WO2022039587A1

WO2022039587A1 - A method for precision agriculture and system thereof

Info

Publication number: WO2022039587A1
Application number: PCT/MY2020/000010
Authority: WO
Inventors: Jin Xi CHEONG; Yong Guan HOW; Li Cheng PHAN; Amir Farhan BIN MUHADZIR; Ruhaizan Fazreen Ashraff BIN MOHD NOR; Amir Rafiuddin BIN MARKOM
Original assignee: Poladrone Solutions Sdn Bhd
Priority date: 2020-08-19
Filing date: 2020-08-24
Publication date: 2022-02-24

Abstract

The present invention discloses a method for precision agriculture executed by an unmanned aeial vehicle (1) and a server (2) having at least one module for controlling operation of the unmanned aerial vehicle (1), the method comprising the steps of stitching, by a mapping module (21), a plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle (l); identifying, by an identification module (22), at least one geo-tagged target from the generated map, where each geo-tagged target is tagged with a reference point based on a height data relative to the ground plane; and generating, by a path planning module (23), a flight pathway for the unmanned aerial vehicle (l) to travel along and towards the geo-tagged targets over the area for discharge of pesticide; wherein the unmanned aerial vehicle (1) discharges pesticide at a targeted spot therebeneath when the unmanned aerial vehicle (l) arrives at the reference point above the geo-tagged target.

Description

A METHOD FOR PRECISION AGRICULTURE AND SYSTEM THEREOF

FIELD OF INVENTION

The invention relates to a method for precision agriculture. More particularly, the invention relates to a method for spot-spraying a crown region of oil palm trees and system thereof.

BACKGROUND OF THE INVENTION

Oryctes rhinoceros is a pest that usually attacks young oil palm trees in South-east Asia. This pest first appeared in the extreme south of Myanmar, probably from Malaysia in 1895, and worked its way through to the north over the next 15 years. The adult form of this pest bores through petiole bases into the central unopened leaves to feed on the crown region of the oil palm tree. Consequently, the bored cluster of unopened leaves causes V-shaped or wedge-shaped cuts in the unfolded fronds. The unopened leaves may collapse or emerged fronds may break off along the petiole or midrib. Thus, after a prolonged and serious rhinoceros beetle attack early the oil palm yields is considerably reduced. Currently, various techniques have been proposed to eliminate oryctes rhinoceros in the oil palm trees. By way of example, these techniques include the use of a tractor-mounted sprayer to spray pesticide at the oil palm trees or pheromone traps to lure and trap the oryctes rhinoceros.

There are a few patented technologies over the prior art relating to the apparatus to eliminate oryctes rhinoceros. US2590677A discloses a tractor mounted spray device comprising a framework attached to the forward end of the tractor, laterally extending spraying pipe members, joints between said framework and said spraying pipe members, said joints including ears extending from said framework, square members positioned between said ears and pivoted thereto, springs attached to the inner end of said square members, said ears including extending portions to which said springs are attached, said square members including further extending ears, said spraying pipe members including extending portions received between said further extending ears and pivotally secured thereto, said further extending ears being positioned at light angles to said ears.

Another apparatus for eliminating oryctes rhinoceros is disclosed in CN 103314961 A. The invention relates to oryctes rhinoceros aggregation pheromone which is prepared by uniformly mixing perfluorooctanoic acid, 4-methyl-ethyI ester, a filler, 3-methoxy- 3 -methyl- 1 -butanol, an antioxidant and a light stabilizer. The oryctes rhinoceros aggregation pheromone is simple, and it can be used by matching with a trap which is common on the market. The trap may be provided with a sticky board or catching bucket to capture the insects after they are lured by the oryctes rhinoceros aggregation pheromone.

However, the inventions disclosed in US2590677A and CN103314961A are unable to effectively eliminate the oryctes rhinoceros in the plantation. As the plantation has a soft and uneven gfound, it is not suitable for the tractor to travel in the plantation and spray the pesticide on the oil palm trees. Furthermore, the tractor sprays the pesticide all over the oil palm trees, which the tractor may miss the crown region of the oil palm trees and contribute to waste of pesticide. It is also troublesome to have the plantation workers to install the traps around the plantation as they have to collect the traps on a regular basis. The traps may also attract more oryctes rhinoceros to the plantation due to the strong scent of pheromone.

