CN115943809A - Tea picking optimization method and system based on quality evaluation - Google Patents
Tea picking optimization method and system based on quality evaluation Download PDFInfo
- Publication number
- CN115943809A CN115943809A CN202310221912.0A CN202310221912A CN115943809A CN 115943809 A CN115943809 A CN 115943809A CN 202310221912 A CN202310221912 A CN 202310221912A CN 115943809 A CN115943809 A CN 115943809A
- Authority
- CN
- China
- Prior art keywords
- tea
- picking
- plucking
- tea picking
- leaves
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Harvesting Machines For Specific Crops (AREA)
- Tea And Coffee (AREA)
Abstract
The invention requests to protect a tea picking optimization method and system based on quality evaluation.A user manually adjusts the initial pose of a tea picking cutter through the man-machine interaction function of a tea picking main interface, controls a tea picking device to collect tea leaves of different grades of a tea puff to be collected and blows the tea leaves into an automatic tea collecting bag behind the tea picking device through a blower; then, adjusting tea picking parameters of the tea picking control interface, controlling the tea picking device to collect tea puffs to be collected again, and collecting the collected tea leaves and putting the collected tea leaves into an artificial tea collecting bag; and extracting a preset number of collected tea leaves from the collecting bag for quality analysis, obtaining tea-picking performance indexes of the tea-picking device to optimize the tea-picking device, and using the optimized parameters of the tea-picking device to perform the rest tea-picking work. According to the scheme, the automatic tea picking process is distinguished and detected, manual correction is combined, and the performance of the tea picking result is evaluated, so that further reference is provided for subsequent tea picking work, and the tea picking efficiency is improved.
Description
Technical Field
The invention belongs to the internet information processing technology, and particularly relates to a tea picking optimization method and system based on quality evaluation.
Background
The pruning and harvesting operations of the tea tree canopy are two important links of tea tree growth management, and are realized by cutting tea tree stems. Machines used for cutting tea tree stalks comprise a trimmer and a tea-leaf picker, and reciprocating double-moving cutters of the existing tea tree trimmer and the existing tea-leaf picker are mostly driven by a crank-slider mechanism or a double-eccentric-wheel mechanism. When the device works, the reciprocating double-acting knives move oppositely to push the tea plant stalks to the cutting edge to clamp and cut, and high-speed cutting cannot be realized; the stalks are greatly and transversely bent, so that the cut is uneven and even torn, and the cutting quality is poor; in addition, the friction heating condition is serious when the double-moving knife works, the temperature reduction treatment is required frequently, and the long-time operation cannot be realized.
In the development process of the tea industry, the wide application of tea machinery provides an important material basis for the industrial development of tea, plays an important role in promoting the rapid development of the tea industry, and is still unbalanced and incomplete in the overall development process. Firstly, the labour is in short supply, and the expense is high, and tea garden "recruitment is wastefully". Tea picking is an important work with the most intensive labor, the most time-consuming work and the strongest seasonality in tea garden production management, most of tea picking still adopts the traditional manual picking mode, the labor demand is extremely high, and the development of cost saving, efficiency increasing and quality improving increment in tea production and processing is seriously restricted.
In addition, the tea picking is not stable manually and different in picking technology, so that the phenomena of less picking, missed picking and excessive rough picking of summer and autumn tea are serious, the quality of fresh tea leaves is difficult to be unified and standard, and the quality of dry tea is difficult to guarantee. Secondly, the manual picking efficiency is low, and the timeliness of tea picking is difficult to ensure. In northern China, the plain language of 'toutianbao, tiancao' refers to tea buds, the manual picking efficiency is low, and the picking speed of tea leaves is inevitably influenced. The mechanical tea picking is a tea picking method which replaces manual tea picking by a machine through the matching of three elements of 'garden, machine and human'. Practice proves that mechanical tea-picking can obviously improve work efficiency, save cost and improve yield, fundamentally solves the problem of shortage of tea-picking labor force, has obvious economic benefit and social benefit, and is a necessary way for continuous and healthy development of tea industry. Thirdly, the requirements on the tea plucking machine are inconsistent due to the difference between the south and the north.
Therefore, a set of scientific tea picking optimization method and system based on quality evaluation is beneficial to screening out the type most suitable for mechanical tea picking, and has extremely important significance for promoting the mechanical process of tea production and processing.
Disclosure of Invention
The invention provides a quality evaluation-based tea-picking optimization method and system, aiming at solving the defects of low automation degree and low quality of tea-picking effect in the current tea-picking link.
According to a first aspect of the invention, the invention requests to protect a tea-picking optimization method based on quality evaluation, which comprises the following steps:
a user manually adjusts the initial pose of the tea picking cutter through the man-machine interaction function of the tea picking main interface so as to adapt to surfaces of tea canopies in different growth states;
a user enters a tea picking control interface, and controls the tea picking device to collect tea with different grades of the tea puffs to be collected according to the tea grade results obtained by the tea grade detection algorithm and blow the tea into a plurality of automatic tea collecting bags behind the tea picking device through a blower;
the user adjusts tea picking parameters of the tea picking control interface, and controls the tea picking device to collect tea puffs to be collected again by adopting the adjusted parameters and places the collected tea leaves into the artificial tea collecting bag;
extracting a preset number of collected tea leaves from the automatic tea leaf collecting bag and the artificial tea leaf collecting bag, and performing quality analysis on the collected tea leaves to obtain a tea leaf collecting performance index of the tea leaf collecting device;
and optimizing the tea picking device according to the tea picking performance index, and performing the rest tea picking work by using the optimized parameters of the tea picking device.
Preferably, the user manually adjusts the initial pose of the tea plucking tool through the human-computer interaction function of the tea plucking main interface so as to adapt to the surfaces of the tea awnings in different growth states, and the method specifically comprises the following steps:
the tea picking main interface is designed into a software main interface through QT design and is laid out into an image information display window, a detection information prompt window and a human-computer interaction operation window;
an image display interface and a real-time data interface are created by adopting built-in QGraphicsView and QLEDNumber components of QT Designer;
the detection information prompt window adopts a QTableWidget component to respectively display cutting time, cutting length and a tool position and pose adjustment instruction based on the profiling logic judgment;
a manual adjusting function of the tool pose is added to the man-machine interaction operation window, so that the requirements of a user in different outdoor operation environments are met;
when the initial pose of the tea picking cutter is manually adjusted, the adjusted slide block coordinate is set as a zero point, and the corresponding screw rod limiting length is input based on the slide block coordinate;
and clicking a start operation button by a user, and checking whether each motor and the RGB-D depth camera are linked with the IPC industrial personal computer.
