KR102496860B1 - Method and devices for measuring the crop of tomato - Google Patents

Abstract

This application relates to a device for measuring the yield of crops. An apparatus for measuring crop shipments according to an embodiment of the present invention includes an image collection unit for collecting crop images; and a shipment measurement unit for detecting a plurality of crop objects from the crop image and measuring a quantity of crops that can be shipped based on detection accuracy and maturity of each of the plurality of crop objects. The shipment measurement device according to the embodiment of the present application can accurately measure the quantity of crops that can be shipped.

Description

Tomato shipment measurement method and its device {METHOD AND DEVICES FOR MEASURING THE CROP OF TOMATO}

This application relates to a device for measuring the yield of crops.

Recently, along with the development of electronic technology, a fruit tree yield prediction system using an imaging device has been developed. The yield estimation system may predict the yield of fruit trees by collecting image information of fruit trees from an imaging device and analyzing the collected image information.

However, a technique capable of accurately and precisely predicting ripeness and shipment of crops, fruits, etc. has not yet been developed.

An object of the present application is to provide a device and method capable of accurately measuring the quantity of crops that can be shipped.

An apparatus for measuring crop shipments according to an embodiment of the present application includes an image collection unit for collecting crop images; and a shipment measurement unit for detecting a plurality of crop objects from the crop image and measuring a quantity of crops that can be shipped based on detection accuracy and maturity of each of the plurality of crop objects.

In one embodiment, the shipment measurement unit, the shipment measurement unit, an image receiving module for receiving the crop image; an object detection module detecting the plurality of crop objects from the crop image; a detection accuracy measurement module for measuring detection accuracy of each of the plurality of crop objects; a maturity measurement module for measuring the maturity of crop objects whose detection accuracy measured by the detection accuracy measurement module among the plurality of crop objects is greater than or equal to a predetermined object detection threshold value; and a yield measurement module that increases the quantity of crop objects that can be shipped by “1” when the maturity measured by the maturity measurement module is equal to or greater than a preset object maturity threshold.

In one embodiment, the shipment measurement unit further includes an attention module for additionally detecting crop objects based on a heat map for crop objects not detected by the object detection module.

In one embodiment, the object detection module first determines the presence/absence of the crop object in each image frame of the received crop image, and displays the image position of the crop object if the crop object exists.

In one embodiment, the object detection module compares a learned image using an artificial intelligence module and the received crop image to determine whether the image matches, and determines whether a convolutional product with the learned image is high is the crop object detected with

In one embodiment, the maturity measurement module extracts an image with respect to a portion where an HSV color value of the image of the crop object changes by more than a preset value in the crop image as a boundary, and for the extracted image, the Displays the degree of distribution of HSV color values as a histogram.

In one embodiment, the crop is characterized in that tomato.

In one embodiment, the ripeness measurement module classifies the ripeness of the tomatoes into green ripening, discoloring, coloring, painting, light red, and mature stages according to the appearance state.

In one embodiment, the yield measurement module determines the ripeness of the crops derived through the object detection module and the attention module, and stores the determined data in a database.

In one embodiment, the crop is a tomato, and the shipment measurement module derives the number of the tomato corresponding to the color change period in the case of export tomatoes and the color change period in the case of domestic tomatoes from the database, and based on the number The location of the image collection unit is calculated to measure the number and location of tomatoes that can be shipped.

In one embodiment, the object detection value through the heat map is an average value around the crop object and a median value of the crop object detection value.

In one embodiment, the image collection unit, an image acquisition module for acquiring the crop image; and an image transmission module for transmitting the crop image to the shipment measurement unit.

In one embodiment, the image transmission module includes a raspberry pi, and transmits image data generated by the raspberry pi to the shipment measurement unit.

In one embodiment, the crop yield measuring device further includes an image relay unit for transmitting the crop image from the image collection unit to the yield measurement unit.

