TWI806721B - Autonomous Mobile Artificial Intelligence Mushroom Cultivation Monitoring System and Method - Google Patents

Abstract

The present invention discloses an autonomously mobile artificial intelligence mushroom cultivation monitoring system and method, which includes a single-soldier autonomously mobile inspection vehicle, an image capture unit, a growth environment sensing unit, a field map information building module, a growth State identification module, inspection path planning module and growth environment control module. The map image and the mushroom image in the mushroom cultivation field are captured by the image capture unit. Use the field map data building module to build ground channel map data and mushroom basket rack map data based on map images. The growth environment data of mushrooms is sensed by the growth environment sensing unit. The growth state recognition module compares the mushroom image with the reference mushroom image to determine whether the mushroom is growing slowly. Use the inspection path planning module to plan and set the walking path and multiple parking positions on the walking path according to the map information of the ground passage, and plan and set the detection path and the parking positions on the detection path according to the map information of the mushroom basket rack Multiple detection positions. Use the walking control module to control the individual autonomous mobile inspection vehicle to walk on the ground passage and park at each parking position according to the walking path. The image capture unit and growth environment sensing unit move to each parking position and detection position sequentially with the individual autonomous mobile inspection vehicle and transfer mechanism to capture mushroom images and sense the growth environment data. When the growth state identification module judges that the mushroom grows slowly, the growth environment regulation module regulates the temperature, humidity and Carbon dioxide concentration to accelerate the growth of mushrooms. In order to achieve the purpose of individual operation to simplify the system and intelligently and effectively monitor the growth of mushroom cultivation fields.

Description

Autonomous Mobile Artificial Intelligence Mushroom Cultivation Monitoring System and Method

The present invention relates to a self-moving artificial intelligence mushroom cultivation monitoring system and method, especially an artificial intelligence mushroom cultivation monitoring technology that can quickly interpret the mushroom growth environment information through the function setting of the visual growth environment chart .

By the way, the edible mushroom industry in Taiwan has a record of man-made planting of shiitake mushrooms since 1909. Up to now, it has a development history of more than one hundred years. Among the various mushrooms grown in China, Pleurotus eryngii is the most popular in Taiwan It originated in 1996, but in just ten years, Pleurotus eryngii has replaced Flammulina velutipes as the second highest value mushroom species, so it is not difficult to find that Pleurotus eryngii is the only mushroom whose output has maintained growth in recent years and has little price fluctuation kind. At present, Pleurotus eryngii and Flammulina velutipes are also cultivated under environmental control, but the degree of automation is far inferior to Flammulina velutipes. The reasons include that most of the industry is produced in bag-grown space packs instead of bottle-grown, followed by Pleurotus eryngii Compared with other mushroom species, automation development started late, especially in the harvesting process, while the outline and size of bag-grown space packs are less consistent than those of bottle-grown, and the number of Taiwan-grown strain suppliers in China accounts for Relatively few, mainly packagers and cultivators account for the majority, highlighting the problem of fewer strains, and this also indirectly affects the final appearance of Pleurotus eryngii, which has a certain degree of impact on harvesting automation.

In addition, the traditional mushroom industry requires a lot of manpower for inspection work. The environment in the warehouse is narrow and humid and there are a large number of warehouses. If traditional manpower is used for inspection work, it will take a lot of time and staffing; similar to that diffused at maturity The spores will also affect the respiratory tract of mushroom growers. If smart agriculture can be applied to the mushroom industry, it will greatly reduce the need to rely on manpower and achieve the goal of automated production.

In order to achieve the purpose of automatic inspection, the applicant proposed a patent as shown in the invention certificate No. I719924 "Mushroom Growth Monitoring System and Method", which includes inspection self-driving cars, growth environment control modules and central control unit. The inspection self-driving car includes a power drive device with traveling wheels, a signal processing unit, a growth environment state sensing module, and a growth image capture unit. The signal processing unit controls the inspection self-driving car to walk along the preset inspection path arranged on the ground passage of the mushroom cultivation field, and arrive at the inspection parking positions and parking positions distributed on the preset inspection path in sequence , and control the growth environment state sensing module and the growth image acquisition unit to sense the real-time mushroom growth environment state and the mushroom growth image respectively. The central control unit receives and processes the growth environment status and mushroom growth images of mushrooms to generate real-time growth environment status parameters and real-time growth image feature parameters in the corresponding real-time cultivation time series, and generates real-time growth environment status parameters and real-time growth image feature parameters. The parameters are compared with the reference growth environment state parameters and reference growth image characteristic parameters of the corresponding reference mushroom cultivation time series. When the difference between the comparison results exceeds a predetermined range, the central control unit controls and starts the growth environment control equipment to adjust The state of the mushroom growth environment in the mushroom cultivation field.

Although the patent has functions such as automatic inspection of the mushroom cultivation field and adjustment of the mushroom growth environment according to the growth state; however, the patent does not have the function setting of a visual growth environment chart, so that the operator cannot quickly interpret the mushrooms. The growth environment information makes it more difficult to create a more suitable environment for the growth of mushrooms; moreover, this patent cannot use big data collection, artificial intelligence frame selection and training, so that it is impossible to predict the production quantity of mushrooms in the warehouse , making it impossible to accelerate or slow down the growth rate of mushrooms in response to market demand.

In view of the fact that there is no mushroom cultivation monitoring technology, patent, or paper published or published without visual growth environment charts and mushroom yield predictions, the above-mentioned conventional technologies and the aforementioned patents are indeed not perfect, and there are still The necessity of further improvement; the reason is that the inventor is actively investing in research and development, and finally has the research and development results of the present invention.

The first purpose of the present invention is to provide an autonomous mobile artificial intelligence mushroom cultivation monitoring system and method that can simplify the system and intelligently and effectively monitor the growth of the mushroom cultivation field. The technical means adopted to achieve the first objective of the present invention include a single-soldier autonomous mobile inspection vehicle, an image capture unit, a growth environment sensing unit, a field map data construction module, a growth status identification module, Inspection path planning module, growth environment regulation module and central processing unit. Use the image capture unit to capture map images and mushroom images in the mushroom cultivation field, and use the field map information construction module to construct ground passage map information including the mushroom cultivation field and Field map map information for mushroom basket racks. The growth environment data of the mushrooms in the mushroom cultivation field is sensed by the growth environment sensing unit. The growth state recognition module compares the mushroom image with the preset reference mushroom image in a database, and judges whether the mushroom grows slowly. Use the inspection path planning module to plan and set the walking path and multiple parking positions on the walking path according to the map information of the ground passage, and plan and set the detection path and the parking positions on the detection path according to the map information of the mushroom basket rack Multiple detection positions. Use the walking control module to control the individual autonomous mobile inspection vehicle to walk on the ground passage of the mushroom cultivation field according to the walking path and stop at each parking position in sequence. The image capture unit and the growth environment sensing unit are installed on the individual autonomous mobile inspection vehicle through the transfer mechanism, and move to each parking position sequentially with the individual autonomous mobile inspection vehicle , and the image capture unit is driven by the transfer mechanism The element and the growth environment sensing unit stop at each detection position sequentially, so that the image capture unit can capture mushroom images and the growth environment sensing unit can sense growth environment data. The growth environment control device is driven by the growth environment control module to control the temperature, humidity and carbon dioxide concentration in the mushroom cultivation field. When the growth state identification module judges that the at least one mushroom grows slowly, the growth environment regulation module regulates the mushroom cultivation field according to a first growth environment condition parameter preset and matched in the database The temperature, humidity and carbon dioxide concentration inside to accelerate the growth of mushrooms.

