CN110844074B - Pesticide sprays unmanned aerial vehicle - Google Patents
Pesticide sprays unmanned aerial vehicle Download PDFInfo
- Publication number
- CN110844074B CN110844074B CN201911157993.2A CN201911157993A CN110844074B CN 110844074 B CN110844074 B CN 110844074B CN 201911157993 A CN201911157993 A CN 201911157993A CN 110844074 B CN110844074 B CN 110844074B
- Authority
- CN
- China
- Prior art keywords
- elastic rod
- current frame
- frame image
- elastic
- target
- 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.)
- Active
Links
- 239000000575 pesticide Substances 0.000 title claims abstract description 29
- 239000007921 spray Substances 0.000 title claims description 14
- 239000003814 drug Substances 0.000 claims abstract description 71
- 239000007788 liquid Substances 0.000 claims abstract description 58
- 238000005507 spraying Methods 0.000 claims abstract description 24
- 238000001125 extrusion Methods 0.000 claims description 12
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 239000011550 stock solution Substances 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 description 43
- 238000001514 detection method Methods 0.000 description 28
- 241000607479 Yersinia pestis Species 0.000 description 24
- 238000011176 pooling Methods 0.000 description 24
- 238000013527 convolutional neural network Methods 0.000 description 13
- 230000004927 fusion Effects 0.000 description 10
- 230000005484 gravity Effects 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 238000012706 support-vector machine Methods 0.000 description 8
- 238000009877 rendering Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 230000036316 preload Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D1/00—Dropping, ejecting, releasing, or receiving articles, liquids, or the like, in flight
- B64D1/16—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting
- B64D1/18—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting by spraying, e.g. insecticides
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0025—Mechanical sprayers
- A01M7/0032—Pressure sprayers
- A01M7/0042—Field sprayers, e.g. self-propelled, drawn or tractor-mounted
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/005—Special arrangements or adaptations of the spraying or distributing parts, e.g. adaptations or mounting of the spray booms, mounting of the nozzles, protection shields
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0082—Undercarriages, frames, mountings, couplings, tanks
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Pest Control & Pesticides (AREA)
- Insects & Arthropods (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention discloses a pesticide spraying unmanned aerial vehicle, which belongs to the field of unmanned aerial vehicle spraying and comprises a machine body, a propeller connected with the machine body, a pesticide box and a fixing frame, wherein the pesticide box is a cylinder, the cylinder is horizontally fixed on the machine body along the central axis of the cylinder, the pesticide box comprises a liquid storage cavity for storing liquid medicine, the liquid storage cavity is communicated with a spout pipe, the spout pipe is provided with a horizontal section connected with the liquid storage cavity and a vertical section for spraying liquid downwards, rollers are arranged on two sides of the pesticide box, a fixing sheet is arranged on the side surface of the pesticide box, a channel is arranged in the middle of the fixing sheet, and internal threads are arranged on the side wall of the channel.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle spraying.
Background
The unmanned plane is called as unmanned plane for short, and is a unmanned plane operated by radio remote control equipment and a self-contained program control device. The machine has no cockpit, but is provided with an automatic pilot, a program control device and other devices. Personnel on the ground, ships or on a mother machine remote control station track, position, remote control, telemetere and digital transmission through radar and other equipment. Can take off like a common plane under radio remote control or launch and lift off by using a boosting rocket, and can also be brought into the air by a master machine to put in flight. When recovered, the aircraft can automatically land in the same way as the landing process of a common aircraft, and can also be recovered by a parachute or a barrier net for remote control. Can be repeatedly used for a plurality of times. The method is widely used for air reconnaissance, monitoring, communication, anti-diving, electronic interference and the like.
Some unmanned aerial vehicles are used in the agricultural field now, such as unmanned aerial vehicle sprays pesticide, unmanned aerial vehicle seeding etc. when unmanned aerial vehicle sprays pesticide, because the liquid medicine is along with gravity sprays, and liquid medicine is easy to shake in the medical kit, and because the consumption of liquid medicine, the pressure of liquid medicine in spout department is more and more little for the average volume of beginning spraying is greater than the average volume of later spraying, sprays unevenly
Disclosure of Invention
The invention aims at disclosing a pesticide spraying unmanned aerial vehicle, which comprises a machine body and a propeller connected with the machine body, wherein the unmanned aerial vehicle further comprises:
the medicine box is a cylinder and is horizontally fixed on the machine body along the central axis of the cylinder, the medicine box comprises a liquid storage cavity for storing liquid medicine, the liquid storage cavity is communicated with a nozzle pipe, the nozzle pipe is provided with a horizontal section connected with the liquid storage cavity and a vertical section for spraying liquid downwards, rollers are arranged on two sides of the medicine box, a fixing sheet is arranged on the side face of the medicine box, a channel is arranged in the middle of the fixing sheet, and internal threads are arranged on the side wall of the channel;
the fixing frame comprises a fixing plate, the fixing plate is fixedly connected with an elastic rod assembly, the elastic rod assembly partially stretches into the medicine box, a piston is arranged at the tail end of the elastic rod assembly, a liquid storage cavity is formed by the piston and the side wall of the medicine box, a motor is arranged on the fixing plate, the motor is connected with a screw rod, the screw rod is driven to rotate by the motor, the screw rod is in threaded connection with a channel of the fixing plate, a track is arranged on the fixing frame, and the roller can horizontally move along the track;
the elastic rod assembly comprises a first elastic rod connected with the fixed plate, a third elastic rod connected with the piston and a second elastic rod positioned between the first elastic rod and the third elastic rod, wherein the second elastic rod is provided with a concave part, the first elastic rod is provided with a connecting rod extending into the concave part of the second elastic rod, a fastening piece is arranged on the connecting rod, a spring is arranged between the second elastic rod and the first elastic rod, the fastening piece is fastened on the connecting rod so that the spring is in a compression state, when the extrusion force of the first elastic rod on the second elastic rod is smaller than the compression force of elastic preloading, the first elastic rod and the second elastic rod are fixed, and when the extrusion force of the first elastic rod on the second elastic rod is larger than the compression force of elastic preloading, the first elastic rod is far away from the second elastic rod so that the elastic rod assembly is elastic;
the piston on be equipped with the pressure sensor of response stock solution chamber pressure, pressure sensor is connected with the controller, the controller is connected with the motor to can control the motor, when pressure sensor induced stock solution chamber pressure chamber is less, the motor control motor, the motor drive screw rod rotates, the screw rod rotates and is close to the fixed plate through control stationary blade with the drive medical kit and remove, so that piston extrusion liquid medicine, with the pressure of increase liquid medicine, make the pressure of liquid medicine keep at stable level, further make spray more evenly.