In the process of measuring the yield of crops according to an embodiment of the present application, receiving image data of crops; detecting a plurality of crop objects from the image data; Measuring detection accuracy for each of the plurality of crop objects; Measuring maturity of crop objects with respect to objects whose detection accuracy is greater than or equal to a threshold value among the plurality of crop objects; and increasing the yield by 1 when the ripeness of the crop object is greater than or equal to a threshold value.

In the crop shipment measurement system according to an embodiment of the present application, at least one image collection unit for collecting crop images; Based on the image of the crop, a shipment amount measurement unit providing a shipment amount of the crop; an image relay unit transmitting the crop image from the image collection unit to the shipment measurement unit; a server capable of communicating with the shipment measurement unit; And a user terminal capable of communicating with the shipment measurement unit through the server, wherein the shipment measurement unit detects a plurality of crop objects from the crop image, and determines the detection accuracy and maturity of each of the plurality of crop objects. Based on this, the quantity of crops that can be shipped is measured.

In the crop shipment measurement device according to an embodiment of the present application, the image receiving module for receiving a crop image;

an object detection module detecting a plurality of crop objects from the crop image;

a detection accuracy measurement module for measuring detection accuracy of each of the plurality of crop objects;

a ripeness measuring module for measuring the maturity of crop objects with respect to crop objects whose measured detection accuracy is greater than or equal to a preset object detection threshold value among the plurality of crop objects; and

When the measured maturity is equal to or greater than a preset object maturity threshold, a shipment amount measurement module that increases the number of crop objects that can be shipped by “1” is included.

The shipment measurement device according to the embodiment of the present application can accurately measure the quantity of crops that can be shipped.

1 is a block diagram of an apparatus for measuring crop yield according to an embodiment of the present invention.
Figure 2 is a block diagram of the image collection unit of the crop yield measuring device according to an embodiment of the present invention.
3 is a block diagram of a shipment measurement unit of a crop shipment measurement device according to an embodiment of the present invention.
4 is a histogram showing the distribution of images and values of crops through HSV color values of a maturity measurement module according to an embodiment of the present invention.
5 is a block diagram illustrating another embodiment of a shipment measurement unit according to an embodiment of the present invention.
6 is a diagram exemplarily illustrating object detection through a heat map of an attention module according to an embodiment of the present invention.
7 is a block diagram showing another embodiment of a crop shipment measurement unit according to an embodiment of the present invention.
8 is a block diagram showing another embodiment of a crop shipment measuring device according to an embodiment of the present invention.
9 is a flow chart showing a method for measuring the amount of shipment of tomatoes according to an embodiment of the present invention.
10 is a diagram showing an example of applying the shipment measurement system according to an embodiment of the present invention to a smart farm.

Hereinafter, the present disclosure will be described with reference to the accompanying drawings. Since the present disclosure can make various changes and have various embodiments, specific embodiments are illustrated in the drawings and related detailed descriptions are described. However, this is not intended to limit the present disclosure to specific embodiments, and should be understood to include all changes and/or equivalents or substitutes included in the spirit and scope of the present disclosure. In connection with the description of the drawings, like reference numerals have been used for like elements.

Expressions such as "include" or "may include" that may be used in this disclosure indicate the presence of the disclosed function, operation, or component, and do not limit one or more additional functions, operations, or components. In addition, in the present disclosure, terms such as “include” or “have” are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more It should be understood that the presence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Expressions such as “or” in this disclosure include any and all combinations of the words listed together. For example, "A or B" may include A, may include B, or may include both A and B.

In the present disclosure, expressions such as “first,” “second,” “first,” or “second,” may modify various elements of the present disclosure, but do not limit the elements. For example, the above expressions do not limit the order and/or importance of corresponding components. The above expressions may be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and represent different user devices. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present disclosure.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when a component is referred to as “directly connected” or “directly connected” to another component, it should be understood that no other component exists in the middle.

