CN111144276B - Monitoring and early warning method for pasture - Google Patents
Monitoring and early warning method for pasture Download PDFInfo
- Publication number
- CN111144276B CN111144276B CN201911350715.9A CN201911350715A CN111144276B CN 111144276 B CN111144276 B CN 111144276B CN 201911350715 A CN201911350715 A CN 201911350715A CN 111144276 B CN111144276 B CN 111144276B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- early warning
- area
- animal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The invention provides a monitoring and early warning method for a pasture, which comprises the steps that a time of flight (TOF) camera shoots an environment image of a first monitoring area of a frame of pasture according to an image acquisition instruction, and three-dimensional point cloud data is generated and sent to a monitoring processor; the monitoring processor carries out denoising processing on the three-dimensional point cloud data, extracts characteristic data and counts the characteristic data to obtain the number of animals in a first monitoring area; the monitoring processor analyzes and calculates the intensity data of the de-noised three-dimensional point cloud data, and performs pasture area calculation processing according to the extracted image edge data to obtain an area estimation value of a pasture; the monitoring processor calculates the ratio of the number of the animals to the estimated area value of the pasture to obtain a first livestock ratio, and when the monitoring processor judges that the first livestock ratio exceeds a first preset livestock ratio, the monitoring processor generates a first early warning message according to the first livestock ratio and the data in a preset range interval; and sending the first early warning message to first early warning terminal equipment corresponding to the first monitoring area ID for outputting the first early warning message.
Description
Technical Field
The invention relates to the field of data processing, in particular to a monitoring and early warning method for a pasture.
Background
In China, animal husbandry has been developed for thousands of years, and has gradually developed from a laggard nomadic breeding mode to a modern semi-modern breeding mode. Particularly, with the introduction of various new raising techniques and management methods in recent years, domestic animal husbandry is greatly developed, and leap-over progress is made in the aspects of breeding, disease prevention and treatment, feed refinement and the like, but the backward production mode of small scale and scattered household management is not fundamentally changed, mainly because the large-scale pasture raising management difficulty is high, and the cost of the mainstream half-house, housing and other modes is too high.
The large-scale natural pasture is available in northern China such as Nemeng and the like, and is very suitable for field grazing of herds, so that the breeding cost can be reduced, the quality of breeding products can be improved by using natural feed, however, due to the wide open environment of the pasture, a large amount of manual intervention is needed for animal distribution, drainage and the like of the pasture, and the labor cost is also increased. With the development of informatization counting, it is possible to adopt modern monitoring and management means to carry out intelligent real-time monitoring and early warning on the grazing condition of a herd in a field pasture so as to reduce the labor cost.
Disclosure of Invention
Aiming at the defects of the prior art, the embodiment of the invention aims to provide a monitoring and early warning method for a pasture. The system is used for monitoring the monitoring area of the pasture in the natural pasture, analyzing the monitoring data, and sending out early warning information to the monitoring terminal of the monitoring area when the livestock ratio of the monitoring area exceeds a preset livestock ratio so as to prompt a pasture manager to reasonably distribute animals.
In order to realize the method, the invention provides a monitoring and early warning method for a pasture, which comprises the following steps:
the method comprises the steps that a time of flight (TOF) camera shoots an environment image of a first monitoring area of a pasture according to an image acquisition instruction to generate three-dimensional point cloud data; wherein the TOF camera has a camera ID;
the TOF camera sends the three-dimensional point cloud data and the camera ID to a monitoring processor;
the monitoring processor carries out denoising processing on the three-dimensional point cloud data to obtain denoised three-dimensional point cloud data;
the monitoring processor extracts feature data of the de-noised three-dimensional point cloud data based on an animal feature data model to obtain animal feature three-dimensional point cloud data, and stores the animal feature three-dimensional point cloud data in an animal feature data list;
the monitoring processor counts the animal characteristic three-dimensional point cloud data in the animal characteristic data list to obtain the number of animals in the first monitoring area;
the monitoring processor performs color classification on the intensity data of the de-noised three-dimensional point cloud data by using a k-means algorithm to obtain a green classification interval;
the monitoring processor captures the intensity data of the de-noised three-dimensional point cloud data according to the green classification interval, and performs binarization processing on the captured intensity data to obtain binarized image data;
the monitoring processor extracts image edge data from the binarized image data;
the monitoring processor calculates and processes the pasture area according to the image edge data to obtain an area estimated value of the pasture;
the monitoring processor calculates the ratio of the number of the animals to the area estimated value of the pasture to obtain a first animal volume ratio, and the first animal volume ratio is stored in a monitoring data list; wherein the monitoring data list includes a first camera ID, a first monitoring area ID, and a first animal-volume ratio;
when the monitoring processor judges that the first animal volume ratio exceeds a first preset animal volume ratio, the monitoring processor generates a first early warning message according to the first animal volume ratio and preset range interval data;
and the monitoring processor sends the first early warning message to first early warning terminal equipment corresponding to a first monitoring area ID for outputting the first early warning message.
