Method for applying a microbial agent using a rotary tiller
By installing a vision module and control system on the straw returning machine, and using image recognition and deep learning algorithms, the application of microbial agents can be differentiated according to the type and distribution of straw, which solves the problems of resource waste and poor fermentation effect in the existing technology and improves the utilization efficiency of straw fertilizer.
Patent Information
- Application Number
- CN202410274873.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-11
- Publication Date
- 2026-01-27
- Estimated Expiration
- 2044-03-11
AI Technical Summary
Existing methods of applying microbial agents cannot differentiate the application based on the uneven distribution of straw, resulting in resource waste and poor fermentation effects.
The straw return machine is equipped with a vision module and control system. Through image recognition and deep learning algorithms, it can distinguish between piled straw and stubble straw, calculate the amount of fungicide to be sprayed in different areas, and achieve precise application.
It improves the utilization efficiency of microbial agents, reduces resource waste, and enhances the fermentation effect of straw fertilizer.
Smart Images

Figure CN118057997B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of agricultural fertilizers, and more particularly to a method for controlling the release of microbial agents by a field return machine. Background Technology
[0002] With the continuous increase in population and changes in agricultural production methods, agricultural waste straw is increasing daily, becoming a serious environmental pollution problem. To effectively utilize straw resources, the currently widely adopted methods include briquetting and pelletizing. However, these methods have several problems, such as wasting straw resources, low utilization rates, consuming large amounts of energy, and causing environmental pollution. Microbial inoculants, as an environmentally friendly and efficient resource utilization method, can effectively solve these problems.
[0003] To accelerate the fermentation of straw fertilizer, it is necessary to add some microbial agents to the straw raw materials. The most commonly used are EM bacteria, brown sugar yeast liquid, and Bacillus subtilis.
[0004] Currently, the application of microbial inoculants is mainly done by uniformly spreading them while walking around. However, after harvesting, straw is often unevenly distributed in the field. This requires different application methods for microbial inoculants in areas with abundant straw and areas with sparse straw, both to utilize the inoculants more rationally and to improve the fermentation effect of straw fertilizer. Obviously, the existing application methods cannot meet these needs. Therefore, a new technical solution is urgently needed to solve at least one of the above technical problems. Summary of the Invention
[0005] In view of the above shortcomings, the purpose of this invention is to provide a method for controlling the application of microbial agents in a straw return machine, which differentiates the application of microbial agents in areas with abundant straw and areas with scarce straw, thereby making more rational use of microbial agents and improving the fermentation effect of straw fertilizer.
[0006] To achieve the above-mentioned technical objectives and meet the above-mentioned technical requirements, the technical solution adopted by the present invention is as follows:
[0007] A method for controlling the application of microbial agents by a field-returning machine, the field-returning machine including a frame, a cutter roller rotatably disposed at the rear of the frame, a microbial agent spraying device disposed on the frame, and a control system, the control system including a vision module disposed at the front of the frame or the front of the cutter roller, and a controller electrically connected to the vision module, the microbial agent spraying device being electrically connected to the controller;
[0008] The control method includes the following steps:
[0009] The type of straw can be determined as either stockpiled straw or stubble straw.
[0010] When the straw is piled up, the area S of the image in the vision module's view on the actual land is calculated. The vision module is set to a delay of 1-3 seconds, and then the RGB threshold of the soil is measured. When the straw returning machine is running, the vision module captures video images of the front of the machine frame or the front of the cutter roller in real time. The image is color-recognized and binarized. Colors falling within the RGB threshold are converted to white, and colors not falling within the RGB threshold are converted to black. The binarized colors are then inverted. The white area is set as piled straw, and the black area is set as soil. The number of white pixels 'a' is output. The amount of microbial agent to be applied to the piled straw per unit area is set to 'c'. The total amount of microbial agent sprayed per unit time by the microbial agent spraying device is calculated according to the following formula:
[0011]
[0012] In the formula: V—total spray volume of microbial agent per unit time, ml; a—number of white pixels; S—actual land area in the image, m. 2 h—average stacking height, m; c—required amount of decomposer per unit volume, ml / m 3 ;
[0013] When the straw type is stubble straw, the stubble straw images are first subjected to deep learning using the YOLOv5 algorithm. Multiple photos containing stubble straw are entered into the YOLOv5 algorithm and labeled as stubble straw, stored as a training set. Multiple photos without stubble straw but containing stones, trees, and irrigation ditches are entered into the YOLOv5 algorithm, stored as a test set, and trained. The stubble straw in each frame is anchored and bounded, and the number of anchored bounding boxes b is output per second. The amount of inoculant to be applied to each stubble straw is set to l. The total amount of inoculant sprayed per unit time V' of the inoculant spraying device is calculated according to the following formula:
[0014] V′=l×b
[0015] Where: V'—total amount of microbial agent sprayed per unit time, ml; l—amount of decomposing agent required for a single stubble straw, ml; b—number of anchoring frames;
[0016] The controller controls the microbial agent spraying device to release the microbial agent based on the calculated values of V and V'.
