TWI838908B - Flying unmanned vehicle laser pest control system based on safety considerations - Google Patents

Abstract

The invention provides an intelligent laser disinfestation system for unmanned vehicle with dynamic and stable aiming, it contains: A mobile vehicle equipped with a flight control module, a laser emitting element, an image capture device, a target distance sensor, a flight state sensing unit and a processing unit; The flight state sensing unit is used to sense the flight state parameters of the mobile vehicle; The target distance sensor measures a distance value of the target image captured by the image capturing device; An analysis module that builds a pest identification model; Therefore, in the present invention, after the image is captured by the image capture device, the analysis module can identify a target (such as a pest) and its position information in the image through the pest identification model. And define a control command according to the position information, flight state parameters, distance value and focal length value of the laser emitting element to define a control command, so that the flight control module can accurately and stably control the mobile vehicle to move to the corresponding position information place, so that the laser emitting element can emit laser to the position corresponding to the position information, so as to remove or disable the pests in an automated way by unmanned vehicles. In addition, the present invention can further identify the images of humans, beneficial insects or other animals by configuring the settings of the photographing device and the warning device, and it can issue a warning accordingly, so that the environmental creatures can actively avoid and avoid being exposed to laser light, so as to improve the safety of the present invention in automatically removing pests.

Description

Safety-based drone laser pest control system

The present invention provides a flying unmanned vehicle laser pest control system based on safety considerations, particularly a system that can automatically detect the location of pests through an unmanned vehicle and emit lasers accordingly to remove or disable the pests, thereby inhibiting the reproduction of pests, and can perform steady-state flight, and can identify other biological images and issue warnings, thereby improving safety during automatic pest removal.

Since the 20th century, the invention of chemical fertilizers and pesticides has reduced pests and diseases, increased production, and increased farmers' incomes, so the customary use of chemical pesticides has been widely used in agriculture; however, with the increasing use of low-cost pesticides, the problems brought by pesticides have gradually emerged. Due to the excessive use of chemical fertilizers and pesticides to improve productivity, the environment has been seriously polluted and human health has been endangered; long-term use of large amounts of chemical pesticides will lead to soil acidification and salinization, and will also damage water resources and the ecological environment, seriously polluting people's living environment; in addition, as the number of spraying increases, pests and diseases will develop resistance, so the concentration of the pesticide needs to be increased. This result will further increase the resistance of pests and diseases, and high concentrations of pesticides will cause greater pollution to the environment. In addition to seriously affecting animals and plants, it will also pose a threat to human food safety. Therefore, how to develop environmentally friendly agriculture is urgent; therefore, creating environmentally friendly agriculture and reducing the harm to the environment, while also effectively preventing pests and diseases and weeds from sharing nutrients, has become one of the important research goals.

In a friendly farming environment, organic agriculture is a production method that is less polluting and less damaging to the environment, and can provide consumers with healthy and safe agricultural products. The definition of organic agriculture varies according to the laws of each country. With the evolution of agricultural technology, the requirements of organic agriculture regulations have become increasingly stringent. According to the definition of Taiwan's Council of Agriculture, organic agriculture is an agriculture that abides by the principle of sustainable use of natural resources, does not allow the use of synthetic chemicals, emphasizes the management system of water and soil resource conservation and ecological balance, and achieves the goal of producing natural and safe agricultural products. In January 2007, the Council of Agriculture began to implement the "Agricultural Product Production and Certification Management Act", which included organic agriculture and its products in legal regulations.

According to statistics from the Department of Agriculture and Food under the Council of Agriculture, Executive Yuan in November 2011, there are 4,413 organic farming households, and the organic farming area is 11,722.3276 hectares. According to the "Current Status of Agricultural Management" of the Council of Agriculture, Executive Yuan, the area of arable land in Taiwan in 2010 is 790,000 hectares, and the annual crop planting is 2.36 million hectares. The cultivated area is 740,000 hectares. At the end of 2019, there were 775,000 farming and animal husbandry households in Taiwan, of which 718,000 were engaged in agriculture and animal husbandry. The farming and animal husbandry population was over 2.69 million. It can be seen that the organic planting area only accounts for 1.5% of the cultivated land area, and the number of organic farming households only accounts for 0.6% of the number of households engaged in agriculture and animal husbandry.