The second purpose of the present invention is to provide an autonomous mobile artificial intelligence mushroom cultivation monitoring system and method with the function of predicting mushroom production, mainly by using big data collection, artificial intelligence frame selection and training to monitor the mushrooms in the warehouse. Class for production quantity forecasting. The technical means adopted to achieve the second objective of the present invention include a single-soldier autonomous mobile inspection vehicle, a central processing unit, a growth environment sensing unit and a display unit. The single-soldier autonomous mobile inspection vehicle performs autonomous inspection tasks in the ground passage of the mushroom cultivation field. It also includes a signal processing module, a walking control module and a visual chart display module. The growth environment sensing unit sequentially senses the growth environment status of each parking position along with the individual autonomous mobile inspection vehicle to generate growth environment sensing signals, which are converted and processed into growth environment data by the signal processing module. The visual chart display module converts the growth environment data into chart format data. The growth recording module collects and records the data in chart format sequentially along the time axis as a growth environment file. The display unit displays the growth environment file as a visual growth environment chart and growth environment data. It also includes a transfer mechanism and an image capture unit arranged on the transfer mechanism, which can be controlled by the signal processing module to move multi-axis on the individual autonomous mobile inspection vehicle, so that the image capture unit Together with the growth environment sensing unit, it is carried and moved to each stop along with the individual autonomous mobile inspection vehicle and the transfer mechanism. Stationary position and each detection position. Each detection position is set with a position code. A plurality of mushroom basket racks are arranged side by side in the mushroom cultivation field, and the plurality of mushroom basket racks are separated from each other to form the plurality of ground passages, and each mushroom basket rack includes a plurality of bottom-up distribution racks. Placement, each placement position is for placing a mushroom basket, and each mushroom basket is to place a plurality of space bags cultivated with mushrooms. When the image capture unit arrives at the parking position, the transfer mechanism drives the image capture unit to stop at each detection position sequentially, so that the image capture unit sequentially captures images of mushrooms in the space bag at each detection position. When the growth recording module superimposes the corresponding position code on each mushroom image one by one, the growth recording module sequentially records the mushroom images superimposed with the position code in the form of a file along the time axis as a growth image file . The growth status identification module includes a mushroom quantity estimation module and a feature database with multiple mushroom head feature samples built in. The mushroom quantity estimation module performs image processing on mushroom images and crops overlapping edges. part, and extract features from mushroom images as mushroom head features, and then perform image recognition processing for counting the number of mushrooms, so as to sequentially input the multiple mushroom head features into the feature database to predict the number of mushrooms The coincidence probability of the plurality of mushroom head features and the mushroom head feature sample, when the coincidence probability is greater than a preset probability, the estimated value of the number of mushrooms at each detection position is output, and then the number of mushrooms at each detection position The estimated value of the mushroom quantity is calculated cumulatively to obtain the estimated information of the mushroom quantity in the entire mushroom cultivation field.

The third object of the present invention is to provide an autonomous mobile artificial intelligence mushroom cultivation monitoring system and method equipped with a thermal imaging camera to sense the growth temperature of the mushroom itself. The technical means adopted to achieve the fourth objective of the present invention include a single-soldier autonomous mobile inspection vehicle, a central processing unit, a growth environment sensing unit and a display unit. The single-soldier autonomous mobile inspection vehicle performs autonomous inspection tasks in the ground passage of the mushroom cultivation field. It also includes a signal processing module, a walking control module, and a visual chart display module. There are multiple parking positions on the walking path. born The long environment sensing unit can sequentially sense the growth environment status of each parking position along with the individual autonomous mobile inspection vehicle to generate growth environment sensing signals, which are converted and processed into growth environment data by the signal processing module. The visual chart display module converts the growth environment data into chart format data. The growth recording module collects and records the data in chart format sequentially along the time axis as a growth environment file. The display unit displays the growth environment file as a visual growth environment chart and growth environment data. It further includes a thermal imager arranged on the transfer mechanism and located near the image capture unit. When the thermal imager reaches one of the parking positions, the signal processing module controls the transfer mechanism to drive the thermal imager. The imager stays at each of the detection positions in sequence, so that the thermal imager sequentially shoots the mushroom thermal images of the space bag at each of the detection positions. When the signal processing module receives each of the detection positions in sequence In the case of thermal images of mushrooms, the corresponding position codes are sequentially superimposed on each thermal image of mushrooms one by one, and the color temperature distribution of each thermal image of mushrooms is analyzed and processed to determine the location of the detection position. Whether the temperature of the mushrooms in each of the space packs exceeds a preset temperature value, if the judgment result is yes, then an alarm signal corresponding to the position code that the temperature of the mushrooms is too high is sent.

1: Mushroom cultivation field

1a: Ground access

10:Individual-type autonomous mobile inspection vehicle

11: Optical radar

12: transfer mechanism

120: rotating mechanism

121: Transfer control module

121: lifting mechanism

122: motor

123: Ball lead screw

124: Nut

125: slider

126: slide rail

127: retractable link mechanism

128:Drive seat

129: Transfer control module

13: Image capture unit

13: Image capture unit

14: thermal imager

15: On-board power system

20: Central processing unit

210: Mushroom Quantity Estimation Module

210a: Artificial Intelligence Deep Learning Module

211: Feature database

212: Calculus model for counting the number of mushrooms

22: Walking control module

23:Visual chart display module

24: Growth record module

25: Setting Module

26: Field map data construction module

27: Growth state identification module

28: Inspection path planning module

30: Growth environment sensing unit

31,32: temperature/humidity sensor

33: Carbon dioxide concentration sensor

40: Display unit

41: Visualizing Growth Environment Charts

410: Environmental monitoring area

50: Mushroom basket rack

51: Mushroom Basket

52: Space Pack

60: Environmental control equipment

600: Growth environment regulation module

61:Control drive module

62: Wireless signal transmission module

pa: park position

pb: detection position

Fig. 1 is a schematic implementation diagram of the functional blocks of the specific architecture of the present invention.

Fig. 2 is a schematic diagram of the implementation of the inspection of the individual soldier autonomous mobile inspection vehicle in the field of mushroom cultivation according to the present invention.

Fig. 3 is a schematic diagram of a specific implementation of a single-soldier autonomous mobile inspection vehicle of the present invention.

Fig. 4 is a specific implementation schematic diagram of another individual soldier autonomous mobile patrol vehicle of the present invention.

FIG. 5 is a schematic diagram of the implementation process of the artificial intelligence deep learning module in the training phase of the present invention.

FIG. 6 is a schematic diagram of the implementation process of the artificial intelligence deep learning module in the prediction stage of the present invention.

Fig. 7 is a schematic diagram of the implementation of the image capture unit of the present invention shooting at the detection position of the mushroom cultivation field.

Fig. 8 is a schematic diagram of the screen display of growth environment graphs and data in each monitoring area of the present invention.

Fig. 9 is a schematic diagram of the implementation of the inspection process of the individual autonomous mobile inspection vehicle of the present invention.

Fig. 10 is a schematic diagram of a thermal imaging image of a mushroom cultivation field according to the present invention.