[0017] As a preferred technical solution, the vision module has a QVGA camera with a resolution of 320×240.
[0018] As a preferred technical solution, the control method sets the visual module to delay by one second, that is, to record one frame of the image and perform image processing every second.
[0019] As a preferred technical solution, the number of photos including stubble straw should be at least 160.
[0020] As a preferred technical solution, the number of photos containing stones, trees, and irrigation ditches but excluding stubble should be at least 40.
[0021] As a preferred technical solution, the frame includes two symmetrically arranged side plates and a mounting plate detachably disposed on the outside of the side plates. The two ends of the cutter roller are rotatably connected to the corresponding mounting plates, and the frame is provided with a cover.
[0022] As a preferred technical solution, the microbial agent spraying device includes a microbial agent storage tank spanning the upper side of the side plate, a spray pipe inserted into the side plate, and a spray pump disposed on the outer side of the side plate. The spray pipe is connected to the microbial agent storage tank, and the spray pump is connected to the microbial agent storage tank. Multiple microbial agent nozzles are spaced apart on the spray pipe, and the microbial agent nozzles are connected to the spray pipe. The spray pump is electrically connected to the controller, and the microbial agent storage tank is located in front of the cover.
[0023] As a preferred technical solution, the vision module is installed on the front side of the rack.
[0024] As a preferred technical solution, the vision module is installed inside the frame and located in front of the cutter roller.
[0025] As a preferred technical solution, a baffle is provided on the rear side of the cover.
[0026] Compared with traditional technical solutions, the beneficial effects of the present invention are:
[0027] 1) It can calculate the total amount of microbial agent sprayed per unit time according to different types and amounts of straw, thereby ensuring more reasonable application of microbial agent, ensuring that the amount of microbial agent sprayed is reduced in areas with less straw, and ensuring sufficient application of microbial agent in areas with more straw, saving microbial agent raw materials and improving the fermentation effect of straw fertilizer.
[0028] 2) Setting a delay of 1-3 seconds is to capture one image every 1-3 seconds, so that the image can be analyzed frame by frame, and the analysis results are more accurate;
[0029] 3) The number of photos containing stubble straw should be at least 160, and the number of photos containing stones, trees, and ditches but not containing stubble straw should be at least 40. This will provide a larger learning base, make the identification of straw quantity more accurate, and make the amount of fungicide sprayed more accurate.
[0030] 4) The microbial agent spraying device has a simple structure and good spraying effect;
[0031] 5) The baffle can block the soil and prevent it from splashing during operation. Attached Figure Description
[0032] Figure 1A structural diagram of a rack provided in one embodiment of the present invention;
[0033] Figure 2 for Figure 1 A bottom view;
[0034] Figure 3 This is a screenshot of the OpenMV recognition screen provided in one embodiment of the present invention;
[0035] Figure 4 This is an OpenMV image for recognizing piled straw, provided as an embodiment of the present invention.
[0036] Figure 5 This is an OpenMV image of soil region identification provided in one embodiment of the present invention.