Preferably, the user gets into the control interface of picking tea, and the tealeaves grade result collection that the control device of picking tea obtained according to tealeaves grade detection algorithm waits to gather the fluffy tealeaves of different grades of tea and blows into a plurality of automatic tealeaves collection bags in the device rear of picking tea with tealeaves through the air-blower, specifically includes:
acquiring tea data, namely acquiring depth information and RGB (red, green and blue) color images of a tea tent under the current position of a camera by adopting an RGB-D (red, green and blue) camera in the operation process of tea acquisition equipment, extracting an identification target of a current frame based on an improved significant target detection algorithm, and acquiring a leaf grade image of the tea tent;
target identification, namely respectively calculating real-time average depth information in the center and marginal areas of a preselected frame of the blade level image, and taking the real-time average depth information as a basis for determining the position and pose information of a cutting tool in the subsequent steps;
profiling operation, namely combining the calculated real-time average depth information with inherent parameters of tea leaf collecting equipment to determine the real-time pose of a cutting tool, and matching the corresponding positions of the cutting tool and a tea tent by combining a self-adaptive adjustment strategy of the real-time pose of the cutting tool based on designed profiling logic;
tea leaf picking, wherein according to the pose determination result of the cutting tool, an executing mechanism of the tea leaf collecting device cuts tea leaves through a reciprocating blade, and the picked tea leaves are blown into a tea leaf collecting bag behind the device through a blower.
Preferably, the user adjusts the parameter of picking tea control interface to the parameter after adopting the regulation once more control the device of picking tea gather wait to gather tea fluffy and collect the tealeaves of this collection and put into artifical tealeaves and collect the bag, specifically include:
the user adjusts the angle adjusting option and the length limiting option of the tea picking control interface;
the angle adjustment option is that the user controls the cutter to rotate at a selected angle according to the requirement of the user;
the length limiting option is that a user initializes a button by setting upper limit and lower limit parameters of the length of the screw rod in the length limiting option and combining zero coordinates in a tea picking main interface, so that the safety of the cutter in operation is ensured;
in the tea picking process, if the running distance of the slide block of the stepping motor exceeds a set limit range, the whole machine stops working immediately.
Preferably, the collected tea leaves of the preset amount are extracted from the automatic tea leaf collecting bag and the artificial tea leaf collecting bag, the collected tea leaves are subjected to quality analysis, and the tea-picking performance index of the tea-picking device is obtained, and the method specifically comprises the following steps:
measuring the density parameter of tea leaves of the tea fluffs in unit area, and pushing the tea picking device to advance for a preset distance along the direction of the ridges of the tea garden, wherein the average moving speed of the equipment is 0.5m/s;
after the tea plucking device operation cycle ended, the automatic tealeaves collection bag and the artifical tealeaves collection bag in following tea plucking device rear side draw the tealeaves harvesting achievement of predetermineeing quantity in the bag, carry out quantitative analysis according to the relevant standard of quality, acquire the tea bud quality, the rate of leaking and the complete rate of bud leaf of automatic tealeaves collection bag and artifical tealeaves collection bag, obtain the tea plucking performance index of tea plucking device.
Preferably, according to the tea-picking performance index, the tea-picking device is optimized, and the optimized parameters of the tea-picking device are used for carrying out the rest tea-picking work, which specifically comprises the following steps:
obtaining a tea picking optimization model, wherein the tea picking optimization model is used for optimizing tea picking actions of a tea picking cutter moving towards each direction of a tea fluffy piece;
acquiring tea picking cutter motion data, wherein the tea picking cutter motion data comprise a tea picking reference value and a height value of a tea picking route when the tea picking cutter moves to pass through a tea tent, and the tea picking reference value comprises a length value of tea in each top direction of the tea tent and/or an area value of a top area in each top direction of the tea tent; the original point of a coordinate system where the length value of the tea leaves is located and the original point of the coordinate system where the area value of the top end area is located are both the starting points of a tea picking route;
carrying out rasterization coding on the tea picking cutter motion data to obtain candidate tea picking motion data, wherein different types of data in the tea picking cutter motion data and data corresponding to different top directions are respectively coded into different tea picking routes in the candidate tea picking motion data;
and inputting the candidate tea picking action data and the tea picking performance indexes into the tea picking optimization model to obtain the feasibility of the tea picking action of the tea picking cutter moving towards each direction of the tea fluffy.
According to a second aspect of the invention, the invention claims a quality evaluation based tea-picking optimization system, comprising: the system comprises an initialization module, an automatic collection module, a manual collection module, a performance detection module and an optimization module;
in the initialization module, a user manually adjusts the initial pose of a tea plucking cutter through the human-computer interaction function of a tea plucking main interface so as to adapt to surfaces of tea canopies in different growth states;
in the automatic collection module, the user enters a tea picking control interface, and controls a tea picking device to collect tea of different grades of tea puffs to be collected according to tea grade results obtained by a tea grade detection algorithm and blow the tea into a plurality of automatic tea collection bags behind the tea picking device through a blower;
in the manual collection module, the user adjusts tea picking parameters of the tea picking control interface, and controls the tea picking device to collect the tea fluffs to be collected again by adopting the adjusted parameters and places the collected tea into a manual tea collection bag;
in the performance detection module, extracting a preset number of collected tea leaves from the automatic tea leaf collecting bag and the manual tea leaf collecting bag, and performing quality analysis on the collected tea leaves to obtain tea-picking performance indexes of the tea-picking device;
and in the optimization module, optimizing the tea picking device according to the tea picking performance index, and performing the rest tea picking work by using the optimized parameters of the tea picking device.
The invention requests to protect a tea picking optimization method and system based on quality evaluation.A user manually adjusts the initial pose of a tea picking cutter through the man-machine interaction function of a tea picking main interface, controls a tea picking device to collect tea leaves of different grades of a tea puff to be collected and blows the tea leaves into an automatic tea collecting bag behind the tea picking device through a blower; then, adjusting tea picking parameters of the tea picking control interface, controlling the tea picking device to collect tea puffs to be collected again, and collecting the collected tea leaves and putting the collected tea leaves into an artificial tea collecting bag; and extracting a preset number of collected tea leaves from the collecting bag for quality analysis, obtaining tea-picking performance indexes of the tea-picking device to optimize the tea-picking device, and using the optimized parameters of the tea-picking device to perform the rest tea-picking work. According to the scheme, the automatic tea picking process is distinguished and detected, manual correction is combined, and the performance of the tea picking result is evaluated, so that further reference is provided for subsequent tea picking work, and the tea picking efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a flow chart of the present invention relating to a quality evaluation based optimization method for tea plucking;
FIG. 2 is a schematic diagram of a prototype of a tea-plucking apparatus according to the present invention;
FIG. 3 is a system hardware diagram of a tea plucking device according to the present invention;
fig. 4 is a second work flow chart of the tea-picking optimization method based on quality evaluation according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
According to a first embodiment of the invention, referring to fig. 1, the invention claims a quality evaluation-based tea-picking optimization method, which comprises the following steps:
a user manually adjusts the initial pose of the tea picking cutter through the man-machine interaction function of the tea picking main interface so as to adapt to surfaces of tea canopies in different growth states;
a user enters a tea picking control interface, and controls a tea picking device to collect tea with different grades of tea puffs to be collected according to a tea grade result obtained by a tea grade detection algorithm and blow the tea into a plurality of automatic tea collecting bags behind the tea picking device through a blower;
the user adjusts tea picking parameters of the tea picking control interface, and controls the tea picking device to collect tea puffs to be collected again by adopting the adjusted parameters and collects the collected tea leaves and puts the collected tea leaves into an artificial tea collecting bag;
extracting a preset number of collected tea leaves from the automatic tea leaf collecting bag and the artificial tea leaf collecting bag, and performing quality analysis on the collected tea leaves to obtain a tea leaf collecting performance index of the tea leaf collecting device;
and optimizing the tea picking device according to the tea picking performance index, and performing the rest tea picking work by using the optimized parameters of the tea picking device.
