JP6573827B2 - Animal tract estimation method, animal tract estimation program, and animal tract estimation apparatus - Google Patents

Description

  The present invention relates to a zodiac estimation method, a zodiac estimation program, and a zodiac estimation device.

  In recent years, a lot of agricultural damage due to bird and animal damage has occurred, and it has become a life and death problem for agricultural workers unless extermination measures are taken. Therefore, the national government and prefectures are promoting countermeasures, and municipalities and hunting associations are implementing extermination activities in cooperation with grants.

  As a method of extermination, it is common to install firewood. In the installation of the fence, after the investigation of the approach road and traces by the reconnaissance (actually go to the place to investigate) by the capture workers (hunting association, hunter, local officials, etc.) An installation location that is considered appropriate is identified. If it is possible to identify the animal path through which the animals to be exterminated pass frequently, it will be easier to determine the effective installation position of the kite, but the scope and timing that can be investigated by reconnaissance are limited, and it is not easy to identify the animal path. For this reason, it is not always possible to specify an effective installation position, and movement of the installation location after the installation of the eaves also occurs, requiring a lot of work and labor. Furthermore, recently, hunters and the like have been declining year by year due to aging, and extermination activities have not stopped.

  On the other hand, there is a disclosure of a passage detector that automatically detects the passage state of an animal even at night in a tunnel for wild animals or a beast road (Patent Document 1, etc.). Further, there is a disclosure of a wildlife detection sensor device that can detect wildlife and record the frequency of using a animal path or the like and moving in a predetermined space in the forest together with information such as date and time (Patent Document 2, etc.) ).

JP-A-11-306313 JP 2007-155389 A

  As described above, it is effective to specify the animal path to efficiently perform the work of installing the cage, but conventionally, it is limited to recording the passage of animals at a fixed point, and the animal path is specified. I couldn't.

  Therefore, in one aspect, an object is to automatically identify the animal path.

In one embodiment, data including the detection date and time of the passage of the animal by a plurality of sensors that perform detection operations when the animal passes in the vicinity is registered, and the detection date and time are continuously adjacent from the plurality of registered data. And calculating the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group, and each data in the data group The computer executes a process of calculating a correlation coefficient value between the detection date and time and the distance, and specifying a data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group.

  The animal path can be automatically identified.

It is a figure which shows the structural example of the system concerning one Embodiment. It is a figure which shows the example of a sensor. It is a figure which shows the software structural example of a server apparatus. It is a figure which shows the data structure example of various databases. It is a figure which shows the hardware structural example of a server apparatus. It is a flowchart which shows the process example of embodiment. It is a figure which shows the example of movement route creation. It is a figure which shows the example of movement route evaluation. It is FIG. (1) which shows the example of a movement route. It is FIG. (2) which shows the example of a movement route. It is a figure which shows the example of a animal path determination.

  Hereinafter, preferred embodiments of the present invention will be described.

<Configuration>
FIG. 1 is a diagram illustrating a configuration example of a system according to an embodiment. In FIG. 1, sensors 1 are installed at various places where an animal to be exterminated may appear. The sensor 1 performs a detection operation when an animal passes in the vicinity of the sensor 1, determines an animal species (large, medium, small, etc.) based on body height, weight, etc., and relays it by a communication function such as a low-power radio. It has a function of transmitting a detection signal to the device 2. The detection signal includes a sensor ID for identifying the sensor 1 and animal species information. The installation position of each sensor 1 is registered in advance on the server device 3 side. For registration of the installation position, position information is measured with a mobile terminal equipped with a GPS (Global Positioning System) function brought into the installation position of the sensor 1, and the sensor ID and the position information are notified from the mobile terminal to the server device 3. Can be done. Alternatively, the sensor 1 itself may have a GPS function, and the sensor ID and position information may be registered from the sensor 1 to the server device 3 at an appropriate timing.

  FIG. 2 is a diagram illustrating an example of the sensor 1. FIG. 2A shows a pyroelectric infrared sensor 12 that reacts to infrared rays emitted from animals at different heights of the support column 11 so that the body height can be discriminated simultaneously with the passage of the animals.