Terms used in the present disclosure are only used to describe specific embodiments, and are not intended to limit the present disclosure. Singular expressions include plural expressions unless the context clearly dictates otherwise.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present disclosure, they should not be interpreted in an ideal or excessively formal meaning. don't

1 is a block diagram of a crop shipment measurement device 100 according to an embodiment of the present application.

Referring to FIG. 1 , the crop shipment measurement device 100 according to an embodiment of the present application includes an image collection unit 110, an image relay unit 130, and a shipment measurement unit 150.

The image collection unit 110 collects images of crops. For example, the image collection unit 110 may be installed in a greenhouse and may collect images of crops grown in the greenhouse. For example, the image collecting unit 110 may be installed in a greenhouse where tomatoes are grown to collect images of tomatoes.

The image relay unit 130 receives the images collected by the image collection unit 110 and transmits them to the shipment measurement unit 150 . For example, the image relay unit 130 may receive images of tomatoes collected by the image collection unit 110 and transmit them to the shipment measurement unit 150 .

Here, the video relay unit 130 may perform a relaying operation through wireless AP communication. However, this is exemplary, and the video relay unit 130 may perform a relaying operation using a wireless module such as RF, Zigbee, Bluetooth, and a wired module using 24 pins, USB, and the like.

The shipment measurement unit 150 receives an image of a crop from the image relay unit 130 . The shipment measurement unit 150 may measure the quantity of shipmentable crops based on the received image of the crops.

In an embodiment according to the technical idea of the present application, the shipment measurement unit 150 detects a plurality of crop objects from a crop image, and the quantity of crops that can be shipped based on the detection accuracy and maturity of each of the plurality of crop objects. can measure For example, the shipment measurement unit 150 may detect a plurality of tomato objects from the tomato image received from the image relay unit 130 . Thereafter, the shipment measurement unit 150 may measure the quantity of tomatoes that can be shipped based on the detection accuracy and ripeness of a plurality of tomato objects.

In this way, the shipment measurement device 100 according to an embodiment of the present application detects a plurality of crop objects from an image of a crop, and determines whether the crop can be shipped based on the detection accuracy and maturity of each of the plurality of crop objects. By discriminating, it is possible to accurately measure the quantity of crops that can be shipped.

FIG. 2 is a block diagram showing the image collection unit 110 of the crop shipment measurement device 100 of FIG. 1 in more detail.

Referring to FIG. 2 , the image collection unit 110 according to an embodiment of the present application includes an image acquisition module 111 and an image transmission module 112 .

The image acquisition module 111 is installed at a crop cultivation site and can capture the growth conditions of crops at a certain time or under certain conditions. For example, the image acquisition module 111 may be a camera or an image collection robot, and may be installed in a greenhouse where tomatoes are grown to photograph the growth conditions of tomatoes. As another example, the image acquisition module 111 may capture a crop image while moving. That is, the image acquisition module 111 may be implemented to move on a rail, and may be implemented to photograph crops while moving on a corresponding rail. The image transmission module 112 may transmit a video or image data of a crop to be generated to the image relay unit 130 . For example, the image transmission module 112 includes a small PC, and the small PC may be a Raspberry Pi. Here, the small PC (Raspberry Pi) may generate image data based on the tomato image acquired by the image acquisition module 111 and transmit the generated image data to the image relay unit 130.

FIG. 3 is a block diagram showing the shipment measurement unit 150 of the crop shipment measurement device 100 of FIG. 1 in more detail.

Referring to FIG. 3, the shipment measurement unit 150 according to an embodiment of the present application includes an image receiving module 151, an object detection module 152, a detection accuracy measurement module 153, a maturity measurement module 154, and It includes a shipment measurement module 155.

The image receiving module 151 may receive the image transmitted from the image collection unit 110 through the image relay unit 130 . For example, the image reception module 151 may configure the same network as a small PC mounted in the image collection unit 110 through a wireless AP module of the image relay unit 130 .

For example, the small PC mounted on the image collecting unit 110 may sequentially transmit communication check data to generated image data. In this case, the image reception module 151 may check the order of image data and communication check data to determine whether there is an error in the data.