Accordingly, it would be desirable to provide a method that incorporate an unmanned aerial vehicle to perform spot-spraying on the crown region of the oil palm trees to effectively eliminate the oryctes rhinoceros and prevent wastage of pesticide. This invention provides such a method and system thereof. SUMMARY OF INVENTION

One object of the invention is to provide a method for precision agriculture executed by an unmanned aerial vehicle, a beacon and a server having at least one module for controlling operation of the unmanned aerial vehicle, such that the unmanned aerial vehicle is operable to fly around in tough terrain plantation to perform pesticide spraying operations.

Yet another object is to provide a method to perform flight planning and fleet management for precision agriculture, where the data for flight planning and fleet management is synchronised with a user device for viewing by a user.

Furthermore, the invention also seeks to reduce wastage of pesticide by spraying the pesticide precisely at the crown region of the oil palm trees with constant volume.

It is also one object of the invention to utilize real time kinematics technology in the beacon and unmanned aerial vehicle for achieving high precision in spot-spraying.

In a first aspect of the invention, there is provided a method for precision agriculture executed by an unmanned aerial vehicle and a server having at least one module for controlling operation of the unmanned aerial vehicle, the method comprising the steps of stitching, by a mapping module, a plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle; identifying, by an identification module, at least one geo-tagged target from the generated map, where each geo-tagged target is tagged with a reference point based on a height data relative to the ground plane; and generating, by a path planning module, a flight pathway for the unmanned aerial vehicle to travel along and towards the geo-tagged targets over the area for discharge of pesticide; wherein the unmanned aerial vehicle discharges pesticide at a targeted spot therebeneath when the unmanned aerial vehicle arrives at the reference point above the geo-tagged targetin this aspect of the invention, the method may further comprise the steps of capturing the plurality of geo-tagged images from a scout aerial vehicle; and obtaining the height data from a sensing unit of the unmanned aerial vehicle to couple with the geotagged images for generation of a three-dimensional map by the server.

In this aspect of the invention, the method may further comprise the steps of computing, by a path analysis module, a flight time to complete the flight pathway and an amount of pesticide for the geo-tagged targets along the flight pathway.

In this aspect of the invention, the unmanned aerial vehicle may comprise a nozzle to discharge the pesticide to the spot on the target upon pressurization to prevent disruption from the updraft of the unmanned aerial vehicle.

In this aspect of the invention, the method may further comprise the steps of recognizing, by the identification module, an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target; and identifying, by the identification module, the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle based on a shape of the outline.

In this aspect of the invention, the unmanned aerial vehicle may further comprise a front and downward proximity sensor to detect any forthcoming obstacles, which enables the unmanned aerial vehicle to halt its flight mission and hover at safety distance from the obstacle.

In a further aspect of the invention, there is provided a system for precision agriculture comprising an unmanned aerial vehicle; and a server having at least one module for controlling operation of the unmanned aerial vehicle, the server comprising a mapping module for stitching a plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle; an identification module for identifying at least one geo-tagged target from the generated map, where each geo-tagged target is tagged with a reference point based on a height data relative to the ground plane; and a path planning module for generating a flight pathway for the unmanned aerial vehicle to travel along and towards the geo-tagged targets over the area for discharge of pesticide; wherein the unmanned aerial vehicle discharges pesticide at a targeted spot therebeneath when the unmanned aerial vehicle arrives at the reference point above the geo-tagged target.

In this aspect of the invention, the system may further comprise a scout aerial vehicle to capture the plurality of geo-tagged images and obtain the height data to couple with the geo-tagged images for generation of a three-dimensional map by the server.

In this aspect of the invention, the server may comprise a path analysis module for computing a flight time to complete the flight pathway and an amount of pesticide for the geo-tagged targets along the flight pathway.

In this aspect of the invention, the identification module may recognize an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target and identify the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle based on a shape of the outline. In this aspect of the invention, the unmanned aerial vehicle may further comprise a front and downward proximity sensor to detect any forthcoming obstacles, which enables the unmanned aerial vehicle to halt its flight mission and hover at safety distance from the obstacle.

One skilled in the art will readily appreciate that the invention is well adapted to carry out the objects and obtain the ends and advantages mentioned, as well as those inherent therein. The embodiments described herein are not intended as limitations on the scope of the invention.