In this embodiment, the tea plucking device is a cutting blade adaptive profiling self-propelled tea plucking machine based on depth perception, and the prototype is shown in fig. 2.
The whole machine mainly comprises a visual perception module and a profiling execution module. The visual perception module takes an Intel RealSense RGB-D depth camera as a main sensor, and comprises an industrial control computer with a professional image processing algorithm, a touch display screen for man-machine interaction and a control hardware combination for operating an execution mechanism. The profiling execution module mainly comprises a manipulator with 2 degrees of freedom and a multi-motor linkage control structure. Fig. 3 shows the hardware components used in the present embodiment, and shows the connection relationship between the components.
Referring to fig. 3, the output information of the controller (5) can be adjusted by a variable frequency pulse signal ranging from 0 to 500 kHz. The pulse signal is generated by a microcontroller in the industrial personal computer (2), and bidirectional serial communication between the industrial personal computer (2) and the controller (5) can be established by utilizing an interface provided by a Windows system. The controller (5) controls the attraction and release of the internal contact of the relay (4) by selecting the current transmission of different interfaces, thereby controlling the forward rotation and the reverse rotation of the direct current motor (7).
In order to realize closed-loop control, the self-propelled tea plucking machine system must acquire real-time position feedback of a slide block of a screw rod stepping motor (9). However, this position information is not directly accessible through the peripheral I/O ports of the stepper motor (9), so we introduce an additional sensing scheme. Specifically, the communication protocol of the stepping motor (9) gives lead parameters of the motor, so that the real-time position information of the sliding block can be deduced by selecting the proper motor rotating speed and calculating the pulse sending time. Based on this theory, a DM542 micro stepper driver (6) is employed as a controller for the stepper motor (9) operation. The controller (5) is connected with the driver (6) through an RS-232 interface, and stable and accurate signal transmission can be provided.
The profiling execution module of the whole machine comprises mechanical structures such as a direct current motor (7), a stepping motor (9), a cutting tool (8) and the like. The pose adjustment operation of the cutting tool (8) is mainly realized by two functional modules of tool rotation and tool lifting. The rotation of the cutter is driven by a 57/100-1605 stepping motor (9) linked by a screw rod, the maximum speed is 3000RPM, and the peak torque is 3.1Nm. The speed and direction of rotation of the stepper motor (9) can be adjusted by a pulse signal ranging from 0 to 400kHz, which is generated by the ECI1200 controller (5). And the lifting of the cutter depends on a direct current speed reducing motor (7), the maximum rotating speed of the cutter is 60r/min, and the peak torque is 192kg.
The whole machine system utilizes a direct current motor (7) and a stepping motor (9) to respectively drive respective screw rod sliding block mechanisms so that the cutter can carry out linkage adjustment of large amplitude height and angle. Specifically, if the controller (5) sends a pulse signal to enable the stepping motor (9) to rotate forwards, the ball screw can drive the cutting tool (8) to rotate upwards around the rotating motion axis of the equipment; when the controller (5) rotates the stepping motor (9) in the reverse direction, the cutter (8) rotates downward along the axis. Meanwhile, the controller (5) can control the on and off of different relays (4) to enable the direct current motor (7) to rotate forwards or backwards, so that the lifting platform where the cutting tool (8) is located is driven to ascend or descend along the linear motion guide rail.
In the tea leaf picking process, an image processing algorithm built in an industrial personal computer extracts real-time depth information of new leaves in a tea tent by using RGB images and depth information acquired by an RGB-D depth camera (1), and judges a real-time pose adjusting instruction of a cutting tool (8) based on the depth information. The encoder converts the command into a specific pulse signal and transmits the specific pulse signal to the controller (5) through the bidirectional serial communication port. The controller (5) sends signals to the stepping driver (6) and the relay (4) to respectively control the running conditions of the stepping motor (9) and the direct current motor (7). The cutting tool (8) can be fitted with the corresponding cutting position of the tea tent by utilizing the linkage adjustment of the double electric generator sets.
In this embodiment, realSense D435i is a stereoscopic depth Camera, including a color Camera (RGB sensor), an infrared laser emitter (IR Projector), and a pair of stereoscopic infrared sensors (IR Stereo Camera). The depth measurement principle used is a 3D structured light technique based on optical triangulation: through infrared laser emitter, will have certain structural feature's light and throw by the infrared sensor collection again on being shot the object. The light with certain structural characteristics can acquire different image phase information for different depth areas of a shot object, and then the change of the structure is converted into depth information through an arithmetic unit, so that a three-dimensional structure is obtained. The depth perception distance of the camera is between 0.1 and 10m, and the view field angle is 85
58 degrees and can shoot at the resolution of 1920 & lt/EN & gt at 30 frames/second>
1080 color image, with a resolution up to 1280->
720 depth image.
Preferably, the user manually adjusts the initial pose of the tea plucking tool through the human-computer interaction function of the tea plucking main interface so as to adapt to surfaces of the tea awls in different growth states, and the method specifically comprises the following steps:
the tea picking main interface is designed into a software main interface through QT design and is laid out into an image information display window, a detection information prompt window and a human-computer interaction operation window;
an image display interface and a real-time data interface are created by adopting built-in QGraphsView and QLEDNumber components of QT Designer;
the detection information prompt window adopts a QTableWidget component to respectively display cutting time, cutting length and a tool position and pose adjustment instruction based on the profiling logic judgment;
a manual tool pose adjusting function is added to the man-machine interaction operation window, so that the requirements of users in different outdoor operation environments are met;
when the initial pose of the tea picking cutter is manually adjusted, the adjusted slide block coordinate is set as a zero point, and the corresponding screw rod limiting length is input based on the slide block coordinate;
and clicking a start operation button by a user, and checking whether each motor and the RGB-D depth camera are linked with the IPC industrial personal computer.
Specifically, in the embodiment, an image display interface and a real-time data interface are respectively created by using built-in qgraphics view and QLEDNumber components of the QT Designer; the detection information prompt window respectively displays cutting time, cutting length and a tool position and pose adjusting instruction judged by the system based on the profiling logic by utilizing a QTableWidget component; the manual adjustment function of the tool pose is added to the man-machine interaction operation window, so that the equipment can meet the requirements of users in different outdoor operation environments.
In order to meet the requirements of bulk tea leaves of different types on the length of the tea stem, an angle adjusting option and a length limiting option are added to the tea stem length adjusting project. The angle adjustment option can enable a user to control the cutter to rotate at a selected angle according to the requirement of the user. In addition, the system adaptability is improved, and meanwhile, the safety of the equipment in the operation process is required to be ensured at all times. Therefore, the limiting function is designed, and the user can ensure the safety of the cutter during operation by setting the upper limiting parameter and the lower limiting parameter of the length of the screw rod in the length limiting option and combining the zero coordinate initialization button in the main interface. Particularly, in the daily picking operation process, if the running distance of the slide block of the stepping motor exceeds the set limit range, the whole machine stops working immediately, and the slide block is prevented from being separated from the screw rod stepping motor, so that operation accidents are avoided.