Preferably, the monitoring and early warning method further includes:
the monitoring processor searches in a monitoring data list according to the animal volume ratio, and determines a second animal volume ratio and a second monitoring area ID, wherein the animal volume ratio is smaller than a second preset animal volume ratio;
the monitoring processor generates a drainage prompt message according to the first animal volume ratio, the second animal volume ratio, the first monitoring area ID and the second monitoring area ID;
and the monitoring processor sends the drainage prompt message to a first early warning terminal device corresponding to the first monitoring area ID for displaying and outputting a drainage prompt.
Preferably, the first early warning message includes an early warning level, and the step of generating the first early warning message by the monitoring process according to the first animal volume ratio and the preset range interval data specifically comprises:
the monitoring processor determines a range interval of the first animal volume ratio and determines an early warning level according to the range interval;
and the monitoring processor generates an early warning message according to the early warning level.
Preferably, after the monitoring processor counts the animal feature three-dimensional point cloud data in the animal feature data list to obtain the number of animals in the first monitoring area, the monitoring and early warning method further comprises:
the monitoring processor generates drinking control instructions according to the animal number and sends the drinking control instructions to drinking control equipment;
and the drinking water control equipment controls the water quantity of the drinking water equipment according to the drinking water control instruction.
Preferably, the monitoring and early warning method further includes:
the monitoring processor counts the animal volume ratio corresponding to each monitoring area ID in the monitoring data list at a first preset time, and generates statistical histogram data;
and the monitoring processor sends the statistical histogram to the early warning terminal equipment for displaying and outputting.
Preferably, before the monitoring processor sends the first warning message to a first warning terminal device corresponding to a first monitoring area ID, the method further includes:
the first early warning terminal equipment establishes communication connection with the monitoring processor according to the first terminal ID;
the monitoring processor establishes a corresponding relationship between the first terminal ID and the first monitoring area ID.
Preferably, before the time of flight TOF camera acquires an environmental image of a first monitored area of a pasture according to image acquisition instructions, the method further comprises:
the monitoring processor receives a monitoring starting command and generates the image acquisition instruction according to a preset time interval;
the monitoring processor sends the image acquisition instructions to the TOF camera.
The embodiment Of the invention provides a monitoring and early warning method for a pasture, which is characterized in that a Time Of Flight (TOF) camera arranged in each monitoring area in the pasture shoots an image Of a breeding environment Of the monitoring area, generates three-dimensional point cloud data and sends the three-dimensional point cloud data to a monitoring processor. The monitoring processor performs denoising processing on the three-dimensional point cloud data, then performs characteristic data extraction and counting to obtain the number of animals in the monitoring area, performs area calculation on a pasture of the monitoring area to obtain an area estimated value, and further calculates the ratio of the number of the animals to the area estimated value to obtain the livestock-volume ratio of the monitoring area. And the monitoring processor judges the animal volume ratio, and when the animal volume ratio exceeds the preset animal volume ratio, the monitoring processor sends an early warning message to the early warning terminal equipment corresponding to the monitored area. Furthermore, the method provided by the embodiment of the invention can automatically control the drinking water equipment in the monitoring area according to the number of the animals obtained by analysis, so that the drinking water equipment can provide a proper amount of drinking water for the animals in the area. The method provided by the embodiment of the invention can automatically monitor and early warn the pasture without being influenced by the external illumination condition, thereby improving the timeliness of early warning and greatly reducing the labor cost of pasture management.
Drawings
Fig. 1 is a flowchart of a monitoring and early warning method for a pasture according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be further noted that, for the convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The invention discloses a monitoring and early warning method for a pasture, which is used in a natural pasture or an artificial pasture. Fig. 1 is a flowchart of a monitoring and early warning method for a pasture according to an embodiment of the present invention. As shown, the method comprises the following steps:
Specifically, the TOF camera is disposed in each monitoring area of the pasture, and is fixedly disposed on any fixed object capable of fixing the camera in the pasture, such as a special pole or a fixed position of a pasture. TOF is used for shooing the breed environment of surveillance area, and TOF camera's shooting angle and setting height can be adjusted according to its surveillance area's scope, make TOF camera can shoot clear complete surveillance area's breed environment image. Wherein the TOF camera has a camera ID.