According to a report from the EU cited by the Organic Agriculture Global Information Network, the current organic agriculture area in the EU accounts for 8.5% of the total agricultural area. If the growth trend in recent years is estimated, it will increase to about 15-15% by 2030. The Organic Action Plan further aims to increase the organic ratio to 25%. Therefore, Taiwan lags far behind the EU in the development of organic agriculture. The main reason is that Taiwan's climate is hot and humid, and there is no sufficiently low temperature in winter, which makes pests and diseases difficult to control. In addition, because Taiwan is in a high temperature and humid environment, organic matter decomposes quickly, leaching is intense, and nutrient loss is large, resulting in a decline in soil fertility, leading to domestic soil The organic matter content is generally low. More than 65% of the country's arable land has an organic matter content of less than 2%. It is necessary to buy expensive organic fertilizers. In addition, the land load is too large. On average, each hectare has to support 24 people, which means there is not enough land for crop rotation. Therefore, the inherent conditions limit the development of organic agriculture. The Agricultural Policy Research Center of the Agricultural Science and Technology Research Institute also pointed out that in terms of agricultural products, Taiwan's organic rice and vegetable technology is mature, but the scale of organic fruit is still small. This is because of the latitude of our country, which makes it vulnerable to climate impact and many diseases and pests, so the crop growth period is also longer, so fewer people invest in planting.

Due to the wide variety of crops in my country, the main damage caused by pests to economic crops such as vegetables, fruit trees and flowers can be divided into three types: feeding damage, non-feeding damage and transmission of diseases. Among them, feeding pests can directly harm the roots, stems, leaves, buds, fruits, seeds and other parts of flowers, causing damage to different parts. Feeding pests mainly have 6 ways of damage: chewing, rolling, Nesting on leaves or leaf bundles, leaf diving, leaf boring, piercing and sucking, and galling; there are two main types of non-feeding damage to crops: egg-laying damage and soil-boring damage; transmitted diseases are wounds caused by pests, which are channels for certain pathogens to invade. Many plant viral diseases are transmitted by pests; pests can be divided into several categories according to the parts they damage, such as underground pests, leaf-feeding pests, piercing and sucking pests, and boring pests. Important pests on different parts of the tree and their damage characteristics can be divided into the following categories: those that damage roots or bulbs include: crickets, grubs, root divers, sweet potato ants, yellow-striped leaf fleas, root mites, etc. They feed on the roots and damage the epidermis, affecting the absorption of water and nutrients by the roots, causing the tree to weaken, and in severe cases, causing the entire above-ground plant to wither; damage to flower bulbs, sweet potato tubers, and potato tubers affects germination, commercial value, and yield. The pests that harm stems, trunks, and branches are: peach heartworm, wood borer, borer, longhorn beetle, weevil, termite, stem miner, shell insect, etc., which will cause the branches or stems to be bored, resulting in branch breakage and new shoot withering, affecting the growth of the tree; some damaged trunks will become peeling, and in severe cases, the whole plant will die; those that harm the flowers are mainly beetles, beet armyworm, and lithotripsy, which will directly affect the commercial value of flowers and indirectly cause the commercial value of flowers or fruits to fall; those that harm fruits, such as oriental fruit flies and melon The adult fruit flies lay eggs in the fruit, and the larvae eat in the flesh, causing the fruit to rot and fall. Among them, fruits have a higher economic value and are the least tolerant to insect damage. As long as they are damaged by a few insects, they will cause serious losses. In addition, pests that harm the roots of seedlings include crickets, cutworms, wireworms, and grubs. After these pests harm plants, they not only cause a reduction in production, but also affect the quality of vegetables and reduce the commercial value. The important pests that harm the leaves can be divided into: moth pests, aphids, artichokes, mites, divers, powder flies, etc.

The main purpose of pest control in organic agriculture is to adopt various non-pesticide natural control methods, hoping to enable beneficial insects and bacteria to maintain a good ecological balance with pests and pathogens; although there are many methods, they can be roughly divided into cultivation control, physical control, biological control and natural pesticide control; the purpose of organic agriculture is to properly protect beneficial insects and various natural enemy animals and microbial communities, and use the antagonistic functions between organisms to restrain the reproduction of pests, so as to achieve natural ecological balance and prevent crops from being seriously damaged; under the organic agricultural management mode, the beneficial insects and various natural enemy animals, antagonistic microorganisms, etc. that have disappeared will gradually reappear, bringing a friendly farming environment.

Australian Centre for Field Robotics has developed a solar-powered field robot called RIPPA, which it attempts to use as a weed and pest control robot. It uses physical pest control, mainly using image processing to determine the location of pests, and controls the suction port of the vacuum cleaner to suck away pests. In the demonstration video of the RIPPA field robot, the pest control part uses blue plastic bottle caps as imaginary pests, so it is still in the experimental stage and there should still be technical problems to be overcome; among them, the vacuum cleaner mouth is slightly larger, so there is a concern that it may damage the planted plants. In addition, some pests will attach to leafy vegetables, so in order to avoid damaging the planted plants and suck away the pests, the control mechanism of its suction force is an important topic.

There are also literatures on precise laser pest control in existing research. It combines key technologies such as monocular stereo vision, rapid laser scanning and intelligent pest recognition to control the number of agricultural pest populations. It is mainly used in experiments to control pests of fruit trees in date orchards. The results show that under specific light wavelengths and powers, larvae of the two-year-old Taiwan yellow tussock moth will be unable to ingest further food after being irradiated for 1.2 seconds. Therefore, the laser pest control device can effectively control the pest population.