Before the equipment starts to operate, a user manually adjusts the initial pose of the cutter through the man-machine interaction function of the main interface so as to adapt to the surfaces of the tea canopies in different growth states. And setting the adjusted coordinates of the slide block as a zero point, and inputting the corresponding limiting length of the screw rod based on the coordinate information. After all the components are ready, a user clicks a start operation button, and the system firstly checks whether hardware such as motors, RGB-D depth cameras and the like are linked with an IPC industrial personal computer. And then, calling a target detection algorithm to extract the initial depth of the tender bud from the image frame acquired by the RGB-D depth camera in real time, and displaying the acquired data on an image display interface in a continuous frame mode. Meanwhile, tool pose adjustment data are obtained based on profiling logic calculation and are displayed on a real-time data interface. Finally, the system utilizes a serial port communication protocol to control the motor set to operate in a pulse signal mode, and combines a mechanical assembly of the actuating mechanism to adjust the pose of the cutting tool in a linkage mode, so that the purpose of real-time profiling of the cutting tool and the surface of the tea tent is achieved, and the accuracy and the intelligence of picking operation are guaranteed.
Preferably, referring to fig. 4, the user enters a tea picking control interface, and the tea picking device is controlled to collect tea leaves of different grades to be picked up according to the tea grade result obtained by the tea grade detection algorithm and blow the tea leaves into a plurality of automatic tea leaf collecting bags behind the tea picking device through a blower, and the automatic tea leaf collecting bags specifically include:
acquiring tea data, namely acquiring depth information and RGB color images of a tea tent under the current position of a camera by adopting an RGB-D camera in the operation process of tea acquisition equipment, extracting an identification target of a current frame based on an improved obvious target detection algorithm, and acquiring a leaf grade image of the tea tent;
target identification, namely calculating real-time average depth information in the center and edge areas of a preselected frame of the blade level image respectively, and taking the real-time average depth information as a basis for determining the pose information of the cutting tool in the subsequent steps;
profiling operation, namely combining the calculated real-time average depth information with inherent parameters of tea leaf collecting equipment to determine the real-time pose of the cutting tool, and matching the corresponding positions of the cutting tool and the tea canopy based on the designed profiling logic and in combination with a self-adaptive adjustment strategy of the real-time pose of the cutting tool;
tea leaf picking, wherein according to the pose determination result of the cutting tool, an executing mechanism of the tea leaf collecting device cuts tea leaves through a reciprocating blade, and the picked tea leaves are blown into a tea leaf collecting bag behind the device through a blower.
Specifically, the tea data acquisition is that in the operation process of the tea acquisition equipment, an RGB-D camera is used for acquiring the depth information and RGB color image of the tea tent at the current position of the camera, the recognition target of the current frame is extracted based on the improved significant target detection algorithm, and the leaf grade image of the tea tent is acquired, and the method specifically includes the following steps:
a new leaf detection method based on the ultragreen characteristics and the maximum inter-class variance method obtains the pixel coordinates of new leaves from the tea tent image;
the depth camera arranged on the cutting tool of the tea plucking machine can acquire leaf grade images of different grades of tea and backgrounds in the tea fluffy in real time;
when the depth camera vertically shoots the top of the tea tree, the tea leaves are densely shielded, abnormal depth values returned by black cavity areas among the tea leaves and undersize depth values returned by new leaves with overhigh growth vigor are filtered, and average depth information of the new leaves on the upper surface of the tea tent is obtained;
and (3) using a new leaf detection algorithm of the ultragreen characteristic and the maximum inter-class variance method to realize the segmentation of the old leaves and the new leaves in the background, and optimizing the obtained average depth information of the new leaves.
Specifically, the target identification is to calculate real-time average depth information in the center and edge regions of a preselected frame of the blade level image respectively, and the real-time average depth information is used as a basis for determining pose information of a cutting tool in subsequent steps, and specifically comprises the following steps:
extracting new leaf regions according to the depth weight of each region cluster by using a depth information-based significant target detection algorithm;
dividing an input blade grade image into K regional clusters based on a K-means clustering algorithm;
calculating an initial significance value of a region cluster k in the depth image;
replacing the central channel prior with a new depth information weight, fusing the initial significant value and the dark channel mapping to obtain a fused significant value obtained after fusion;
after the fusion significant value is obtained, combining the average depth of the output significant target area with the new leaf and the corresponding position coordinate which are obtained by being divided in the RGB space to obtain the position-depth integrated information of the new leaf;
in the subsequent step of calculating the cutting pose, the position-depth integrated information is used as initial input information to carry out cutting knife self-adaptive profiling of the cutting knife to the tea tent.
Specifically, profiling operation, namely combining the calculated real-time average depth information with inherent parameters of tea leaf collection equipment to determine the real-time pose of the cutting tool, and matching the corresponding positions of the cutting tool and the tea canopy by combining a self-adaptive adjustment strategy of the real-time pose of the cutting tool based on designed profiling logic, specifically comprises the following steps:
fix depth camera position: fixing the relative position between the depth camera and the tea plucking device, and acquiring relative position data between the depth camera and the cutting tool,
obtaining the tea leaves and adopting the length: acquiring a video frame of a tea tent at a cutting tool by using a depth camera, wherein the data of the video frame is three-dimensional space data including depth information, and calculating the distance from the edge of the cutting tool to the top of the tea tent according to the data of the video frame, wherein the distance from the edge of the cutting tool to the top of the tea tent is the tea leaf taking length;
adjusting the pose state of the cutting tool: comparing the tea leaf collecting length with the expected tea leaf length, and adjusting the position posture state of the cutting tool to enable the tea leaf collecting length to meet the requirement of the expected tea leaf length, wherein the adjustment of the position posture state of the cutting tool comprises the adjustment of ascending and descending of the cutting tool.
Preferably, the user adjusts the parameter of picking tea control interface to the parameter after adopting the regulation once more control the device of picking tea gather wait to gather tea fluffy and collect the tealeaves of this collection and put into artifical tealeaves and collect the bag, specifically include:
the angle adjusting option and the length limiting option of the tea-picking control interface are adjusted by the user
The angle adjustment option is that the user controls the cutter to rotate at a selected angle according to the requirement of the user;
the length limiting option is that a user sets upper limiting and lower limiting parameters of the length of the screw rod in the length limiting option and initializes the button by combining zero coordinates in the tea picking main interface, so that the safety of the cutter in operation is ensured;
in the tea picking process, if the running distance of the slide block of the stepping motor exceeds a set limit range, the whole machine stops working immediately.
Preferably, the collection tealeaves of the volume of predetermineeing has been extracted from automatic tea collection bag and artifical tea collection bag, carries out quality analysis to the collection tealeaves, obtains the performance index of picking tea-leaves of the device of picking tea-leaves, specifically includes:
measuring the density parameter of tea leaves of the tea fluffs in unit area, and pushing the tea picking device to advance for a preset distance along the direction of the ridges of the tea garden, wherein the average moving speed of the equipment is 0.5m/s;
after the tea plucking device operation cycle ended, the automatic tealeaves collection bag and the artifical tealeaves collection bag in following tea plucking device rear side draw the tealeaves harvesting achievement of predetermineeing quantity in the bag, carry out quantitative analysis according to the relevant standard of quality, acquire the tea bud quality, the rate of leaking and the complete rate of bud leaf of automatic tealeaves collection bag and artifical tealeaves collection bag, obtain the tea plucking performance index of tea plucking device.