[0037] exist Figures 1-5 In the middle, 1. Frame; 101. Side plate; 102. Mounting plate; 103. Cover; 2. Knife roller; 3. Microbial agent storage tank; 4. Spray pump; 5. Spray pipe; 6. Microbial agent nozzle; 7. Baffle. Detailed Implementation
[0038] The invention will now be further described with reference to the accompanying drawings.
[0039] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "top", "bottom", "left", "right", "front", "rear", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present patent. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.
[0040] Please refer to Figures 1-5 An embodiment of the present invention provides a method for controlling the application of microbial agents by a field-returning machine. The field-returning machine includes a frame 1, a cutter roller 2 rotatably disposed at the rear of the frame 1, a microbial agent spraying device disposed on the frame 1, and a control system. The control system includes a vision module disposed at the front of the frame 1 or the front of the cutter roller 2, and a controller electrically connected to the vision module. The microbial agent spraying device is electrically connected to the controller. The microbial agent application is controlled by the control system. The controller can be a PLC, and the communication transmission can be RS485. The control method includes the following steps:
[0041] When the straw is piled up, the area S of the image in the vision module's view on the actual land is calculated. The vision module is set to a delay of 1-3 seconds, and then the RGB threshold of the soil is measured. When the straw returning machine is running, the vision module captures video footage of the front of the machine frame 1 or the front of the cutter roller 2 in real time. The image is color-recognized and binarized. Colors falling within the RGB threshold are converted to white, and colors not falling within the RGB threshold are converted to black. The binarized colors are then inverted. The white area is set as piled straw, and the black area is set as soil. The number of white pixels 'a' is output. The amount of microbial agent to be applied to the piled straw per unit area is set to 'c'. The total amount of microbial agent sprayed per unit time by the microbial agent spraying device is calculated according to the following formula:
[0042]
[0043] In the formula: V—total spray volume of microbial agent per unit time, ml; a—number of white pixels; S—actual land area in the image, m. 2 h—average stacking height, m; c—required amount of decomposer per unit volume, ml / m 3 ;
[0044] When the straw type is stubble straw, the stubble straw images are first subjected to deep learning using the YOLOv5 algorithm. Multiple photos containing stubble straw are entered into the YOLOv5 algorithm and labeled as stubble straw, stored as a training set. Multiple photos without stubble straw but containing stones, trees, and irrigation ditches are entered into the YOLOv5 algorithm, stored as a test set, and trained. The stubble straw in each frame is anchored and bounded, and the number of anchored bounding boxes b is output per second. The amount of inoculant to be applied to each stubble straw is set to l. The total amount of inoculant sprayed per unit time V' of the inoculant spraying device is calculated according to the following formula:
[0045] V′=l×b
[0046] Where: V'—total amount of microbial agent sprayed per unit time, ml; l—amount of decomposing agent required for a single stubble straw, ml; b—number of anchoring frames;
[0047] The controller controls the microbial agent spraying device to release the microbial agent based on the calculated values of V and V'.
[0048] Because different types of straw require different amounts of microbial agent, the vision module transmits real-time images. The vision module is OpenMV and is used for identification. When the straw is piled up, the amount of straw is identified by color differences. Although the average pile height cannot be identified, in actual operation, because the planting density and operation method are the same, the pile height after stubble cutting in a field is roughly similar. Only one pile height needs to be measured. Then, the amount of straw and the average pile height are obtained, and the total amount of microbial agent sprayed per unit time is calculated according to the formula.
[0049] After determining the RGB threshold of the soil, if the pixel is within the RGB threshold, it will be identified as belonging to the soil area and automatically marked as white. If the pixel is not within the RGB threshold, it will be identified as belonging to the straw and automatically marked as black. However, the characteristic of OpenMV is that its return value must be white, so binarization color inversion is required, turning white parts into black, and vice versa.
[0050] In actual operation, the soil in the same area is generally of a uniform color, but the color of different parts of the straw varies greatly after being exposed to wind and rain, so the RGB threshold of the straw was not directly measured.
[0051] Based on the shape characteristics of the stubble, YOLOv5 is used for anchoring and selection, followed by deep learning. YOLOv5 is a deep learning code that transmits images to a computer to learn the anchors within the images. For example, if 500 photos of people wearing masks are transmitted to a database, labelme can be used to label all the masked faces in the images. After deep learning, transmitting or taking a picture of a masked face will automatically select the location of the masked face in the image.