In 1988, there was a document proposing the use of lasers to remove pests. It used lasers to irradiate fruit flies in a closed space and found that green light was more effective than infrared light. In 2008, the Gates Foundation also sponsored the Intellectual Ventures laboratory laser mosquito control project to eliminate malaria. Although insecticides can effectively kill mosquitoes, they are very harmful to the environment and mosquitoes can develop resistance to them. The goal of the project is to use the laser in the Blu-ray DVD plus a photoreceptor (CCD or CMOS) to kill mosquitoes using physical methods. It is hoped that the cost will be controlled within NT$2,000 and can help fight malaria in Africa. However, the laser energy of the Blu-ray DVD is too small, so the Lighting Science team published the results in Optics in 2016. Express, its working principle is to first emit low-power infrared light, the illumination range can reach 30 meters, and place a reflector, and use an infrared camera to monitor the reflector. Once an insect enters the optical network, it will leave a silhouette on the reflector. The infrared camera can preliminarily determine whether it is a mosquito based on the measured silhouette. It can also use the size of the mosquito, the frequency of wing flapping and the flying speed to determine the gender of the mosquito. Since female mosquitoes are larger and the frequency of wing flapping is also lower, once the system software determines that it is a female mosquito, it will emit a high-energy laser to shoot down the mosquito. According to research, the laser power does not need to be high enough to completely burn the mosquito's wings, as long as it can destroy the mosquito's flying ability, the mosquito can be shot down. However, the size of the machine is huge and the price is far beyond expectations, so it is still in the research stage.

Currently, there is another patent case similar to the "System and Method for Locating and Removing Insects" in Taiwan's Patent Publication No. 202022698. It mainly detects the location of insects based on images, can mark them, can be mounted on a drone, and dispose of insects mechanically or chemically through components; and its main technology is that it obtains spatial images through a camera and determines the location of the insect in the space based on the image. However, the position in space cannot be obtained through a single camera because a single camera only captures two-dimensional images. It is difficult to obtain three-dimensional space. At least two cameras are needed to capture the actual position of insects in space. According to another embodiment, the time difference between two images is used to capture the actual position of insects in space. However, the configuration requires that the position of the camera moving is a known value. The required technology and computing power are very high, so the cost will increase significantly and it is difficult to actually apply it to drones. In addition, it is also mentioned that the camera and the pointing device of the laser or indicator mark will be placed at least 10 cm away from each other. However, this setting is difficult for mobile pest control devices, and in 2008, the Gates Foundation also sponsored Intellectual Ventures Laboratory Laser Mosquito Killing Project, projection-type mosquito removal device is feasible, but the restrictions on autonomous mobile insect removal device are high, making it difficult to effectively implement it; further investigation, the 202022698 case explains that its processor can analyze the image of the space containing insects and mobile devices in a single frame of the image, control the mobile device to move to the vicinity of the insect, and the direction to the insect can be estimated from the location of the insect in the image within a single frame. The processor uses the pixel distance between the two objects in a single frame to regularly judge the angular distance between the mobile device and the insect in the single frame, and calculates based on this. Calculate the distance and direction that the mobile device needs to move; however, as mentioned above, since a single camera can only obtain planar information, unless the size of the insect is assumed to be known, the distance of the insect can be estimated based on the size of the insect image in the captured image. Otherwise, only the information of the insect's moving direction can be obtained, and the distance of the insect cannot be calculated; in addition, it is further explained that the method of removing insects may include a method of determining whether there is a creature (or an object or material that can be harmed by the action of the auxiliary device) near the location of the insect, which uses the relative size of the action in space or the shape and color of the material to make the judgment. However, the size of general insects relative to the creatures that are avoided from being harmed is very different. When using relative size of motion to judge, the movement of plants in the wind may be similar to the movement of organisms and difficult to distinguish. In addition, it is almost impossible to identify insects and organisms by shape in the same captured image.

In view of this, we, the inventors, have devoted ourselves to further study the dynamic stability control of unmanned vehicle pest control and its safety considerations during operation, and have started to carry out research and development and improvement, hoping to find a better invention to solve the above problems. After continuous testing and modification, the present invention was born.

Therefore, the purpose of the present invention is to solve the above problems. To achieve the above purpose, we, the inventors, provide a flying unmanned vehicle laser pest control system based on safety considerations, which includes: a mobile vehicle, which is equipped with a flight control module, a laser emitting element, an image capture device, a camera device, a target distance sensor, a flight status sensing unit and a processing unit; the flight control module is used to control The flight state sensing unit is used to sense at least one flight state parameter of the mobile vehicle; the laser emitting element has a focal length value; the processing unit is coupled to the flight control module, the laser emitting element, the image capture device, the photographic device, the target distance sensor and the flight state sensing unit; and an analysis module is connected to the processing unit; and the analysis module The device is provided with a pest recognition model; the image capture device is used to capture an image, the camera device is used to capture a second image, the processing unit transmits the image, the second image, the focal length value and the flight state parameter to the analysis module, the analysis module recognizes a target in the image and the second image through the pest recognition model, and measures the target distance sensor based on the target distance. The distance value is measured, and a position information is generated accordingly, and a control instruction is defined according to the position information, the flight state parameter, the distance value and the focal length value, and is sent back to the processing unit, so that the processing unit controls the flight control module to move the mobile vehicle to a position corresponding to the position information according to the control instruction, so that the focal length of the laser emitted by the laser emitting element corresponds to the position of the position information.