In order to verify the performance indexes such as picking efficiency, bud and leaf integrity rate, missed picking rate and missed collecting rate of the developed self-propelled tea picking machine, the project carries out a large amount of tea on-site picking experiments in the Qiong and Gao city Wenjun tea garden in Sichuan province. Based on the principle of a diagonal quartering method, 3 tea rows with normal growth are randomly selected from a tea garden before an experiment for repeated experiments, and 1 tea row with poor growth vigor and uneven surface is specially selected as a control group. Firstly, measuring the density parameter of tea leaves in a unit area, then pushing the equipment to travel for a certain distance along the direction of the ridges of the tea garden, wherein the average moving speed of the equipment is about 0.5m/s, and the height of a cutter from the ground is adjustable between 650 mm and 950 mm. After the operation period of the equipment is finished, a certain amount of tea picking achievements are taken from the tea collecting bag at the rear of the picking robot, and the achievements are quantitatively analyzed according to relevant standards of NY/T2614-2014 and the like, so that the experimental performance of the sample machine is measured. The experimental indexes are mainly divided into the following 3 points:
(1) Tea bud quality (%): collecting the contents of impurities such as old leaves and tea stalks in tea buds;
(2) Missed mining rate (%): the number percentage of tender leaves and new buds which are not picked on the surface of the tea tent after the experiment is finished;
(3) Bud leaf integrity (%): the percentage of the number of intact young leaves in the tea shoots that have been harvested.
Preferably, according to the tea-picking performance index, the tea-picking device is optimized, and the optimized parameters of the tea-picking device are used for carrying out the rest tea-picking work, which specifically comprises the following steps:
obtaining a tea picking optimization model, wherein the tea picking optimization model is used for optimizing tea picking actions of a tea picking cutter moving towards each direction of a tea fluffy piece;
acquiring tea picking cutter motion data, wherein the tea picking cutter motion data comprise a tea picking reference value and a height value of a tea picking route when the tea picking cutter moves to pass through a tea tent, and the tea picking reference value comprises a length value of tea in each top direction of the tea tent and/or an area value of a top area in each top direction of the tea tent; the original point of the coordinate system where the length value of the tea leaves is located and the original point of the coordinate system where the area value of the top end region is located are both the starting points of a tea picking route;
carrying out rasterization coding on the tea picking cutter motion data to obtain candidate tea picking motion data, wherein different types of data in the tea picking cutter motion data and data corresponding to different top directions are respectively coded into different tea picking routes in the candidate tea picking motion data;
and inputting the candidate tea picking action data and the tea picking performance indexes into the tea picking optimization model to obtain the feasibility of the tea picking action of the tea picking cutter moving towards each direction of the tea fluffy.
Obtaining a tea-picking optimization model, comprising:
and receiving a tea picking optimization model sent by the model training equipment, wherein the tea picking optimization model is obtained by training based on a plurality of historical motion data obtained by rasterizing and coding a plurality of pieces of motion data, and the data format of each piece of motion data in the plurality of pieces of motion data is the same as that of the motion data of the tea picking cutter.
Wherein, the step of carrying out rasterization coding on the tea picking cutter motion data to obtain candidate tea picking action data comprises the following steps:
determining a change factor according to the specification of the reference image and the starting point of the tea picking route in the tea picking cutter motion data;
changing the height value of the tea picking route and the tea picking reference value in the tea picking cutter motion data according to the change factor to obtain a first tea picking missing position value and a second tea picking missing position value;
generating candidate tea picking action data corresponding to the tea picking cutter motion data, wherein the candidate tea picking action data comprise a first tea picking route and at least one second tea picking route, a position filling numerical value represented by a first tea picking missing position value on the first tea picking route and a position filling numerical value represented by a second tea picking missing position value on the at least one second tea picking route;
if the reference value for picking tea comprises a length value and an area value, the second missing position value for picking tea comprises an abnormal depth value returned by the black cavity area and an excessively small depth value returned by the new leaves with excessively high growth vigor, the abnormal depth value returned by the black cavity area is obtained by changing the length value through a change factor, and the excessively small depth value returned by the new leaves with excessively high growth vigor is obtained by changing the area value through a change factor; the abnormal depth value returned by the black cavity area and the over-small depth value returned by the new leaves with over-high growth vigor are respectively used in different second tea picking routes for filling data;
filling data in different second tea picking routes respectively corresponding to second tea picking missing position values obtained by changing the tea picking reference values in different top end directions;
on the first tea picking line, the numerical value filled in the position represented by the first tea picking missing position value obtained by the change of the height value at the later corresponding time is larger; on the second tea plucking path, the value of filling at a position indicated by the second tea plucking missing position value obtained by changing the tea plucking reference value closer to the tip end region or the center position of the tip end region is larger.
The motion data further comprises the motion speed of the tea picking cutter on one tea picking route, the candidate tea picking motion data further comprises a third tea picking route, and the motion speed is filled in the position represented by the first tea picking missing position value on the third tea picking route;
and/or the presence of a gas in the gas,
the motion data further comprises a plurality of relative motion orientations of the first tea plucking tool on one tea plucking route, and the historical motion data further comprises a plurality of fourth tea plucking routes, wherein the position represented by the first tea plucking missing position value on each fourth tea plucking route is filled with information related to one motion orientation, and the plurality of relative motion orientations are respectively motion orientations of different top end directions of the relative tea fluffs.
The variation factor satisfies the following relationship:
wherein scale is a variation factor, h is a height of the reference image, and w is a width of the reference image, | P, G i |' represents the starting point P of the tea-plucking path in the first athletic data and the ith topmost area G of the teaseed i The distance of (c).
According to a second aspect of the invention, the invention claims a quality evaluation based tea plucking optimization system, comprising:
the initialization module is used for manually adjusting the initial pose of the tea picking cutter by a user through the human-computer interaction function of the tea picking main interface so as to adapt to surfaces of the tea canopies in different growth states;
the automatic collection module is used for controlling the tea picking device to collect tea leaves of different grades of tea puffs to be collected according to the tea leaf grade result obtained by the tea leaf grade detection algorithm and blowing the tea leaves into a plurality of automatic tea leaf collection bags behind the tea picking device through the air blower;
the manual collection module is used for adjusting tea picking parameters of the tea picking control interface by a user, controlling the tea picking device to collect tea puffs to be collected again by adopting the adjusted parameters, and collecting the collected tea leaves and putting the collected tea leaves into the manual tea leaf collection bag;
the performance detection module extracts a preset number of collected tea leaves from the automatic tea leaf collecting bag and the artificial tea leaf collecting bag, and performs quality analysis on the collected tea leaves to obtain tea-picking performance indexes of the tea-picking device;
and the optimization module optimizes the tea picking device according to the tea picking performance index and uses the optimized parameters of the tea picking device to carry out the rest tea picking work.