And the TOF camera receives a monitoring data acquisition instruction to shoot an environment image of the monitoring area, and the environmental information of the acquired image is analyzed and processed by a processing unit of the TOF camera to generate three-dimensional point cloud data.
In a preferred scheme of the embodiment of the invention, before the time of flight TOF camera acquires the environmental image of the first monitoring area of the pasture according to the image acquisition instruction, the control processor receives the monitoring start command, generates the image acquisition instruction according to the preset time interval, and sends the image acquisition instruction to the TOF camera. That is to say, when the monitoring and early warning method provided by the embodiment of the present invention needs to be started, a pasture manager inputs a monitoring start command on an interactive interface of the monitoring processor or sends a monitoring start instruction to the monitoring processor through other external devices. The monitoring processor receives the monitoring starting instruction and then reads a preset time interval stored in the storage unit, namely the shooting frequency of the TOF camera, such as 5 minutes or 1 minute, and the preset time interval can be set by a pasture manager according to the breeding environment and the breeding condition of a pasture. And the monitoring processor generates an image acquisition instruction according to a preset time interval and sends the image acquisition instruction to the TOF camera.
In the preferred scheme of the embodiment of the invention, the adopted TOF camera transmits the optical signal through the built-in laser emission module and acquires the distance field depth data of the three-dimensional scene through a built-in Complementary Metal Oxide Semiconductor (CMOS) pixel array, the imaging rate can reach hundreds of frames per second, and meanwhile, the structure is compact and the power consumption is low. The three-dimensional data acquisition mode for the target scene is as follows: TOF cameras use an amplitude modulated light source that actively illuminates the target scene and is coupled to an associated sensor that is locked onto each pixel of the same frequency. The emission light of the built-in laser emission and the reflected light emitted after the emission light irradiates on the scene object have phase shift, and multiple measurements are obtained by detecting different phase shift amounts between the emission light and the reflected light. The amplitude modulation of the built-in laser transmitter is in the modulation frequency interval of 10-100MH, while the frequency controls the TOF camera sensor depth range and depth resolution. Meanwhile, a processing unit of the TOF camera independently executes phase difference calculation on each pixel to obtain depth data of a target scene, the processing unit of the TOF camera analyzes and calculates the reflection intensity of the reflected light to obtain intensity data of the target scene, and the intensity data is combined with the acquired two-dimensional data to perform analysis processing to obtain three-dimensional point cloud data of the target scene.
In a specific example of the embodiment of the present invention, the TOF camera uses a solid-state laser or an LED array as a built-in laser transmitter that transmits light waves with a wavelength around 850 nm. The emitting light source is continuous square wave or sine wave obtained by continuous modulation. The TOF camera processing unit obtains intensity data by calculating phase angles of emitted light and reflected light in a plurality of sampling samples and distances of target objects, analyzing and calculating current intensity converted by reflected light intensity, and then performing fusion processing by combining two-dimensional image data obtained by the optical camera to obtain three-dimensional point cloud data of a target scene.
In the process of collecting the culture environment image of the monitored area, due to the fact that scene shooting is carried out through non-visible light actively emitted by the TOF camera, clear three-dimensional point cloud data of the environment image of the monitored area can be obtained even under the dark condition. Therefore, the method provided by the embodiment of the invention is also suitable for use in night or dark environment with poor lighting state or even without lighting.
In step 102, the TOF camera sends the three-dimensional point cloud data and the camera ID to a monitoring processor.
Specifically, each TOF camera stores a camera ID, and each TOF camera ID corresponds to a monitoring area ID of a monitoring area to which the camera ID belongs. The TOF camera sends the generated three-dimensional point cloud data and the camera ID to the monitoring processor, so that the monitoring processor can determine which TOF camera collects the three-dimensional point cloud data when receiving the three-dimensional point cloud data, and then the monitoring area ID can be determined according to the corresponding relation.
And 103, denoising the three-dimensional point cloud data by the monitoring processor to obtain denoised three-dimensional point cloud data.
