of the 25 measurement points 32 in the detection frame 31 is completed, the determination unit 24 determines whether or not an abnormality has occurred in the monitoring target based on a plurality of conditions. The process proceeds to the process of determination steps S112 to S118. In step S112, a process of investigating the frequency of all the abnormal points in the detection frame 31 for each direction is performed.

First, the abnormal point set at the measurement point 32 will be described with reference to FIG. FIG. 12 is a schematic diagram showing the distribution of abnormal points with respect to the measurement points 32 measured by the environmental abnormality detection device 10 of the present embodiment. The measurement point 32 shown by the white circle 33 in FIG. 12 is the measurement point 32 that was not determined to be an abnormal point, and the measurement point 32 shown by the cross 34 is the measurement point 32 that was determined to be an abnormal point. In this example, 20 measurement points 32 excluding the uppermost 5 measurement points 32 are determined to be abnormal points for 4 seconds.

FIG. 13 is an example of a graph showing the frequency distribution of abnormal points in each direction measured by the environmental abnormality detection device 10 of the present embodiment. FIG. 13 shows the frequency distribution of the measurement points 32 set as abnormal points for each direction. In this example, it can be seen that the maximum number of times at the measurement point 32 set as the abnormal point is the direction P5 inside the broken line frame, and the frequency of appearance is 70%. In the case of the example described with reference to FIG. 12, the data as shown in FIG. 13 is calculated based on the frequency of each direction at the 20 measurement points 32 determined to be abnormal points.

Return to the flow of FIG. The determination unit 24 at the measurement point 32 determined to be an abnormality point in the detection frame 31 in step S113 in order to confirm whether or not the first condition for determining whether or not an abnormality has occurred in the monitoring target is satisfied. It is determined whether or not the appearance frequency in the direction of the maximum number of times is 40% or more set as a threshold value. Here, if it is less than 40%, it means that no abnormality is detected in this time unit, the process proceeds to step S102 for reading a new moving image, and the processes after step S103 are executed for this new moving image.

As in the example of FIG. 13, when the frequency of appearance in the direction of the maximum number of times is 40% or more, in order to confirm whether or not the second condition is satisfied, the maximum number of abnormal points in the detection frame 31 in step S114. A process of investigating the frequency of appearance in adjacent directions in the direction in which the above is obtained is executed (step S113). FIG. 14 is an example of a graph showing the frequency distribution of abnormal points in each direction measured by the environmental abnormality detection device 10 of the present embodiment. It is the same graph as FIG. In the example of FIG. 14, the application frequency is calculated in the three directions P4 to P6 inside the broken line frame.

Return to the flow of FIG. In the present embodiment, the threshold value of the appearance frequency in the three directions is set to 50%, and the determination unit 24 determines whether or not the second condition is satisfied (step S115). Here, when the threshold value of the appearance frequency in the three directions is less than 50%, it means that no abnormality is detected in this time unit. In this case, the process proceeds to step S102 for reading a new moving image, and the processes after step S103 are executed for this new moving image.

When the threshold value of the appearance frequency in the three directions is abnormal by 50% in step S115, the determination unit 24 confirms whether or not the third condition for determining whether or not the monitoring target has an abnormality is satisfied. The process proceeds to step S116.

In step S116, it is determined whether or not the direction in which the maximum number of abnormal points in the detection frame 31 is reached and the direction to be detected set in step S101 match. This determination can also be said to be a third condition for determining whether or not an abnormality has occurred in the monitored object. In the present embodiment, since the direction to be detected in step S101 is set downward, it is determined whether or not the direction in which the maximum number of times is reached is the downward direction P5. If the direction in which the maximum number of times is reached in step S116 matches the direction to be detected (downward), the process proceeds to step S117. In step S117, a process of investigating whether the same state is continued for a continuous time is performed, and information on an abnormal point of the detection frame 31 is acquired twice or more (4 seconds) continuously. If the direction of the maximum number of times at the measurement point 32 set as the abnormal point in step S116 and the set direction to be detected (downward) do not match, the process proceeds to step S102 and the processing after step S103 is performed. Is executed.

The determination unit 24 determines whether or not the same state continues twice (4 seconds) in succession (step S118). As a result of step S118, if the same state continues, it is confirmed that an abnormality has been detected (step S119). If it is determined that the same state is not continued twice in succession (4 seconds), the process proceeds to step S102 for reading a new moving image, and the processes after step S103 are executed for this new moving image.

Through the series of processes described above, it is determined whether or not the debris flow 100 is detected as an abnormality in the detection frame 31. When an abnormality is detected in the detection frame 31, a special color (for example, red) is displayed or blinked in the detection frame 31a on the image on which the debris flow 100 is detected as shown in FIG. The control device 26 performs this.