The above-mentioned flying unmanned vehicle laser pest control system based on safety considerations further includes a warning device, which is configured on the mobile vehicle and correspondingly coupled to the processing unit; the analysis module is configured with a safety recognition model, and the safety recognition model is used to recognize at least one safety target. The processing unit transmits the second image to the analysis module, and the analysis module uses the safety recognition model to identify whether the second image contains the safety target. When the second image is identified to contain the safety target, the processing unit causes the warning device to issue a warning.

According to the above-mentioned flying unmanned vehicle laser pest control system based on safety considerations, the camera device is a wide-angle camera, and the image capture device is a long-distance camera.

According to the above-mentioned flying unmanned vehicle laser pest control system based on safety considerations, the flight state parameter includes at least one of the longitude, latitude, altitude, pitch angle, yaw angle, roll angle, speed and angular velocity of the mobile vehicle.

The above-mentioned flying unmanned vehicle laser pest control system based on safety considerations further includes a rotating platform, which is arranged on the mobile vehicle and correspondingly carries the laser emitting element and the image capturing device; and at least one driving device, which is coupled to the processing unit and correspondingly connects and drives the rotating platform. The processing unit drives the driving device to make the focal length of the laser emitted by the laser emitting element correspond to the position of the position information.

The above-mentioned flying unmanned vehicle laser pest control system based on safety considerations further includes a remote control device, which is provided with a transmission module and the analysis module, and the transmission module is connected to the analysis module; and the processing unit is further provided with a communication module, and the communication module is signal-connected to the transmission module to enable the processing unit to connect and transmit signals to the analysis module.

According to the above-mentioned flying unmanned vehicle laser pest control system based on safety considerations, the target identified by the pest recognition model in the image is the image of the mouth of a pest.

The above-mentioned flying unmanned vehicle laser pest control system based on safety considerations further includes a control module, which is connected to the processing unit and the laser emitting element; the pest recognition model is used to identify the target and its corresponding type information in the image, and the control module recognizes the type information of the target based on the pest recognition model to adjust the power intensity of the laser emitting element through pulse width modulation (PWM), and accordingly controls the time and interval of the laser emitted.

According to the above-mentioned flying unmanned vehicle laser pest control system based on safety considerations, the power of the laser emitted by the laser emitting element is less than 5W.

According to the above-mentioned flying unmanned vehicle laser pest control system based on safety considerations, the pest recognition model is obtained by training with deep neural networks (DNN), deep belief networks (DBN), convolutional neural networks (CNN), regions with convolutional neural networks (R-CNN), fast regional convolutional neural networks (Faster R-CNN) or YOLO (You only look once) algorithm.

From the above description and configuration, it is clear that the present invention mainly has the following advantages and effects, which are described in detail as follows:

1. The present invention can sense the flight state parameters of the mobile vehicle by setting up a flight state sensing unit, and the analysis module builds a pest recognition model, so that when the image capture device captures an image, the analysis module can recognize a target (such as a pest) and its corresponding position information in the image. The position information, flight state parameters, distance value and focal length value of the laser emission element are used to define a control instruction, so that the control instruction is defined. The management unit can accurately and stably control the flight control module to move the mobile vehicle to the location corresponding to the location information according to the control instructions, and can make the laser emitting element emit lasers toward the location corresponding to the location information to remove pests or disable them, so that pest removal can be automated to properly control the reproduction of pests to prevent damage, and help achieve natural ecological balance to promote the development of related agriculture.

2. The present invention uses a remote control device and configures the analysis module in the remote control device, so that the calculation of the pest recognition model for image recognition can be handed over to the analysis module located at the remote end for processing, thereby reducing the hardware configuration of the mobile vehicle, so that the mobile vehicle can be configured to be lightweight, so that its overall weight can be controlled within 2 kilograms, and its power consumption can be reduced, and its operating performance can be improved.

3. The present invention is further configured with a camera and an alarm device to further identify images of humans, beneficial insects or other animals, and to issue an alarm accordingly, so that environmental organisms can actively avoid being exposed to lasers, thereby improving the safety of the present invention in automatically removing pests.