The object detection module 152 may detect crop objects from crop images (image data).

For example, the object detection module 152 may first determine the presence or absence of a tomato in an individual image frame of the tomato image received by the image receiving module 151 . If there is a tomato, the object detection module 152 may calculate and display the image location of the tomato.

As another example, the object detection module 152 may determine whether the images match by comparing the learned image and the received tomato image using the artificial intelligence module. In this case, the object detection module 152 may detect a part having a high convolutional product compared to the learned image as a crop object.

Meanwhile, the object detection module 152 may measure the total quantity of crop objects by counting the quantity of detected crop objects.

The detection accuracy measurement module 153 may measure the detection accuracy of the crop object detected by the object detection module 152 . The detection accuracy measuring module 153 may select crops whose detection accuracy of crop objects is greater than or equal to a preset detection accuracy value. For example, the detection accuracy measuring module 153 may measure the detection accuracy of the tomato object detected by the object detection module 152 and select a tomato having a detection accuracy of the tomato object equal to or greater than a predetermined detection accuracy value.

The maturity measurement module 154 may measure the maturity of crops selected in the detection accuracy measurement module 153 .

For example, the maturity measurement module 154 may extract an image of a tomato measured through the object detection module 152 with a boundary where the HSV color value changes rapidly. Further, the maturity measurement module 154 may express the degree of distribution of HSV color values with respect to the extracted image as a histogram. Thereafter, the ripeness measurement module 154 classifies the ripeness of tomatoes into six grades (greening, discoloration, coloration, painting, light redness, and maturity) according to the appearance state, and HSV color values are distributed The maturity can be determined by calculating the ratio.

For example, the maturity measurement module 154 may measure the maturity of crops as shown in Table 1 below.

ripeness explanation rusting period Whole rind is green color changing machine Orange color is expressed at the apex of the fruit, and less than 10% of the entire rind is colored Saekki Choi Pigmentation of more than 10% to 30% of the entire rind paint machine More than 30% to 60% of the entire rind is colored, the entire rind is colored, but very light color pale red flag More than 60% to 90% of the entire rind is colored, and the surface of the fruit is pinkish red. maturity More than 90% of the entire rind is pigmented, dark red

The yield measurement module 155 may measure the quantity of crops that can be shipped based on the maturity of the crops measured by the maturity measurement module 154 .

For example, the yield measurement module 155 may increase the yield value by 1 when the ripeness of the crop measured by the ripeness measurement module 154 is equal to or greater than a preset maturity value. The shipment amount measurement module 155 may repeat this process as many times as the object quantity of the crop measured by the object detection module 152, output the shipment amount, and end the process. For example, if the ripeness of tomatoes measured by the ripeness measurement module 154 is greater than or equal to a predetermined ripeness value, the shipment quantity measuring module 155 increases the quantity shipped by 1, and this process is performed as measured by the object detection module 152. After repeating as much as the number of objects of tomatoes, the number of shipments can be adjusted and output.

According to one embodiment of the present application, the shipment amount measurement module 155 may determine the maturity through the maturity measurement module 154 and create a database (DB) of the determined data. In this case, the shipment measurement module 155 may derive the number of tomatoes corresponding to the color change period in the case of export tomatoes and the color period in the case of domestic tomatoes from the database (DB). Based on the number derived here, the shipping amount measurement module 155 may measure the quantity and location of shippingable tomatoes by calculating the location where the corresponding tomato image was captured.

For example, the yield measurement module 155 may set ripeness values of crops as shown in Table 2.

ripeness ripeness value rusting period One color changing machine 2 Saekki Choi 3 paint machine 4 pale red flag 5 full maturity 6

The shipping amount measuring module 155 may measure the shipping amount of tomatoes by setting the set value of the ripeness value to 4 in order to measure the shipping amount of tomatoes with a painting machine or higher among the ripeness values set as shown in Table 2.