BRIEF DESCRIPTION OF THE DRAWINGS

For the purpose of facilitating an understanding of the invention, there is illustrated in the accompanying drawing the preferred embodiments from an inspection of which when considered in connection with the following description, the invention, its construction and operation and many of its advantages would be readily understood and appreciated.

Fig. 1 is a diagram illustrating a system for precision agriculture.

Fig. 2 is a diagram illustrating an assembled view of an unmanned aerial vehicle in an open position.

Fig. 3 is a diagram illustrating an assembled view of an unmanned aerial vehicle in a folded position.

Fig. 4 is a diagram illustrating an exploded view of an unmanned aerial vehicle. Fig. 5 is a block diagram illustrating the modules in an unmanned aerial vehicle.

Fig. 6 is a block diagram illustrating the modules in a server.

Fig. 7 is a flow chart diagram illustrating the process flow to carry out spotspraying of pesticide.

DETAILED DESCRIPTION OF THE INVENTION

For the purpose of description, the term “unmanned aerial vehicle” or drones are aircraft that can be operated remotely by a user or by pre-programmed schedules or automation systems, allowing it to fly autonomously. The unmanned aerial vehicle is designed differently depending on its application. By way of example, the unmanned aerial vehicle may be a multicopter unmanned aerial vehicile for a very flexible deployment in term of vertical and horizontal flight, a fixed-wing unmanned aerial vehicle for horizontal flight trajectories of longer flight times, or a tilt- wing unmanned aerial vehicle that supports both vertical take-off and landing as well as energyefficient gliding flight.

The term “beacon” refers to a base station that uses primarily radio, ultrasonic, optical, laser or other types of signals that indicate the proximity or location of an unmanned aerial vehicle or its readiness to perform a task. The beacon transmit a corrected position information to the unmanned aerial vehicle such that the unmanned aerial vehicle flies along a corrected flight pathway.

The term “remote controller” refers to a ground station which signals several critical, constantly changing parameters, such as power-supply information, relative address, location, timestamp, signal strength, available bandwidth resources, temperature and pressure to a receiver on the unmanned aerial vehicle. The signals may cover a wide coverage such that the unmanned aerial vehicle can travel further away without being disconnected from the remote controller.

The term “server” is defined as a computer or a cluster of computers having one or more processors. For example, the server computer can be a large mainframe, a minicomputer cluster, or a group of servers functioning as a single unit.

The term “crown region” refers to the upper branching or spreading part of a tree or other plant. The crown region of the oil palm trees consists of 35-60 pinnate fronds arranged on a vascular stem. The base of the crown region consist of a single bud where fronds and inflorescences originate.

The invention will now be described in greater detail, by way of example, with reference to the drawings.

Referring to Fig. 1, there is illustrated a system for precision agriculture. In one exemplary embodiment, the system comprises an unmanned aerial vehicle 1, a server 2 having at least one module for controlling operation of the unmanned aerial vehicle 1, and a beacon 3 for correcting position information of the unmanned aerial vehicle 1. According to the illustrated embodiment, the system is suitable for use in an agricultural plantation, where the plantation consists of uneven and soft grounds which are inconvenient for plantation workers to move around. A user may install the beacon 3 on the ground of the plantation so that the unmanned aerial vehicle 1 flies within a coverage of the beacon 3 to receive the corrected position information from the beacon 3, while the user monitors the flight pathway of the unmanned aerial vehicle 1 through an electronic device 4 and a remote controller 5.

Referring to Fig. 2, Fig. 3 and Fig. 4, there is illustrated an isometric view of the unmanned aerial vehicle 1. The unmanned aerial vehicle 1 comprises a frame assembly having a middle plate 15a being sandwiched by a top frame 15b and a bottom frame 15c, where the frame assembly having connectors to receive a plurality of propellers 16a via its arm connector 16b. The propellers 16a may be a clockwise propeller or a counter clockwise propeller. Preferably, each propeller 16a is extendable from its respective arm connector 16b through adjustment of an arm 16c which is foldable with respect to the arm connector 16b, and upon extension of the arm 16c to a desired length, a clipper 16d is used to secure the arm 16c when packing the unmanned aerial vehicle 1 after flight mission. The unmanned aerial vehicle 1 can be switched between an open position and a folded position as per Fig. 2 and Fig. 3.