As an improvement, the rail is provided with an upper rail and a lower rail, and the roller is positioned between the upper rail and the lower rail.
As an improvement, the elastic rod component is sleeved with a limiting block (5), the limiting block is fixedly connected with the medicine box, and when the medicine box approaches to the fixed plate to reach the limit, the limiting block can limit the medicine box to move towards the fixed plate continuously.
As an improvement, two fixing sheets are connected to the medicine chest, the fixing sheets protrude out of the outer side surface of the medicine chest, two screws are correspondingly connected to the two fixing sheets, and two motors are correspondingly connected to the two screws.
As an improvement, a stop rod is arranged at the bottom of the fixing frame, and the stop rod is contacted with the ground when the unmanned aerial vehicle stops.
As an improvement, the machine body is uniformly connected with four propellers.
As an improvement, the medicine chest is provided with a liquid adding port, and the liquid adding port can add medicine liquid into the medicine chest and can be closed.
Drawings
FIG. 1 is a schematic view of the overall structure of the present invention;
FIG. 2 is a schematic diagram of another side view;
FIG. 3 is a cross-sectional view of the medicine chest;
FIG. 4 is a cross-sectional view of another state of the medicine box;
FIG. 5 is a cross-sectional view of the elastomeric lever assembly
The marks in the figure: 1-organism, 2-screw, 3-medical kit, 31-gyro wheel, 32-spout pipe, 33-stationary blade, 4-mount, 41-track, 42-fixed plate, 43-elastic rod subassembly, 431-first elastic rod, 432-second elastic rod, 433-concave part, 434-connecting rod, 435-fastener, 436-spring, 437-third elastic rod, 44-piston, 45-motor, 46-screw rod, 5-stopper.
Detailed Description
Example 1:
the present invention will be described in detail with reference to the accompanying drawings.
The embodiment discloses pesticide sprays unmanned aerial vehicle, including organism 1, the screw 2 of being connected with organism 1, the organism on be equipped with controlling means etc. control unmanned aerial vehicle operation, screw 2 is rotatory in order to provide flight power for unmanned aerial vehicle. The traditional unmanned aerial vehicle's organism is connected with the medical kit, is equipped with the liquid medicine in the medical kit, and the medical kit bottom is equipped with the spout, and the liquid medicine spouts in the spout owing to gravity or the effect of pump, and under the effect of gravity, the liquid medicine rocks easily to along with the consumption of liquid medicine, the thinner and thinner that sprays, the inhomogeneous that sprays around, if use the pump, make unmanned aerial vehicle's weight bigger on the one hand, consume more electricity, simultaneously, the pump is plugged up easily when spraying.
The machine body is connected with the medicine box 3, the medicine box is a cylinder, as shown in fig. 1 and 2, the cylinder is horizontally fixed on the machine body along the central axis of the cylinder, as shown in fig. 3 and 4, the medicine box comprises a liquid storage cavity 30 for storing liquid medicine, the liquid storage cavity is communicated with a spout pipe 32, as shown in fig. 3, the spout pipe is provided with a horizontal section connected with the liquid storage cavity and a vertical section for spraying liquid downwards, the horizontal section is communicated with the liquid storage cavity, the vertical section is used for spraying liquid, and the vertical section is provided with a plurality of parts capable of spraying liquid, which are of the prior art and are not repeated.
As shown in fig. 3, the rollers 31 are disposed on two sides of the medicine chest, the fixing plates 33 are disposed on two sides of the medicine chest, a channel is disposed in the middle of the fixing plates, internal threads are disposed on the side walls of the channel, in a preferred scheme of a further step, two fixing plates are connected to the medicine chest, the fixing plates protrude from the outer side of the medicine chest, and the fixing plates are symmetrically distributed relative to the central axis of the medicine chest, and of course, a fixing plate can be disposed, so that the stress of the medicine chest is more uniform due to the two fixing plates.
