CN110855797A - Sheep behavior monitoring system and method based on action recognition - Google Patents

Abstract

The invention discloses a sheep behavior monitoring system based on action recognition, comprising a behavior monitoring terminal and a control terminal; the behavior monitoring terminal is connected with the control terminal through a wireless network; the behavior monitoring terminal includes: a processor, a power supply module, a communication module, a The sensor module; the control terminal includes a PC and control software installed on the PC, and the control terminal is used to analyze the data of multiple behavior monitoring terminals and back up the acquired data. The invention can collect the information of multiple animals at one time, avoiding the problem that the traditional image collection is prone to errors in the collection of group animals; the collection frequency can be modified remotely, the collected data can be compared with the animal behavior analysis database, and the behavior of the animals can be judged; The collected actions can be compared with the high-risk action database, and the animal's high-risk actions can be alarmed.

Description

A sheep behavior monitoring system and method based on motion recognition

technical field

The invention relates to the technical field of animal behavior recognition, in particular to a sheep behavior monitoring system and method based on motion recognition.

Background technique

The current animal behavior recognition generally relies on manual recording, and some rely on machine vision behavior recognition. However, the number of animals detected by these two methods is small, and the cost of machine vision image processing is high.

Patent application number: CN201010140888.0 discloses a method and device for video monitoring of animal behavior in natural environment, through the main control module, camera module, data storage module, adjustable magnetic stimulation module, GPS module and GPRS module, tracking the movement path of animals, automatically According to the motion state of the animal, start/stop video or picture recording, store the observation data, and send the data to the background server.

The patent is based on image acquisition to realize animal behavior monitoring. This method detects a small number of animals and is prone to errors.

SUMMARY OF THE INVENTION

In order to solve the above problems, the present invention provides a sheep behavior monitoring system and method based on motion recognition. The present application solves the drawback that traditional visual behavior recognition cannot record a large number of animals, and the present application utilizes the Kalman dynamic filtering algorithm to quickly solve the problem of animal behavior. Real-time status, collects a lot of behavior information, and can give early warning of abnormal behavior in time.

The purpose of this invention is to realize through the following technical solutions:

A sheep behavior monitoring system based on action recognition, comprising a behavior monitoring terminal and a control terminal; the behavior monitoring terminal is connected with the control terminal through a wireless network; the behavior monitoring terminal includes:

a processor, which is used to quickly solve and process the acquired data through the Kalman dynamic filtering algorithm to obtain the current motion posture of the animal carrier;

a power supply module, the power supply module is used to provide power for each power consumption module in the behavior monitoring terminal;

a communication module, which is used to establish a data link channel with the control terminal and realize remote data transmission;

a sensor module, the sensor module is used for acquiring the angular velocity, acceleration, three-axis Euler angle, three-axis magnetic field, air pressure and altitude information of the animal carrier, and sending the acquired information to the processor;

The control terminal includes a PC and control software arranged on the PC, and the control terminal is used for analyzing the data of multiple behavior monitoring terminals and backing up the acquired data.

Further, it also includes an early warning module, and the early warning module is used to give early warning to the abnormal behavior of the animal carrier.

Further, the power supply module includes a micro button battery or a micro solar panel.

Further, the model of the processor is STM32F103.

Further, the sensor modules are MPU6050 three-axis module and BMP180 barometer module.

A sheep behavior monitoring method, the method comprises:

S1, obtain the data information of the animal carrier, the data information includes speed, acceleration, three-axis Euler angles, three-axis magnetic field, air pressure and altitude information;

S2. Quickly solve and process the acquired data information through the Kalman dynamic filtering algorithm to obtain the current motion posture of the animal carrier;

S3. Determine the behavior of the animal according to the current movement posture of the animal carrier.

Further, in step S3, judging the behavior of the animal according to the current motion posture of the animal carrier specifically includes:

Retrieve animal behavior analysis database;

Compare the current motion posture with the content in the animal behavior analysis database. If there is a similar action, the behavior corresponding to the similar action is taken as the judgment result. If there is no similar action, the animal action is uploaded to the expert database. analyze;

Obtain the analysis results of the expert database, and update the actions and results of the expert analysis to the animal behavior analysis database.