[0052] In this invention, by transmitting at least 160 images containing stubble straw, the location of the stubble straw is anchored. After deep learning, the vision module can select whether there are any stubble straw plants in the captured image and how many. Then, based on this number, the total amount of microbial agent sprayed per unit time is calculated. This allows for the differentiation between piled straw and stubble straw, and the microbial agent application can be controlled according to different straw types. This ensures more reasonable microbial agent application, reducing the amount of microbial agent sprayed in areas with less straw and ensuring sufficient microbial agent application in areas with more straw, saving microbial agent raw materials and improving the fermentation effect of straw fertilizer.
[0053] like Figures 1-5 As shown, the vision module has a QVGA camera with a resolution of 320×240. The resolution does not need to be too high to reduce costs, as higher resolution data transmission results in higher prices for the corresponding camera and controller.
[0054] like Figures 1-5 As shown, in the control method, the vision module is set to delay by one second, that is, to record one frame of the picture and perform image processing every second. The video captured by the vision module cannot be processed frame by frame. The delay of 1 second is to capture one picture every second. The image of this frame is processed every second. The video in the folder is a test recording. Its stuttering is due to capturing one frame of the picture every second. Then, it is more reasonable to analyze frame by frame and determine the RGB threshold.
[0055] like Figures 3-5As shown, the number of photos containing stubble should be at least 160. A learning base of more than 160 photos will yield more accurate results, but considering processing performance, on-site operation reaction time, and spraying efficiency, 200 photos are more reasonable.
[0056] like Figures 3-5 As shown, the number of photos containing stones, trees, and ditches but excluding stubble should be at least 40. A learning base of at least 40 photos will yield more accurate results. The ratio of the number of images in the training set to the test set should be 4:1.
[0057] like Figures 1-2 As shown, the frame 1 includes two symmetrically arranged side plates 101 and a mounting plate 102 detachably disposed on the outside of the side plates 101. The two ends of the cutter roller 2 are rotatably connected to the corresponding mounting plate 102. The frame 1 is provided with a cover 103. The structure is simple and easy to install and maintain.
[0058] like Figures 1-2 As shown, the microbial agent spraying device includes a microbial agent storage tank 3 spanning the upper side of the side plate 101, a spray pipe 5 inserted into the side plate 101, and a spray pump 4 located on the outside of the side plate 101. The spray pipe 5 is connected to the microbial agent storage tank 3, and the spray pump 4 is connected to the microbial agent storage tank 3. Multiple microbial agent nozzles 6 are spaced apart on the spray pipe 5, and the microbial agent nozzles 6 are connected to the spray pipe 5. The spray pump 4 is electrically connected to the controller. The microbial agent storage tank 3 is located in front of the cover 103. The controller controls the spray pump 4 to spray microbial agent according to the calculated values of V and V'. The controller can be installed on the frame 1, or a separate mounting arm can be set to install the controller, depending on the specific structure and operating conditions. The device can also till the land during the microbial agent spraying process.
[0059] like Figures 1-2 As shown, the vision module is installed on the front side of the frame 103, or the vision module is installed on the inner side of the frame 103 and located in front of the cutter roller 2. The position of the vision module should be installed according to the specific situation, and is affected by dust, crop lifting under force, water mist, etc. during agricultural operations.
[0060] like Figures 1-2 As shown, a baffle 7 is provided on the rear side of the cover 103 to prevent mud from splashing and dust from rising.
[0061] Example
[0062] A method for controlling the release of microbial agents by a field-returning machine is disclosed. The control system installed on the field-returning machine controls the release of microbial agents. The field-returning machine includes a frame 1, a cutter roller 2 rotatably mounted at the rear of the frame 1, and a microbial agent spraying device mounted on the frame 1. The control system includes a vision module mounted at the front of the frame 1 or the front of the cutter roller 2, and a controller electrically connected to the vision module. The microbial agent spraying device is electrically connected to the controller. The vision module has a QVGA camera with a resolution of 320×240. The frame 1 includes two symmetrically arranged side plates 101 and a detachable mounting plate 102 mounted on the outside of the side plates 101. The two ends of the cutter roller 2 are respectively connected to the corresponding mounting plates 102. The frame 1 is rotatably connected and equipped with a cover 103. The microbial agent spraying device includes a microbial agent storage tank 3 spanning the upper side of the side plate, a spray pipe 5 inserted into the side plate 101, and a spray pump 4 located outside the side plate 101. The spray pipe 5 is connected to the microbial agent storage tank 3, and the spray pump 4 is also connected to the microbial agent storage tank 3. Multiple microbial agent nozzles 6 are spaced apart on the spray pipe 5 and are connected to the spray pipe 5. The spray pump 4 is electrically connected to the controller. The microbial agent storage tank 3 is located in front of the cover 103. The vision module is installed on the front side of the frame 103, and a baffle 7 is provided on the rear side of the cover 103. The control method includes the following steps:
[0063] When the straw is piled up, the area S of the image in the vision module's view on the actual land is calculated. The vision module is delayed by 1 second, and then the RGB threshold of the soil is measured. When the straw returning machine is running, the vision module captures video images of the front of the machine frame or the front of the cutter roller in real time. The image is color-recognized and binarized. Colors falling within the RGB threshold are converted to white, and colors not falling within the RGB threshold are converted to black. The binarized colors are then inverted. The white area is set as piled straw, and the black area is set as soil. The number of white pixels 'a' is output. The amount of microbial agent to be applied to the piled straw per unit area is set as 'c'. The total amount of microbial agent sprayed per unit time by the microbial agent spraying device is calculated according to the following formula:
[0064]
[0065] In the formula: V—total spray volume of microbial agent per unit time, ml; a—number of white pixels; S—actual land area in the image, m. 2 h—average stacking height, m; c—required amount of decomposer per unit volume, ml / m 3 ;
[0066] When the straw type is stubble straw, the stubble straw images are first subjected to deep learning using the YOLOv5 algorithm. 200 photos containing stubble straw are input into the YOLOv5 algorithm and labeled as such, stored as the training set. 40 photos without stubble straw but containing stones, trees, and irrigation ditches are input into the YOLOv5 algorithm, stored as the test set, and used for learning. Stubble straw within each frame is anchored and bounded, and the number of anchored bounding boxes is output per second, b. The required inoculant dosage per stubble straw is set to l. The total inoculant spray volume V' per unit time of the inoculant spraying device is calculated using the following formula:
[0067] V′=l×b
[0068] Where: V'—total amount of microbial agent sprayed per unit time, ml; l—amount of decomposing agent required for a single stubble straw, ml; b—number of anchoring frames;
[0069] The controller controls the microbial agent spraying device to release the microbial agent based on the calculated values of V and V'.
[0070] In this application, the control device can be implemented in any suitable manner. Specifically, for example, the control device can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the microprocessor or processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontroller units (MCUs). Examples of such modules include, but are not limited to, the following microcontroller units: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. Those skilled in the art will also recognize that, in addition to implementing the functions of the control device in purely computer-readable program code form, the same functions can be achieved by logically programming the method steps to make the control unit take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontroller units.
[0071] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.
[0072] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. The computer software product may include several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application. The computer software product can be stored in memory, which may include non-permanent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media. Computer-readable media includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0073] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, for system / electronic device embodiments, since the software functions executed by their processors are basically similar to those of the method embodiments, the descriptions are relatively simple; relevant parts can be found in the descriptions of the method embodiments.
[0074] Although this application has been described through embodiments, those skilled in the art will know that this application has many modifications and variations without departing from the spirit of this application, and it is intended that the appended claims cover such modifications and variations without departing from the spirit of this application.
[0075] It should be noted that in the description of this application, the terms "first," "second," etc., are used only for descriptive purposes and to distinguish similar objects; there is no order between them, nor should they be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more.
[0076] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the appended claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the preceding claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the inventors have not considered that subject matter as part of the disclosed inventive subject matter.