Fig. 11 is a schematic diagram of the present invention for calculating the number of mushrooms and intelligent frame selection at four viewpoints; Fig. 11a is point A; Fig. 11b is point B; Fig. 11c is point C; Fig. 11d is point D.

In order to allow your review committee to further understand the overall technical characteristics of the present invention and the technical means to achieve the purpose of the present invention, specific embodiments and accompanying drawings are hereby described in detail:

Please refer to Figures 1 to 4, in order to achieve the first purpose of the present invention, the first embodiment includes a single-soldier autonomous mobile inspection vehicle 10, a central processing unit 20, and a growth environment sensing unit 30 , a display unit 40 , an image capture unit 13 , a domain map information building module 26 , a growth state identification module 27 , a patrolling path planning module 28 and a growth environment control module 600 . A walking control module 22, a transfer mechanism 12 and a transfer control module 121 are provided on the individual soldier autonomous mobile inspection vehicle 10, and the travel control module 22 is used to control the individual soldier autonomous mobile inspection The carrier 10 operates, and the transfer control module 121 is used to control the transfer mechanism 12 to operate. The image capture unit 13 is used to capture a plurality of images in a mushroom cultivation field 1, and the plurality of images include at least one map image of the mushroom cultivation field 1 and at least one mushroom in a growth sequence image. The growth environment sensing unit 30 is used to sense multiple growth environment data of the mushrooms in the mushroom cultivation field, and the multiple growth environment data The data includes temperature data, humidity data and carbon dioxide concentration data. The field map data construction module 26 is used to construct a field map data according to the at least one map image captured by the image capture unit 13; wherein, the field map data includes the mushroom cultivation At least one map of the ground passage and at least one map of the mushroom basket rack in Field 1. The growth state identification module 27 is used to process the at least one mushroom image and compare it with a reference mushroom image preset in a database that is the same as the growth time series; wherein, when the at least one mushroom image is smaller than the reference mushroom image When the image of the mushrooms and the difference is greater than a first predetermined threshold, it is determined that the at least one mushroom is slow-growing. The inspection path planning module 28 is used to plan and set at least one walking path and a plurality of parking positions on the at least one walking path according to the at least one ground passage map information, and according to the at least one mushroom basket placement map Planning and setting at least one detection path and a plurality of detection positions on the at least one detection path; the walking control module 22 is used to control the individual-type autonomous mobile inspection vehicle 10 according to the inspection path planning model The at least one walking path planned by the group 28 travels through the plurality of ground passages 1 a of the mushroom cultivation field 1 and stops at each of the plurality of parking positions pa in sequence during at least one predetermined inspection period. Wherein, the image capture unit 13 and the growth environment sensing unit 30 are set on the individual-type autonomous mobile inspection vehicle 10 through the transfer mechanism 12, and follow the individual-type autonomous mobile inspection vehicle. The tool 10 moves to each of the plurality of parking positions pa in sequence; the transfer control module 121 is used to control the transfer mechanism 12 to drive the image capture unit 13 and the growth environment sensing unit 30 according to the The at least one detection path planned by the inspection path planning module 28 stops at each of the plurality of detection positions pb in the mushroom cultivation field 1 sequentially based on each of the parking positions, so that the The image capture unit 13 can capture the at least one mushroom image, and enable the growth environment sensing unit 30 to sense the plurality of growth environment data. The growth environment control module 600 is used to drive at least one growth environment control device to control the temperature, humidity and carbon dioxide concentration in the mushroom cultivation area 1; wherein, when the growth state identification module 27 judges that the at least one mushroom is During slow growth, the growth environment regulation module 600 The temperature, humidity and carbon dioxide concentration in the mushroom cultivation field 1 are adjusted according to a first growth environment condition parameter preset and matched in the database, so as to accelerate the growth of the at least one mushroom. The central processing unit 20 is used to integrate and process the walking control module 22, the transfer control module 121, the image capture unit 13, the growth environment sensing unit 30, the field map data construction module 26, The signals and information of the growth state identification module 27 , the inspection path planning module 28 and the growth environment regulation module 600 . Preferably, when the at least one mushroom image is larger than the reference mushroom image and the difference is greater than a second predetermined threshold, it is judged that the at least one mushroom is over-growing; when the growth state identification module 27 judges that the When at least one mushroom grows over-speed, the growth environment regulation module 600 regulates the temperature and humidity in the mushroom cultivation field 1 according to a second growth environment condition parameter preset and matched in the database and carbon dioxide concentration to slow down the growth of the at least one mushroom. Preferably, the image capture unit 13 includes at least one LED fisheye supplementary light module 131, the at least one LED fisheye supplementary light module 131 is used to provide supplementary light when the image capture unit 13 is activated, To improve the quality of the plurality of images captured in the dark mushroom cultivation field 1 . Execute the method of the present invention, that is, use the image capture unit 13 to capture a plurality of images in a mushroom cultivation field 1, and the plurality of images include at least one map image of the mushroom cultivation field 1 and in a growth sequence at least one mushroom image; use the growth environment sensing unit 30 to sense a plurality of growth environment data of mushrooms in the mushroom cultivation field 1, the plurality of growth environment data includes temperature data, humidity data and carbon dioxide concentration data; use the field map data construction module 26 to construct a field map data according to the at least one map image captured by the image capture unit 13, and the field map data includes the At least one ground passage map and at least one mushroom basket rack map of the mushroom cultivation field 1; the at least one mushroom image is processed by the growth state identification module 27 and is the same as the one preset in a database. Comparing the reference mushroom images of the growth time series; wherein, when the at least one mushroom image is smaller than the reference mushroom image and the difference is greater than a first predetermined threshold value, it is determined that the at least one mushroom is retarded growth Long; use the inspection path planning module 28 to plan and set at least one walking path and a plurality of parking positions pa on the at least one walking path according to the at least one ground passage map information, and according to the at least one mushroom basket Plan and set at least one detection path and a plurality of detection positions pb on the at least one detection path by setting up the frame map data; the walking control module 22 is used to control the individual soldier autonomous mobile inspection vehicle 10 according to the inspection Checking the at least one walking path planned by the path planning module 28, walking in the plurality of ground passages 1a of the mushroom cultivation field during at least one predetermined inspection period and stopping at each of the plurality of parking positions pa in sequence Make the image capture unit 13 and the growing environment sensing unit 30 set on the individual-type autonomous mobile inspection vehicle 10 through the transfer mechanism 12, and follow the individual-type autonomous mobile inspection vehicle The tool 10 moves to each of the plurality of parking positions pa in sequence; the transfer control module 121 is used to control the transfer mechanism 12 to drive the image capture unit 13 and the growth environment sensing unit 30 according to the The at least one detection path planned by the inspection path planning module 28 stops at each of the plurality of detection positions pb in the mushroom cultivation field 1 sequentially based on each of the parking positions, so that the The image capture unit 13 can capture the at least one mushroom image, and enable the growth environment sensing unit 30 to sense the plurality of growth environment data; use the growth environment control module 600 to drive at least one growth environment control device 60 to regulate the temperature, humidity and carbon dioxide concentration in the mushroom cultivation area 1; wherein, when the growth state identification module 27 judges that the at least one mushroom grows slowly, the growth environment regulation module 600 then according to the A first growth environment condition parameter preset and matched in the database is used to regulate the temperature, humidity and carbon dioxide concentration in the mushroom cultivation field 1, so as to accelerate the growth of the at least one mushroom; wherein, when the growth state is identified When the module 27 determines that the at least one mushroom is overgrown, it regulates the temperature, humidity and carbon dioxide in the mushroom cultivation field 1 according to a second growth environment condition parameter preset in the database. Concentration, to slow down the growth of the at least one mushroom; and use the central processing unit 20 to integrate and process the walking control module 22, the transfer control module 121, the image capture unit 13, the growth environment The signals and information of the sensing unit 30 , the field map information construction module 26 , the growth state identification module 27 , the inspection path planning module 28 and the growth environment control module 600 .