The machine body is also connected with a fixing frame 4, the fixing frame comprises a fixing plate 42, the fixing plate is fixedly connected with an elastic rod assembly 43, part of the elastic rod assembly extends into the medicine box, the tail end of the elastic rod assembly is provided with a piston 44, the piston and the side wall of the medicine box form a liquid storage cavity 30, the fixing plate is provided with a motor 45, the motor is connected with a screw 46, the screw is driven to rotate by the motor, the screw 46 is in threaded connection with a channel of a fixing sheet, the fixing frame is provided with a track 41, and the roller can horizontally move along the track;
the elastic rod assembly comprises a first elastic rod 431 connected with the fixed plate, a third elastic rod 437 connected with the piston, and a second elastic rod positioned between the first elastic rod and the third elastic rod, wherein the second elastic rod is provided with a concave part 433, the first elastic rod is provided with a connecting rod 434 extending into the concave part of the second elastic rod, the connecting rod is provided with a fastening piece 435, a spring 436 is arranged between the second elastic rod and the first elastic rod, the fastening piece is fastened on the connecting rod so as to enable the spring to be in a compressed state, when the extrusion force of the first elastic rod to the second elastic rod is smaller than the compression force of elastic preload, the first elastic rod and the second elastic rod are fixed, and when the extrusion force of the first elastic rod to the second elastic rod is larger than the compression force of elastic preload, the first elastic rod is far away from the second elastic rod so that the elastic rod assembly is elastic;
the piston on be equipped with the pressure sensor of response stock solution chamber pressure, pressure sensor is connected with the controller, the controller is connected with the motor to can control the motor, when pressure sensor induced stock solution chamber pressure chamber is less, the controller control motor, motor drive screw 46 rotates, the screw rod rotates and is close to the fixed plate through control stationary blade with the drive medical kit and remove, so that the piston extrudes the liquid medicine, with the pressure of increase liquid medicine, makes the pressure of liquid medicine keep at stable level, further makes spraying more even.
The track is provided with an upper track and a lower track, and the roller is positioned between the upper track and the lower track. The elastic rod assembly is sleeved with a limiting block 5, the limiting block is fixedly connected with the medicine box, and when the medicine box approaches to the fixed plate to reach the limit, the limiting block can limit the medicine box to continue to move towards the fixed plate.
Two screws are correspondingly connected with the two fixing sheets, and two motors are correspondingly connected with the two screws. The bottom of the fixing frame is provided with a stop rod, and the stop rod is contacted with the ground when the unmanned aerial vehicle stops. The machine body is uniformly connected with four propellers 2. The medicine box is provided with a liquid adding port 34, and the liquid adding port can add liquid medicine into the medicine box and can be closed.
Example 2: the embodiment discloses a pest detection method, wherein the unmanned aerial vehicle determines pest distribution conditions according to the pest detection method when spraying pesticides, and comprises a pest detection system, and the following method is executed when the pest detection system realizes the functions:
obtaining a video of an area to be detected, wherein the video is obtained through a camera according to an inorganic person;
acquiring a residual region based on a previous frame image and a next frame image of a current frame image in the pest video;
fusing the residual error area with the current frame image to obtain a fused current frame image;
performing high-pass filtering on the fused current frame image to obtain a high-frequency current frame image;
performing low-pass filtering on the fused current frame image to obtain a low-frequency current frame image;
fusing the high-frequency current frame image and the low-frequency frame image to obtain a composite current frame image;
performing target detection on the current frame image based on a first convolutional neural network to obtain a current frame target region;
performing target detection on the composite current frame image based on a second convolutional neural network to obtain a composite target region;
obtaining the distance between the current frame target area and the composite target area;
and if the distance is smaller than a set threshold value, acquiring a target to be detected based on the current frame target area and the composite target area.
The unmanned aerial vehicle determines pest distribution conditions according to the pest detection method when spraying pesticides, and sprays pesticides on the pest area.
Wherein, based on the previous frame image and the next frame image of the current frame image in the pest video, the step of obtaining the residual region specifically comprises: and obtaining a front pixel point of the previous frame image and a rear pixel point corresponding to the front pixel point in the next frame image. And obtaining first difference information between the front pixel point and the rear pixel point through absolute difference sum operation based on the front block and the rear block corresponding to the front pixel point. The front block is a block in the previous frame image, and the rear block is a region in the next frame image. The front block includes a plurality of pixel points. When the previous block corresponding to the pixel point is a rectangular block with the previous pixel point as the center and the size is set, for example, the current block is a rectangular block of a 2x2 block. If the position of the front pixel is at the edge of the current frame image, the front block takes the current pixel as the center to obtain a plurality of pixels adjacent to the pixel, and a determined block formed by the pixels is the current block. For example, the front pixel is (0, 0), and the front block is a block composed of (0, 0), (0, 1), (1, 0), and (1, 1). For each pixel point in the front block, obtaining a difference value between the value of each pixel point and the value of the pixel point corresponding to the position of each pixel point in the rear block; and carrying out summation operation on the absolute values of the differences to obtain first difference information, wherein the plurality of front pixel points correspond to the plurality of first difference information, and the plurality of first difference information form a residual block according to the corresponding relation with the front pixel points. Wherein, each pixel point in each front block corresponds to a difference value, and specifically, the absolute value of each difference value is summed. In order to obtain a rear block corresponding to a front block position in a front frame image, in a rear frame image, a rear block corresponding to the front block position is obtained, and each pixel point in the current block corresponds to each pixel point in the rear block in a one-to-one position. The position correspondence refers to one-to-one correspondence between positions, for example, the position of the front pixel is the same as the position of the rear pixel, which is specifically shown that the value of the position of the front pixel is the same as the value of the position of the rear pixel, for example, if the value of the position of the front pixel is (1, 2) and the value of the position of the rear pixel is (1, 2), the front pixel corresponds to the rear pixel. Thus, the front block and the rear block are identical in size. Specifically, the first difference information is obtained by the following formula (1).