  FIG. 2 (b) is provided with a mat sensor 13 so that the body weight can be measured simultaneously with the passage of the animal. The mat sensor 13 can also detect the ground contact position of the animal's foot. In this case, the animal type (size, animal name, etc.) is determined from the distance between the four legs, the stride length, the walking speed, etc. Can also be determined.

  Returning to FIG. 1, the repeater 2 has a function of transmitting (transferring) a detection signal to the server device 3 through a wireless digital line or the like when a detection signal is received from the sensor 1 by low-power radio or the like. In addition, as a communication function of the sensor 1, when the wireless power of the level which can communicate directly with the server apparatus 3 can be given, the repeater 2 can also be abbreviate | omitted. The repeater 2 has a GPS function, and the position information of the repeater 2 is managed on the server device 3 side as representative position information of an area where a plurality of sensors 1 to be relayed are installed.

  When the server apparatus 3 receives the detection signal from the sensor 1 via the repeater 2, the server apparatus 3 accumulates the detection result data, and performs the animal path estimation based on the accumulated detection result data at a predetermined timing. The result is output (notified) to a terminal device 4 such as a PC (Personal Computer) or a mobile terminal device 5 such as a smartphone.

  FIG. 3 is a diagram illustrating a software configuration example of the server device 3. In FIG. 3, the server device 3 includes, as functional means realized by software (computer program), a detection reception unit 31, a movement route creation unit 32, a movement route evaluation unit 33, a animal path determination unit 34, and a animal path output unit 35. And. In addition, as a means for holding data (information) to be referred to / updated at the time of processing, a sensor position database DB1, a detection result database DB2, a travel route database DB3, and a travel route evaluation result database DB4 are provided.

  FIG. 4 is a diagram showing examples of data structures of various databases. In FIG. 4, the sensor position database DB1 is a database for managing the installation position of the sensor 1, and has items such as “sensor ID” and “position”. “Sensor ID” is information for identifying the sensor 1. “Position” is the coordinates (latitude, longitude, etc.) of the installation position of the sensor 1. In addition, although the database which manages the position of the repeater 2 exists separately, since it is not used for animal path estimation, illustration is abbreviate | omitted.

  The detection result database DB2 is a database that accumulates information of detection signals received from the sensor 1, and includes items such as “detection date and time (reception date and time)” “sensor ID” and “animal species”. “Detection date and time (reception date and time)” is the date and time when the passage of the animal is detected, and the date and time when the server device 3 receives the detection signal from the sensor 1 is used instead. “Sensor ID” is information for identifying the sensor 1 that has performed detection. The “animal species” is the type (large, medium, small, etc.) of the animal that has detected passage.

  The movement route database DB3 is a database that holds a detection data group extracted as a series of movement routes in which detection dates and times are close to each other for each species, and includes “route ID” “detection date” “sensor ID” “ It has items such as “distance from first detection”. “Route ID” is information for identifying a travel route. “Detection date and time” is the date and time when the passage of the animal is detected. “Sensor ID” is information for identifying the sensor 1 that has performed detection. “Distance from first detection” is a distance from the installation position of the sensor corresponding to the first data of the data group constituting the movement route to the installation position of the sensor corresponding to each data in the data group. This distance assumes a linear distance obtained from coordinates.

  The travel route evaluation result database DB4 is a database that holds the results of evaluation of travel routes, and includes items such as “route ID”, “sensor ID string”, and “correlation coefficient value”. “Route ID” is information for identifying a travel route. The “sensor ID column” is a list of sensor IDs of the sensors 1 included in the travel route. The “correlation coefficient value” is a value indicating the correlation between the detection date and time of the data group constituting the moving route and the distance, and indicates an evaluation value as a beast path.

  Returning to FIG. 3, the detection receiving unit 31 has a function of receiving a detection signal from the sensor 1 via the repeater 2 and registering information of the detection signal in the detection result database DB2. The movement route creation unit 32 has a function of extracting a movement route based on the data accumulated in the detection result database DB2 and the data of the sensor position database DB1.