Please refer to Figures 1 to 4. In a specific embodiment, the individual soldier-type autonomous mobile inspection vehicle 10 is executed in multiple ground passages 1a of a mushroom cultivation field 1 at each preset interval. Autonomous inspection tasks. A signal processing module 21 with a built-in walking path further includes a visual chart display module 23, a growth recording module 24 and a wireless signal transmission module 62. The central processing unit 20 integrates and processes the visual chart display module, the growth recording module 24 and the wireless signal transmission module 62 for signals and information. The traveling path is set with a plurality of parking positions pa. The travel control module 22 is controlled by the signal processing module 21 to drive the individual autonomous mobile inspection vehicle 10 to travel along the travel path in multiple ground passages 1 a and to park at each parking position pa sequentially. The growth environment sensing unit 30 is installed on the individual autonomous mobile inspection vehicle 10 via the transfer mechanism 12, and can sense the growth environment sequentially as the individual autonomous mobile inspection vehicle 10 performs inspection tasks. Each parking position pa corresponds to the growth environment state of each detection position pb to generate a growth environment sensing signal, and the signal processing module 21 converts and processes the growth environment data corresponding to the growth environment sensing signal. The growth environment data is selected At least two of temperature, humidity and carbon dioxide concentration. The visual chart display module 23 is used to convert the growth environment data into chart format data displayed in a visual chart manner. The growth recording module 24 is set on the individual soldier-type autonomous mobile inspection vehicle 10, and sequentially collects the chart format data and the growth environment data along a time axis with each preset interval as a file. Recorded as a growth environment file. The visualized graph display module 23 transmits the visualized growth environment graph and the growth environment data to an electronic device via the wireless signal transmission module 62 for display by a display unit of the electronic device.

Please refer to the embodiment shown in Figure 8. This embodiment is a specific embodiment of the above-mentioned first embodiment to more specifically describe the visualization of the growth environment chart 41 technology. The chemical growth environment graph 41 is equally divided into a plurality of environmental monitoring areas 410 that are arrayed and correspond to the plurality of parking positions one by one. Coding of resident positions (pa1, pa2, pa3, pa4). Each of the plurality of environmental monitoring areas 410 is divided into a plurality of data monitoring areas in an array and corresponding to the plurality of detection positions one by one, and each of the plurality of data monitoring areas is marked with a corresponding number of each of the plurality of detection positions Code (pb101, pb102, pb103, pb104, pb201, pb202, pb203, pb204, pb301, pb302, pb303, pb304, pb401, pb402, pb403, pb404) and display the corresponding real-time Temperature data, humidity data and carbon dioxide concentration data.

Please cooperate with referring to the embodiment shown in Fig. 1, 3 and Fig. 4, this embodiment is the concrete embodiment that more specifically describes technologies such as growth environment file and path planning in the above-mentioned first embodiment, and this growth environment file system is based on one day A unit is arranged according to the date, and when the central processing unit reads one of the growth environment files according to the needs, each environment monitoring area 410 displays temperature curves and humidity curves that change along the time axis Figure and carbon dioxide concentration curve; the individual autonomous mobile inspection vehicle 10 is equipped with at least one optical radar 11, the signal processing module 21 passes through at least one optical radar 11, and cooperates with the ROS SLAM algorithm to perform field map data and then import the established map into the walking path to perform autonomous inspection tasks in the mushroom cultivation field 1, and record the path points as the plurality of parking positions pa in the plurality of ground passages 1a.

Please refer to Figures 1-4 and Figures 7-8, in order to achieve the second embodiment of the second purpose of the present invention, this embodiment not only includes the overall technical content of the above-mentioned first embodiment, but also includes The military-style autonomous mobile inspection vehicle 10 can be controlled by the signal processing module 21 to perform multi-axis movement of the transfer mechanism 12 and the image capture unit 13 arranged on the transfer mechanism 12, so that the image capture unit 13 and The growth environment sensing unit 30 is carried and moved to each parking position pa along with the individual autonomous mobile inspection vehicle 10 and the transfer mechanism 12; the signal processing module 21. Each parking position pa is set with a plurality of detection positions pb, and each detection position pb is set with a position code. The mushroom cultivation field 1 is juxtaposed with a plurality of mushroom basket racks 50, the plurality of mushroom basket racks 50 are separated from each other to form a plurality of ground passages 1a, and each of the plurality of mushroom basket racks 50 includes a plurality of There are two placement positions distributed from bottom to top, and each placement position is for placing a mushroom basket 51, and each mushroom basket 51 places a plurality of space bags 52 that are cultivated with mushrooms; when the image capture unit 13 arrives at one of them When parked at the position pa, the signal processing module 21 controls the transfer mechanism 12 to drive the image capture unit 13 to stop at each detection position pb sequentially, so that the image capture unit 13 sequentially takes pictures of space at each detection position pb. Packet 52 of the mushroom images, when the signal processing module 21 receives the mushroom images in sequence, the corresponding position codes are superimposed on each mushroom image one by one, and the signal processing module 21 drives growth The recording module sequentially records the images of mushrooms superimposed with position codes in the form of files along the time axis as growth image files. The signal processing module 21 includes a mushroom quantity estimation module 210 and a feature database 211 with a plurality of mushroom head feature samples built in. When the mushroom quantity estimation module 210 receives the image capture unit 13 When detecting the mushroom images taken at position pb, perform image processing and cut out the overlapped parts of the edges, and sequentially perform feature extraction on the mushroom images to generate multiple mushroom head features, and then perform the calculation of the number of mushrooms image recognition processing, so as to sequentially input the multiple mushroom head features into the feature database 211 to predict the matching probability of the multiple mushroom head features and the mushroom head feature samples, when the matching probability is greater than a preset probability , the estimated value of the number of mushrooms at the detection position pb is output; when the mushroom number estimation module 210 receives the mushroom image captured by the image capture unit 13 at the next detection position pb, the above-mentioned image processing is repeated , cropping and image recognition processing steps, and calculate and output the estimated value of the number of mushrooms at the next detection position pb, until all the mushroom images at the detection position pb have completed the above steps of image processing, cropping and image recognition processing, etc. , and then cumulatively calculate the estimated mushroom quantity of each detection position pb, so that the estimated mushroom quantity information of the entire mushroom cultivation field 1 can be obtained. Please also refer to FIG. 7 , where IA is the shooting range of the image capture unit 13 at one of the detection positions pb, that is, the shooting range of the mushroom image. The transfer mechanism 12 is a multi-axis transfer mechanism; the walking control module 22 includes an obstacle avoidance module, the obstacle avoidance module includes at least one optical radar, and the at least one optical radar moves autonomously in the individual soldier When the inspection vehicle 10 walks, it senses whether there is an obstacle on the at least one walking path, and when it senses that there is an obstacle before arriving at the next plurality of parking positions, the at least one walking path is corrected so that the The single-soldier autonomous mobile inspection vehicle 10 can reach the next plurality of parking positions, and then continue the follow-up journey of the at least one walking path; wherein, when the obstacle is at one of the plurality of parking positions, The walking control module 22 controls the individual autonomous mobile inspection vehicle 10 to park at one of the plurality of parking positions adjacent to the obstacle, and the transfer control module 121 is based on Comparing the coordinates of the parking position with the coordinates of the plurality of parking positions with the obstacle to obtain a compensation displacement coordinate parameter, and controlling the multi-axis transfer mechanism to move according to the compensation displacement coordinate parameter The image capture unit 13 and the growth environment sensing unit 30 are sequentially transferred to each of the plurality of detection positions based on the plurality of parking positions where the obstacle is located.