1: Mobile vehicle

11: Flight control module

12: Flight status sensing unit

2: Processing unit

21: Communication module

22: Control module

23: Warning device

3: Rotating stage

31: Laser emitting element

32: Image capture device with variable focal length

32’: Image capture device

33: Target distance sensor

34: Drive device

35:Photographic equipment

4:Analysis module

41: Transmission module

5: Remote control device

S001~S005: Steps

Figure 1 is a schematic diagram of the system architecture of the present invention.

Figure 2 is a flow chart of the present invention.

Figure 3 is a three-dimensional schematic diagram of the present invention.

Figure 4 is a partial cross-sectional schematic diagram of the present invention.

Figure 5 is a schematic diagram of the present invention in use.

Figure 6 is a schematic diagram of the system architecture of another embodiment of the present invention.

Figure 7 is a three-dimensional schematic diagram of another embodiment of the present invention.

Regarding the technical means of our inventors, several preferred embodiments are described in detail below with accompanying drawings, so that you can have a deeper understanding and recognize the present invention.

Please refer to FIGS. 1 to 3. The present invention provides a flying unmanned vehicle laser pest control system based on safety considerations, which includes: a mobile vehicle 1, which in one embodiment can be a multi-rotor drone, but it is only an example and is not limited to this; the mobile vehicle 1 is equipped with a flight control module 11, a flight state sensing unit 12 and a processing unit 2, and in one embodiment, the mobile vehicle 1 is equipped with a rotating platform 3, and a laser emitting element 31, a variable focal length image capture device 32 and a target distance sensor 33 are arranged on the rotating platform 3; wherein, The flight control module 11, as known, can be the rotor of the mobile vehicle 1, so as to control the position, lift, pitch angle, yaw angle, roll angle and speed of the mobile vehicle 1. The control method belongs to the known technology, so it is not repeated here; and the flight state sensing unit 12 is used to sense at least one flight state parameter of the mobile vehicle 1, such as: at least one of the longitude, latitude, altitude, pitch angle, yaw angle, roll angle, speed and angular velocity of the mobile vehicle 1. Therefore, it can be known that the flight state sensing unit 12 can be configured as a corresponding inertial sensor, altimeter, GPS or RTK with higher accuracy. At least one of the GPS positioning devices; and as for the setting of the laser emitting element 31, it can emit lasers accordingly, and the shorter the wavelength of the laser, the more harmful it is. Therefore, if efficiency is considered, the wavelength of the laser can be set to below 400nm. If safety is considered, it can be set to between 450nm and 550nm, so that its wavelength is closer to green and less likely to be absorbed by green plants; in one embodiment, the wavelength can also be set to other wavelengths, so that when the pest is green in color, it can also be affected; and in one embodiment, The laser spot irradiated by the laser emitting element 31 can be set to a diameter of less than 2mm and a power of less than 5W, which is convenient for carrying lightweight drones; the laser emitting element 31 can adjust the power to the appropriate level according to the properties of the pests by pulse modulation, and irradiate the vital parts of the pests for a short time, which is set to less than 2 seconds in this embodiment, to increase the mobility of the drone to quickly move and remove pests; and thereby kill the pests, or disable them, such as: unable to take in food, thereby reducing their reproductive capacity. However, the above configuration is only an example and is not intended to be limiting.

As for the configuration of the variable focal length image capture device 32, since the present invention is mainly used to photograph and identify pests, it can be a camera, a single lens with optical telescopic function, or a plurality of single-focus lenses forming an image capture device to capture images. Since the pest part has a protective color, in a preferred embodiment, it can be configured as a thermal imager or a multi-spectrometer, or a combination of the aforementioned camera, thermal imager or multi-spectrometer, so as to be more conducive to the extraction of pest characteristics.

The processing unit 2 is coupled to the flight control module 11, the laser emitting element 31, the variable focus image capture device 32 and the flight state sensing unit 12; and in order to make it lightweight, the mobile vehicle 1 and its overall mounted device objects can be controlled within 2 kilograms to reduce its energy consumption, so the processing unit 2 can be set as an embedded system architecture; and an analysis module 4, which is connected to the processing unit 2; and the analysis module 4 ... The analysis module 4 is equipped with a pest recognition model. It is known that the pest recognition model is used to detect whether there are pests in the target image. The general target detection can be processed by region selection, feature extraction or classifier. The better one is based on image learning principles, such as deep learning, which is based on a neural network-like framework and is an algorithm for characterizing data. In the present invention, it can be based on a deep neural network (Deep Neural Networks (DNN), Deep Belief Networks (DBN), Convolutional Neural Networks (CNN), Regions with Convolutional Neural Networks (R-CNN), Faster R-CNN or YOLO (You only look once) algorithm, and in this embodiment, it is carried out through the YOLO intelligent recognition algorithm with higher real-time performance, and through sufficient pest image information through YOLO training to form its training model, which is the pest recognition model; and in order to facilitate the construction of the pest recognition model, in one embodiment, it can also be used through iNaturalist The API is used as a pest identification model to identify pests, but this is only an example and is not intended to be limiting.