Preferably, the initialization module specifically includes:
the tea picking main interface is designed into a software main interface through QT Designer and is laid out into an image information display window, a detection information prompt window and a human-computer interaction operation window;
an image display interface and a real-time data interface are created by adopting built-in QGraphicsView and QLEDNumber components of QT Designer;
the detection information prompt window adopts a QTableWidget component to respectively display cutting time, cutting length and a tool position and pose adjustment instruction based on the profiling logic judgment;
a manual adjusting function of the tool pose is added to the man-machine interaction operation window, so that the requirements of a user in different outdoor operation environments are met;
when the initial pose of the tea picking cutter is manually adjusted, the adjusted slide block coordinate is set as a zero point, and the corresponding screw rod limiting length is input based on the slide block coordinate;
a user clicks a start operation button to check whether each motor and the RGB-D depth camera are linked with an IPC (industrial personal computer);
the automatic collection module specifically comprises:
acquiring tea data, namely acquiring depth information and RGB color images of a tea tent under the current position of a camera by adopting an RGB-D camera in the operation process of tea acquisition equipment, extracting an identification target of a current frame based on an improved obvious target detection algorithm, and acquiring a leaf grade image of the tea tent;
target identification, namely calculating real-time average depth information in the center and edge areas of a preselected frame of the blade level image respectively, and taking the real-time average depth information as a basis for determining the pose information of the cutting tool in the subsequent steps;
profiling operation, namely combining the calculated real-time average depth information with inherent parameters of tea leaf collecting equipment to determine the real-time pose of a cutting tool, and matching the corresponding positions of the cutting tool and a tea tent by combining a self-adaptive adjustment strategy of the real-time pose of the cutting tool based on designed profiling logic;
tea leaf picking, wherein according to the pose determination result of the cutting tool, an executing mechanism of the tea leaf collecting device cuts tea leaves through a reciprocating blade, and the picked tea leaves are blown into a tea leaf collecting bag behind the device through a blower.
Preferably, the manual collection module specifically includes:
the user adjusts the angle adjusting option and the length limiting option of the tea picking control interface;
the angle adjustment option is that the user controls the cutter to rotate at a selected angle according to the requirement of the user;
the length limiting option is that a user initializes a button by setting upper limit and lower limit parameters of the length of the screw rod in the length limiting option and combining zero coordinates in a tea picking main interface, so that the safety of the cutter in operation is ensured;
in the tea picking process, if the running distance of the slide block of the stepping motor exceeds a set limit range, the whole machine stops working immediately;
the performance detection module specifically comprises:
measuring the density parameter of tea leaves of the tea fluffs in unit area, and pushing the tea picking device to advance for a preset distance along the direction of the ridges of the tea garden, wherein the average moving speed of the equipment is 0.5m/s;
after the operation cycle of the tea picking device is finished, tea picking achievements of preset quantity are extracted from the automatic tea collecting bags and the artificial tea collecting bags behind the tea picking device, quantitative analysis is carried out according to quality related standards, the tea bud quality, the missing picking rate and the bud and leaf integrity rate of the automatic tea collecting bags and the artificial tea collecting bags are obtained, and the tea picking performance indexes of the tea picking device are obtained.
Preferably, the optimization module specifically includes:
obtaining a tea picking optimization model, wherein the tea picking optimization model is used for optimizing tea picking actions of a tea picking cutter moving towards each direction of a tea fluffy piece;
acquiring tea picking cutter motion data, wherein the tea picking cutter motion data comprise a tea picking reference value and a height value of a tea picking route when the tea picking cutter moves to pass through a tea tent, and the tea picking reference value comprises a length value of tea in each top direction of the tea tent and/or an area value of a top area in each top direction of the tea tent; the original point of the coordinate system where the length value of the tea leaves is located and the original point of the coordinate system where the area value of the top end region is located are both the starting points of a tea picking route;
carrying out rasterization coding on the tea picking cutter motion data to obtain candidate tea picking motion data, wherein different types of data in the tea picking cutter motion data and data corresponding to different top directions are respectively coded into different tea picking routes in the candidate tea picking motion data;
and inputting the candidate tea picking action data and the tea picking performance indexes into the tea picking optimization model to obtain the feasibility of the tea picking action of the tea picking cutter moving towards each direction of the tea fluffy.
Those skilled in the art will appreciate that the disclosure may be susceptible to variations and modifications. For example, the various devices or components described above may be implemented in hardware, or may be implemented in software, firmware, or a combination of some or all of the three.
Flow charts are used in this disclosure to illustrate steps of methods according to embodiments of the disclosure. It should be understood that the preceding and following steps are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order or simultaneously. Also, other operations may be added to the processes.
It will be understood by those skilled in the art that all or part of the steps of the above methods may be implemented by instructing the relevant hardware through a computer program, and the program may be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, and the like. Alternatively, all or part of the steps of the above embodiments may be implemented using one or more integrated circuits. Accordingly, each module/unit in the above embodiments may be implemented in the form of hardware, and may also be implemented in the form of a software functional module. The present disclosure is not limited to any specific form of combination of hardware and software.
Unless otherwise defined, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present disclosure and is not to be construed as limiting thereof. Although a few exemplary embodiments of this disclosure have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this disclosure. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims. It is to be understood that the foregoing is illustrative of the present disclosure and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (7)
1. A tea-picking optimization method based on quality evaluation is characterized by comprising the following steps:
a user manually adjusts the initial pose of the tea picking cutter through the man-machine interaction function of the tea picking main interface so as to adapt to surfaces of tea canopies in different growth states;
the user enters a tea picking control interface, and controls the tea picking device to collect tea with different grades of tea puffs to be collected according to the tea grade results obtained by the tea grade detection algorithm and blow the tea into a plurality of automatic tea collecting bags behind the tea picking device through a blower;
the user adjusts tea picking parameters of the tea picking control interface, and controls the tea picking device to collect the tea puffs to be collected again by adopting the adjusted parameters and places the collected tea leaves into the artificial tea leaf collecting bag;
extracting a preset number of collected tea leaves from the automatic tea leaf collecting bag and the manual tea leaf collecting bag, and performing quality analysis on the collected tea leaves to obtain tea-picking performance indexes of the tea-picking device;
and optimizing the tea picking device according to the tea picking performance index, and performing the rest tea picking work by using the optimized parameters of the tea picking device.
2. The quality evaluation-based tea plucking optimization method according to claim 1, wherein the user manually adjusts the initial pose of the tea plucking tool through the man-machine interaction function of the tea plucking main interface to adapt to surfaces of the tea puffs in different growth states, specifically comprising:
the tea picking main interface is designed into a software main interface through QT design and is laid out into an image information display window, a detection information prompt window and a human-computer interaction operation window;
an image display interface and a real-time data interface are created by adopting built-in QGraphsView and QLEDNumber components of QT Designer;
the detection information prompt window adopts a QTableWidget component to respectively display cutting time, cutting length and a tool position and pose adjustment instruction based on the profiling logic judgment;
the man-machine interaction operation window is added with a manual tool pose adjusting function, so that the requirements of users in different outdoor operation environments are met;
when the initial pose of the tea picking cutter is manually adjusted, the adjusted coordinates of the sliding block are set as zero points, and corresponding lead screw limiting lengths are input based on the coordinates of the sliding block;
and clicking a start operation button by a user, and checking whether each motor and the RGB-D depth camera are linked with the IPC industrial personal computer.