Please refer to FIGS. 5-6 , this embodiment is a specific embodiment of the second embodiment using artificial intelligence image recognition technology. The growth state identification module 27 includes a mushroom quantity estimation module 210, and the mushroom quantity estimation module 210 includes an artificial intelligence deep learning module 210a, and the artificial intelligence deep learning module 210a is based on a training learning step In the feature database 211, a calculation model 212 for calculating the number of mushrooms is established, and a huge number of mushroom head feature samples, feature parameters of mushrooms, artificial intelligence frame selection parameters and image recognition are input into the calculation model 212 of mushroom numbers. parameters, and the calculation model 212 for calculating the number of mushrooms tests the image recognition accuracy rate of each mushroom image, and then judges whether the image recognition accuracy rate of each mushroom image is sufficient, and when the judgment result is yes, the identification result is output and stored; When the judgment result is negative, the calculation model 212 for calculating the number of mushrooms is made to self-correct and learn; when the artificial intelligence deep learning module 210a executes image recognition processing, it executes a step in the prediction stage, which is tied to the calculation model 212 for calculating the number of mushrooms Sequential input Real-time continuous input of cropped mushroom images, and counted by the number of mushrooms The calculation model 212 predicts and recognizes the estimated value of the number of mushrooms represented by the real-time input mushroom image, and then predicts and recognizes the estimated number of mushrooms in the entire mushroom cultivation field 1 .

Please refer to the third embodiment shown in Figure 4, in order to achieve the third embodiment of the third purpose of the present invention, in addition to the overall technical content of the above-mentioned first and second embodiments, the transfer mechanism 12 includes a horizontal A rotating mechanism 120 that rotates and a lifting mechanism 121 that can do longitudinal linear telescopic displacement and is located on the rotating mechanism 120, the lifting mechanism 121 includes a motor 122, a ball guide screw 123 with two mutually opposite thread segments , two nuts 124, a slide rail 126, a slide block 125 that can slide on the slide rail 126, a retractable linkage mechanism 127 and a drive seat 128 located on the slide block 125; the drive seat 128 is fixed The image capture unit 13 is provided, and the two nuts 124 are respectively sleeved on the opposite thread sections of the ball lead screw 123, so as to drive the two nuts 124 along a reverse thread on both sides of the ball lead screw 123. The segment is reversed. The two power input ends of the collapsible link mechanism 127 are rotatably pivoted to the two nuts 124, and the power output ends are pivotally connected to the drive seat 128; when the motor 122 drives the ball lead screw 123 to rotate, the two nuts are driven When 124 is reversely displaced to the outside, the interlocking retractable link mechanism 127 is in a retracted state, and the interlocking drive seat 128 and the slide block 125 move downward along the slide rail 126 (i.e. contraction action); when the motor 122 drives When the ball guide screw 123 reversely rotates to drive the second nut 124 to make a reverse displacement inwardly, the interlocking retractable link mechanism 127 is in an extended state, and interlockingly drives the driving seat 128 and the slider 125 to move upward along the slide rail 126 Move (i.e. stretch).

Please refer to Fig. 1, 3 and Fig. 4, in order to achieve the fourth embodiment of the fourth purpose of the present invention, in addition to the overall technical content of the above-mentioned first and second embodiments, this embodiment also includes The transfer mechanism 12 is a thermal imager 14 located near the image capture unit 13. When the thermal imager 14 arrives at one of the parking positions pa, the signal processing module 21 controls the transfer mechanism 12 to drive the thermal imager 14. The imager 14 stays at each detection position pb sequentially, so that the thermal imager 14 sequentially shoots the thermal images of the mushrooms in the space package 52 at each detection position pb. When the signal processing module 21 receives the thermal images of each mushroom in sequence image, the corresponding The position code of each mushroom is superimposed one by one on the thermal image of each mushroom, and the analysis and processing of the color temperature distribution of each thermal image of the mushroom is carried out to determine whether the temperature of the mushrooms in each space bag 52 at the detection position pb exceeds the preset temperature value , the judgment result is yes, then send out the warning signal that the temperature of the mushroom corresponding to the position code is too high.

Please refer to the fifth embodiment shown in Fig. 1, in order to achieve the fifth embodiment of the present invention, this embodiment not only includes the overall technical content of the above-mentioned first embodiment, but also includes a field 1 for regulating and controlling mushroom cultivation. The growth environment regulation equipment 60 and a control drive module 61 for the state of the growth environment. The growth environment regulation module 600 includes a setting module 25 which can be selected to be an accelerated growth mode, a normal growth mode and a slow growth mode. When the accelerated growth mode is selected with the setting module 25, the growth environment regulation module 600 then produces a control command for accelerated growth, and passes through a wireless signal transmission module 62 (such as a bluetooth communication module; but not with This limit) is transmitted to the control drive module 61, so as to control the drive module 61 to drive the growth environment regulation device 60, so that the growth environment conditions of the mushroom cultivation field 1 conform to the accelerated growth mode. When the normal growth mode is selected by the setting module 25, the growth environment regulation module 600 generates a control command for normal growth, and transmits it to the control driving module 61 through the wireless signal transmission module 62 to control the driving module 61 to drive the environmental control device 60, so that the growth environment conditions of the mushroom cultivation field 1 conform to the normal growth mode. When the growth slowing mode is selected by the setting module 25, the growth environment regulation module 600 generates a control command for slowing growth, and transmits it to the control driving module 61 through the wireless signal transmission module 62, and the control driving module 61 to drive the growth environment control device 60, so that the growth environment conditions of the mushroom cultivation field 1 conform to the mode of slowing growth.

Furthermore, based on the need to reduce manpower for inspections, an autonomous mobile smart device with self-navigation, obstacle avoidance, multi-point cruise, and various sensor data collection and uploading databases is designed and developed by using the existing mushroom house field configuration. IoT module, this module uses image recognition and artificial intelligence technology to achieve the purpose of mushroom production environment monitoring and production quantity prediction. The autonomous mobile intelligent IoT module of the present invention is developed and designed based on the mobile robot chassis architecture. This module is Build a robot operating system (Robot Operating System, ROS) based on Ubuntu, know the position and distance to obstacles through Lidar, and then communicate with the inertial measurement unit (Inertial Measurement Unit, IMU) and DC geared motor on the module Combined with the parameters of the Hall feedback on the Hall encoder to achieve the purpose of self-navigation, obstacle avoidance, and multi-point cruise. The production forecast quantity is based on big data collection, artificial intelligence frame selection and training, so that the autonomous mobile intelligent IoT module can take pictures in the production warehouse room, so as to predict the production quantity of the Pleurotus eryngii in the warehouse.