  The travel route evaluation unit 33 has a function of performing evaluation as a beast path by calculating a correlation coefficient value between the detection date and distance for each of the travel routes extracted by the travel route creation unit 32. The animal road determination unit 34 has a function of determining a movement route estimated as a animal road from the correlation coefficient value of the movement route and the appearance frequency. The animal road output unit 35 has a function of outputting the movement route of the animal road determined by the animal road determination unit 34 to the outside (the terminal device 4, the mobile terminal device 5, etc.).

  FIG. 5 is a diagram illustrating a hardware configuration example of the server device 3. 5, the server device 3 includes a CPU (Central Processing Unit) 302, a ROM (Read Only Memory) 303, a RAM (Random Access Memory) 304, and an NVRAM (Non-Volatile Random Access Memory) 305 connected to a system bus 301. It has. The server device 3 includes an I / F (Interface) 306, an I / O (Input / Output Device) 307, an HDD (Hard Disk Drive) / flash memory 308, a NIC (Network Interface) connected to the I / F 306. Card) 309, a monitor 310 connected to the I / O 307, a keyboard 311, a mouse 312 and the like. A CD / DVD (Compact Disk / Digital Versatile Disk) drive or the like can be connected to the I / O 307.

  The functions of the server device 3 described with reference to FIG. 3 are realized by executing a predetermined program in the CPU 302. The program may be acquired via a recording medium, may be acquired via a network, or may be incorporated in a ROM.

<Operation>
The sensor 1 installed in each position transmits a detection signal when it detects the passage of an animal. When the detection signal is received by the server device 3 via the repeater 2, the detection reception unit 31 registers information on the detection signal in the detection result database DB2.

  The subsequent processing will be described with reference to the flowchart of FIG. In FIG. 6, the movement route creation unit 32 reads the detection result data accumulated from the detection result database DB2, and creates time-series data sorted for each animal species (step S1). FIG. 7A shows an example of time-series data for animal species: large. Note that the date of the detection date and time is not shown.

  Next, returning to FIG. 6, the moving route creation unit 32 recognizes the continuous data within a predetermined time (for example, 10 minutes) as a continuous data group, focusing on the detection date and time of the time series data. Take out (step S2). In FIG. 7A, detection date and time: between 2:27 53 "and detection date and time: 3:04 12", detection date and time: between 3:25 24 "and detection date and time: 3:57 30", detection date and time: There is a time interval between 3:57 30 "and detection date: 4:16 12", detection date: 4:30 01 "and detection date: 5:04 12" Regardless, detection date and time: 3:04 12 "to detection date and time: 3:25 24" and detection date and time: 4:16 12 "detection date and time: 4:30 01" are extracted as a continuous data group.

  Next, returning to FIG. 6, the movement route creation unit 32 refers to the sensor position database DB1 for the distance (distance of the sensor installation position) from the first detection point (the first data in a series of data groups) of each point. (Step S3). FIG. 7B shows a state in which the calculated distance is added to each point of the extracted data group.

  Next, returning to FIG. 6, the movement route creation unit 32 excludes the non-movable data from the first detection point as noise data (step S4). For example, data exceeding a predetermined distance (for example, animal species: 1000 m for large) predetermined for each animal species is removed. In FIG. 7B, detection date and time: 3:04 21 "distance: 2450, detection date and time: 3:14 17" distance: 1920, detection date and time: 4:17 34 "distance: 1650, detection Date: 4:23 09 "distance: 3600 and detection date: 4:24 56" distance: 2970 data is removed. Time series data after removal is shown in Fig. 7C. Noise As a result of removing the data, when the detection date and time of the preceding and succeeding data exceeds a predetermined time for determining as a continuous data group, the data may be left as it is, or the movement route may be divided.

  As shown in FIG. 7D, the time-series data after removing the noise data is registered in the moving route database DB3 by adding a unique route ID to a continuous data group.

  Next, returning to FIG. 6, the travel route evaluation unit 33 calculates a correlation coefficient value between the detection date and distance and the distance for each of the travel routes extracted by the travel route creation unit 32 (step S5). The calculated correlation coefficient value is registered in the travel route evaluation result database DB4 together with the route ID and sensor ID string.

  FIG. 8 shows an example of evaluation based on the movement route data of FIG. The movement route of the route ID: R001 indicates movement as indicated by a bold line with respect to the arrangement of the sensors 1 “a”, “b”,... As shown in FIG. Further, for example, as shown in FIG. 10, the movement route of the route ID: R002 indicates movement as indicated by a thick line with respect to the arrangement of the same sensor 1. Here, since the animal path to be obtained by estimation is generally the main route through which animals move between mountains and villages (fields), it is not a route that tricks a part as shown in FIG. A route that moves in substantially one direction at a substantially constant speed is desirable.

  Returning to FIG. 8, in the route that moves in substantially one direction at a substantially constant speed, the distance changes linearly with respect to the time, so the moving route evaluation unit 33 calculates the phase calculated by the following equation, for example. It can be evaluated as more appropriate when the relational value is high. The meaning of each symbol is as shown in FIG.

  In the example shown in the figure, the correlation coefficient value of the movement route with the route ID: R001 is calculated as “0.24”, and the correlation coefficient value of the movement route with the route ID: R002 is calculated as “0.87”. The travel route is more likely to be a beast path.

  Next, returning to FIG. 6, the animal path determination unit 34 determines that the route having the point sequence having the highest appearance frequency among the route groups having the correlation coefficient value equal to or higher than the predetermined threshold is the animal path (step S <b> 6). The appearance frequency is the number of times the same travel route has appeared within a predetermined period in the past. FIG. 11 is an example in which the vertical axis indicates the route ID and the sensor ID column, the horizontal axis indicates the appearance frequency, and the appearance frequency is arranged in descending order. For example, the moving route indicated by the route ID having the highest appearance frequency is the beast. Judge the road. Note that a threshold value may be set for the appearance frequency, and a plurality of moving routes exceeding a predetermined threshold value may be determined as the animal path.

  Next, returning to FIG. 6, the animal road output unit 35 outputs the movement route determined to be the animal road to the outside (the terminal device 4, the mobile terminal device 5, etc.) (step S 7). Although various output forms exist, a sensor ID string may be output, a position coordinate string may be output, or a movement route may be output on a map.

<Summary>
As described above, according to the present embodiment, the animal path can be automatically specified, and it is possible to contribute to the efficiency of the installation of the cage and the promotion of the extermination measures.

  In the above, it demonstrated by preferred embodiment. While specific embodiments have been illustrated and described herein, it will be apparent that various modifications and changes may be made thereto without departing from the broad spirit and scope as defined in the claims. . That is, it should not be construed as being limited by the details of the specific examples and the accompanying drawings.