Wherein a (i, j) represents the value of a pixel (i, j) in the front block corresponding to the front pixel (m, n), b (i, j) represents the value of a pixel corresponding to the position of the pixel (i, j) in the rear block, k represents the number of pixels in the horizontal axis direction of the front block, and s1 (m, n) represents the first difference information. The value of each pixel point in the front block corresponding to the front pixel point is subtracted from the value of each pixel point in the rear block corresponding to the front pixel point, the absolute value of the obtained difference value is obtained, the absolute values corresponding to the pixel points are summed to obtain first difference value information, and the obtained residual block can accurately represent the difference of the front frame image relative to the rear frame image.
The residual error area is fused with the current frame image to obtain a fused current frame image, specifically:
first, a sum of pixel values of pixel points (i, j) in a residual region and pixel values of pixel points (i, j+k) in the current frame image is obtained, wherein i, j is a positive integer and k is an integer greater than or equal to 0. Then, if the sum is greater than 255, fusing the pixel value of the pixel point (i, j) of the current frame image as a first difference value, wherein the first difference value is the difference value between 255 and the remainder of the quotient of the sum and 255. For example, if the sum of the pixel value of the pixel point (i, j) in the residual region and the pixel value of the pixel point (i, j+k) in the current frame image is Y, Y >255, and the remainder of Y/255 is X, the first difference value is equal to 255-X. If the sum is not more than 255, fusing the pixel value of the pixel point (i, j) of the current frame image to be the sum. I.e. the pixel value of the pixel point (i, j) fused with the current frame image is Y. By adopting the scheme, the characteristics that the pixel value of the current frame image is fused with the residual region and the pixel value of the pixel point of the current frame image are fused, the feature of the fused current frame image is enhanced, the fidelity of the fused current frame image is ensured, and a foundation is laid for improving the accuracy of target detection.
The method comprises the steps of fusing a high-frequency current frame image and a low-frequency frame image to obtain a composite current frame image, wherein the method specifically comprises the following steps of: obtaining the average value of the pixel point (i, j) in the high-frequency current frame image and the pixel point (i, j) in the low-frequency current frame image; the average value is determined as the pixel value of the pixel point (i, j) of the composite current frame image. The accuracy of the characteristics of the composite current frame image is improved.
As an optional implementation manner, the step of fusing the high-frequency current frame image and the low-frequency frame image to obtain the composite current frame image specifically includes: if the pixel value of the pixel point (i, j) in the high-frequency current frame image is equal to the pixel value of the pixel point (i, j) in the low-frequency current frame image and the pixel value of the pixel point is a first value, assigning the pixel value of the pixel point (i, j) of the composite current frame image to a second value; if the pixel value of the pixel point (i, j) in the high-frequency current frame image is the same as the pixel value of the pixel point (i, j) in the low-frequency current frame image and the pixel value of the pixel point is not the first value, expanding the pixel point (i, j) of the composite current frame image so that the pixel point (i, j) comprises a fusion channel; and assigning the fusion channel to enable the value of the fusion channel to be a second value, wherein the second value is different from the pixel value of the pixel point and the first value. By adopting the scheme, the obtained composite current frame image comprises the pixel information in the high-frequency current frame image and the pixel information in the low-frequency current frame image, so that the characteristics of the composite current frame image are enhanced, and the accuracy of a detected target is improved.
In the embodiment of the invention, the step of performing target detection on the current frame image based on the first convolutional neural network to obtain the target region of the current frame comprises the following specific steps: at least one convolution treatment is carried out on the current frame image to obtain first output data; carrying out pooling treatment on the first output data twice to obtain second output data; carrying out convolution processing on the second output data at least twice to obtain third output data; carrying out pooling treatment on the third output data at least three times to obtain fourth output data; and classifying the fourth output data to obtain the current target area.
Optionally, the first convolutional neural network comprises at least four convolutional layers, at least five pooling layers, and one classification layer. The structure of the first convolutional neural network may be a convolutional layer, a pooling layer, a convolutional layer, a pooling layer, a classification layer. The first convolutional neural network may also be structured as a convolutional layer a convolution layer, a pooling layer convolution layer, pooling layer, classification layer. Wherein the classification layer may be a support vector machine model. And the pooling layer connected with the classifying layer outputs an image feature vector, and the classifying layer classifies and identifies the image feature vector to obtain a target area of the current frame.
By adopting the scheme, the convolution kernel pooling operation is carried out on the current frame image, and finally the classification layer classifies and identifies the image feature vector to obtain the current frame target area, so that the accuracy of identifying and detecting the current frame target area is improved.