Thus, as shown in FIGS. 1 to 5, the variable focus image capturing device 32 is used to capture an image, the target distance sensor 33 is used to measure a distance value of the target image captured by the variable focus image capturing device 32, and the processing unit 2 transmits the image, the distance value and the flight state parameter to the analysis module 4, so that the analysis module 4 recognizes a target (i.e., the pest image in the image) in the image through the pest recognition model, and thereby, according to the internal parameters of the variable focus image capturing device 32, such as the focal length, position and angle of the variable focus image capturing device 32, to determine the target. and the position of the mobile vehicle 1, the position information corresponding to the target can be calculated in the image, and the flight path of the mobile vehicle 1 can be defined by the relative position of the target position information and the mobile vehicle 1, and a control instruction can be defined by combining the flight state parameters of the mobile vehicle 1, and sent back to the processing unit 2, so that the processing unit 2 controls the flight control module 11 to move the mobile vehicle 1 to the position corresponding to the position information according to the control instruction, and makes the laser emitting element 31 emit laser toward the position corresponding to the position information, so as to remove pests or disable them through laser irradiation as mentioned above.

As mentioned above, since the pest identification model requires a large amount of computation for image recognition, in order to enable the present invention to perform real-time computation and reduce the hardware configuration of the mobile vehicle 1 carrying the processing unit 2 so that it can be lightweight, in a preferred embodiment, a remote control device 5 can be deployed in the area where the pests are to be removed, which is provided with a transmission module 41 and the analysis module 4, and the transmission module 41 is The processing unit 2 is further provided with a communication module 21, which is signal-connected to the transmission module 41, so that the processing unit 2 is connected and transmits signals to the analysis module 4; thereby, since the processing unit 2 is mounted on the mobile vehicle 1, it can transmit images and flight status parameters to the transmission module 41 through the communication module 21, so that the analysis module 4 can receive the images and flight status parameters. The above-mentioned target image recognition through the pest recognition model is received and performed, and the control command is calculated, so that the mobile vehicle 1 can focus on its flight control, image capture and acquisition of flight status parameters. In addition to reducing its hardware configuration to make it lightweight, it can also reduce its energy consumption, which can help to improve the navigation distance and range of the mobile vehicle 1; and the communication between the communication module 21 and the transmission module 41 In one embodiment, wireless connection can be achieved through mobile communication, wireless network, Bluetooth, LoRaWAN, NBIot or ZigBee. In another preferred embodiment, a directional antenna can be configured in the transmission module 41, and a rotating platform can be set up thereon to connect in the form of a scanning antenna to enhance its signal receiving capability. However, this is only an example and is not intended to be limiting.

In a preferred embodiment, in order to facilitate the acquisition of the internal parameters of the variable focal length image acquisition device 32, so as to improve the accuracy of the target position information acquisition, and facilitate the control of the emission direction of the laser emitting element 31, it is preferred that the mobile carrier 1 is provided with a rotating platform 3 at one end thereof. This embodiment is described by disposing the rotating platform 3 at the bottom of the mobile carrier 1, but this is not used as a reference. The rotating stage 3 is correspondingly supported by the laser emitting element 31, the target distance sensor 33 and the variable focal length image acquisition device 32; and at least one driving device 34 is coupled to the processing unit 2, and is correspondingly connected to and drives the rotating stage 3, thereby, the processing unit 2 can track the target through the variable focal length image acquisition device 32, and thereby cooperate with the The flight state parameters are calculated and driven by the driving device 34, so that the laser emitting element 31 emits laser light toward the position corresponding to the position information, and the transmission position of the driving device 34 is fed back to the analysis module 4, so that the position and angle information of the variable focal length image capture device 32 and the laser emitting element 31 can be captured, so that the analysis module 4 can accurately obtain the position of the target. Information is used to define control instructions, and it is known that the control instructions may include parameters for controlling the driving device 34, so that the target (i.e., pests) can be locked and tracked according to the pest control environment, and the mobile carrier 1 can be controlled to a better retention position. The driving device 34 controls the angle of the rotating platform 3, so that the laser emitting element 31 can accurately emit lasers toward the position corresponding to the position information.

As for the arrangement of the driving device 34, in one embodiment, it can be arranged in a single or multi-axis direction, so that the rotating stage 3 can be controlled at multiple angles. In a preferred embodiment, the rotating stage 3 can be configured to be capable of rotating in at least two axis directions. Therefore, in one embodiment, as shown in FIG. 4, the driving device 34 can be a motor, and can be arranged in a single or multiple number, so as to be arranged individually or simultaneously at the bottom or side of the rotating stage 3, so as to adjust the angle of the rotating stage 3, so that the angle of the laser emitting element 31 and the variable focal length image capture device 32 can be controlled as described above; however, it is only an example and is not limited thereto.