The environmental abnormality detection device 10 of the present embodiment is a detection frame setting unit 22 that sets a receiving unit 21 that receives an image of an image to be monitored and a detection frame 31 having a plurality of measurement points 32 in a predetermined range in the image. When the flow acquisition unit 23 that acquires the vector of each optical flow of the measurement point 32 and each vector of the measurement point 32 are biased in a specific direction, it is determined as abnormal and not biased in a specific direction. In this case, a determination unit 24 that does not determine an abnormality is provided.

As a result, even if the camera 2 shakes or rains, it becomes a momentary movement and the direction of the vector becomes non-uniform movement, and it can be judged as normal, and when the debris flow 100 occurs, the vector in the same direction (downward). Is generated for a continuous period of time, so that the debris flow 100 can be reliably detected. Further, since the abnormality is detected based on the change from the non-uniform state to the uniform state in the detection frame 31, false detection caused by a person or an animal entering the image can be effectively reduced.

The detection frames 31 of this embodiment are set at a plurality of places.

As a result, a plurality of small frames can be set, so that the user can freely select an arbitrary place to be detected, such as avoiding a place where false detection is likely to occur. In addition, the debris flow 100 can be detected at any place, and the scale (width) of the debris flow 100 can also be expressed. Further, it is not necessary to detect an abnormality in the entire image, and the load on the computer can be reduced.

When the size of the vector measured at the measurement point 32 exceeds a preset threshold value, the determination unit 24 of the present embodiment sets the measurement point 32 as an abnormal point, and the measurement point set as the abnormal point. When the vector of 32 is biased in a specific direction, it is determined to be abnormal.

The effect of setting the reference for determining the magnitude of the vector will be described with reference to FIG. FIG. 15 is a schematic diagram showing an example of detection due to a difference in vector states by the environmental abnormality detection device 10 of the present embodiment. As shown in FIG. 15, in the present embodiment, the flow directions (directions) of the vectors are different in normal times, and it is not determined to be abnormal. Further, even if the flow direction is directed to a certain downward direction due to the influence of rain, it is not determined to be abnormal if the flow velocity is not high. Then, it is determined to be abnormal only when the flow direction is in a certain direction and the flow velocity is large. As a result, the debris flow 100 that produces a large flow can be reliably detected, and the possibility that a small flow such as raindrops is erroneously detected can be further reduced.

In the determination unit 24 of the present embodiment, the vector is biased in a specific direction so that the ratio of the most common direction among the directions of the vectors acquired from each of the measurement points 32 exceeds a preset threshold value. Judge as a case.

As a result, the threshold value can be set according to the position, angle, distance, etc. of the monitoring target and the camera 2, and high detection accuracy according to the environment can be realized. Further, since the determination is made based on the generation rate in continuous time, the threshold value can be set so that the continuous flow of raindrops or the like other than the debris flow 100 is not detected. For example, even if raindrops adhere to the lens of the camera 2 and flow down, even if the vector moves significantly downward, it flows down in a short time, so that a continuous flow does not occur and the generation rate is less than the threshold value. It will not be judged as abnormal. In this way, it is possible to effectively suppress erroneous detection caused by shaking of the camera 2, intrusion of a monitoring target of a person or animal, and temporary movement such as rain.

Although the preferred embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment and can be appropriately modified.

For example, in the above embodiment, the method of setting the direction of the vector acquired by the optical flow technique to any of the eight directions of the directions P1 to P8 has been described, but the method of determining the direction of the vector is not limited to this method. .. The range of the detection frame 31 may be divided by a grid, and the direction of the vector may be determined based on which square of the grid the tip or base end of the optical flow is located.

Although three cameras 2 are shown in FIG. 1 of the above embodiment, the number of cameras 2 is not limited. The number of cameras 2 installed can be appropriately changed depending on the circumstances, such as one, two, four or more.

In the above embodiment, the threshold value of the determination criterion in step S106 is 30% and the threshold value of the determination criterion in step S108 is 50%, or the threshold value of the determination criterion in step S113 is 40% and the determination in step S115. An example in which the reference threshold value is 50% or more is shown, but the numerical value set as the threshold value can be changed as appropriate. Similarly, the frame rate in step S103, the strength of the vector in step S110, the numerical value of the number of consecutive times (continuous time) in step S117, and the like can be appropriately changed. In this way, various reference numerical values may be set empirically or empirically, and are based on the distance and angle of the monitoring target and the shooting point with respect to the monitoring target, the type of abnormality to be detected, and the detection accuracy. May be set. For example, the vector in the state where the debris flow is generated and the state where the debris flow is not generated in the video imaged in advance under the monitoring target is analyzed, and numerical values such as the strength and the ratio of the direction of the vector as the judgment standard are set. May be good.