Optionally, target detection is performed on the composite current frame image based on the second convolutional neural network, so as to obtain a composite target area, which specifically includes: carrying out pooling treatment on the composite current frame image for at least three times to obtain fifth output data; carrying out convolution processing on the fifth output data at least twice to obtain sixth output data; carrying out pooling treatment and one-time convolution treatment on the sixth output data to obtain seventh output data; fusing the sixth output data and the seventh output data to obtain eighth output data; carrying out pooling treatment and convolution treatment on the eighth output data at least twice to obtain ninth output data; and classifying the ninth output data to obtain a composite target area.
The second convolutional neural network at least comprises six pooling layers, at least five convolutional layers, a fusion layer and a classification layer. Optionally, the method comprises the steps of. The structure of the second convolutional neural network may be a pooling layer, a convolutional layer, a pooling layer, a convolutional layer, a fusion layer, a pooling layer, a convolutional layer, a classification layer. The structure of the second convolutional neural network can be a pooling layer, a pooling layer, convolution layer a pooling layer, a convolution layer, a fusion layer, a pooling layer pooling layer, convolution layer, classification layer. The classification layer may be a support vector machine model as described above. The fusion layer is used for respectively carrying out merging processing on the output of the neurons of the convolution layer connected with the fusion layer, the merging mode can be weighted accumulation or OR operation, and the like, so as to obtain a merging processing result, and then the merging processing result is output to the pooling layer for pooling processing. And outputting the region vector by the final convolution layer, and classifying the region vector by a classification layer to obtain the composite target region.
By adopting the scheme, the multi-length convolution kernel pooling operation is carried out on the composite current frame image, the final convolution layer outputs the region vector, the region vector is classified by the classification layer, the target region is obtained, and the accuracy of identifying and detecting the composite target region is improved.
Optionally, the specific implementation manner of obtaining the distance between the target area of the current frame and the composite target area is as follows:
obtaining a circumcircle of a target area of the current frame and a compound target area; obtaining the Euclidean distance between the circle center of the circumscribed circle of the target area of the current frame and the circle center of the circumscribed circle of the composite target area; and determining the Euclidean distance as the distance between the target area of the current frame and the composite target area. The distance between the current frame target area and the composite target area is specifically: respectively obtaining the gravity centers of a current frame target area and a composite target area; obtaining Euclidean distance between the gravity center of the target area of the current frame and the gravity center of the composite target area; and determining the Euclidean distance as the distance between the target area of the current frame and the composite target area.
The specific implementation manner of obtaining the target to be detected based on the current frame target area and the composite target area may be: obtaining a crossing area of a current frame target area and a composite target area; and determining the crossing area as an object to be detected. Thus, the accuracy of the target to be detected is improved.
In order to further improve the accuracy of the target to be detected, the pest image target detection method further includes, before determining the crossing area as the target to be detected: rendering the intersection region. The rendering method can be to perform color rendering according to pathological features and color features of the checked part, for example, if the target is lung of the pest image, the object to be detected after rendering is a colorful lung image. If the target is the head of the pest image, the target to be detected after rendering is a head skeleton image and the like.
In order to improve the accuracy of rendering and further improve the accuracy of target detection, before rendering the intersection area, the pest image target detection method further comprises the following steps: and performing expansion treatment on the crossing area so that the size of the crossing area is close to the size of the object to be measured. And the intersection area is expanded, so that the size of the intersection area is close to the size of the target to be detected, the definition of the rendered intersection area is improved, and the accuracy of target detection is improved.
In the embodiment of the present invention, the target value may be a preset value based on experience, for example, 0.2. In order to further improve the accuracy of target detection, the target value is obtained by: obtaining a first target vector based on a current frame target area; obtaining a second target vector based on the composite target region; classifying the first target vector based on the trained support vector machine model to obtain a first target value; classifying the second target vector based on the trained support vector machine model to obtain a second target value; and obtaining a difference between the first target value and the second target value to obtain a target difference value, and taking the target difference value as a target value. The second target value may be 0.3.
As an alternative embodiment, a pest image target detection method includes: and obtaining pest videos of the region to be detected, which is scanned by the pest scanner. And obtaining a residual region based on a previous frame image and a next frame image of the current frame image in the pest video. And fusing the residual error area with the current frame image to obtain a fused current frame image. And carrying out high-pass filtering on the fused current frame image to obtain a high-frequency current frame image. And carrying out low-pass filtering on the fused current frame image to obtain a low-frequency current frame image. And fusing the high-frequency current frame image and the low-frequency frame image to obtain a composite current frame image. And performing target detection on the current frame image based on the first convolutional neural network to obtain a current frame target region. A first target vector is obtained based on the current frame target region. And performing target detection on the composite current frame image based on the second convolutional neural network to obtain a composite target region. A second target vector is obtained based on the composite target region. Classifying the first target vector based on the trained support vector machine model to obtain a first target value; classifying the second target vector based on the trained support vector machine model to obtain a second target value; and obtaining a difference between the first target value and the second target value to obtain a target difference value, and taking the target difference value as a target value. And obtaining the distance between the target area of the current frame and the composite target area. And if the distance is smaller than the target value, acquiring a pest image to be detected based on the target area of the current frame and the composite target area.