In this particular embodiment, a landing gear 17a is attached to an underside of the frame assembly for absorbing shock upon landing of the unmanned aerial vehicle 1. Preferably, the landing gear 17a is provided with dampening means such as rubber pad 17b to absorb shock upon landing on the ground.

In one preferred embodiment, a spraying assembly is provided between the landing gear 17a and the frame assembly. The spraying assembly comprises a nozzle 11c that is connected to a pump lib via a nozzle mount Ila, in which when the pump lib pressurizes a pesticide-containing tank lid, the pesticide is discharged to a target through the nozzle Ila. In one preferred embodiment, the nozzle 11c and the pump 11b are optimised for oil palm spraying application. Preferably, the nozzle 11c is configured with a tip that discharges a stream jet style of spraying pattern so that the unmanned aerial vehicle 1 is capable of conducting spot-spraying to discharge the pesticide to a spot on the target upon pressurization. Besides, the pump lib also supplies sufficient high pressure and flow rate to produce a liquid stream that can withstand the updraft produced by the propellers 16a to prevent disruption from the updraft during spot-spraying. Preferably, the frame assembly is made of carbon fibre material to reduce the overall weight so that the unmanned aerial vehicle 1 can support up to 16 kilograms of weight, which is equivalent to 16 litres capacity of the pesticide-containing tank lid.

Preferably, a battery hot swap power system is included in the unmanned aerial vehicle 1 by adding parallel power source from a power distribution board to a flight controller. The user is allowed to swap batteries one by one without powering off the flight controller. Advantageously, the unmanned aerial vehicle 1 remains stable stable. The unmanned aerial vehicle 1 is resumed operation upon swapping of batteries and the unmanned aerial vehicle 1 resumes the previous flight pathway.

Referring to Fig. 5, the unmanned aerial vehicle 1 further comprises a plurality of detectors in communication with the flight controller to achieve spot-spraying of pesticide. The unmanned aerial vehicle 1 comprises a front and downward proximity sensor 12, a real time kinematics module 13a and a receiver 13b.

Preferably, the flight controller is used to control the operations of the unmanned aerial vehicle 1. One primary function of the flight controller is to direct the revolutions per minute of each propeller motor 16e in response to an input received from the server 2 such that the unmanned aerial vehicle 1 is able to travel along a flight pathway in the plantation.

Preferably, a pre-programmed microcontroller is provided to process the data of the detectors so that the data is readable by the flight controller. The microcontroller also enables the unmanned aerial vehicle 1 to switch between an autonomous flight mode and a manual flight mode. When the unmanned aerial vehicle 1 is switched to the autonomous flight mode, the microcontroller activates a safety measure, which is an obstacle avoidance mode. This obstacle avoidance mode enables the unmanned aerial vehicle 1 to be aware of its surroundings and be responsive to obstacles. Therefore, the unmanned aerial vehicle 1 can fly in various terrains and relatively complicated environments autonomously. The obstacle avoidance mode utilises the sensing unit 12 to detect obstacles and the flight controller to automatically fly the unmanned aerial vehicle 1 to a safer space. The microcontroller also regulates the operation of the spraying assembly, for example the pressure induced by the pump lib, so that a proper amount of pesticide is discharged to a spot on the target.

Preferably, the front and downward proximity sensor 12 detects any forthcoming obstacles, which enables the unmanned aerial vehicle 1 to halt its flight mission and hover at safety distance from the obstacle. The front and downward proximity sensor 12 is in the form of micro wave radars, which are disposed underneath and in front of the unmanned aerial vehicle 1 such that it detects a distance between the unmanned aerial vehicle 1 and its nearby objects, such as the distance between the ground to the unmanned aerial vehicle 1 or the distance between an obstacle to the unmanned aerial vehicle 1. Furthermore, the front and downward proximity sensor 12 is preferred to be insulated by a protective layer so that the front and downward proximity sensor 12 is dust-proof, water-proof and not affected by ambient light, which satisfies IP65 rating. This is to enable the unmanned aerial vehicle 1 to perform efficiently under sunny and dusty environments.