The implementation of the action flow control of the autonomous mobile intelligent IoT module designed and developed by the present invention is shown in Figure 9. After the small computer (i.e., the signal processing module) on the module is started, the chassis drive system and optical radar are used together with ROS The SLAM algorithm constructs the map data of the field, and imports the established map into ROS Navigation for autonomous navigation of the field and sets the recorded path points. Through ROS Python, the established map and the recorded path points are matched with the image capture system The image capture unit 13 (that is, the network camera; Logitech C525) and the transfer mechanism 12 (that is, the arm drive system) are used to take pictures to realize the needs of multi-point cruising and taking pictures in the field, and then import the pictures taken through the module into the The object detection system is used for object detection and quantity calculation of Pleurotus eryngii. In addition, after the module is turned on, the environmental sensing system is also activated. When the module reaches the set waypoint, the environmental sensing system will be triggered, and the industrial-grade sensor mounted on the module will be used to sense the environment in the field environment. Temperature, humidity and carbon dioxide concentration, and then send the sensor value to the self-built database server (MySQL) and LINE Notify of the production manager through the ESP32 single-chip computer, and then use the visualization software (Grafana) to transfer the value to Displayed in the form of charts to achieve the purpose of collecting, storing and displaying environmental sensing data.

The hardware system architecture of the present invention is shown in FIG. 1 , and can be divided into a signal processing module 21 (ie the upper system unit) and a transfer mechanism 12 (ie the lower execution unit). The upper system unit uses a small computer (ASUS Mini PC PB60G) as the core of the entire system architecture. The small computer runs the Ubuntu operating system and the ROS robot operating system. The main tasks include field SLAM map construction, field map data navigation, and computer vision. It is used for object judgment, and communicates with USB through ROS for The lower-level execution unit sends commands, receives and processes data from the lower-level units. The lower execution unit is divided into chassis drive system, environment sensing system, and arm drive system. The chassis drive system is mainly responsible for the control of the DC motor, the processing of the Encoder signal, and the signal processing of the MPU9250 nine-axis acceleration sensor through the STM32 development board developed by the manufacturer. The environmental sensing system uses the temperature and humidity sensors 31, 32 (eYc THS13) and carbon dioxide concentration sensors 33 (eYc GS43) loaded on the smart IoT module, and then uses the ESP32 DOIT DEVKIT single-chip computer to transmit the sensor values to the self-built The configured database and LINE Notify of the production manager to achieve environmental monitoring of the warehouse. The arm drive system uses the Open MANIPULATORX arm with the U2D2 control board to allow the host computer to control the arm's posture through commands through USB.

As shown in FIG. 3 , the on-board power system 15 is divided into two parts, the chassis power supply and the system load power supply. The chassis power supply is responsible for supplying power to the chassis control board and the motor. The battery is composed of three 18650 lithium batteries connected in series with a voltage of 12.6V. The system load power supply is responsible for supplying power to the on-board computer, environmental sensors, and arms. It uses 18650 lithium batteries in a 6-series and 2-parallel manner, with a voltage of 25.2V, and then reduces it to 20V through the step-down module to supply to the on-board computer and 12V. Supply for sensors and arm systems.

In order to adapt to the dark environment of the mushroom house, this autonomous mobile smart IoT module is equipped with a 2.5W fisheye LED on the module, and the relay is controlled to turn on and off the LED through Python. When the module is performing multi-point cruise and taking pictures in the field, the LED will turn on automatically, and it will turn off automatically when the cruise is over.

In order to calculate the number of Pleurotus eryngii in the space pack, the present invention is based on the YOLO V4 algorithm plus a counting function to complete the image object detection and quantity counting function, as shown in Figure 11. The hardware configuration and important dimensions of the autonomous mobile smart IoT module designed and developed by the present invention are illustrated with pictures.

The present invention utilizes the thermal imager 14 loaded on the autonomous mobile intelligent IoT module to measure the temperature of the Pleurotus eryngii space bag in the field of the agricultural laboratory and the simulated test field, which can It can record the temperature and growth status of the mushroom body, and provide data for subsequent mushroom growth prediction. In the thermal imaging images captured by agricultural experiments, the temperature of the mushroom body falls between 16°C and 16.5°C. It is known from the literature that the fruiting bodies in this temperature range grow and develop normally, as shown in Figure 10.

The present invention utilizes the photographs taken during multi-point cruising and photographing in the field, and through the self-trained Pleurotus eryngii deep learning model, the multi-point cruising and photographing target detection and quantity calculation of Pleurotus eryngii photos are carried out. The result of the quantity calculation is shown in the upper left corner of the photo, as shown in Table 4.3. The present invention gives photos to 8 persons to count the number of Pleurotus eryngii in the photos with the naked eye and compares the error and calculation accuracy with the self-trained neural network model. The results are shown in Figure 11, the highest among the four photos The mode error is 3, and the lowest accuracy rate is 82.4%.

Table I

Therefore, by the detailed description of the above specific embodiments, the present invention does possess the following characteristics:

1. The present invention can indeed use the function setting of the visualized growth environment chart for the monitor to interpret the information of the mushroom growth environment more quickly, so as to create a more suitable environment for mushroom planting and growth.

2. The present invention does have the mushroom cultivation Internet of Things monitoring system and method with the function of mushroom yield prediction, mainly by using big data collection, artificial intelligence frame selection and training, To predict the production quantity of mushrooms in the warehouse.

3. The present invention can indeed allow the image capture unit to stably increase the longitudinal telescopic displacement distance of the self-mushroom cultivation Internet of Things monitoring system and method.

4. The present invention does have the function of thermal imager sensing the growth temperature of the mushroom itself.

5. The present invention has the function of accelerating or slowing down the growth rate of mushrooms in response to market demands.

The above is only a feasible embodiment of the present invention, and is not intended to limit the patent scope of the present invention. Any equivalent implementation of other changes based on the content, characteristics and spirit of the following claims should be Included in the patent scope of the present invention. The structural features of the invention specifically defined in the claims are not found in similar items, and are practical and progressive, and have met the requirements of an invention patent. I file an application in accordance with the law. I would like to ask the Jun Bureau to approve the patent in accordance with the law to maintain this invention. The legitimate rights and interests of the applicant.

11: Optical radar

12: transfer mechanism

129: Transfer control module

13: Image capture unit

14: thermal imager

20: Central processing unit

210: Mushroom Quantity Estimation Module

211: Feature database

22: Walking control module

23:Visual chart display module

24: Growth record module

25: Setting Module

26: Field map data construction module

27: Growth state identification module

28: Inspection path planning module

30: Growth environment sensing unit

31,32: temperature/humidity sensor

33: Carbon dioxide concentration sensor

40: Display unit

60: Environmental control equipment

600: Growth environment regulation module

61:Control drive module

62: Wireless signal transmission module

Claims (9)