Claims
1. A method for controlling the release of microbial agents by a field-returning machine, characterized in that, The fertilization machine includes a frame, a cutter roller rotatably disposed at the rear of the frame, a fungicide spraying device disposed on the frame, and a control system. The control system includes a vision module disposed at the front of the frame or the front of the cutter roller, and a controller electrically connected to the vision module. The fungicide spraying device is electrically connected to the controller. The control method includes the following steps: When the straw type is stacked straw, calculate the area S of the actual land occupied by the image in the vision module screen. Set the vision module delay to 1-3 seconds, then measure the RGB threshold of the soil. When the straw returning machine is running, the vision module captures video images of the front of the machine frame or the front of the cutter roller in real time. Perform color recognition on the video images and perform image binarization processing. Colors falling within the RGB threshold are converted to white, and colors not falling within the RGB threshold are converted to black. Then, the binarized colors are inverted. Set the white area as stacked straw and the black area as soil, and output the number of white pixels 'a'. Set the amount of microbial agent to be applied to the stacked straw per unit area as 'c'. Calculate the total amount of microbial agent sprayed per unit time by the microbial agent spraying device according to the following formula: ; In the formula: V—total spray volume of microbial agent per unit time, ml; a—number of white pixels; S—actual land area in the image, m. 2 h—average stacking height, m; c—required amount of decomposer per unit volume, ml / m 3 ; When the straw type is stubble straw, the stubble straw images are first subjected to deep learning using the YOLOv5 algorithm. Multiple photos containing stubble straw are entered into the YOLOv5 algorithm and labeled as stubble straw, stored as a training set. Multiple photos without stubble straw but containing stones, trees, and irrigation ditches are entered into the YOLOv5 algorithm, stored as a test set, and trained. The stubble straw in each frame is anchored and bounded, and the number of anchored bounding boxes b is output per second. The amount of inoculant to be applied to each stubble straw is set to l. The total amount of inoculant sprayed per unit time V' of the inoculant spraying device is calculated according to the following formula: ; Where: V'—total amount of microbial agent sprayed per unit time, ml; l—amount of decomposing agent required for a single stubble straw, ml; b—number of anchoring frames; The controller controls the microbial agent spraying device to release the microbial agent based on the calculated values of V and V'.
2. The method for controlling the release of microbial agents by the returning machine according to claim 1, characterized in that, The control method sets the vision module to delay by one second, that is, to record one frame per second and perform image processing.
3. The method for controlling the release of microbial agents by the returning machine according to claim 1, characterized in that, The number of photos including those of stubble straw must be at least 160.
4. The method for controlling the application of microbial agents by the returning machine according to claim 1, characterized in that, The number of photos must be at least 40, excluding stubble but including stones, trees, and irrigation ditches.
5. The method for controlling the release of microbial agents by the returning machine according to claim 1, characterized in that, The frame includes two symmetrically arranged side plates and a mounting plate detachably disposed on the outside of the side plates. The two ends of the cutter roller are rotatably connected to the corresponding mounting plates. The frame is provided with a cover.
6. The method for controlling the release of microbial agents by a field-returning machine according to claim 5, characterized in that, The microbial agent spraying device includes a microbial agent storage tank spanning the upper side of the side plate, a spray pipe inserted into the side plate, and a spray pump located on the outer side of the side plate. The spray pipe is connected to the microbial agent storage tank, and the spray pump is also connected to the microbial agent storage tank. Multiple microbial agent nozzles are spaced apart on the spray pipe, and the microbial agent nozzles are connected to the spray pipe. The spray pump is electrically connected to the controller, and the microbial agent storage tank is located in front of the cover.
7. The method for controlling the release of microbial agents by the returning machine according to claim 5, characterized in that, The vision module is mounted on the front side of the rack.
8. The method for controlling the release of microbial agents by the returning machine according to claim 5, characterized in that, The vision module is installed inside the frame and located in front of the cutter roller.
9. The method for controlling the release of microbial agents by the returning machine according to claim 5, characterized in that, A baffle is provided on the rear side of the cover.
Citation Information
Patent Citations
Target spraying test bed based on machine vision and control method
CN111397936A
Spray control system based on visual processing and control method thereof
CN113312986A