Specifically, the monitoring processor selects a specific filtering mode to filter the received three-dimensional point cloud data, and removes noise in the three-dimensional point cloud data. The three-dimensional point cloud data is subjected to filtering processing using, for example, the following method:
in the embodiment of the invention, the resolution ratio of the TOF camera is M multiplied by N (both M and N are positive integers), so that one frame of three-dimensional point cloud data acquired by the TOF camera has M multiplied by N pixel points, and each pixel point further comprises X, Y and Z three-dimensional coordinate values. Wherein, the TOF camera is used for converting original depth data to three-dimensional point cloud data required by people: firstly, carrying out preliminary correction and temperature calibration on original depth data; secondly, distortion correction processing is carried out on the image; thirdly, converting the depth image coordinate system (x 0, y0, z 0) into a camera coordinate system (x 1, y1, z 1), and converting the depth information on the image into a three-dimensional coordinate system with the camera as an origin; finally, the camera coordinate system (x 1, y1, z 1) is converted into the required world coordinate system (x 2, y2, z 2), and the camera coordinate system is converted into the coordinate system required by the project, i.e. the coordinate system of the final point cloud. The data values of the X axis and the Y axis represent plane coordinate positions of scene points, and the data value of the Z axis represents an acquired actual depth value of the acquired scene.
The monitoring processor converts the three-dimensional point cloud data into an mxnx3 matrix, with each row representing a pixel arranged in the time-of-flight sensor. By resetting the M × N × 3 matrix to an M × N matrix and expressing the value of each element in the reset matrix with a depth value, the three-dimensional point cloud data is converted into two-dimensional planar image data.
The monitoring processor calculates the depth value of each pixel point of the two-dimensional plane image data by adopting a 3 multiplied by 3 space filtering operator based on the three-dimensional point cloud, and calculates the depth difference between the pixel of the central point and the pixel around the central point. And comparing the depth difference with a preset global threshold, judging that the depth value measured by the pixel point is a noise point when the depth difference is greater than the preset global threshold, and filtering the pixel point in the corresponding three-dimensional point cloud data. Otherwise, the corresponding pixel points in the three-dimensional point cloud data are reserved. And denoising to obtain denoised three-dimensional point cloud data.
And 104, the monitoring processor extracts feature data of the de-noised three-dimensional point cloud data based on the animal feature data model to obtain animal feature three-dimensional point cloud data, and the animal feature three-dimensional point cloud data is stored in an animal feature data list.
Specifically, an animal feature data model is stored in the monitoring processor, the monitoring processor extracts three-dimensional point cloud data matched with the animal feature model from the de-noised three-dimensional point cloud data to obtain a plurality of animal feature three-dimensional point cloud data, and the animal feature three-dimensional point cloud data are stored in an animal feature data list. The TOF camera shoots a frame of environment image of the first monitoring area, and the environment image is processed by the monitoring processor to generate an animal characteristic data list.
And 105, counting the animal characteristic three-dimensional point cloud data in the animal characteristic data list by the monitoring processor to obtain the number of animals in the first monitoring area.
Specifically, the monitoring processor calculates the list length of the animal feature data list to obtain the number of animal feature three-dimensional point cloud data in the animal feature data list, namely the number of animals in the first monitoring area.
And 106, carrying out color classification on the intensity data of the de-noised three-dimensional point cloud data by the monitoring processor by using a k-means algorithm to obtain a green classification interval.
Specifically, the k-means algorithm is a hard clustering algorithm, is an optimization algorithm for obtaining the optimal distance from a data point to a center by an iterative method, and has the following principle: and calculating the coordinate average value of each point to obtain a central point, classifying according to the Euclidean distance from each point to the central point, and finding out partitions so that the objects in each cluster are close to each other as much as possible and are far away from the objects in other clusters as much as possible. The monitoring processor classifies the color of the intensity data of the de-noised three-dimensional point cloud data in the RGB space by using a k-means algorithm, and the RGB space can be divided into a plurality of color intervals, wherein the color intervals comprise green classification intervals. The monitoring processor determines a green classification interval from the plurality of color classification intervals according to the RGB range of the green color.
And 107, the monitoring processor captures the intensity data of the de-noised three-dimensional point cloud data according to the green classification interval, and performs binarization processing on the captured intensity data to obtain binarized image data.
Specifically, the monitoring processor captures pixel points of which the RGB values of the intensity data meet a green classification interval from the de-noised three-dimensional point cloud data, and performs binarization processing on the captured intensity data to obtain binarized image data.
Specifically, the monitoring processor performs edge detection on the binarized image data by using a conventional edge detection algorithm, such as a canny algorithm, a sobel edge detection algorithm, and the like, and extracts edge data to obtain image edge data.
And step 109, the monitoring processor calculates and processes the pasture area according to the image edge data to obtain an area estimation value of the pasture.
Specifically, the monitoring processor performs pasture area calculation processing on the image edge data by adopting a specific two-dimensional plane graph area calculation method to obtain an area estimation value of the pasture.
For example, in a specific example of the preferred embodiment of the present invention, the monitoring processor determines the maximum x coordinate value, the minimum x coordinate value, the maximum y coordinate value, and the minimum y coordinate value of all the pixel points in the image edge data. The monitoring processor substitutes the maximum x coordinate value, the minimum x coordinate value, the maximum y coordinate value and the minimum y coordinate value into a rectangular area calculation formula for calculation to obtain an area estimated value.
The monitoring processor can also perform graph matching on the obtained image edge data according to the obtained image edge data, match the image edge data with a graph in a preset graph library, determine a corresponding area calculation method, and perform area calculation processing according to the corresponding area calculation method to obtain an area estimation value of the pasture.
Specifically, the monitoring processor calculates a ratio of the number of animals in the first monitoring area to the estimated area of the pasture, and takes the ratio as an animal volume ratio of the first monitoring area, that is, the first animal volume ratio. The first animal ratio is then saved in the monitoring data list. The monitoring data list stores data information of all monitoring areas, including a first camera ID, a first monitoring area ID and a first storage ratio. For example, in one specific example, the number of animals in the first monitoring area is 400, and the area of the pasture is estimated to be 200, then the animal-to-volume ratio is 2.
And step 111, when the monitoring processor judges that the first animal volume ratio exceeds the first preset animal volume ratio, the monitoring processor generates a first early warning message according to the first animal volume ratio and the data of the preset range interval.
Specifically, in order to protect the reasonable utilization of the pasture for a long time, the data volume of the animals cultured in the pasture must be ensured to be in a certain range, and the animals cannot be cultured in an overload mode. The first preset animal volume ratio is a parameter for measuring whether the number of the cultured animals in the pasture reaches an upper limit or is overloaded, and when the animal volume ratio is larger than the first preset animal volume ratio, the number of the cultured animals exceeds the bearing range of the pasture, so that the culture environment of the pasture is damaged. The preset range interval data comprises a plurality of preset range intervals, and each preset range interval corresponds to one early warning level. For example: the first preset range interval corresponds to a first-level early warning, the second preset range interval corresponds to a second-level early warning, and the third preset range interval corresponds to a third-level early warning.
In the preferred scheme of the embodiment of the invention, the monitoring processor determines the range interval of the first animal volume ratio and determines the early warning level according to the range interval; and the monitoring processor generates an early warning message according to the early warning level. That is to say, the monitoring processor firstly confirms the range interval of the first livestock-storage ratio, determines the early warning level, and then generates a first early warning message according to the early warning level and the first livestock-storage ratio. For example, in one embodiment, the monitoring processor determines that it is within a second predetermined range interval based on the first product-to-volume ratio, and then determines the pre-alarm level as a secondary pre-alarm.
In step 112, the monitoring processor sends the first warning message to the first warning terminal device corresponding to the first monitoring area ID, so as to output the first warning message.
Specifically, the monitoring processor searches for a first early warning terminal device corresponding to the first monitoring area ID in the early warning terminal list, and sends the first early warning message to the first early warning terminal device.
In a preferred scheme of the embodiment of the invention, before the monitoring processor sends the first early warning message to the first early warning terminal equipment corresponding to the first monitoring area ID, the first early warning terminal equipment establishes communication connection with the monitoring processor according to the first terminal ID; the monitoring processor establishes a corresponding relation between the first terminal ID and the first monitoring area ID, and stores the corresponding relation in an early warning terminal list.
In a preferred embodiment of the present invention, when the first animal volume ratio exceeds the first preset animal volume ratio, the monitoring processor may further prompt a drainage area of the animal in the first monitoring area, and the specific steps are as follows:
first, the monitoring processor searches in the monitoring data list according to the animal volume ratio, and determines a second animal volume ratio and a second monitoring area ID, the animal volume ratio of which is smaller than a second preset animal volume ratio.
Specifically, when the animal volume ratio is smaller than the second preset animal volume ratio, it indicates that the number of animals in the second monitoring area is small and the upper limit of the second monitoring area for accommodating the animals is not reached. And the monitoring processing is carried out to find the position in the monitoring data list according to the animal ratio, and a second animal ratio and a second monitoring area ID, of which the animal ratio is smaller than a second preset animal ratio, are obtained. To prompt the user that a portion of the animal in the first monitored zone may be drained to the second monitored zone.
And secondly, the monitoring processor generates a drainage prompt message according to the first storage ratio, the second storage ratio, the first monitoring area ID and the second monitoring area ID.
Specifically, the drainage prompt message is mainly used for prompting that animals in a first monitoring area of a pasture manager are excessive and need to be drained, and prompting an area where drainage can be performed. In one specific example, the drain prompt message may be "the number of animals in the first monitored area is excessive, please drive a portion of the animals to the second monitored area. ".
And finally, the monitoring processor sends a drainage prompt message to the first early warning terminal equipment corresponding to the first monitoring area ID for displaying and outputting the drainage prompt.
In the preferred scheme of the embodiment of the invention, after the monitoring processor counts the animal characteristic three-dimensional point cloud data in the animal characteristic data list to obtain the number of animals in the first monitoring area, the monitoring processor can also control the drinking equipment, and the main steps comprise; the monitoring processor generates drinking water control instructions according to the number of animals and sends the drinking water control instructions to the drinking water control equipment. And the drinking water control equipment controls the water quantity of the drinking water equipment according to the drinking water control instruction.
In a preferred scheme of the embodiment of the invention, the monitoring processor counts the animal volume ratio corresponding to each monitoring area ID in the monitoring data list at a first preset time, and generates statistical histogram data. And then sending the statistical histogram to early warning terminal equipment for displaying and outputting. That is, at a first preset time, for example, 8. Managers can visually see the animal flow condition of each area according to the histogram, and more reasonable management is carried out.
The embodiment Of the invention provides a monitoring and early warning method for a pasture. The monitoring processor performs denoising processing on the three-dimensional point cloud data, then performs characteristic data extraction and counting to obtain the number of animals in the monitoring area, performs area calculation on a pasture of the monitoring area to obtain an area estimated value, and further calculates the ratio of the number of the animals to the area estimated value to obtain the livestock-volume ratio of the monitoring area. And the monitoring processor judges the animal volume ratio, and sends an early warning message to the early warning terminal equipment corresponding to the monitoring area when the animal volume ratio exceeds the preset animal volume ratio. Furthermore, the method provided by the embodiment of the invention can automatically control the drinking water equipment in the monitoring area according to the number of the animals obtained by analysis, so that the drinking water equipment can provide a proper amount of drinking water for the animals in the area. The method provided by the embodiment of the invention can automatically monitor and early warn the pasture without being influenced by the external illumination condition, thereby improving the timeliness of early warning and greatly reducing the labor cost of pasture management.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A monitoring and early warning method for a pasture is characterized by comprising the following steps:
the method comprises the steps that a time of flight (TOF) camera shoots an environment image of a first monitoring area of a pasture according to an image acquisition instruction to generate three-dimensional point cloud data; wherein the TOF camera has a camera ID;
the TOF camera sends the three-dimensional point cloud data and the camera ID to a monitoring processor;
the monitoring processor carries out denoising processing on the three-dimensional point cloud data to obtain denoised three-dimensional point cloud data;
the monitoring processor extracts feature data of the de-noised three-dimensional point cloud data based on an animal feature data model to obtain animal feature three-dimensional point cloud data, and stores the animal feature three-dimensional point cloud data in an animal feature data list;
the monitoring processor counts the animal characteristic three-dimensional point cloud data in the animal characteristic data list to obtain the number of animals in the first monitoring area;
the monitoring processor performs color classification on the intensity data of the de-noised three-dimensional point cloud data by using a k-means algorithm to obtain a green classification interval;
the monitoring processor captures the intensity data of the de-noised three-dimensional point cloud data according to the green classification interval, and performs binarization processing on the captured intensity data to obtain binarized image data;
the monitoring processor extracts image edge data from the binary image data;
the monitoring processor calculates and processes the pasture area according to the image edge data to obtain an area estimation value of the pasture;
the monitoring processor calculates the ratio of the number of the animals to the area estimated value of the pasture to obtain a first livestock-area ratio, and the first livestock-area ratio is stored in a monitoring data list; wherein the monitoring data list includes a first camera ID, a first monitoring area ID, and a first animal-volume ratio;
when the monitoring processor judges that the first animal volume ratio exceeds a first preset animal volume ratio, the monitoring processor generates a first early warning message according to the first animal volume ratio and preset range interval data;
and the monitoring processor sends the first early warning message to first early warning terminal equipment corresponding to a first monitoring area ID for outputting the first early warning message.