In terms of the safety considerations of this case, the safety part includes the stability of the mobile vehicle 1 in the flying state and the related harm of the emitted laser to the surrounding organisms; therefore, the present invention takes safety considerations into account, so that when performing pest removal operations, the images of other organisms can be identified to prevent other organisms from entering the flying area of the mobile vehicle 1 or being irradiated by the laser and causing adverse effects. Therefore, in a preferred embodiment, if As shown in FIG. 6 and FIG. 7, based on the above, the variable focal length image capture device 32 can be configured as an image capture device 32', so that it can have or not have the variable focal length function, and further set a camera device 35, which is respectively configured on the mobile vehicle 1 and correspondingly coupled to the processing unit 2; the camera device 35 is used to capture a second image, and the analysis module 4 is built with a security recognition model The safety recognition model is used to recognize at least one safety target, and the safety target can be an image of a human, a beneficial insect or other animal. As mentioned above, the processing unit 2 transmits the second image to the analysis module 4, and the analysis module 4 uses the safety recognition model to recognize whether the second image contains the safety target. When the second image is recognized to contain the safety target, the processing unit 2 can control the mobile vehicle. 1 stays away, or stands by without activating the laser emitting element 31 to emit laser. In one embodiment, a warning device 23 is configured, which is coupled to the processing unit 2. When the second image has the safety target, the processing unit 2 causes the warning device 23 to issue a warning through sound or light, so that the environmental organisms can actively avoid and avoid being affected by the laser, thereby improving the overall safety of the present invention.

It should be particularly noted that, since the camera 35 needs to search for surrounding organisms in a large range, the camera 35 is preferably configured as a wide-angle camera. In an embodiment, the camera 35 can also be used to search for target images in a wide range and a wide angle, so that the analysis module 4 can recognize the target in the second image in advance through the pest recognition model, and then use the image capture device 32' to capture the pest image and assist in positioning and tracking the position. Therefore, the image capture device 32' can be configured as a long-distance camera; In addition, the image can be captured synchronously by the camera 35 and the image capture device 32', and the spatial coordinate information of the target can be obtained by an algorithm (such as binocular ranging method), so that the analysis module 4 can define the control instruction accordingly. In this embodiment, the rotating stage 3 corresponds to the camera 35, the laser emitting element 31, the target distance sensor 33 and the image capture device 32', so as to cooperate with the aforementioned control of the rotating stage 3, so as to facilitate the image capture device 32' to lock and track the target; however, it is only an example and is not limited to it.

In addition, since the laser itself still has a focus, the energy density at the focus is the highest. Therefore, in a preferred embodiment, the focal length value of the laser emitting element 31 is further captured, so that when the pests are removed, the focus of the laser emitting element 31 can be aligned with the pests, thereby reducing the power of the laser emitting element 31. When irradiating the surrounding environment or organisms, the focus is not located at their position, so the harm to the surrounding environment or organisms can be reduced. It can be known that the configuration of the processing unit 2 can be coupled to the flight control module 11, the laser emitting element 31, the image capture device 32' and the flight status sensing unit 12 ; Therefore, the processing unit 2 transmits the image, the focal length value, the distance value and the flight state parameter to the analysis module 4, so that the analysis module 4 can further accurately identify a target and its corresponding position information in the image through the pest recognition model, and can define a control instruction based on the position information, the flight state parameter, the distance value and the focal length value, and return it to the processing unit 2, so that the processing unit 2 controls the flight control module 11 to move the mobile vehicle 1 to the position corresponding to the position information according to the control instruction, so that the focal length of the laser emitted by the laser emitting element 31 corresponds to the position of the position information.

Furthermore, in a specific embodiment, the flight state parameters include at least one of the longitude, latitude, altitude, pitch angle, yaw angle, roll angle, speed and angular velocity of the mobile vehicle 1, so the posture of the variable focus image capture device 32 can be obtained, and the analysis module 4 can perform pre-processing, contour encoding, noise removal, expansion and wrapping of broken blocks, block separation, feature extraction and comparison according to the target identified in the image, and extract the relevant internal parameters of the aforementioned variable focus image capture device 32 to compensate for the posture of the variable focus image capture device 32, and the mobile vehicle 1 can be made to fly to the corresponding position information by defining the control command, and can The driving device 34 is further controlled to drive the rotating stage 3 so that the focus of the laser emitting element 31 can be accurately placed on the pest; preferably, the target identified by the pest identification model in the image is a weak point image of the pest, such as the image of the mouth or its wings. In this embodiment, by placing the focus of the laser emitting element 31 at the weak point of the pest, a laser with lower power or energy can be used. For example, the power of the laser emitted by the laser emitting element 31 can be less than 5W, and the laser spot is about less than 2mm, and the irradiation is performed for about 1 to 2 seconds, so that the pest can be removed or disabled accordingly, and the relevant harm can be caused when the environment or other organisms are accidentally irradiated, and damage to crops can be prevented.