By adopting the scheme, the residual region is obtained based on the previous frame image and the next frame image of the current frame image in the video, and the residual region is fused with the current frame image to obtain the fused current frame image, so that the characteristic information of the current frame image is enhanced. The high-frequency current frame image is obtained by carrying out high-pass filtering on the fusion current frame image, the high-frequency current frame image keeps the high-frequency characteristic information of the current frame image, the fusion current frame image is subjected to low-pass filtering to obtain the low-frequency current frame image, the low-frequency current frame image keeps the low-frequency characteristic information of the current frame image, the high-frequency current frame image and the low-frequency frame image are fused to obtain the composite current frame image, the characteristic information in the composite current frame image is enhanced, and meanwhile, the fidelity of the characteristic information is improved. Performing target detection on the current frame image based on the first convolutional neural network to obtain a current frame target region; and performing target detection on the composite current frame image based on the second convolution neural network to obtain a composite target area, so that the probability of the target in the conforming target area is further improved, and the accuracy of target detection is improved. Obtaining a first target vector based on a target area of a current frame, obtaining a second target vector based on a composite target area, and classifying the first target vector based on a trained support vector machine model to obtain a first target value; classifying the second target vector based on the trained support vector machine model to obtain a second target value; and obtaining a difference between the first target value and the second target value to obtain a target difference value, and taking the target difference value as a target value. And if the distance is smaller than the target value, acquiring a target to be detected based on the target area of the current frame and the composite target area, combining the target detection result of the traditional neural network and the target detection result of the second neural network with high accuracy, thereby improving the accuracy of target detection and the accuracy of the target to be detected. Meanwhile, the target value is obtained based on the target area of the previous frame and the composite target area, and the target value is used as a judging standard, so that the accuracy of target detection can be improved.
The invention has the beneficial effects that:
1. the medicine chest is horizontally arranged, the liquid medicine is not changed in the horizontal height in the process of consumption, so that the influence of the height change on the pressure at the nozzle is avoided, the spraying uniformity is further influenced, meanwhile, in order to reduce the influence of the consumption of the liquid medicine on the gravity center, the pressure at the piston is reduced along with the consumption of the liquid medicine, the pressure sensor transmits a pressure signal to the controller, the controller controls the motor to drive the screw rod to rotate, the screw rod pulls the fixing piece and then pulls the medicine chest to move towards the direction of the fixing plate, the piston can not move the medicine chest to reduce the change distance of the gravity center as much as possible, and the stability of the unmanned aerial vehicle is improved;
2. according to the invention, the pressure in the liquid medicine can be maintained at a stable level in a mode of extruding the liquid medicine by the piston, so that the spraying is more uniform;
3. the elastic rod assembly has the functions of rigidity and elasticity, when the extrusion force applied to the elastic rod assembly is small, the first elastic rod and the second elastic rod cannot move, the whole elastic rod is kept in a rigid state, a sufficient extrusion piston is provided, when the extrusion force applied to the elastic rod assembly is large, the first elastic rod and the second elastic rod can move relatively, the length of the elastic rod assembly is reduced, the extrusion of the elastic assembly to the piston is reduced, and the pressure of a liquid storage cavity is prevented from being greatly changed, so that the pressure is kept at a stable level.
4. The pest detection system and the pest detection method can realize accurate detection of pests, acquire the distribution situation of the pests, spray the pesticides according to the distribution situation of the pests, save the pesticides and prevent the damage to the environment.
Claims (7)
1. Pesticide sprays unmanned aerial vehicle, including organism (1), screw (2) be connected with organism (1), its characterized in that, unmanned aerial vehicle still include:
the medicine box (3) is a cylinder, the cylinder is horizontally fixed on the machine body (1) along the central axis of the cylinder, the medicine box (3) comprises a liquid storage cavity (30) for storing liquid medicine, the liquid storage cavity is communicated with a nozzle pipe (32), the nozzle pipe is provided with a horizontal section connected with the liquid storage cavity and a vertical section for spraying liquid downwards, rollers (31) are arranged on two sides of the medicine box, a fixing sheet (33) is arranged on the side face of the medicine box, a channel is arranged in the middle of the fixing sheet, and internal threads are arranged on the side wall of the channel;
the fixing frame (4) comprises a fixing plate (42), the fixing plate is fixedly connected with an elastic rod assembly (43), the elastic rod assembly partially stretches into the medicine box, a piston (44) is arranged at the tail end of the elastic rod assembly, a liquid storage cavity (30) is formed by the piston and the side wall of the medicine box, a motor (45) is arranged on the fixing plate, the motor is connected with a screw rod (46), the screw rod is driven to rotate by the motor, the screw rod (46) is in threaded connection with a channel of the fixing piece, a track (41) is arranged on the fixing frame, and the roller can horizontally move along the track;
the elastic rod assembly comprises a first elastic rod (431) connected with the fixing plate, a third elastic rod (437) connected with the piston, and a second elastic rod positioned between the first elastic rod and the third elastic rod, wherein the second elastic rod is provided with a concave part (433), the first elastic rod is provided with a connecting rod (434) extending into the concave part of the second elastic rod, a fastening piece (435) is arranged on the connecting rod, a spring (436) is arranged between the second elastic rod and the first elastic rod, the fastening piece is fastened on the connecting rod so that the spring is in a compression state, when the extrusion force of the first elastic rod to the second elastic rod is smaller than the compression force of elastic preloading, the first elastic rod and the second elastic rod are fixed, and when the extrusion force of the first elastic rod to the second elastic rod is larger than the compression force of elastic preloading, the first elastic rod is far away from the second elastic rod so that the elastic rod assembly is elastic enough;
the piston on be equipped with the pressure sensor of response stock solution chamber pressure, pressure sensor is connected with the controller, the controller is connected with the motor to can control the motor, when pressure sensor induced stock solution chamber pressure chamber is less, the controller control motor, motor drive screw rod (46) rotates, the screw rod rotates and is close to the fixed plate through control stationary blade with the drive medical kit and remove, so that piston extrusion liquid medicine, with the pressure of increase liquid medicine, make the pressure of liquid medicine keep at stable level, further make spray more even.