2. The monitoring and forewarning method for the pasture as claimed in claim 1, further comprising:
the monitoring processor searches in a monitoring data list according to the animal volume ratio, and determines a second animal volume ratio and a second monitoring area ID, wherein the animal volume ratio is smaller than a second preset animal volume ratio;
the monitoring processor generates a drainage prompt message according to the first livestock volume ratio, the second livestock volume ratio, the first monitoring area ID and the second monitoring area ID;
and the monitoring processor sends the drainage prompt message to a first early warning terminal device corresponding to the first monitoring area ID for displaying and outputting a drainage prompt.
3. The monitoring and early-warning method for the pasture as claimed in claim 1, wherein the first early-warning message includes an early-warning level, and the generating of the first early-warning message by the monitoring process according to the first livestock-volume ratio and the preset range interval data is specifically:
the monitoring processor determines a range interval of the first animal volume ratio and determines an early warning level according to the range interval;
and the monitoring processor generates an early warning message according to the early warning level.
4. The monitoring and early warning method for the pasture as claimed in claim 1, wherein after the monitoring processor counts the animal feature three-dimensional point cloud data in the animal feature data list to obtain the number of animals in the first monitoring area, the monitoring and early warning method further comprises:
the monitoring processor generates drinking control instructions according to the animal number and sends the drinking control instructions to drinking control equipment;
and the drinking water control equipment controls the water quantity of the drinking water equipment according to the drinking water control instruction.
5. The monitoring and forewarning method for the pasture as claimed in claim 1, further comprising:
the monitoring processor counts the animal volume ratio corresponding to each monitoring area ID in the monitoring data list at a first preset time, and generates statistical histogram data;
and the monitoring processor sends the statistical histogram to the early warning terminal equipment for display and output.
6. The monitoring and early warning method for the pasture as claimed in claim 1, wherein before the monitoring processor sends the first early warning message to a first early warning terminal device corresponding to a first monitoring area ID, the method further comprises:
the first early warning terminal equipment establishes communication connection with the monitoring processor according to the first terminal ID;
the monitoring processor establishes a corresponding relationship between the first terminal ID and the first monitoring area ID.
7. The monitoring and pre-warning method for pastures, according to claim 1, characterized in that before the time of flight TOF camera acquires the environmental image of the first monitoring area of the pasture according to the image acquisition instruction, the method further comprises:
the monitoring processor receives a monitoring starting command and generates the image acquisition instruction according to a preset time interval;
the monitoring processor sends the image acquisition instructions to the TOF camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911350715.9A CN111144276B (en) | 2019-12-24 | 2019-12-24 | Monitoring and early warning method for pasture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911350715.9A CN111144276B (en) | 2019-12-24 | 2019-12-24 | Monitoring and early warning method for pasture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144276A CN111144276A (en) | 2020-05-12 |
| CN111144276B true CN111144276B (en) | 2023-04-18 |
Family
ID=70519783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911350715.9A Active CN111144276B (en) | 2019-12-24 | 2019-12-24 | Monitoring and early warning method for pasture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144276B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114500960B (en) * | 2022-04-06 | 2022-08-02 | 潍坊学院 | Inspection and alarm management system and method for livestock and poultry farm |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006031645A (en) * | 2004-07-12 | 2006-02-02 | Nariyuki Mitachi | Real-time estimation method for dynamic crowd density and crowd accident prevention system |
| CN106060479A (en) * | 2016-07-13 | 2016-10-26 | 三峡大学 | Smart pasture monitoring system based on beyond visual range video technology |
| JP2018099114A (en) * | 2016-12-19 | 2018-06-28 | いであ株式会社 | Determination/distribution system of position and kind of wild animal |
| CN109376584A (en) * | 2018-09-04 | 2019-02-22 | 湖南大学 | A kind of poultry quantity statistics system and method for animal husbandry |
| CN109584348A (en) * | 2018-10-29 | 2019-04-05 | 天津大学 | A kind of design method of the virtual painting system of Qin's figurines based on virtual reality technology |