Preferably, the real time kinematics module 13a is used to execute satellite navigation technique through communication with the beacon 3. The unmanned aerial vehicle 1 is equipped with a receiver 13b to receive a corrected position information from the beacon 3. In one example, the real time kinematics module 13a and the receiver 13b are a U-Blox Zed F9P and a SX1268 LoRa module respectively. A receiver antenna 20 is provided to communicate with the receiver 13b. In one particular embodiment, the corrected position information is a RTCM3 data. The real time kinematics module 13a converts the RTCM3 data into a UBX navigation data prior to transmitting the UBX navigation data to the flight controller. Advantageously, the real time kinematics module 13a enhances the precision of position data derived from satellite-based positioning systems, such as GPS, GLONASS, Galileo, NavIC and BeiDou, in order for the unmanned aerial vehicle 1 to fly to the target within centimetre level accuracy. This ensures the unmanned aerial vehicle 1 to discharge the pesticide at a specific spot on the target within centimetre accuracy.

Preferably, the remote controller 5 is a ground station used for controlling the flight pathway of the unmanned aerial vehicle 1 when the unmanned aerial vehicle 1 is switched to fly in manual flight mode. The remote controller 5 communicates with the flight controller so that the user can control the operation of the propeller motors 16e thereby controlling the flight pathway of the unmanned aerial vehicle 1. Preferably, the remote controller 5 uses LoRa technology, which is a spread spectrum modulation technique derived from chirp spread spectrum technology, and redundant algorithms to ensure radio signal and image transmission distance can reach up to 20 kilometres. The remote controller is also adapted to house and communicate with the electronic device 4, such as a personal digital assistant (PDA), a smart phone, a tablet or any suitable means which is capable of receiving inputs from the server 2 and the beacon 3, processing the inputs and performing data transmission, through a web application or a mobile application via internet connection. This enables the user to view flight data and a first-person-view of the flight pathway from the electronic device 4 through a first person view camera 22 attached onto the unmanned aerial vehicle 1. Preferably, the remote controller 5 establishes 2.4 giga hertz radio frequency with the unmanned aerial vehicle 1 for telemetry, first person view recording and remote control. The electronic device 4 also synchronizes its data with the server 2 in real time.

Preferably, the beacon 3 is a base station that communicates with the unmanned aerial vehicle 1 as long as the unmanned aerial vehicle 1 is within a coverage of the beacon 3. The beacon 3 comprises a real time kinematics module 31a that is used to correct position information retrieved from satellite-based positioning systems, such as GPS, GLONASS, Galileo, NavIC and BeiDou, prior to transmitting to the unmanned aerial vehicle 1 by a transmitter 31b. In one example, the real time kinematics module 31a and the transmitter 31b are a U-Blox Zed F9P and a SX1268 LoRa module respectively. In further examples, the board used for SX1268 LoRa module is E22400T30S. In one particular embodiment, the position information is a GNSS satellite signal. The real time kinematics module 31a converts and corrects the GNSS satellite signal into a RTCM3 data prior to transmitting the RTCM3 data to the receiver 13b of the unmanned aerial vehicle 1. Advantageously, the real time kinematics module 31a enhances the precision of position data derived from, in order for the unmanned aerial vehicle 1 to fly to the target within centimetre level accuracy. This ensures the unmanned aerial vehicle 1 to discharge the pesticide at a specific spot on the target within centimetre accuracy. One main advantage of the beacon 3 is elimination of the needs of frequent setup of beacons 3, which operation team can move from one point to another without setting up the beacons 3 again while getting RTCM correction for the unmanned aerial vehicle 1 within the coverage of the beacon 3. Preferably, each beacon 3 can cover at least 5 kilometres radius without obstruction.

In one preferred embodiment, the system further comprises a scout aerial vehicle that flies over the plantation to capture a plurality of geo-tagged images via imaging unit. The imaging unit is in the form of a high speed photographing device to capture the images. The imaging unit may be coupled with a GPS module so that the GPS module automatically tags a GPS coordinate to the images captured by the imaging unit. The scout aerial vehicle also obtains height data and to couple with the geo-tagged images for generation of a three-dimensional map by the server 2. Referring to Fig. 6, the server 2 comprises at least one module for controlling operation of the unmanned aerial vehicle 1. The server 2 comprises a mapping module 21, an identification module 22, a path planning module 23 and a path analysis module 24.

Preferably, the mapping module 21 is used for stitching a plurality of geo-tagged images captured by the scout aerial vehicle to generate a map of an area to be travelled by the unmanned aerial vehicle 1. For example, the mapping module 21 arranges the plurality of geo-tagged images according to its geolocation data and stitches the geo-tagged images together with elevation data. By way of example, the elevation data is a Digital Terrain Model.

Preferably, the identification module 22 is used for identifying at least one geo-tagged target from the generated map. In one particular embodiment, the identification module 22 recognizes an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target. Preferably, each geotagged target is tagged with a reference point based on a height data relative to the ground plane, in which the reference point represents the spot to receive the pesticide. To enhance the accuracy of the system, the identification module 22 corrects and adjusts the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle 1 based on its outline. The outline may be recognized by eliminating background surrounding the geo-tagged target. In this particular embodiment, the identification module 22 executes localization method to measure a centre of the geotagged target from the recognised outline and take the measured centre as an initial predicted crown region. Further steps such as feature extraction around the initial predicted crown region may be executed as to correct and adjust the measured centre such that an accurate crown region is obtained by the system. The corrected centre is then marked as the spot to receive the pesticide. The identification module 22 also counts the number of geo-tagged targets on the map and the geolocation data of each geo-tagged target is retrieved for generating a flight pathway.

Preferably, the path planning module 23 is used for generating the flight pathway for the unmanned aerial vehicle 1 to travel along and towards the geo-tagged targets over the area for discharge of pesticide. The path planning module 23 is configured to plan the flight pathway with shortest flight time and broadest coverage over the plantation.

Preferably, the path analysis module 24 is used for computing a flight time to complete the flight pathway and an amount of pesticide for the geo-tagged targets along the flight pathway. In this particular embodiment, the path analysis module 24 forms an array based on a distance calculated between consecutive geo-tagged targets. The path analysis module 24 retrieves several parameters pertaining to the unmanned aerial vehicle 1, such as acceleration and peak velocity, and from these parameters the path analysis module 24 calculates a time taken to travel between the consecutive geo-tagged targets. Preferably, the time taken to travel between the consecutive geotagged targets is added with spray delay time, and the sum is multiplied with tolerance to obtain the flight time. Preferably, the amount of pesticide is computed based a summation of a pre-set amount of pesticide allocated for each geo-tagged target.

In one advantageous embodiment, the system enables the unmanned aerial vehicle 1 to hover at right above the targeted spot on the geo-tagged target. In one example, the unmanned aerial vehicle 1 detects its current GPS location to determine if the unmanned aerial vehicle 1 is right above the targeted spot. The unmanned aerial vehicle 1 then discharges pesticide at a targeted spot therebeneath. When the unmanned aerial vehicle 1 arrives at the reference point above the geo-tagged target, the unmanned aerial vehicle 1 only discharges the pesticide as the reference point defines an ideal spray pattern of the spot-spraying technique, which includes angle of spray and radius of spray. The system is advantageous for application in oil palm plantation as the ground plane is uneven and the oil palm trees are varied in heights. The precision of real time kinematics module of the beacon 3 and the unmanned aerial vehicle 1 enables the unmanned aerial vehicle 1 to hover at a desired height for each oil palm tree of various ground elevation, and spot-spray the pesticide at the targeted spot, particularly at a crown region of the tree. Preferably, a home point is determined based on a current position of the unmanned aerial vehicle 1 at its point of departure. The home point refers to a height of the unmanned aerial vehicle 1 at the point of departure. The desired height of flight for the unmanned aerial vehicle 1 is computed based on the height of each geo-tagged target and the home point. Therefore, the unmanned aerial vehicle 1 is able to hover at the desired height relative to the reference point when the unmanned aerial vehicle 1 approaches the geo-tagged target. It is preferred to launch the unmanned aerial vehicle 1 at a consistent home point to ensure high accuracy of the system.

Referring to Fig. 7, a flow chart is provided to illustrate a method for precision agriculture by utilizing the system as described above. At step 101, the scout aerial vehicle obtains a plurality of geo-tagged images by flying over the area. At step 102, the geo-tagged images are transmitted to the server 2 for the mapping module 21 to stitch the plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle 1. At step 103 and 104, the identification module 22 recognizes an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target and identifies the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle 1 based on a shape of the outline. At step 105 and 106, the identification module 22 counts the number of geo-tagged targets on the map and retrieves the geolocation data of each geo-tagged target for generating a flight pathway. At step 107, the path planning module 23 generates a flight pathway for the unmanned aerial vehicle 1 to travel along and towards the geo-tagged targets over the area for discharge of pesticide. At step 108, when the unmanned aerial vehicle 1 arrives at the reference point above the geo-tagged target the unmanned aerial vehicle 1 discharges pesticide at a targeted spot therebeneath to execute spot-spraying.