Since there are many types of pests, in order to adjust the laser power according to the types of pests, it is better to further configure a control module 22, which is connected to the processing unit 2 and the laser emitting element 31; the pest recognition model is used to identify the target and its corresponding type information in the image, and the control module 22 recognizes the type information of the target according to the pest recognition model to adjust the power intensity of the laser emitting element 31 through pulse width modulation (PWM), and accordingly control the time and interval of the laser emitted, so that the pests can be removed or disabled more accurately and effectively.

In summary, the technical means disclosed in this invention can effectively solve the problems of knowledge and achieve the expected purpose and effect. It has not been seen in publications before the application, has not been publicly used, and has long-term progress. It is truly an invention as defined in the Patent Law. Therefore, I have filed an application in accordance with the law and sincerely pray that the Supreme Court will give a detailed review and grant the invention patent. I will be very grateful.

However, the above are only several preferred embodiments of the present invention, and should not be used to limit the scope of implementation of the present invention. In other words, all equivalent changes and modifications made according to the scope of the patent application of the present invention and the content of the invention specification should still fall within the scope of the present invention patent.

1: Mobile vehicle

11: Flight control module

12: Flight status sensing unit

2: Processing unit

21: Communication module

22: Control module

23: Warning device

31: Laser emitting element

32’: Image capture device

33: Target distance sensor

34: Drive device

35:Photographic equipment

4:Analysis module

41: Transmission module

5: Remote control device

Claims (9)

A flying unmanned vehicle laser pest control system based on safety considerations comprises: a mobile vehicle, which is equipped with a flight control module, a laser emitting element, an image capturing device, a photographing device, a target distance sensor, a flight state sensing unit and a processing unit; the flight control module is used to control the movement of the mobile vehicle, and the flight state sensing unit is used to sense at least one flight state parameter of the mobile vehicle; the laser emitting element has a focal length value; the processing unit is coupled to the flight control module, the laser emitting element, the image capture device, the photographic device, the target distance sensor and the flight state sensing unit; and an analysis module is connected to the processing unit; and the analysis module is built with a pest recognition model; a control module is connected to the processing unit and the laser emitting element; whereby the image capture device is used to capture an image, and the photographic device is used to capture a second image, the processing unit transmits the image, the second image, the focal length value and the flight state parameter to the analysis module, the analysis module recognizes a target in the image and the second image through the pest recognition model, measures the distance value thereof by the target distance sensor, generates position information accordingly, defines a control instruction according to the position information, the flight state parameter, the distance value and the focal length value, and transmits the control instruction back to the processing unit; The processing unit controls the flight control module to move the mobile vehicle to a position corresponding to the position information according to the control instruction, so that the focal length of the laser emitted by the laser emitting element corresponds to the position of the position information, and the pest identification model is used to identify the target and its corresponding type information in the image. The control module identifies the type information of the target according to the pest identification model to adjust the power intensity of the laser emitting element through pulse width modulation (PWM), and controls the time and interval of the laser emitted accordingly. The flying unmanned vehicle laser pest control system based on safety considerations as described in claim 1 further includes a warning device, which is configured on the mobile vehicle and correspondingly coupled to the processing unit; the analysis module is configured with a safety recognition model, and the safety recognition model is used to recognize at least one safety target. The processing unit transmits the second image to the analysis module, and the analysis module uses the safety recognition model to identify whether the second image contains the safety target. When the second image is identified to contain the safety target, the processing unit causes the warning device to issue a warning. The flying unmanned vehicle laser pest control system based on safety considerations as described in claim 2, wherein the camera device is a wide-angle camera and the image capture device is a long-range camera. A flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim 1 to claim 3, wherein the flight state parameter includes at least one of the longitude, latitude, altitude, pitch angle, yaw angle, roll angle, speed and angular velocity of the mobile vehicle. The flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim items 1 to 3 further includes a rotating platform, which is arranged on the mobile vehicle and correspondingly carries the laser emitting element, the camera device, the target distance sensor and the image capture device; and at least one driving device, which is coupled to the processing unit and correspondingly connects and drives the rotating platform. The processing unit drives the driving device to make the focal length of the laser emitted by the laser emitting element correspond to the position of the position information. The flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim items 1 to 3 further includes a remote control device, which is provided with a transmission module and the analysis module, and the transmission module is connected to the analysis module; and the processing unit is further provided with a communication module, and the communication module is signal-connected to the transmission module to enable the processing unit to connect and transmit signals to the analysis module. A flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim 1 to claim 3, wherein the target identified by the pest recognition model in the image is an image of the mouth of a pest. A flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim items 1 to 3, wherein the power of the laser emitted by the laser emitting element is less than 5W. A flying unmanned vehicle laser pest control system based on safety considerations as described in any one of claim 1 to claim 3, wherein the pest recognition model is obtained by training with a deep neural network (DNN), a deep belief network (DBN), a convolutional neural network (CNN), a region with convolutional neural network (R-CNN), a fast region with convolutional neural network (Faster R-CNN) or a YOLO (You only look once) algorithm.

Images