3. The quality-evaluation-based tea plucking optimization method according to claim 1, wherein the user enters a tea plucking control interface to control a tea plucking device to pluck different grades of tea leaves of the tea plucker to be plucked according to the tea grade results obtained by the tea grade detection algorithm and blow the tea leaves into a plurality of automatic tea leaf collection bags behind the tea plucking device through a blower, and the method specifically comprises the following steps:
acquiring tea data, namely acquiring depth information and RGB color images of a tea leaf in the current position of a camera by adopting an RGB-D camera in the operation process of tea leaf acquisition equipment, extracting an identification target of a current frame based on an improved obvious target detection algorithm, and acquiring a leaf grade image of the tea leaf;
target identification, namely calculating real-time average depth information in the center and edge areas of a preselected frame of the blade level image respectively, and taking the real-time average depth information as a basis for determining the pose information of a cutting tool in the subsequent steps;
profiling operation, namely combining the calculated real-time average depth information with inherent parameters of the tea leaf collecting equipment to determine the real-time pose of the cutting tool, and matching the corresponding positions of the cutting tool and the tea tent by combining a self-adaptive adjustment strategy of the real-time pose of the cutting tool based on designed profiling logic;
tea leaf picking, wherein according to the pose determination result of the cutting tool, an executing mechanism of the tea leaf collecting equipment cuts tea leaves through a reciprocating blade and blows the picked tea leaves into a tea leaf collecting bag behind the equipment through an air blower.
4. The quality evaluation-based tea plucking optimization method according to claim 1, wherein the user adjusts tea plucking parameters of the tea plucking control interface, and controls the tea plucking device to pick up the puffy tea to be picked up and place the picked tea into an artificial tea leaf collecting bag again by using the adjusted parameters, specifically comprising:
the user adjusts an angle adjusting option and a length limiting option of the tea picking control interface;
the angle adjusting option is that a user controls the cutter to rotate at a selected angle according to the requirement of the user;
the length limiting option is that a user initializes a button by setting upper limit and lower limit parameters of the length of the screw rod in the length limiting option and combining zero coordinates in a tea picking main interface, so that the safety of the cutter in operation is ensured;
in the tea picking process, if the running distance of the slide block of the stepping motor exceeds a set limit range, the whole machine stops working immediately.
5. The quality-evaluation-based tea plucking optimization method according to claim 1, wherein the steps of extracting a preset number of collected tea leaves from the automatic tea leaf collection bag and the artificial tea leaf collection bag, and performing quality analysis on the collected tea leaves to obtain the tea plucking performance index of the tea plucking device specifically comprise:
measuring the density parameter of tea leaves of the tea fluffs in unit area, and pushing the tea picking device to advance for a preset distance along the direction of the ridges of the tea garden, wherein the average moving speed of the equipment is 0.5m/s;
after the operation cycle of the tea plucking device is finished, tea plucking achievements of preset quantity are extracted from the automatic tea leaf collecting bags and the artificial tea leaf collecting bags behind the tea plucking device, quantitative analysis is carried out according to quality related standards, the tea bud quality, the tea missing rate and the bud and leaf integrity rate of the automatic tea leaf collecting bags and the artificial tea leaf collecting bags are obtained, and the tea plucking performance indexes of the tea plucking device are obtained.
6. The quality evaluation-based tea-plucking optimization method according to claim 5, wherein the optimization of the tea-plucking device according to the tea-plucking performance index and the use of the optimized parameters of the tea-plucking device for the remaining tea-plucking work, specifically comprises:
obtaining a tea picking optimization model, wherein the tea picking optimization model is used for optimizing tea picking actions of a tea picking cutter moving towards each direction of a tea fluffy piece;
acquiring tea picking cutter motion data, wherein the tea picking cutter motion data comprise a tea picking reference value and a height value of a tea picking route when a tea picking cutter moves to pass through the tea pufas, and the tea picking reference value comprises a length value of tea leaves in each top direction of the tea pufas and/or an area value of a top area in each top direction of the tea pufas; the original point of the coordinate system where the length value of the tea leaves is located and the original point of the coordinate system where the area value of the top end region is located are both the initial points of the tea picking route;
carrying out rasterization coding on the tea picking cutter motion data to obtain candidate tea picking motion data, wherein different types of data in the tea picking cutter motion data and data corresponding to different top directions are respectively coded into different tea picking routes in the candidate tea picking motion data;
and inputting the candidate tea picking action data and the tea picking performance indexes into the tea picking optimization model to obtain the feasibility of the tea picking action of the tea picking cutter moving towards each direction of the tea fluffy piece.
7. A tea-picking optimization system based on quality evaluation is characterized by comprising: the system comprises an initialization module, an automatic collection module, a manual collection module, a performance detection module and an optimization module;
in the initialization module, a user manually adjusts the initial pose of a tea plucking cutter through the human-computer interaction function of a tea plucking main interface so as to adapt to the surfaces of tea awnings in different growth states;
in the automatic collection module, the user enters a tea picking control interface, and controls a tea picking device to collect tea of different grades of tea puffs to be collected according to tea grade results obtained by a tea grade detection algorithm and blow the tea into a plurality of automatic tea collection bags behind the tea picking device through a blower;
in the manual collection module, the user adjusts tea picking parameters of the tea picking control interface, and controls the tea picking device to collect the tea fluffs to be collected again by adopting the adjusted parameters and places the collected tea into a manual tea collection bag;
in the performance detection module, extracting a preset number of collected tea leaves from the automatic tea leaf collecting bag and the manual tea leaf collecting bag, and performing quality analysis on the collected tea leaves to obtain tea-picking performance indexes of the tea-picking device;
and in the optimization module, optimizing the tea picking device according to the tea picking performance index, and performing the rest tea picking work by using the optimized parameters of the tea picking device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310221912.0A CN115943809B (en) | 2023-03-09 | 2023-03-09 | Tea-picking optimization method and system based on quality evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310221912.0A CN115943809B (en) | 2023-03-09 | 2023-03-09 | Tea-picking optimization method and system based on quality evaluation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115943809A true CN115943809A (en) | 2023-04-11 |