However, it will be understood that this is exemplary and the technical spirit of the present invention is not limited thereto.

As described above, the shipment measurement device 100 according to an embodiment of the present application detects a plurality of crop objects from an image of the crop, and can ship the crop based on the detection accuracy and maturity of each of the plurality of crop objects. It can be determined whether Therefore, the shipment measurement device 100 according to the embodiment of the present application can accurately measure the quantity of shipmentable crops and can be efficiently used in the agricultural field.

4 is a histogram showing images of crops and distribution of values through HSV color values of a maturity measurement module according to an embodiment of the present application.

Referring to FIG. 4 , it is possible to see an exemplary diagram displaying a tomato object corresponding to a light red color period of tomatoes and a tomato object corresponding to a green ripening period according to an embodiment of the present invention.

5 is a block diagram showing a shipment measurement unit 150_1 according to another embodiment of the present application. The shipment measurement unit 150_1 of FIG. 5 is similar to the shipment measurement unit 150 of FIG. 3 . Accordingly, identical or similar elements are designated using identical or similar reference numerals. Also, for brevity, redundant descriptions will be omitted below.

Referring to FIG. 5 , the shipment measurement unit 150_1 according to an embodiment of the present application may further include an attention module 156 .

The attention module 156 is a module for additionally improving detection accuracy of crop objects preferentially detected by the object detection module 152 . That is, the attention module 156 is a module for determining whether there are undetected objects and additionally detecting them.

For example, the object detection module 152 primarily detects a part with a high match strength (a part with a high convolution compared to the learned image), and the attention module 156 uses a heat map of the image to increase detection accuracy. Additional objects can be detected. In this case, the image heat map may be implemented to express the degree of matching with colors for points similar to the learned image.

In this case, taking tomato as an example, the detection accuracy may be set to a median value between the peripheral average value and the object detection value of tomato. The reason is that the images conveyed through the video are so incomplete that it can be said that there are no other images other than the stem, leaf, and fruit of the tomato. However, it will be understood that this is exemplary and the technical spirit of the present invention is not limited thereto.

The detection accuracy measurement module 153 may measure the detection accuracy of the object of the crop detected by the object detection module 152 and the attention module 156 . Also, the detection accuracy measurement module 153 may select crops whose detection accuracy of crop objects is greater than or equal to a predetermined detection accuracy value. For example, the detection accuracy measuring module 153 measures the detection accuracy of the tomato object detected by the object detection module 152 and the attention module 156, and detects a tomato object whose detection accuracy is equal to or greater than a predetermined detection accuracy value. can be selected.

The ripeness measurement module 154 may extract an image of the tomato detected through the object detection module 152 and the attention module 156 with a boundary where the HSV color value changes rapidly. Further, the maturity measurement module 154 may express the degree of distribution of HSV color values with respect to the extracted image as a histogram. Then, in order to classify the ripeness of tomatoes, the ripeness measurement module 154 classifies them into 6 grades (greening period, discoloration period, coloration period, painting period, light red period, maturity period) according to the appearance state, and the HSV color value is The maturity can be determined by calculating the distribution ratio.

The shipment amount measurement module 155 determines the ripeness of the tomatoes derived from the ripeness measurement module 154 through the object detection module 152 and the attention module 156. After that, the process is as described in FIG. same.

6 is a diagram exemplarily illustrating object detection through a heat map of an attention module according to an embodiment of the present invention.

Object detection through a heat map expresses the degree of coincidence in color for similar points between the learned image and the comparison target image.

For example, a point having a high similarity between the learned image and the comparison target image may be expressed in red, and a point having a low similarity may be expressed in blue. Accordingly, through heat map detection of the tomato image of the learned image and the tomato image of the comparison target image, it is determined whether there are tomato objects that were not detected by the object detection module 152, and they can be additionally detected. .

7 is a block diagram showing a shipment measurement unit 150_2 according to another embodiment of the present application in more detail. The shipment measurement unit 150_2 of FIG. 7 is similar to the shipment measurement unit 150_1 of FIG. 5 . Accordingly, identical or similar elements are designated using identical or similar reference numerals. Also, for brevity, redundant descriptions will be omitted below.

Referring to FIG. 7 , the shipment measurement unit 150_2 according to an embodiment of the present application may further include a database (DB) for receiving ripeness data for crop objects detected by the shipment measurement module 155 and storing them. can

For example, the shipment amount measurement module 155 determines the ripeness of tomatoes derived from the ripeness measurement module 154 through the object detection module 152 and the attention module 156 . The shipment measurement module 155 may store the data in the database 157 in order to convert the determined data into a database (DB). Thereafter, the shipment measurement module 155 may derive the number of tomatoes corresponding to the color change period in the case of export tomatoes and the color period in the case of domestic tomatoes by referring to the data stored in the database (DB).

8 is a block diagram showing a crop shipment measuring device 100_1 according to another embodiment of the present application. The crop shipment measurement device 100_1 of FIG. 8 is similar to the crop shipment measurement device 100 of FIG. Accordingly, identical or similar elements are designated using identical or similar reference numerals. Also, for brevity, redundant descriptions will be omitted below.

Referring to FIG. 8 , the crop shipment measurement apparatus 100_1 according to an embodiment of the present application may include a plurality of image collection units 110 .

For example, each of the plurality of image collection units 110_1 to 110_n may be installed at each location of a target crop to collect an image of the crop. As another example, the plurality of image collectors 110_1 to 110_n may be installed at a predetermined distance from each other. In this case, the plurality of image collectors 110_1 to 110_n may configure a network through wifi or a wired network.

In this case, the shipment measurement unit 150 may derive the location of the shipmentable tomato based on the location of the image collection unit 110. For example, the shipment measurement unit 150 determines the ripeness of the detected tomato object. In this case, the shipment measurement unit 150 stores the number of tomatoes corresponding to the color change period in the case of export tomatoes and the color period in the case of domestic tomatoes in the database (DB). Based on the derived number, the shipment measurement unit 150 may calculate the location of the corresponding image collection unit 110 to measure the quantity and location of shipping tomatoes.

9 is a flowchart illustrating a method for measuring shipments of tomatoes according to an embodiment of the present application.

In step S110, the image collecting unit 110 (see FIG. 1) acquires an image (image data) of the crop. For example, the image collection unit 110 may be installed in a tomato growing greenhouse to acquire and collect images of tomatoes.

In step S120, the image relay unit 130 (see FIG. 1) transmits the obtained crop image to the shipment measurement unit 150. For example, the video relay unit 130 may receive images of tomatoes from the image collection unit 110 and transmit them sequentially or simultaneously to the shipment measurement unit 150 .

In step S130, the shipment measurement unit 150 (see FIG. 1) receives a crop object image. For example, the image receiving module 151 (see FIG. 3 ) of the shipment measurement unit 150 may receive an image of tomatoes from the image relay unit 130 .

In step S140, the shipment measurement unit 150 detects crop objects in the received image. For example, the object detection module 152 (see FIG. 3 ) of the shipment measurement unit 150 may detect a tomato object from the received tomato image. As another example, the object detection module 152 and the attention module 156 of the shipment measurement unit 150 may detect a tomato object from the received tomato image.

In step S150, the shipment measurement unit 150 measures the detection accuracy of the detected crop object and determines whether it is equal to or greater than a predetermined object detection threshold. For example, the detection accuracy measurement module 153 of the shipment measurement unit 150 measures the detection accuracy of the detected tomato object, and determines whether the detection accuracy is greater than or equal to a predetermined object detection threshold.

If the detection accuracy is greater than or equal to the preset object detection threshold, the shipment amount measurement unit 150 measures the maturity of the corresponding crop object and determines whether the maturity of the corresponding crop object is equal to or greater than the preset maturity threshold (step S160). For example, the ripeness measuring module 154 (see FIG. 3 ) of the shipped quantity measurer 150 measures the ripeness of the selected tomato object and determines whether the ripeness of the corresponding tomato is equal to or greater than a preset ripeness threshold.

If the maturity of the corresponding crop object is equal to or greater than the preset maturity threshold, the shipment quantity measurement unit 150 increases the quantity of the crop object that can be shipped by “1” (step S170). For example, the shipment measurement module 155 (see FIG. 3 ) of the shipment measurement unit 150 determines that a tomato object whose ripeness is equal to or higher than a threshold value can be shipped, and increases the quantity of tomatoes that can be shipped by “1”. In step S180, the shipment measurement unit 150 determines whether all of the detected crop objects can be shipped. If the detection accuracy and maturity measurement operation is performed for all detected objects, the shipment measurement unit 150 outputs the shipment amount of the crop object (step S190).

10 is a diagram showing an example of applying the shipment measurement system according to an embodiment of the present application to a smart farm.

Referring to Figure 10, the shipment measurement system can also be applied to the smart farm (2000). The smart farm 2000 may include a shipment measurement system, a server 300, and a user terminal 400. The shipment measurement system includes an image collection unit 110, a video relay unit 130, and a shipment measurement unit 150, and the video collection unit 110, the video relay unit 130, and the shipment measurement unit 150 are shown in FIG. Since the image collection unit 110, the image relay unit 130, and the shipment measurement unit 150 disclosed in 1 are the same, detailed descriptions will be omitted. In one embodiment of the present invention, the shipment measurement system may be placed inside or outside crop cultivation facilities such as greenhouses or vinyl houses. The shipment measurement system may communicate with the user terminal 400 through the server 300 .

For example, the user terminal 400 includes a smartphone, a smart pad, a tablet PC, a wearable device, a personal communication system (PCS), a global system for mobile communication (GSM), and a personal digital cellular (PDC). , PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (WirelessBroadband Internet) It may be all kinds of wireless communication devices such as terminals, desktop computers, and stationary terminals such as smart TVs.

The server 300 connects the user terminal 400 and the shipment measurement system to enable communication with each other.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art or those having ordinary knowledge in the art do not deviate from the spirit and technical scope of the present invention described in the claims to be described later. It will be understood that the present invention can be variously modified and changed within the scope not specified.

Therefore, the technical scope of the present invention is not limited to the contents described in the detailed description of the specification, but should be defined by the claims.

100: Tomato shipment measurement device
110: image collection unit
111: image acquisition module
112: video transmission module
130: video relay unit
150: shipment measurement unit
151: video receiving module
152: object detection module
153: detection accuracy measurement module
154: maturity measurement module
155: shipment measurement module
156: Attention module
157 DB
300: server
400: user terminal
2000 : Smart Farm

Claims (17)