Further, the method also includes alarming the abnormal behavior, specifically including:

Get the current motion posture of the animal;

The current movement posture is compared with the high-risk action database. If the comparison is successful, the control terminal will give an early warning. If the comparison fails, it will be moved to the animal behavior analysis database for comparison.

Further, setting in the monitoring process also includes adjusting the frequency of animal monitoring and analysis.

Further, in the process of setting re-monitoring, it also includes alarming the low-power state of the behavior monitoring terminal.

The beneficial effects of the present invention are:

(1) The present invention can collect multiple animal information at one time, avoiding the problem that the traditional image collection is prone to errors in the collection of group animals;

(2) The present invention can remotely modify the collection frequency, and can compare the collected data with the animal behavior analysis database to judge the behavior of the animal;

(3) The present invention can compare the collected actions with the high-risk action database, and give an alarm to the animal's high-risk actions.

Description of drawings

Fig. 1 is the system structure schematic diagram of the present invention;

2 is a schematic structural diagram of a behavior monitoring terminal of the present invention;

In the figure, 10-behavior monitoring terminal, 11-processor, 12-early warning module, 13-communication module, 14-power supply module, 15-sensor module, 20-control terminal.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In order to make the objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

Example 1:

This embodiment provides a sheep behavior monitoring system based on motion recognition, as shown in FIG. 1 , including a behavior monitoring terminal 10 and a control terminal 20; the behavior monitoring terminal 10 is connected with the control terminal 20 through a wireless network; as shown in FIG. 2 , The behavior monitoring terminal 10 includes:

The processor 11, the processor 11 is used to quickly solve and process the acquired data through the Kalman dynamic filtering algorithm, so as to obtain the current motion posture of the animal carrier;

a power supply module 14, the power supply module 14 is used to provide power for each power consumption module in the behavior monitoring terminal;

A communication module 13, the communication module 13 is used to establish a data link channel with the control terminal and realize remote data transmission;

an early warning module 12, the early warning module 12 is used to give an early warning to the abnormal behavior of the animal carrier;

a sensor module 15, the sensor module 15 is used to acquire the angular velocity, acceleration, three-axis Euler angle, three-axis magnetic field, air pressure and altitude information of the animal carrier, and send the acquired information to the processor 11;

The control terminal 20 includes a PC and control software installed on the PC. The control terminal 20 is used for analyzing the data of multiple behavior monitoring terminals and backing up the acquired data.

Further, the power supply module 14 includes a miniature button battery or a miniature solar panel, the processor 11 is a model of STM32F103, and the sensor module 15 is an MPU6050 triaxial module and a BMP180 barometer module.

The present invention adopts the sensor module 15 worn on the animal, the processor 11 is a low-power MO series, the sensor module 15 is an MPU6050 three-axis module and a BMP180 barometer module, and the MPU6050 three-axis module integrates a high-precision three-axis gyroscope, three-axis Accelerometer, three-axis Euler angle and three-axis magnetic field, the BMP180 barometer module can measure the air pressure, and the air pressure can calculate the altitude data. Through the Kalman dynamic filtering algorithm, the current real-time motion pose can be quickly solved.

Example 2:

On the basis of Embodiment 1, this embodiment includes a sheep behavior monitoring method, and the method includes:

S1, obtain the data information of the animal carrier, the data information includes speed, acceleration, three-axis Euler angles, three-axis magnetic field, air pressure and altitude information;

S2. Quickly solve and process the acquired data information through the Kalman dynamic filtering algorithm to obtain the current motion posture of the animal carrier;

S3. Determine the behavior of the animal according to the current movement posture of the animal carrier.

Further, in step S3, judging the behavior of the animal according to the current motion posture of the animal carrier specifically includes:

Retrieve animal behavior analysis database;

Compare the current motion posture with the content in the animal behavior analysis database. If there is a similar action, the behavior corresponding to the similar action is taken as the judgment result. If there is no similar action, the animal action is uploaded to the expert database. analyze;

Obtain the analysis results of the expert database, and update the actions and results of the expert analysis to the animal behavior analysis database.