| CN115943809B CN115943809B (en) | 2023-05-16 |
Family
ID=85896212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310221912.0A Active CN115943809B (en) | 2023-03-09 | 2023-03-09 | Tea-picking optimization method and system based on quality evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115943809B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3204831A1 (en) * | 1982-02-11 | 1983-09-29 | Seitz Enzinger Noll Maschinenbau Ag, 6800 Mannheim | Method and device for testing filling and tapping fittings, which remain constantly in metal containers, for tightness |
| JP2000092952A (en) * | 1998-09-22 | 2000-04-04 | Iseki & Co Ltd | Fruit controlling and harvesting robot |
| WO2009116613A1 (en) * | 2008-03-21 | 2009-09-24 | 株式会社 伊藤園 | Method and apparatus of evaluating fitness-for-plucking of tea leaf, system of evaluating fitness-for-plucking of tea leaf, and computer-usable medium |
| CN104063862A (en) * | 2014-06-18 | 2014-09-24 | 浙江工业大学 | Method for controlling cutting knife of tea-leaf picker based on visual inspection |
| US20160057940A1 (en) * | 2014-07-21 | 2016-03-03 | The Penn State Research Foundation | Selective automated blossom thinning |
| US20180332767A1 (en) * | 2017-05-18 | 2018-11-22 | Deere & Company | Self-learning system that takes into account corrective inputs for automatic control of an operating parameter of a crop transport or processing device |
| CN210491728U (en) * | 2019-09-02 | 2020-05-12 | 四川省农业机械研究设计院 | Profiling picking device for tender leaves in tea garden |
| CN211406883U (en) * | 2019-10-29 | 2020-09-04 | 宜宾市双星茶业有限责任公司 | Automatic tea-picking device |
| US20210227752A1 (en) * | 2020-01-24 | 2021-07-29 | Sergio ZANINI | Method and apparatus for identifying and harvesting agricultural products |
| JP6964316B1 (en) * | 2021-01-26 | 2021-11-10 | 株式会社アドイン研究所 | Artificial intelligence (AI) estimation system, learning data generator, learning device, fruit thinning object estimation device, learning system, and program |
| CN115216579A (en) * | 2022-06-23 | 2022-10-21 | 首钢集团有限公司 | Method and device for optimizing automatic tapping model curve of converter |
| CN115272791A (en) * | 2022-07-22 | 2022-11-01 | 仲恺农业工程学院 | Multi-target detection positioning method for tea based on YoloV5 |
| CN115328019A (en) * | 2022-08-10 | 2022-11-11 | 四川省农业机械研究设计院 | Machine vision depth information-based tea fluffy cutter adjusting method and tea picking system |
| CN115496804A (en) * | 2022-09-19 | 2022-12-20 | 浙江理工大学 | Mechanized tea leaf picking method based on three-dimensional point cloud deep learning network |
-
2023
- 2023-03-09 CN CN202310221912.0A patent/CN115943809B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3204831A1 (en) * | 1982-02-11 | 1983-09-29 | Seitz Enzinger Noll Maschinenbau Ag, 6800 Mannheim | Method and device for testing filling and tapping fittings, which remain constantly in metal containers, for tightness |
| JP2000092952A (en) * | 1998-09-22 | 2000-04-04 | Iseki & Co Ltd | Fruit controlling and harvesting robot |
| WO2009116613A1 (en) * | 2008-03-21 | 2009-09-24 | 株式会社 伊藤園 | Method and apparatus of evaluating fitness-for-plucking of tea leaf, system of evaluating fitness-for-plucking of tea leaf, and computer-usable medium |
| CN104063862A (en) * | 2014-06-18 | 2014-09-24 | 浙江工业大学 | Method for controlling cutting knife of tea-leaf picker based on visual inspection |
| US20160057940A1 (en) * | 2014-07-21 | 2016-03-03 | The Penn State Research Foundation | Selective automated blossom thinning |
| US20180332767A1 (en) * | 2017-05-18 | 2018-11-22 | Deere & Company | Self-learning system that takes into account corrective inputs for automatic control of an operating parameter of a crop transport or processing device |
| CN210491728U (en) * | 2019-09-02 | 2020-05-12 | 四川省农业机械研究设计院 | Profiling picking device for tender leaves in tea garden |
| CN211406883U (en) * | 2019-10-29 | 2020-09-04 | 宜宾市双星茶业有限责任公司 | Automatic tea-picking device |
| US20210227752A1 (en) * | 2020-01-24 | 2021-07-29 | Sergio ZANINI | Method and apparatus for identifying and harvesting agricultural products |
| JP6964316B1 (en) * | 2021-01-26 | 2021-11-10 | 株式会社アドイン研究所 | Artificial intelligence (AI) estimation system, learning data generator, learning device, fruit thinning object estimation device, learning system, and program |
| CN115216579A (en) * | 2022-06-23 | 2022-10-21 | 首钢集团有限公司 | Method and device for optimizing automatic tapping model curve of converter |
| CN115272791A (en) * | 2022-07-22 | 2022-11-01 | 仲恺农业工程学院 | Multi-target detection positioning method for tea based on YoloV5 |
| CN115328019A (en) * | 2022-08-10 | 2022-11-11 | 四川省农业机械研究设计院 | Machine vision depth information-based tea fluffy cutter adjusting method and tea picking system |
| CN115496804A (en) * | 2022-09-19 | 2022-12-20 | 浙江理工大学 | Mechanized tea leaf picking method based on three-dimensional point cloud deep learning network |
Non-Patent Citations (4)
| Title |
|---|
| 王攀等: "4CJZ-1000型自走式采茶机的设计与试验", 西南大学学报(自然科学版) * |
| 王辉;毛文华;刘刚;胡小安;李树君;: "基于视觉组合的苹果作业机器人识别与定位", 农业机械学报 * |
| 袁志英: "果蔬采摘机器人的发展现状、问题及对策分析", 四川农业与农机 * |
| 高帅等: "基于YOLOv3算法与3D视觉的农业采摘机器人目标识别与定位研究", 中国农机化学报 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115943809B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101356877B (en) | Cucumber picking robot system and picking method in greenhouse | |
| AU2016324492B2 (en) | A self-guided blossom picking device | |
| CN109937685A (en) | A kind of control device and its control method of combine harvester header job parameter | |
| CN104239886B (en) | The extracting method on lawn and background line of demarcation based on graphical analysis | |
| CN110232736A (en) | A kind of down-hole combined mining working three-dimensional scenic fast construction method | |
| CN110178540B (en) | Tea picking machine based on image processing and working method | |
| CN112764416B (en) | Self-walking mowing system and outdoor walking equipment | |
| CN105785986A (en) | Automatic working equipment | |
| CN108064560A (en) | The automatic picker system of fruit and method based on Kinect depth of field cameras | |
| CN113906900B (en) | Sugarcane harvester and method for adjusting position and posture of cutter head of sugarcane harvester based on multi-sensor fusion | |
| CN115861988A (en) | Tea leaf picking method and system based on RGB discrimination | |
| CN209185088U (en) | A kind of fruit picking | |
| CN115316129B (en) | Self-adaptive bionic picking device based on binocular vision recognition and fruit stringing picking method | |
| CN116686545B (en) | Litchi picking robot shade removing method based on machine vision control | |
| CN206178392U (en) | Real -time reciprocity monitoring devices of greenhouse crop growth information | |
| WO2021139397A1 (en) | Method for controlling self-moving device | |
| CN109588102A (en) | The new and effective adjustable grass trimmer of one kind, system and method | |
| CN115943809A (en) | Tea picking optimization method and system based on quality evaluation | |
| CN205540215U (en) | Machine people motion control system is plucked to fruit vegetables | |
| CN116778327A (en) | Real-time evaluation method for picking effect of bulk tea based on semantic segmentation | |
| CN116267235A (en) | Scraping type automatic prickly ash picking machine | |
| CN210900392U (en) | Foreign matter removing device | |
| CN114600641A (en) | Strawberry picking machine based on image recognition technology and picking method thereof | |
| KR102642313B1 (en) | Image collection device for learning harvester robot | |
| CN110794860A (en) | Multi-rotor unmanned aerial vehicle fruit harvesting method and device using visual navigation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |