Background
The grain problem is one of the urgent problems which have attracted attention at present, and the grain country can stably and healthily develop industry, national defense, service industry, scientific culture industry and the like. Food problems are not only economic and civil problems, but also development and safety issues. Along with the rapid development of green food and the continuous improvement of the living standard of people, the grain green storage technology is greatly developed in China, the grain storage technology is developing from the traditional grain storage technology to the green grain storage technology, and simultaneously, the grain storage technology is gradually developing from the extensive grain transportation supervision to the refined grain transportation supervision.
In order to supervise the storage condition of the stored grain, real-time grain transportation supervision needs to be realized, and the common grain transportation supervision is carried out by 3D detection equipment. However, no general 3D detection device can calculate the irregular contour of the stored grain object at present, the stored grain calculation commonly used in the market is calculated according to the conveying times of the conveying belt, the stored grain is easy to mix with dishes under the condition of more conveying tasks, and the calculation has errors.
Therefore, the invention provides a real-time grain storage monitoring device and method.
Disclosure of Invention
In order to solve the above problems, the present invention provides a real-time grain storage monitoring device and method, which can effectively avoid errors of manual single statistical calculation and single calculation, and accurately obtain actual grain storage conditions.
In order to achieve the above purpose, the present invention provides the following technical solutions.
A real-time grain storage monitoring method comprises the following steps:
s1: carrying out multi-point monitoring data acquisition on the warehouse through detection equipment, and carrying out data transformation, data compensation and data filtering operation on image data according to the image data generated by analyzing different states of entering and exiting the granary;
s2: compensating multipath interference data in the processed image data according to the data characteristics, filling missing data through the change of the image data, filtering data outside a visible area through the change of a threshold value, and extracting effective data; dividing the effective data, dividing the grain storage surface and the ground, calculating to obtain the ground, the grain storage surface, the grain storage shadow and the personnel access data, and filtering data edge information by adopting corrosion and expansion operations on the ground, the grain storage surface, the grain storage shadow and the personnel access data;
s3: a square with 5 pixel points is given to traverse the ground, the grain storage surface, the grain storage shadow and personnel access data, effective area data are extracted, the outline of a corresponding view field is detected through image detection, and edge identification detection is carried out on corresponding outline information to form a ground, grain storage surface and shadow density map;
s4: performing mean interpolation and threshold filtering on the ground, the grain storage surface and the shadow density map to obtain shadows and a dot map of a grain storage area, and finally extracting and segmenting through data points to obtain a grain storage surface and shadow surface density map;
s5: cleaning the data, extracting the outline of the grain storage surface to obtain the outline of the real stored goods, and carrying out differential operation on the corresponding outline to obtain the data of the grain storage surface; and calculating the stored objects in the corresponding time period according to the grain storage surface and the shadow density graph in combination with the time sequence to obtain the grain storage amount in the time period, and giving a voice prompt according to the change of the volume.
Preferably, the voice prompt comprises the following steps:
setting time period volume change according to the obtained volume, and reminding the volume increase of the later time period through voice if the volume of the later time period is larger than that of the former time period; if the volume of the later period of time is smaller than that of the previous period of time, the volume of the later period of time is reminded to be reduced through voice; if the volume of the later period of time is not changed compared with the volume of the previous period of time, the reminding is not carried out.
The invention also provides a real-time grain storage monitoring device, which comprises:
the detection equipment comprises a plurality of sensors and is used for carrying out multi-point monitoring data acquisition on the warehouse;
the file analysis device is used for processing and analyzing the data, acquiring ground, grain storage surface and grain storage shadow data and storing the data in a cloud end;
the data storage cloud is used for storing ground, grain storage surface and grain storage shadow data in real time;
the computing equipment is used for processing and computing the ground, the grain storage surface and the grain storage shadow data to obtain the grain storage data;
the display equipment is used for displaying the stored grain data in real time;
and the voice prompt device carries out voice prompt in real time according to the grain storage data.
The invention provides a real-time grain storage monitoring device and a real-time grain storage monitoring method, which are characterized in that:
(1) the method is based on a data dot matrix monitored by hardware equipment in real time to carry out ground segmentation, grain storage surface and shadow to calculate a corresponding density map, and a corresponding visible area outline is calculated through the grain storage density map.