Regarding the above description, the following items are further disclosed.
(Appendix 1)
Register data including detection date and time by multiple sensors,
Take out a data group in which detection dates and times are continuous from a plurality of registered data,
Calculate the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group,
Calculating the correlation coefficient value of the detection date and distance of each data in the data group,
Identify the data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group,
A method for estimating a beast tract, wherein a computer executes processing.
(Appendix 2)
The data includes information on animal species detected by the sensor,
The processing for the data group is performed for each animal species.
The method for estimating a canine tract according to supplementary note 1, wherein:
(Appendix 3)
Before the process of calculating the correlation coefficient value of the distance, the data exceeding a predetermined distance is removed from the installation position of the sensor corresponding to the first data of the data group,
The method for estimating a canal tract according to appendix 1 or 2, characterized by:
(Appendix 4)
The process of identifying the data group corresponding to the animal path identifies the data group with which the correlation coefficient value exceeds a predetermined threshold and the appearance frequency is highest.
The method for estimating the animal tract according to any one of appendices 1 to 3, characterized in that:
(Appendix 5)
Register data including detection date and time by multiple sensors,
Take out a data group in which detection dates and times are continuous from a plurality of registered data,
Calculate the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group,
Calculating the correlation coefficient value of the detection date and distance of each data in the data group,
Identify the data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group,
Beast tract estimation program characterized by causing a computer to execute processing.
(Appendix 6)
The data includes information on animal species detected by the sensor,
The processing for the data group is performed for each animal species.
6. The animal tract estimation program according to appendix 5, wherein
(Appendix 7)
Before the process of calculating the correlation coefficient value of the distance, the data exceeding a predetermined distance is removed from the installation position of the sensor corresponding to the first data of the data group,
The animal tract estimation program according to appendix 5 or 6, characterized in that:
(Appendix 8)
The process of identifying the data group corresponding to the animal path identifies the data group with which the correlation coefficient value exceeds a predetermined threshold and the appearance frequency is highest.
The animal tract estimation program according to any one of appendices 5 to 7, characterized in that:
(Appendix 9)
Means for registering data including detection date and time by a plurality of sensors;
Means for extracting a data group in which detection dates and times are adjacent to each other from a plurality of registered data;
Means for calculating the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group;
Means for calculating a correlation coefficient value of the detection date and distance of each data in the data group;
Means for identifying a data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group;
A beast tract estimation device characterized by comprising:
(Appendix 10)
The data includes information on animal species detected by the sensor,
The processing for the data group is performed for each animal species.
The animal tract estimation apparatus according to appendix 9, characterized by:
(Appendix 11)
Before the process of calculating the correlation coefficient value of the distance, the data exceeding a predetermined distance is removed from the installation position of the sensor corresponding to the first data of the data group,
The animal tract estimation apparatus according to appendix 9 or 10, characterized in that.
(Appendix 12)
The means for identifying the data group corresponding to the animal path identifies the data group with which the correlation coefficient value exceeds a predetermined threshold and the appearance frequency is highest.
The animal tract estimation device according to any one of appendices 9 to 11, characterized in that:

DESCRIPTION OF SYMBOLS 1 Sensor 11 Support | pillar 12 Infrared sensor 13 Matt sensor 2 Repeater 3 Server apparatus 31 Detection receiving part 32 Movement route creation part 33 Movement route evaluation part 34 Animal path determination part 35 Animal path output part DB1 Sensor position database DB2 Detection performance database DB3 Movement Route database DB4 Travel route evaluation result database 4 Terminal device 5 Mobile terminal device

Claims (6)

Register data including the detection date and time of the passage of animals by multiple sensors that perform detection operations when an animal passes in the vicinity ,
Take out a data group in which detection dates and times are continuous from a plurality of registered data,
Calculate the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group,
Calculating the correlation coefficient value of the detection date and distance of each data in the data group,
Identify the data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group,
A method for estimating a beast tract, wherein a computer executes processing. The data includes information on animal species detected by the sensor,
The processing for the data group is performed for each animal species.
The method for estimating the animal tract according to claim 1. Before the process of calculating the correlation coefficient value of the distance, the data exceeding a predetermined distance is removed from the installation position of the sensor corresponding to the first data of the data group,
The method for estimating the animal tract according to claim 1 or 2. The process of identifying the data group corresponding to the animal path identifies the data group with which the correlation coefficient value exceeds a predetermined threshold and the appearance frequency is highest.
The method for estimating the animal tract according to any one of claims 1 to 3. Register data including the detection date and time of the passage of animals by multiple sensors that perform detection operations when an animal passes in the vicinity ,
Take out a data group in which detection dates and times are continuous from a plurality of registered data,
Calculate the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group,
Calculating the correlation coefficient value of the detection date and distance of each data in the data group,
Identify the data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group,
Beast tract estimation program characterized by causing a computer to execute processing. Means for registering data including the detection date and time of the passage of an animal by a plurality of sensors that perform detection operations when the animal passes in the vicinity ;
Means for extracting a data group in which detection dates and times are adjacent to each other from a plurality of registered data;
Means for calculating the distance from the installation position of the sensor corresponding to the first data of the data group to the installation position of the sensor corresponding to each data in the data group;
Means for calculating a correlation coefficient value of the detection date and distance of each data in the data group;
Means for identifying a data group corresponding to the animal path from the correlation coefficient value and the appearance frequency of the data group;
A beast tract estimation device characterized by comprising:

Images