An image collection unit for collecting crop images; and
A shipment measurement unit detecting a plurality of crop objects from the crop image and measuring the quantity of crops that can be shipped based on the detection accuracy and maturity of each of the plurality of crop objects,
The shipment measurement unit,
an object detection module detecting the plurality of crop objects from the crop image; and
An attention module for additionally detecting crop objects based on a heat map for crop objects not detected by the object detection module,
The object detection value through the heat map is an average value around the crop object and a median value of the crop object detection value, crop shipment measurement device.
According to claim 1,
The shipment measurement unit,
an image receiving module for receiving the crop image;
a detection accuracy measurement module for measuring detection accuracy of each of the plurality of crop objects;
a maturity measurement module for measuring the maturity of crop objects whose detection accuracy measured by the detection accuracy measurement module among the plurality of crop objects is greater than or equal to a predetermined object detection threshold value; and
When the maturity measured by the maturity measurement module is greater than or equal to the preset object maturity threshold, the crop shipment measurement device further comprising a shipment measurement module that increases the quantity of shipmentable crop objects by “1”.
delete According to claim 1,
The object detection module,
Apparatus for measuring crop shipments, which first determines whether or not there is a crop object in an individual image frame of the received crop image, and displays an image position of the crop object when the crop object exists.
According to claim 4,
The object detection module,
A crop shipment measurement device that compares the learned image and the received crop image using an artificial intelligence module to determine whether the image matches, and detects a portion having a high convolutional product compared to the learned image as the crop object. According to claim 2,
The maturity measurement module,
Extracting an image with respect to the image of the crop object in the crop image with a boundary where the HSV color value changes by more than a preset value, and displaying the degree of distribution of the HSV color value in a histogram for the extracted image, Crop yield measurement device. According to claim 6,
Characterized in that the crop is a tomato, crop shipments measuring device. According to claim 7,
The ripeness measuring module classifies the ripening period, discoloration period, coloration period, painting period, light red period, and maturity period according to the appearance state in order to classify the ripeness of the tomato. According to claim 2,
The shipment measurement module determines the maturity of the crops derived through the object detection module and the attention module, and stores the determined data in a database. According to claim 9,
The crop is tomato,
The shipment measurement module derives the number of tomatoes corresponding to the discoloration period in the case of export tomatoes and the coloration period in the case of domestic tomatoes from the database, calculates the location of the image collection unit based on the number, and determines the location of the tomatoes that can be shipped. A device for measuring crop yields.
delete According to claim 1,
The image collection unit may include an image acquisition module acquiring the crop image; and
Crop shipment measurement device comprising an image transmission module for transmitting the crop image to the shipment measurement unit. According to claim 12,
The video transmission module includes a Raspberry Pi,
Crop shipment measurement device for transmitting image data generated by the Raspberry Pi to the shipment measurement unit. According to claim 1,
Crop shipment measurement device further comprising an image relay unit for transmitting the crop image from the image collection unit to the shipment measurement unit. Receiving crop image data;
detecting a plurality of crop objects from the image data;
Measuring detection accuracy for each of the plurality of crop objects;
Measuring the maturity of a crop object for an object whose detection accuracy is greater than or equal to a threshold value among the plurality of crop objects.
increasing the yield by 1 when the ripeness of the crop object is greater than or equal to a threshold value; and
Further detecting crop objects based on a heat map for crop objects not detected in the step of detecting the plurality of crop objects,
The object detection value through the heat map is an average value around the crop object and a median value of the crop object detection value.
At least one image collection unit for collecting crop images;
Based on the image of the crop, a shipment amount measurement unit providing a shipment amount of the crop;
an image relay unit transmitting the crop image from the image collection unit to the shipment measurement unit;
a server capable of communicating with the shipment measurement unit; and
Including a user terminal capable of communicating with the shipment measurement unit through the server,
The shipment measurement unit,
Detecting a plurality of crop objects from the crop image, measuring the quantity of crops that can be shipped based on the detection accuracy and maturity of each of the plurality of crop objects,
The shipment measurement unit,
an object detection module detecting the plurality of crop objects from the crop image; and
An attention module for additionally detecting crop objects based on a heat map for crop objects not detected by the object detection module,
The object detection value through the heat map is the average value around the crop object and the median value of the crop object detection value, crop shipment measurement system.
An image receiving module for receiving a crop image;
an object detection module detecting a plurality of crop objects from the crop image;
a detection accuracy measurement module for measuring detection accuracy of each of the plurality of crop objects;
a ripeness measuring module for measuring the maturity of crop objects with respect to crop objects whose measured detection accuracy is greater than or equal to a preset object detection threshold value among the plurality of crop objects; and
When the measured maturity is greater than or equal to a preset object maturity threshold, a shipment amount measurement module that increases the number of crop objects that can be shipped by “1”,
The shipment measurement module,
An attention module for additionally detecting crop objects based on a heat map for crop objects not detected by the object detection module,
The object detection value through the heat map is an average value around the crop object and a median value of the crop object detection value, crop shipment measurement device.

Images