Further, the method also includes alarming the abnormal behavior, specifically including:

Get the current motion posture of the animal;

The current movement posture is compared with the high-risk action database. If the comparison is successful, the control terminal will give an early warning. If the comparison fails, it will be moved to the animal behavior analysis database for comparison.

Further, setting in the monitoring process also includes adjusting the frequency of animal monitoring and analysis.

Further, in the process of setting re-monitoring, it also includes alarming the low-power state of the behavior monitoring terminal.

The invention can collect the information of multiple animals at one time, avoiding the problem that the traditional image collection is prone to errors in the collection of group animals; the collection frequency can be modified remotely, and the collected data can be compared with the animal behavior analysis database to judge the behavior of the animals; The collected actions can be compared with the high-risk action database, and the animal's high-risk actions can be alarmed.

The above-mentioned embodiments only represent specific embodiments of the present invention, and the descriptions thereof are specific and detailed, but should not be construed as limiting the patent scope of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can also be made, which all belong to the protection scope of the present invention.

Claims (10)

1. a sheep behavior monitoring system based on action recognition, is characterized in that, comprises behavior monitoring terminal and control terminal; Behavior monitoring terminal is connected with control terminal by wireless network; Described behavior monitoring terminal comprises: a processor, which is used to quickly solve and process the acquired data through the Kalman dynamic filtering algorithm to obtain the current motion posture of the animal carrier; a power supply module, the power supply module is used to provide power for each power consumption module in the behavior monitoring terminal; a communication module, which is used to establish a data link channel with the control terminal and realize remote data transmission; a sensor module, the sensor module is used for acquiring the angular velocity, acceleration, three-axis Euler angle, three-axis magnetic field, air pressure and altitude information of the animal carrier, and sending the acquired information to the processor; The control terminal includes a PC and control software arranged on the PC, and the control terminal is used for analyzing the data of multiple behavior monitoring terminals and backing up the acquired data. 2. A sheep behavior monitoring system based on motion recognition according to claim 1, characterized in that, it further comprises an early warning module, and the early warning module is used to give an early warning to the abnormal behavior of the animal carrier. 3 . The sheep behavior monitoring system based on motion recognition according to claim 1 , wherein the power supply module comprises a micro button battery or a micro solar panel. 4 . 4 . The sheep behavior monitoring system based on motion recognition according to claim 1 , wherein the model of the processor is STM32F103. 5 . 5 . A sheep behavior monitoring system based on motion recognition according to claim 1 , wherein the sensor modules are MPU6050 triaxial modules and BMP180 barometer modules. 6 . 6. A method for monitoring sheep behavior based on claim 1 to claim 5, wherein the method comprises: S1, obtain the data information of the animal carrier, the data information includes speed, acceleration, three-axis Euler angles, three-axis magnetic field, air pressure and altitude information; S2. Quickly solve and process the acquired data information through the Kalman dynamic filtering algorithm to obtain the current motion posture of the animal carrier; S3. Determine the behavior of the animal according to the current movement posture of the animal carrier. 7. a kind of sheep behavior monitoring method based on motion recognition according to claim 6, is characterized in that, in step S3, according to the current motion posture of animal carrier, the behavior of judging animal specifically comprises: Retrieve animal behavior analysis database; Compare the current motion posture with the content in the animal behavior analysis database. If there is a similar action, the behavior corresponding to the similar action is taken as the judgment result. If there is no similar action, the animal action is uploaded to the expert database. analyze; Obtain the analysis results of the expert database, and update the actions and results of the expert analysis to the animal behavior analysis database. 8. a kind of sheep behavior monitoring method based on motion recognition according to claim 6-7, is characterized in that, described method also comprises alarming abnormal behavior, specifically comprises: Get the current motion posture of the animal; The current movement posture is compared with the high-risk action database. If the comparison is successful, the control terminal will give an early warning. If the comparison fails, it will be moved to the animal behavior analysis database for comparison. 9 . The method for monitoring sheep behavior based on motion recognition according to claim 6 , wherein setting in the monitoring process further comprises adjusting the frequency of animal monitoring and analysis. 10 . 10 . The method for monitoring sheep behavior based on motion recognition according to claim 6 , wherein, in the process of setting and re-monitoring, it also includes alarming the low battery state of the behavior monitoring terminal. 11 .

Images