The present disclosure includes as contained in the appended claims, as well as that of the foregoing description. Although this invention has been described in its preferred form with a degree of particularity, it is understood that the present disclosure of the preferred form has been made only by way of example and that numerous changes in the details of construction and the combination and arrangements of parts may be resorted to without departing from the scope of the invention.

Claims

1. A method for precision agriculture executed by an unmanned aerial vehicle (1) and a server (2) having at least one module for controlling operation of the unmanned aerial vehicle (1), the method comprising the steps of: stitching, by a mapping module (21), a plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle (1); identifying, by an identification module (22), at least one geo-tagged target from the generated map, where each geo-tagged target is tagged with a reference point based on a height data relative to the ground plane; and generating, by a path planning module (23), a flight pathway for the unmanned aerial vehicle (1) to travel along and towards the geo-tagged targets; wherein the unmanned aerial vehicle (1) discharges pesticide at a targeted spot therebeneath when the unmanned aerial vehicle (1) arrives at the reference point above the geo-tagged target.

2. The method according to claim 1 further comprising the steps of: capturing the plurality of geo-tagged images from an imaging unit (11) of a scout aerial vehicle; and obtaining the height data from a sensing unit (12) of the scout aerial vehicle to couple with the geo-tagged images for generation of a three-dimensional map by the server (2).

3. The method according to claim 1 further comprising the steps of computing, by a path analysis module (24), a flight time to complete the flight pathway and an amount of pesticide for the geo-tagged targets along the flight pathway.

4. The method according to claim 1, wherein the unmanned aerial vehicle (1) comprises a nozzle (11c) to discharge the pesticide to the spot on the target upon pressurization to prevent disruption from the updraft of the unmanned aerial vehicle (1).

5. The method according to claim 1 further comprising the steps of: recognizing, by the identification module (22), an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target; and identifying, by the identification module (22), the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle (1) based on a shape of the outline.

6. The method according to claim 1, wherein the unmanned aerial vehicle (1) further comprises a front and downward proximity sensor to detect any forthcoming obstacles, which enables the unmanned aerial vehicle (1) to halt its flight mission and hover at safety distance from the obstacle.

7. A system for precision agriculture comprising: an unmanned aerial vehicle (1); and a server (2) having at least one module for controlling operation of the unmanned aerial vehicle (1), the server (2) comprising: a mapping module (21) for stitching a plurality of geo-tagged images to generate a map of an area to be travelled by the unmanned aerial vehicle (1); an identification module (22) for identifying at least one geo-tagged target from the generated map, where each geo-tagged target is tagged with a reference point based on a height data relative to the ground plane; and a path planning module (23) for generating a flight pathway for the unmanned aerial vehicle (1) to travel along and towards the geo-tagged targets over the area for discharge of pesticide; wherein the unmanned aerial vehicle (1) discharges pesticide at a targeted spot therebeneath when the unmanned aerial vehicle (1) arrives at the reference point above the geo-tagged target.

8. The system according to claim 7 further comprising a scout aerial vehicle to capture the plurality of geo-tagged images and obtain the height data to couple with the geo-tagged images for generation of a three-dimensional map by the server (2).

9. The system according to claim 7, wherein the server (2) comprises a path analysis module (24) for computing a flight time to complete the flight pathway and an amount of pesticide for the geo-tagged targets along the flight pathway.

10. The system according to claim 7, wherein the unmanned aerial vehicle (1) comprises a nozzle (11c) to discharge the pesticide to the spot on the target upon pressurization to prevent disruption from the updraft of the unmanned aerial vehicle (1).

11. The system according to claim 7, wherein the identification module (22) recognizes an outline of the geo-tagged target from the geo-tagged images by eliminating background surrounding the geo-tagged target and identifies the spot on the geo-tagged target to receive the pesticide from the unmanned aerial vehicle (1) based on a shape of the outline.

12. The system according to claim 7, wherein the unmanned aerial vehicle (1) further comprises a front and downward proximity sensor to detect any forthcoming obstacles, which enables the unmanned aerial vehicle (1) to halt its flight mission and hover at safety distance from the obstacle.