2. The pesticide spraying unmanned aerial vehicle of claim 1, wherein the rail is provided with an upper rail and a lower rail, and the roller is positioned between the upper rail and the lower rail.
3. The unmanned pesticide spraying machine according to claim 2, wherein the elastic rod assembly is sleeved with a limiting block (5), the limiting block is fixedly connected with the pesticide box, and when the pesticide box approaches the fixed plate to the limit, the limiting block can limit the pesticide box to move towards the fixed plate continuously.
4. A pesticide spraying unmanned aerial vehicle according to claim 3, wherein the pesticide box is connected with two fixing plates, the fixing plates protrude from the outer side surface of the pesticide box, two screws are correspondingly connected with the two fixing plates, and two motors are correspondingly connected with the two screws.
5. The unmanned pesticide spraying system of claim 4, wherein a stop bar is arranged at the bottom of the fixed frame, and the stop bar contacts the ground when the unmanned aerial vehicle stops.
6. The unmanned pesticide spraying machine according to claim 5, wherein the machine body is uniformly connected with four propellers (2).
7. The pesticide spraying unmanned aerial vehicle of claim 6, wherein the medicine box is provided with a liquid filling port (34), and the liquid filling port can be used for adding liquid medicine into the medicine box and can be closed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157993.2A CN110844074B (en) | 2019-11-22 | 2019-11-22 | Pesticide sprays unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157993.2A CN110844074B (en) | 2019-11-22 | 2019-11-22 | Pesticide sprays unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110844074A CN110844074A (en) | 2020-02-28 |
| CN110844074B true CN110844074B (en) | 2023-04-28 |
Family
ID=69603778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911157993.2A Active CN110844074B (en) | 2019-11-22 | 2019-11-22 | Pesticide sprays unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110844074B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132480A (en) * | 2020-09-29 | 2020-12-25 | 姜锡忠 | Master and resource matching method and system for big data online education platform |
| CN114375846B (en) * | 2022-01-19 | 2023-03-24 | 安徽农业大学 | Goose is bred house and is used ammonia deodorization system that falls |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0094231A1 (en) * | 1982-05-08 | 1983-11-16 | E.J. Price (Developments) Limited | Nebulizers |
| FR2586194A1 (en) * | 1985-08-13 | 1987-02-20 | Lejosne Alain | Helicopter-borne firefighting methods and devices and helicopters equipped with these devices |
| EP0269880A1 (en) * | 1986-11-20 | 1988-06-08 | ACCORD Landmaschinen Heinrich Weiste & Co. GmbH | Fertiliser spreader comprising booms and lifting device |
| JPH08163946A (en) * | 1994-12-14 | 1996-06-25 | Yamaha Motor Co Ltd | Apparatus for spraying chemical by unmanned helicopter |
| JPH09206395A (en) * | 1996-02-05 | 1997-08-12 | Masanori Fujisaki | Monitor stand |
| KR20040105660A (en) * | 2004-11-22 | 2004-12-16 | 주식회사 백등원 | A movable sprayer |
| CN204070258U (en) * | 2014-07-08 | 2015-01-07 | 西北农林科技大学 | A kind of sensor and bellows adjustable sprayer |
| CN207191440U (en) * | 2017-09-20 | 2018-04-06 | 江门市植保科技有限公司 | A kind of plant protection unmanned plane medicine-chest fixed structure |
| CN107980753A (en) * | 2017-12-10 | 2018-05-04 | 张红彬 | A kind of intelligence unmanned plane pesticide spraying device |
| CN207595267U (en) * | 2017-10-20 | 2018-07-10 | 胡沛剑 | A kind of unmanned plane is sprayed insecticide equipment |
| JP6565005B1 (en) * | 2018-04-08 | 2019-08-28 | 广州克力労保用品有限公司 | Medicine machine |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4746065A (en) * | 1983-10-17 | 1988-05-24 | Gorder Norman S | Crop sprayer |
| FR2649294B1 (en) * | 1989-07-10 | 1991-10-11 | Bobard Jeune Sa Ets | IMPROVEMENTS ON SPRAYING RAMPS FOR LINE CROPS |
| DE102005036046A1 (en) * | 2005-08-01 | 2007-02-08 | Gloria Haus- und Gartengeräte GmbH | Cartridge system for adding concentrate directly into diluent liquid, e.g. horticultural or cleaning chemical compositions into hosepipe spray-gun attachment |
| CA2795118A1 (en) * | 2012-11-02 | 2014-05-02 | Rick Solomon | Method for mixing fire fighting gel in situ within a water tank of a fire fighting aircraft, and a fire fighting aircraft modified in accordance with the teachings of the method |
| US10478841B2 (en) * | 2016-04-06 | 2019-11-19 | Harris Aerial Llc | Modular sprayer system for heavy-lift unmanned aerial vehicles |
| US10172274B2 (en) * | 2017-05-26 | 2019-01-08 | Deere & Company | Autonomous or remote-controlled vehicle platform for spraying |