The setting is not limited to the detection frame 31 and the measurement point 32 shown in the above embodiment. The range and shape of the detection frame 31, the number and arrangement of measurement points 32 set in one detection frame 31 can be changed as appropriate. Further, the display method and the detection accuracy (threshold setting) may be changed depending on the position of the detection frame 31, for example, the upper range 91, the middle range 92, and the lower range 93 in FIG.

In the above embodiment, the state of detecting the debris flow 100 flowing downward is described on the image, but the debris flow 100 flowing in the lateral direction can also be detected. That is, the direction to be detected set in step S101 can be set to a direction other than the downward direction. Further, the directions adjacent to the desired direction may be included. For example, in step S116, if the maximum number of directions is any one of the direction P4, the direction P5, and the direction P6, the flow may be shifted to step S117. Further, in some cases, the step of setting and determining the direction to be detected may be omitted. In this way, the direction to be detected can be appropriately set based on the distance and angle of the monitoring target and the shooting point with respect to the monitoring target, the type of abnormality to be detected, and the detection accuracy, and the direction to be detected as in the above embodiment. Is not limited to the downward direction.

In the above embodiment, the environmental abnormality detection device that detects the debris flow 100 has been described as an example, but the present invention is not limited to this. Since a strong flow in a predetermined direction that does not occur in normal times can be detected as an environmental abnormality, the present invention can also be applied to detect various environmental abnormalities such as landslides other than the debris flow 100.

Next, the difference in detection accuracy between the examples of the present invention and the comparative examples will be described. FIG. 16 is a graph comparing the determination systems of the environmental abnormality detection device of the embodiment of the present invention and the environmental abnormality detection device of the comparative example.

First, an embodiment will be described. The embodiment is the same as the environmental abnormality detection device described in the above embodiment, except that the threshold value of the determination criterion in step S106 is set to 25% instead of 30%. A comparative example will be described. A comparative example is a conventional environmental abnormality detection device that determines an abnormality using a so-called image difference method. In the image difference method of the comparative example, the object moves when the image difference mean value (rtav), which is the average value of the density relative differences in the processing range, exceeds the reference value for determining whether or not the object has moved. Judged as The image difference mean value (rtav) is obtained by the following equation (1) by utilizing the density fast-removal, which is the number of pixels exceeding the image difference threshold.

(Equation 1) Image difference mean value (rtav) = Σ density relative difference / total prime number of processing range

FIG. 16 shows the state of detection and erroneous detection when abnormality detection is performed in each of the examples and the comparative examples for a moving image of a debris flow. As shown in FIG. 16, when a debris flow is detected before the debris flow occurrence time (0 minutes), it is a false detection. In the comparative example using the image difference method, the detected points are indicated by white circles. In the comparative example, erroneous detection occurred 73 times due to raindrops, etc. within 100 minutes before the debris flow occurred, and even after the debris flow occurred, the debris flow was detected intermittently rather than continuously. ..

On the other hand, in the embodiment according to the present invention, the detected points are indicated by black circles. In the embodiment, the false detection is only twice in 100 minutes before the debris flow occurs, and the detection continues normally without interruption after the debris flow occurs. Further, when the threshold value of the determination criterion in step S106 was changed from 25% to 30% and abnormality detection was performed with the same moving image, the number of false detections within 100 minutes was 0. As described above, even in the embodiment, the environmental abnormality detection device according to the present invention can surely reduce the false detection.

10 Environmental abnormality detection device 21 Receiver 22 Detection frame setting unit 23 Flow acquisition unit 24 Judgment unit

Claims (4)

An environmental anomaly detection device that detects anomalies from multiple images that are continuous in time.
A receiver that receives an image of the monitored object and
A detection frame setting unit that sets a detection frame that includes a plurality of measurement points in a predetermined range in the image,
A flow acquisition unit that acquires the vector of each optical flow of the measurement points, and
When the vector of each of the measurement points is biased in a specific direction, it is determined to be abnormal, and when it is not biased in a specific direction, it is not determined to be abnormal.
Environmental anomaly detection device equipped with. The environmental abnormality detection device according to claim 1, wherein the detection frame is set at a plurality of places. The determination unit sets the measurement point as an abnormal point when the magnitude of the vector measured at the measurement point exceeds a preset threshold value.
The environmental abnormality detection device according to claim 1 or 2, wherein when the vector of the measurement point set to the abnormality point is biased in a specific direction, it is determined to be an abnormality. The determination unit
Claim 1 for determining that the vector is biased in a specific direction when the ratio of the most common directions among the directions of the vectors acquired from each of the measurement points exceeds a preset threshold value. The environmental abnormality detection device according to any one of 3 to 3.

Images