An autonomous mobile artificial intelligence mushroom cultivation monitoring system, which includes: A single-soldier autonomous mobile inspection vehicle is provided with a walking control module, a transfer mechanism and a transfer control module. The walking control module is used to control the individual-soldier autonomous mobile inspection vehicle. tool actuation, the transfer control module is used to control the actuation of the transfer mechanism; An image capture unit, which is used to capture a plurality of images in a mushroom cultivation field, and the plurality of images include at least one map image of the mushroom cultivation field and at least one mushroom in a growth time series image; A growth environment sensing unit, which is used to sense a plurality of growth environment data of mushrooms in the mushroom cultivation field, and the plurality of growth environment data includes temperature data, humidity data and carbon dioxide concentration data; A field map data construction module, which constructs a field map data according to the at least one map image captured by the image capture unit; wherein, the field map data includes the mushroom cultivation field At least one map of ground access and at least one map of mushroom basket racks; A growth state recognition module, which is used to process the at least one mushroom image and compare it with a reference mushroom image preset in a database that is the same as the growth time series; wherein, when the at least one mushroom image is smaller than When the difference of the reference mushroom image is greater than a first predetermined threshold, it is judged that the at least one mushroom is growing slowly; An inspection path planning module, which plans and sets at least one walking path and a plurality of parking positions on the at least one walking path according to the at least one ground passage map information, and according to the at least one mushroom basket placement map Planning and setting at least one detection path and a plurality of detection positions on the at least one detection path; the walking control module is used to control the individual autonomous mobile inspection vehicle according to the inspection path planning module The at least one planned walking path is to walk in multiple ground passages in the mushroom cultivation field during at least one scheduled inspection period and to walk in each of the multiple ground passages in sequence. Several parking positions are parked; the image capture unit and the growth environment sensing unit are set on the individual-type autonomous mobile inspection vehicle through the transfer mechanism, and follow the individual-type autonomous mobile inspection vehicle The inspection carrier moves to each of the plurality of parking positions in sequence; the transfer control module is used to control the transfer mechanism to drive the image capture unit and the growth environment sensing unit according to the inspection path planning The at least one detection path planned by the module stops at each of the plurality of detection positions in the mushroom cultivation field sequentially based on each of the parking positions, so that the image capture unit can capture The at least one mushroom image, and enabling the growth environment sensing unit to sense the plurality of growth environment data; a growth environment control module, which is used to drive at least one growth environment control device to control the mushroom cultivation field The temperature, humidity and carbon dioxide concentration in the area; wherein, when the growth state identification module judges that the at least one mushroom is slow-growing, the growth environment regulation module will use a preset and consistent one in the database a growth environment condition parameter to adjust the temperature, humidity and carbon dioxide concentration in the mushroom cultivation area to accelerate the growth of the at least one mushroom; and a central processing unit for integrating and processing the walking control module, the The transfer control module, the image capture unit, the growth environment sensing unit, the field map information construction module, the growth state identification module, the inspection path planning module and the growth environment control module signals and information; wherein, the growth environment sensing unit includes a thermal imager, and the thermal imager sequentially shoots the thermal image of each of the plurality of space bags at each of the plurality of detection positions, when the signal When the processing module sequentially receives the mushroom thermal images of each of the plurality of space packs, it sequentially superimposes the corresponding position codes on each of the mushroom thermal images one by one, and for each of the plurality of The thermal image of the mushrooms in the space bag is analyzed and processed for the color temperature distribution to determine whether the temperature in each of the plurality of space bags exceeds the preset temperature value. High warning signs. The autonomous mobile artificial intelligence mushroom cultivation monitoring system as described in claim 1 further includes a visual chart display module, a growth recording module and a wireless signal transmission module, and the central processing unit is used for integration and processing The visual chart display module, the growth record module and the signal and information of the wireless signal transmission module; the visual chart display module is used to convert the growth environment data into a chart format data displayed in a visual chart; the The growth recording module is used to sequentially collect each of the chart format data and record each of the growth environment data as a growth environment file along a time axis of the growth time series in the manner that each preset interval is a file; The visualized graph display module is used to transmit the visualized growth environment graph and the growth environment data to an electronic device through the wireless signal transmission module for display by a display unit of the electronic device; the visualized growth environment graph, etc. Divide a plurality of environmental monitoring areas in an array and correspond to the plurality of parking positions one by one, each of the plurality of environmental monitoring areas is marked with a code corresponding to each of the plurality of parking positions, and each of the plurality of parking positions A plurality of environmental monitoring areas are divided into a plurality of data monitoring areas in an array and corresponding to the plurality of detection positions one by one, each of the plurality of data monitoring areas is marked with a code corresponding to each of the plurality of detection positions and displayed The corresponding real-time temperature data, humidity data and carbon dioxide concentration data of each of the plurality of detection locations; the growth environment file is arranged according to the date with one day as a unit, and the central processing unit reads according to the needs In one of the growth environment files, the temperature curve, humidity curve, and carbon dioxide concentration curve that change along the time axis are displayed in each of the environmental monitoring areas; the individual autonomous mobile inspection vehicle There is at least one optical radar, the signal processing module uses the at least one optical radar, and cooperates with the ROS SLAM algorithm to construct field map information, and then imports the established map into the walking path for the mushroom The cultivation field performs the autonomous inspection task, and records the waypoints as the plurality of parking positions in the plurality of ground passages. As the autonomous mobile artificial intelligence mushroom cultivation monitoring system described in claim 1, its wherein, the image capture unit includes at least one image capture unit, and the image capture unit and the growth environment sensing unit are moved to each The plurality of parking positions; each of the plurality of detection positions is set with a position code; the mushroom cultivation field is equipped with a plurality of mushroom basket racks, and the plurality of mushroom basket racks are separated from each other to form a plurality of ground channel; the image capture unit captures images of the plurality of ground channels as the at least one map image to construct the at least one ground channel map; each of the plurality of mushroom basket racks includes bottom-up A plurality of placement positions are distributed, and each of the plurality of placement positions is for placing a mushroom basket, and each of the mushroom baskets is placed with a plurality of space bags cultivated with mushrooms, and the image capture unit captures each of the mushroom baskets. A plurality of mushroom basket racking images are used as the at least one map image to construct the at least one mushroom basket racking map data; when the single-soldier autonomous mobile inspection vehicle arrives at each of the plurality of parking positions, The transfer mechanism drives the image capture unit to stop at each of the plurality of detection positions in sequence, so that the image capture unit can sequentially capture the mushroom images of the plurality of space bags at each of the plurality of detection positions. As the at least one mushroom image; the growth recording module sequentially receives the mushroom images of each of the plurality of space packets, and superimposes the corresponding position codes one by one on the corresponding position codes of each of the plurality of space packets mushroom images, and sequentially record the mushroom images of each of the plurality of space bags superimposed with the position codes in a file format along the time axis as a growth image file. The self-moving artificial intelligence mushroom cultivation monitoring system as described in claim 1, wherein the transfer mechanism is a multi-axis transfer mechanism; the walking control module includes an obstacle avoidance module, and the obstacle avoidance module includes There is at least one optical radar, and the at least one optical radar senses whether there is an obstacle on the at least one walking path when the individual autonomous mobile inspection vehicle is walking. When there is an obstacle before the position, the at least one walking path is corrected, so that the individual autonomous mobile inspection vehicle can reach the next plurality of parking positions, and then continue the follow-up journey of the at least one walking path; wherein , when the obstacle is at a When there are multiple parking positions, the walking control module controls the individual autonomous mobile inspection vehicle to park at one of the multiple parking positions adjacent to the obstacle, and the transfer The control module obtains a compensation displacement coordinate parameter based on comparing the coordinates of the temporary parking position with the coordinates of