| CN107792366A (en) * | 2017-12-12 | 2018-03-13 | 南京市雨花台区创新创业法治宣传与法律服务中心 | A kind of agricultural plant protection unmanned plane that can improve pesticide spraying precision |
| CN109050927A (en) * | 2018-08-13 | 2018-12-21 | 江苏森宝包装有限公司 | A kind of plant protection drone for agricultural production |
| CN209572947U (en) * | 2019-01-29 | 2019-11-05 | 河南泽达智能科技有限公司 | A kind of plant protection drone is anti-to swing cabinet |
| CN109733608A (en) * | 2019-03-12 | 2019-05-10 | 四川极云智飞科技有限公司 | A kind of unmanned plane sprinkling system and unmanned plane |
-
2019
- 2019-11-22 CN CN201911157993.2A patent/CN110844074B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0094231A1 (en) * | 1982-05-08 | 1983-11-16 | E.J. Price (Developments) Limited | Nebulizers |
| FR2586194A1 (en) * | 1985-08-13 | 1987-02-20 | Lejosne Alain | Helicopter-borne firefighting methods and devices and helicopters equipped with these devices |
| EP0269880A1 (en) * | 1986-11-20 | 1988-06-08 | ACCORD Landmaschinen Heinrich Weiste & Co. GmbH | Fertiliser spreader comprising booms and lifting device |
| JPH08163946A (en) * | 1994-12-14 | 1996-06-25 | Yamaha Motor Co Ltd | Apparatus for spraying chemical by unmanned helicopter |
| JPH09206395A (en) * | 1996-02-05 | 1997-08-12 | Masanori Fujisaki | Monitor stand |
| KR20040105660A (en) * | 2004-11-22 | 2004-12-16 | 주식회사 백등원 | A movable sprayer |
| CN204070258U (en) * | 2014-07-08 | 2015-01-07 | 西北农林科技大学 | A kind of sensor and bellows adjustable sprayer |
| CN207191440U (en) * | 2017-09-20 | 2018-04-06 | 江门市植保科技有限公司 | A kind of plant protection unmanned plane medicine-chest fixed structure |
| CN207595267U (en) * | 2017-10-20 | 2018-07-10 | 胡沛剑 | A kind of unmanned plane is sprayed insecticide equipment |
| CN107980753A (en) * | 2017-12-10 | 2018-05-04 | 张红彬 | A kind of intelligence unmanned plane pesticide spraying device |
| JP6565005B1 (en) * | 2018-04-08 | 2019-08-28 | 广州克力労保用品有限公司 | Medicine machine |
Non-Patent Citations (2)
| Title |
|---|
| 付大平 ; 田耘 ; .我国植保机械的发展状况与前景分析.农业与技术.2012,(第11期),全文. * |
| 宋灿灿 ; 周志艳 ; 罗锡文 ; 姜锐 ; 兰玉彬 ; 张海艳 ; .农业物料撒播技术在无人直升机中应用的思考.农机化研究.2018,(09),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110844074A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110844074B (en) | Pesticide sprays unmanned aerial vehicle | |
| US11748898B2 (en) | Methods and system for infrared tracking | |
| CN105197252B (en) | A kind of SUAV landing method and system | |
| JP6391694B2 (en) | Video encoding method and system | |
| CN104504748B (en) | A kind of infrared 3-D imaging system of unmanned plane oblique photograph and modeling method | |
| CN108171787A (en) | A kind of three-dimensional rebuilding method based on the detection of ORB features | |
| WO2021221758A3 (en) | Performing 3d reconstruction via an unmanned aerial vehicle | |
| CN106289186B (en) | The airborne visual detection of rotor wing unmanned aerial vehicle and multi-target positioning system and implementation method | |
| WO2016023224A1 (en) | System and method for automatic sensor calibration | |
| CN108605098A (en) | system and method for rolling shutter correction | |
| Kim et al. | A vision-based target tracking control system of a quadrotor by using a tablet computer | |
| JP2017529710A (en) | How to evaluate the search area | |
| CN106530239B (en) | The mobile target low altitude tracking method of miniature self-service gyroplane based on the bionical flake of big visual field | |
| CN109118534B (en) | Method for acquiring icing type detailed information on surface of model in icing wind tunnel in real time | |
| CN114038193B (en) | Intelligent traffic flow data statistics method and system based on unmanned aerial vehicle and multi-target tracking | |
| CN111079546B (en) | Unmanned aerial vehicle pest detection method | |
| CN111027415A (en) | Vehicle detection method based on polarization image | |
| CN113406975A (en) | Bionic intelligent multi-unmanned aerial vehicle cluster autonomous formation navigation control method and device | |
| US10721404B1 (en) | Configuring imaging devices based on control signals | |
| CN115291536B (en) | Visual unmanned aerial vehicle tracking ground target semi-physical simulation platform verification method | |
| WO2018095490A1 (en) | Method and device for generating a view around a vehicle for a vehicle | |
| CN114415695A (en) | Tea garden inspection system based on vision technology and inspection robot | |
| CN109709975B (en) | Four-rotor aircraft indoor security system and method based on visual SLAM | |
| CN112308900B (en) | Four-rotor unmanned aerial vehicle relative pose estimation method based on LED (light emitting diode) ring detection | |
| CN115840459B (en) | Monocular vision obstacle avoidance system for ornithopter |
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 |