(2) The invention has special scenes through the application of actual grain storage supervision projects, and the grain storage size is calculated by using an artificial intelligence algorithm in the grain storage supervision. Calculating shadow area and grain storage area by visual area outline
(3) The invention provides a method for real-time calculating the grain storage amount in a corresponding area by means of digital supervision, and simultaneously, logical judgment is provided for the change of the stored grain, and finally, the change of the stored grain is prompted by voice to provide a change decision for a supervision layer.
(4) The stored grain supervision provided by the invention has particularity, provides real-time supervision on corresponding stored grain changes, provides real-time volume changes according to stored grain rules, and provides convenience conditions for a supervisor to sense, make a real-time decision and supervise in real time.
The invention is further described with reference to the following figures and examples.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
A real-time monitoring device and method for stored grain, the structure composition diagram is shown in figure 3, comprising:
the detection equipment comprises a plurality of sensors and is used for carrying out multi-point monitoring data acquisition on the warehouse;
the file analysis device is used for processing and analyzing the data, acquiring ground, grain storage surface and grain storage shadow data and storing the data in a cloud end;
the data storage cloud is used for storing ground, grain storage surface and grain storage shadow data in real time;
the computing equipment is used for processing and computing the ground, the grain storage surface and the grain storage shadow data to obtain the grain storage data;
the display equipment is used for displaying the stored grain data in real time;
and the voice prompt device carries out voice prompt in real time according to the grain storage data.
In this embodiment, the monitoring method based on the monitoring device includes the following steps, and a flowchart is shown in fig. 1:
s1: carrying out multi-point monitoring data acquisition on the warehouse through detection equipment to form data points in a monitoring range; analyzing the generated image data according to different states of the grain bin, and performing data transformation, data compensation and data filtering operation on the image data; the data is logarithmically transformed, here taking into account the data accuracy in mm, as follows:
z=ln(zi),ziis the original data
Performing data compensation on missing data, performing data compensation according to the interpolation of a near point, simultaneously performing filtering processing on a noise point, filtering according to the range of test data and a threshold value,
z=8000,if|z|≥8000,
x=2560,if|x|≥3000
s2: transmitting the data to a file analysis device, compensating multipath interference data in the processed image data according to data characteristics, filling missing data through data change, filtering data outside a visible region through threshold value change, and extracting effective data; cut apart effective data, cut apart storage grain face and ground, calculate and acquire ground, storage grain face and storage grain shadow and personnel business turn over data, adopt corruption and inflation operation to filter data edge information ground, storage grain face and storage grain shadow and personnel business turn over data to with data storage to high in the clouds, wherein corrode with the inflation operation as follows:
erosion is a process by which boundary points are eliminated and the boundaries are shrunk inward. Small and meaningless objects can be eliminated by using the etching operation;
dilation is the process of merging all background points in contact with an object into the object, expanding the boundary outward. By expansion, small holes in the image and small recessed portions at the edges of the image can be filled.
S3: the computing equipment calls cloud image data to perform data calculation: a square with 5 pixel points is given to traverse the ground, the grain storage surface, the grain storage shadow and personnel access data, effective area data are extracted, the outline of a corresponding view field is detected through image detection, and edge identification detection is carried out on corresponding outline information to form a ground, grain storage surface and shadow density map;
s4: the computing equipment performs mean value interpolation and threshold value filtration on the ground, the grain storage surface and the shadow density map to obtain shadows and dot maps of grain storage areas, and finally obtains the density maps of the grain storage surface and the shadow surface by data point extraction and segmentation;
s5: the method comprises the steps of cleaning data, processing invalid values and deficiency values, extracting a real stored goods contour from a grain storage surface contour, and carrying out differential operation on a corresponding contour, wherein the differential operation aims to reduce detection errors of irregular goods contours according to differential operation, irregular objects are basically adopted in the market and are regularly processed, and thus the detection errors are very large. The stored grain surface data are further accurately obtained through differential operation and are transmitted to display equipment for displaying; and calculating the stored objects in the corresponding time period according to the grain storage surface and the shadow density chart in combination with the time sequence, namely calculating the proportion of the cargo profile to the grain storage surface to obtain the grain storage amount in the time period, and giving a voice prompt according to the change of the volume.
Further, the voice prompt includes the following steps, and the specific flowchart is shown in fig. 2:
setting time period volume change according to the obtained volume, and reminding the volume increase of the later time period through voice if the volume of the later time period is larger than that of the former time period; if the volume of the later period of time is smaller than that of the previous period of time, the volume of the later period of time is reminded to be reduced through voice; if the volume of the later period of time is not changed compared with the volume of the previous period of time, the reminding is not carried out.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.