the plurality of parking positions where the obstacle is located, and controls the multi-axis transfer according to the compensation displacement coordinate parameter The mechanism operates to sequentially transfer the image capture unit and the growth environment sensing unit to each of the plurality of detection positions based on the plurality of parking positions where the obstacle is located. The autonomous mobile artificial intelligence mushroom cultivation monitoring system as described in claim 1, wherein the growth state identification module includes a mushroom quantity estimation module, and a plurality of mushrooms are built in the mushroom quantity estimation module A feature database of head feature samples; the mushroom quantity estimation module processes the at least one mushroom image captured by the image capture unit at each of the plurality of detection positions, and performs the at least one mushroom image image processing and cropping the overlapping parts of the edges, and performing feature extraction on the at least one mushroom image to obtain multiple mushroom head features, and then sequentially input the multiple mushroom head features into the feature database for comparison Yes, to determine the coincidence probability of the plurality of mushroom head features and the mushroom head feature sample, when the coincidence probability is greater than a preset probability, output an estimated number of mushrooms for each of the plurality of detection positions value, and then accumulate the estimated value of the mushroom quantity at each of the plurality of detection positions to obtain the estimated mushroom quantity information of the entire mushroom cultivation field; the mushroom quantity estimation module includes a Artificial intelligence deep learning module, the artificial intelligence deep learning module establishes a calculation model of the number of mushrooms in the feature database according to a training and learning step, and inputs a huge amount of mushrooms into the calculation model of the number of mushrooms Head feature samples, mushroom feature parameters, artificial intelligence frame selection parameters and image recognition parameters, and the calculation model of the number of mushrooms is used to test the image recognition accuracy of each mushroom image, and then judge the image of each mushroom image Whether the recognition accuracy is sufficient, if the judgment result is yes, then output and store the recognition result; Correction learning; when the artificial intelligence deep learning module executes the image recognition process, it executes a prediction stage step, which is to input the cropped mushroom images sequentially and continuously in real time in the calculation model of the mushroom quantity, and by The calculation model for calculating the number of mushrooms predicts and recognizes the estimated value of the mushrooms represented by the real-time input image of the mushrooms, and then predicts and recognizes the estimated number of mushrooms in the entire mushroom cultivation field. The autonomous mobile artificial intelligence mushroom cultivation monitoring system as described in claim 1, wherein when the at least one mushroom image is greater than the reference mushroom image and the difference is greater than a second predetermined threshold value, it is judged that the at least one mushroom overgrowth; when the growth state identification module judges that the at least one mushroom category is overgrowth, the growth environment regulation module is based on a second growth environment condition parameter preset in the database to regulate the temperature, humidity and carbon dioxide concentration in the mushroom cultivation field, so as to slow down the growth of the at least one mushroom. The self-moving artificial intelligence mushroom cultivation monitoring system as described in claim 1, wherein the growth environment regulation device includes a control drive module, and the growth environment regulation module includes an accelerated growth mode, an accelerated growth mode, and a A setting module for a normal growth mode and a slowing growth mode. When the accelerated growth mode is selected by the setting module, the growth environment regulation module generates a control command for accelerated growth to the control drive module to The control drive module is used to drive the growth environment regulation equipment, so that the growth environment conditions of the mushroom cultivation field conform to the accelerated growth mode; when the normal growth mode is selected by the setting module, the growth environment regulation module The control group generates a normal growth control instruction to the control drive module, and uses the control drive module to drive the growth environment regulation equipment, so that the growth environment conditions of the mushroom cultivation field conform to the normal growth mode; When the setting module selects the growth slowing mode, the growth environment regulation module generates a growth slowdown control command to the control drive module, and the control drive module drives the growth environment control device to make the mushroom The growth environment conditions in the similar cultivation field conform to the slow growth mode. The autonomous mobile artificial intelligence mushroom cultivation monitoring system as described in claim 1, wherein the image capture unit includes at least one LED fisheye fill light module, and the at least one LED fisheye fill light module is used to provide The supplementary light function of the image capture unit when it is in operation is used to improve the quality of the plurality of images captured in the dark mushroom cultivation field. An autonomous mobile artificial intelligence mushroom cultivation monitoring method, which includes: providing a single-soldier autonomous mobile inspection vehicle, an image capture unit, a growth environment sensing unit, a field map data construction module, a A growth state identification module, a patrol inspection path planning module, a growth environment control module and a central processing unit; wherein, the single-soldier autonomous mobile inspection vehicle is equipped with a walking control module and a transfer mechanism and a transfer control module, the walking control module is used to control the movement of the individual autonomous mobile inspection vehicle, the transfer control module is used to control the movement of the transfer mechanism; the image capture unit captures Take a plurality of images in a mushroom cultivation field, the plurality of images include at least one map image of the mushroom cultivation field and at least one mushroom image in a growth sequence; use the growth environment sensing unit to sense Measure the multiple growth environment data of the mushrooms in the mushroom cultivation field, the multiple growth environment data include temperature data, humidity data and carbon dioxide concentration data; build a module based on the image data of the field The at least one map image captured by the extraction unit is constructed into a field map data, and the field map data includes at least one ground passage map and at least one mushroom basket rack map of the mushroom cultivation field resources; use the growth state recognition module to process the at least one mushroom image and compare it with a reference mushroom image preset in a database that is the same as the growth time series; wherein, when the at least one mushroom image is smaller than the When the reference mushroom image and the difference are greater than a first predetermined threshold, it is determined that the at least one mushroom is slow-growing; Using the inspection path planning module to plan and set at least one walking path and a plurality of parking positions on the at least one walking path according to the at least one ground passage map information, and according to the at least one mushroom basket racking map information and planning and setting at least one detection path and a plurality of detection positions on the at least one detection path; the walking control module is used to control the individual autonomous mobile inspection vehicle according to the planning module of the inspection path planning module The at least one walking path walks in the plurality of ground passages of the mushroom cultivation field during at least one predetermined inspection period and stops at each of the plurality of parking positions in sequence; the image capture unit and the growing The environmental sensing unit is installed on the individual autonomous mobile inspection vehicle through the transfer mechanism, and moves to each of the plurality of parking positions sequentially with the individual autonomous mobile inspection vehicle; The transfer control module is used to control the operation of the transfer mechanism to drive the image capture unit and the growth environment sensing unit to stop at the at least one inspection path planned by the inspection path planning module. stop at each of the plurality of detection positions in the mushroom cultivation field sequentially based on the position, so that the image capture unit can capture the at least one mushroom image, and the growth environment sensing unit can Sensing the plurality of growth environment data; using the growth environment control module to drive at least one growth environment control device to control the temperature, humidity and carbon dioxide concentration in the mushroom cultivation field; wherein, when the growth state identification module When it is judged that the at least one mushroom grows slowly, the growth environment regulation module regulates the temperature, humidity and carbon dioxide concentration, to accelerate the growth of the at least one mushroom; and use the central processing unit to integrate and process the walking control module, the transfer control module, the image capture unit, the growth environment sensing unit, and the field The signals and information of the map data construction module, the growth state identification module, the inspection path planning module, and the growth environment regulation module; wherein, the growth environment sensing unit includes a thermal imager, and the thermal imager in order of each A thermal image of the mushrooms of each of the plurality of space packs is shot at the plurality of detection positions, and when the signal processing module sequentially receives the thermal images of the mushrooms of each of the plurality of space packs, the corresponding The location codes are superimposed on each of the mushroom thermal images one by one, and the color temperature distribution of the mushroom thermal images of each of the plurality of space bags is analyzed and processed to determine whether the temperature in each of the plurality of space bags is If the temperature exceeds the preset temperature value, if the judgment result is yes, then an alarm signal corresponding to the location code for excessive temperature is sent.

Images