| CN109636779A (en) * | 2018-11-22 | 2019-04-16 | 华南农业大学 | Identify the method, apparatus and storage medium of poultry volume ruler |
| CN109961466A (en) * | 2017-12-14 | 2019-07-02 | 翔升（上海）电子技术有限公司 | Ranch animals monitoring method and system |
| CN110210408A (en) * | 2019-06-04 | 2019-09-06 | 黑龙江省七星农场 | Plant growth forecasting system and method based on satellite in conjunction with unmanned aerial vehicle remote sensing |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7399220B2 (en) * | 2002-08-02 | 2008-07-15 | Kriesel Marshall S | Apparatus and methods for the volumetric and dimensional measurement of livestock |
| US20070288249A1 (en) * | 2004-04-13 | 2007-12-13 | Rowe James B | Integrated Animal Management System And Method |
| US9824276B2 (en) * | 2014-04-15 | 2017-11-21 | Open Range Consulting | System and method for assessing rangeland |
| JP7341991B2 (en) * | 2018-05-23 | 2023-09-11 | 株式会社Ｎｔｔドコモ | monitoring device |
-
2019
- 2019-12-24 CN CN201911350715.9A patent/CN111144276B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006031645A (en) * | 2004-07-12 | 2006-02-02 | Nariyuki Mitachi | Real-time estimation method for dynamic crowd density and crowd accident prevention system |
| CN106060479A (en) * | 2016-07-13 | 2016-10-26 | 三峡大学 | Smart pasture monitoring system based on beyond visual range video technology |
| JP2018099114A (en) * | 2016-12-19 | 2018-06-28 | いであ株式会社 | Determination/distribution system of position and kind of wild animal |
| CN109961466A (en) * | 2017-12-14 | 2019-07-02 | 翔升（上海）电子技术有限公司 | Ranch animals monitoring method and system |
| CN109376584A (en) * | 2018-09-04 | 2019-02-22 | 湖南大学 | A kind of poultry quantity statistics system and method for animal husbandry |
| CN109584348A (en) * | 2018-10-29 | 2019-04-05 | 天津大学 | A kind of design method of the virtual painting system of Qin's figurines based on virtual reality technology |
| CN109636779A (en) * | 2018-11-22 | 2019-04-16 | 华南农业大学 | Identify the method, apparatus and storage medium of poultry volume ruler |
| CN110210408A (en) * | 2019-06-04 | 2019-09-06 | 黑龙江省七星农场 | Plant growth forecasting system and method based on satellite in conjunction with unmanned aerial vehicle remote sensing |
Non-Patent Citations (3)
| Title |
|---|
| 吴方明等."三江源大型食草动物数量无人机自动监测方法".《兽类学报》.2019,第39卷(第39期),第450-457页. * |
| 孙雨坤 ; 岳奎忠 ; 李文茜 ; 么恩悦 ; 刘鑫 ; 李洋 ; 张永根 ; .图像信息技术在奶牛生产中的应用.动物营养学报.2018,(第05期),第23-29页. * |
| 宫一男等.基于深度学习的红外相机动物影响人工智能识别：以东北豹国家公园为例.《兽类学报》.2019,(第004期),度458-465页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144276A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10195008B2 (en) | System, device and method for observing piglet birth | |
| CN111127411B (en) | Monitoring control method for fishery cultivation | |
| CN111753609B (en) | Target identification method and device and camera | |
| CN108288289B (en) | LED visual detection method and system for visible light positioning | |
| CN105894003A (en) | Large-field fruit tree disease monitoring early-warning system based on machine vision | |
| CN110728810B (en) | Distributed target monitoring system and method | |
| US20190191632A1 (en) | Plant phenotyping techniques using optical measurements, and associated systems and methods | |
| CN111144252B (en) | Monitoring and early warning method for people stream analysis | |
| CN111144276B (en) | Monitoring and early warning method for pasture | |
| CN113537049B (en) | Ground point cloud data processing method and device, terminal equipment and storage medium | |
| AU2021225057A1 (en) | Method and apparatus for determining an index of insect biodiversity, an insect sensor and a system of insect sensors | |
| CN113273178A (en) | Animal house monitoring method and animal house monitoring system | |
| CN210428540U (en) | Insect type identification equipment and system | |
| Fu et al. | Kiwifruit yield estimation using image processing by an Android mobile phone | |
| CN115631421A (en) | Intelligent protection method and system for cultivated land | |
| CN110689507A (en) | Insect type identification device, system and method | |
| CN111127436B (en) | Displacement detection early warning method for bridge | |
| González et al. | Real-time monitoring of poultry activity in breeding farms | |
| CN116665120A (en) | Tornado formation recognition and early warning system and method based on video | |
| US20230196560A1 (en) | Systems and methods for automatically grading cannabis plants and adjusting control parameters | |
| CN104010165A (en) | Automatic collecting device for precipitation particle shadow image | |
| Chiron et al. | Outdoor 3D Acquisition System for Small and Fast Targets. Application to honeybee monitoring at the beehive entrance | |
| CN110764561A (en) | Building environment parameter automatic control method and system | |
| CN203872283U (en) | Automatic precipitation particle shadow image acquisition device | |
| KR102307609B1 (en) | Apparatus and method for detecting abnormal object and imaging device comprising the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |