CN112862054B - Real-time pest detecting and counting system - Google Patents
Real-time pest detecting and counting system Download PDFInfo
- Publication number
- CN112862054B CN112862054B CN202110221101.1A CN202110221101A CN112862054B CN 112862054 B CN112862054 B CN 112862054B CN 202110221101 A CN202110221101 A CN 202110221101A CN 112862054 B CN112862054 B CN 112862054B
- Authority
- CN
- China
- Prior art keywords
- pest
- image
- real
- collector
- detection
- 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
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 245
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 238000011897 real-time detection Methods 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000012806 monitoring device Methods 0.000 claims abstract description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 17
- 229910052710 silicon Inorganic materials 0.000 claims description 17
- 239000010703 silicon Substances 0.000 claims description 17
- 238000013480 data collection Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000007726 management method Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 230000007306 turnover Effects 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 3
- 238000003491 array Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 13
- 238000007689 inspection Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 241000238631 Hexapoda Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003016 pheromone Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
- G06M1/00—Design features of general application
- G06M1/27—Design features of general application for representing the result of count in the form of electric signals, e.g. by sensing markings on the counter drum
- G06M1/272—Design features of general application for representing the result of count in the form of electric signals, e.g. by sensing markings on the counter drum using photoelectric means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention provides a pest real-time detection counting system, which comprises: the pest monitoring device comprises a data acquisition part, a pest monitoring part and an image recognition part; the pest monitoring part at least comprises a photoelectric counting device, a pest collector and an image acquisition device; the data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency; under the condition that the pest is determined to enter the pest collector according to the detection signal, the data acquisition part drives an image acquisition device positioned in the pest collector to take a picture so as to acquire a target image; the image recognition section recognizes the target image to determine a detection count result of the target pest based on the recognition result. According to the pest real-time detection counting system provided by the invention, the real-time detection counting of pests is carried out simultaneously by the photoelectric sensor and the pest image, so that the problem that the calibration cannot be carried out when the pests are counted in a single counting mode in the past is avoided, and the accuracy of the counting is ensured.
Description
Technical Field
The invention relates to the technical field of agricultural information, in particular to a pest real-time detection and counting system.
Background
The pest occurrence monitoring has great significance to agriculture and forestry production, at present, the pest and disease monitoring of agriculture and forestry in China mainly depends on manual regular inspection, the manual inspection period of large-area farmland and forest lands is long, the randomness of the inspection process is large, the pest and disease occurrence position cannot be monitored for a long time, and the uncertainty of the inspection result is increased. In places such as mountain forests where manpower is difficult to reach, the occurrence of pests is more difficult to patrol, so that the occurrence of pests cannot be known timely.
At present, pest monitoring is mostly carried out in a single mode such as a photoelectric mode or an image mode, the monitoring result data are single, and when data are wrong, data cannot be corrected.
The photoelectric sensor is easy to be influenced by external natural light during monitoring, and when the collected data is used for directly judging the number of pests, the collected data is easy to be interfered by external signals, and occasional primary triggering signals can not ensure that certain pests enter the device
The image type pest monitoring can only singly shoot pest images, data in the images are not effectively utilized, and target pests and non-target pests in the images are mixed together and are not effectively distinguished.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a real-time pest detection and counting system which can help workers to effectively observe the occurrence condition of pests in time and provide important data support for researching the survival condition of pests and the possible damage caused by the pests.
The invention provides a pest real-time detection counting system, which comprises: the pest monitoring device comprises a data acquisition part, a pest monitoring part and an image recognition part; the pest monitoring part at least comprises a photoelectric counting device, a pest collector and an image acquisition device; the data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency; under the condition that the pest is determined to enter the pest collector according to the detection signal, the data acquisition part drives an image acquisition device positioned in the pest collector to take a picture so as to acquire a target image; the image recognition section recognizes the target image to determine a detection count result of the target pest based on the recognition result.
The invention provides a real-time pest detection and counting system, wherein a photoelectric counting device comprises a linear light source and a silicon photocell array which takes the linear light source as a circle center and is arranged in an arc shape; the linear light source and the silicon photocell arrays are arranged on two sides of the pest falling channel; the detection signals collected each time comprise multipath silicon photocell signals; the data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency and then further comprises: constructing a two-dimensional array based on the multi-channel silicon photocell signals acquired in each sampling period; carrying out gray image processing on the two-dimensional array to obtain a gray image of the two-dimensional array; and adopting an edge detection operator to carry out edge detection on the two-dimensional array gray level graph so as to judge whether pests fall into the pest collector through the channel in a sampling period.
According to the pest real-time detection counting system provided by the invention, the data acquisition part further comprises: a satellite navigation module; under the condition that the data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency or the data acquisition part drives the image acquisition device positioned in the pest collector to take a picture, the data acquisition part also acquires time information and geographic position information through the satellite navigation module.
According to the pest real-time detection and counting system provided by the invention, the pest real-time detection and counting system further comprises: an environment monitoring section; the environment monitoring part comprises an air temperature and humidity sensor, a wind direction sensor, an illumination sensor and a rainfall sensor.
According to the real-time pest detection and counting system provided by the invention, the pest monitoring part further comprises a pest trapping unit; the pest trapping unit communicates with the pest collector through a pest falling passage for trapping pests.
According to the pest real-time detection counting system provided by the invention, the pest monitoring part further comprises a turnover motor; the lower bottom plate of the pest collector is a movable turning plate; the lower bottom plate of the pest collector is connected with the rotating shaft of the overturning motor; the data acquisition part drives an image acquisition device positioned in the pest collector to take a picture so as to acquire a target image, and the pest collector further comprises: the overturning motor is driven to drive the lower bottom plate of the pest collector to overturn.
According to the pest real-time detection counting system provided by the invention, the pest monitoring part further comprises a light supplementing lamp; the data acquisition part drives the image acquisition device to take a picture and simultaneously drives the light supplementing lamp.
According to the pest real-time detection counting system provided by the invention, the pest real-time detection counting system further comprises a power management part; the power management part consists of a storage battery, a solar controller and a solar panel and is used for supplying power to the pest real-time detection counting system.
According to the pest real-time detection counting system provided by the invention, the data acquisition part further comprises a data storage module, wherein the data storage module is used for storing the meteorological information, the pest quantity information, the image information, the meteorological information, the time information and the geographic position information acquired in each sampling period and storing the meteorological information, the time information and the geographic position information into the txt text.
According to the pest real-time detection counting system provided by the invention, the data acquisition part further comprises a network transmission module, and the network transmission module is connected with the remote server.
The remote server side provided by the invention can be provided with the image recognition part, the image recognition part has an image recognition function, and can recognize the images transmitted by the data acquisition part and judge the number of the target pests.
According to the pest real-time detection counting system provided by the invention, the real-time detection counting of pests is carried out simultaneously by the photoelectric sensor and the pest image, so that the problem that the calibration cannot be carried out when the pests are counted in a single counting mode in the past is avoided, and the accuracy of the counting is ensured.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a real-time pest detection and counting system according to the present invention;
FIG. 2 is a schematic diagram of the structure of a pest monitoring section provided by the present invention;
FIG. 3 is a schematic diagram of a photoelectric counting device according to the present invention
FIG. 4 is a second schematic diagram of the real-time pest detection and counting system according to the present invention;
fig. 5 is a schematic structural diagram of a software system of an upper computer provided by the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that in the description of embodiments of the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. The orientation or positional relationship indicated by the terms "upper", "lower", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of description and to simplify the description, and are not indicative or implying that the apparatus or elements in question must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The method and system for detecting and counting pests in real time according to the embodiments of the present invention are described below with reference to fig. 1 to 5.
Fig. 1 is a schematic structural diagram of a real-time pest detection and counting system provided by the invention, as shown in fig. 1, including but not limited to: a data acquisition section 2, a pest monitoring section 1, and an image recognition section 3; the pest monitoring section 1 includes at least a photoelectric counting device 11, a pest collector 12, and an image collecting device 13; the data acquisition part 2 drives the photoelectric counting device 11 to acquire detection signals according to a preset working frequency; in the case where it is determined that there is a pest entering pest collector 12 based on the detection signal, the data collection section 2 drives an image collection device 13 located inside the pest collector 12 to take a picture to obtain a target image; the image recognition portion 3 is mainly used for recognizing the target image to determine the detection count result of the target pest from the recognition result.
According to the pest real-time detection counting system provided by the invention, on one hand, the number of pests entering the pest collector 12 is counted through the photoelectric counting device; on the other hand, by analyzing the detection signal of the photoelectric counting device, after it is determined that there is a pest entering the pest collector 12, the image collecting device 13 is driven by the data collecting section 2 to start the photographing function to obtain a frame of target image of the pest located in the pest collector 12.
The camera resolution of the image capturing device 13 is selected to be not lower than 1920×1080. If the data collection part 2 does not detect that pests enter the pest collector 12 within a continuous time period, the image collection device 13 is automatically driven to start a photographing function, and a frame of image is obtained to judge whether equipment failure occurs according to the image.
For example, when no pest falls into the pest collector 12 is detected for more than 4 hours in succession with the data collection part 2, one frame of image is acquired and the image is recognized. If the identification result shows that the pests exist in the pest collector, the photoelectric counting device is proved to have faults, and the entering condition of the pests cannot be accurately detected.
Wherein, the photoelectric counting device can adopt an automatic counter taking a singlechip STM32F407RET6 as a core. The direct-irradiation photoelectric sensor is adopted to place the infrared luminous tube and the photoelectric receiving tube relatively, whenever pests pass once, infrared light is shielded by the pests, the output voltage of the photoelectric receiving tube changes once, the changed detection signal (voltage signal) is amplified and processed to form counting pulse, the counting pulse is collected by an IO port of the STM32F407RET6 singlechip, and the counting value is set by software control and a keyboard and displayed by a nixie tube, so that the statistics of the number of the pests can be realized.
The pest collector can be a container made of airtight and light-transmitting materials, or can be made of airtight and light-proof materials. Under the condition that the pest collector is made of airtight and light-proof materials, the internal space of the pest collector 12 is isolated from the external environment, natural light cannot enter, and the stable light source is additionally arranged in the pest collector, so that the interference of light rays in the external environment on the imaging effect can be effectively avoided, and the accuracy of image recognition is improved.
FIG. 2 is a schematic diagram of a pest monitoring part according to the present invention, and as shown in FIG. 2, pest drop channels 14 are formed in the top wall of pest collector 12; the photoelectric counting device 11 is arranged inside the side wall of the pest falling channel 14; the camera of the image acquisition device 13 is arranged inside the pest collector 12, specifically fixed on the top wall and faces the lower bottom plate of the pest collector 12.
Further, the above method for identifying the target image to determine the detection count result of the target pest may be implemented by using an artificial intelligence model, for example:
A deep network model for realizing pest identification is built in advance, and a sample set related to the pests to be identified is adopted to pretrain the model. After training is completed, only the acquired target image is input into the trained depth network model, and then the detection counting result output by the model can be acquired.
According to the pest real-time detection counting system provided by the invention, the real-time detection counting of pests is carried out simultaneously by the photoelectric sensor and the pest image, so that the problem that the calibration cannot be carried out when the pests are counted in a single counting mode in the past is avoided, and the accuracy of the counting is ensured.
Fig. 3 is a schematic structural diagram of a photoelectric counting device according to the present invention, as an alternative embodiment, as shown in fig. 3, the photoelectric counting device 11 mainly includes a linear light source 110 and a silicon photocell array 111 arranged in an arc shape with the linear light source 110 as a center; a linear light source 110 and a silicon photocell array 111 are disposed on both sides of pest drop channel 14; the detection signals collected each time comprise multipath silicon photocell signals; after the data acquisition part 2 drives the photoelectric counting device 11 to acquire the detection signal according to the preset working frequency, the method further comprises: constructing a two-dimensional array based on the multi-channel silicon photocell signals acquired in each sampling period; carrying out gray image processing on the two-dimensional array to obtain a gray image of the two-dimensional array; edge detection is performed on the two-dimensional array gray scale map using an edge detection operator to determine whether any pest falls into the pest collector 12 through the pest fall channel 14 during the sampling period.
Specifically, the photoelectric counting device 11 is installed on the pest drop-in passage 14, and emits a detection signal when there is a pest passing. The vermin collector 12 is mainly responsible for collecting the caught vermin, and the image pickup device 3 is located inside thereof for obtaining the target image.
The photoelectric counting device 11 adopts an infrared band of 850nm, a linear light source 110 with a light emitting angle of 120 degrees, the whole pest is covered by a fan angle falling into a channel 14 during light emission, the infrared receiving tube is a silicon photocell array 111, and the linear light source 110 is used as a circle center and is arranged in an arc shape to receive infrared light.
When a pest falls, a part of the units in the silicon photocell array 111 generate signal fluctuation as a detection signal for the pest falling. The data acquisition part 2 can simultaneously acquire x paths of silicon photocell signals V x, is provided with once every 2ms, continuously acquires 100 times in each sampling period, the data acquired for the nth time of the x paths of silicon photocells is V xn, the acquired data are stored in a two-dimensional array data, and the data structure is as follows:
V1,1V1,2V1,3....V1,100
V2,1V2,2V2,3....V2,100
....................
Vx,1Vx,2Vx,3....Vx,100
and then, using an edge detection template of a Sobel operator to perform edge detection calculation on the two-dimensional array data so as to judge that harmless insects pass in the sampling period according to an edge detection result.
The real-time pest detection counting system provided by the invention adopts the silicon photocell array to be simultaneously connected with multiple photoelectric signals based on an AD conversion mode, and the data acquisition part can automatically acquire data at high speed so as to provide a large amount of available data, so that the detection signals when pests fall into the system can be timely detected, and the phenomena of missing counting and multiple counting are avoided. And a continuous multi-group data unified analysis method is adopted, the acquired signal data are placed in a two-dimensional array, the array is subjected to gray image processing, an edge detection operator is adopted for detection, the signal change condition of a photoelectric sensor is monitored, and an effective judgment method is selected through multiple test detection.
Based on the content of the above embodiment, as an alternative embodiment, the data acquisition section 2 may further include: a satellite navigation module (Global Navigation SATELLITE SYSTEM, GNSS); in the case that the data collection part 2 drives the photoelectric counting device 11 to collect the detection signal according to the preset working frequency, or the data collection part 2 drives the image collection device 13 positioned in the pest collector 12 to take a picture, the data collection part 2 also obtains time information and geographical position information through the satellite navigation module.
Specifically, the GNSS module provides a standard time (which may be accurate to seconds) for the entire system, mainly including: the time the pest falls into, the time the target image is acquired; meanwhile, the geographical position information of the pest real-time detection counting system can be obtained in real time.
Optionally, the time information and the geographic position information acquired by the GNSS module may be combined with the target image acquired by the image acquisition device 13, and displayed to the user, so that the user manually performs an independent identification on each target image, so as to determine whether the target pest falls into the acquired target image, mark and identify the target pest in the target image, and finally statistics the detection and counting result.
Fig. 4 is a second schematic structural diagram of the pest real-time detection and counting system provided by the present invention, as an alternative embodiment, as shown in fig. 4, the pest real-time detection and counting system may further include: an environment monitoring section 6; the environment monitoring section 6 mainly includes one or more of an air temperature and humidity sensor, a wind direction sensor, an illumination sensor, and a rainfall sensor.
The real-time pest detection and counting system provided by the invention acquires the meteorological parameters of the environment where the real-time pest detection and counting system is located, such as: and the air temperature, humidity, wind speed, wind direction, illumination, rainfall, geographic position, host and other environmental information are combined, and the photoelectric counting information and the target image are simultaneously acquired, so that whether the pests falling into the pest collector are target pests or not is judged by combining the meteorological parameters, the host and the geographic position, and the counting accuracy is ensured.
Based on the above-described embodiments, as an alternative embodiment, as shown in fig. 2, pest monitoring section 1 further includes pest trapping unit 15;
The pest trapping unit 15 communicates with the pest collector 12 through the pest falling passage 14 for trapping pests.
In the present invention, the pest monitoring section 1 is a pest trapping, capturing and information acquiring section, wherein the pest trapping unit 15 is responsible for trapping pests, and the pests are attracted by the built-in pheromones thereof to ensure that the pests cannot escape after entering, and the pest falling channel 14 is responsible for connecting the pest trapping unit 15 with the pest collector 12, through which the pests fall into the pest collector 12 through the pest falling channel 14.
Based on the above-described embodiments, as an alternative embodiment, as shown in fig. 2, pest monitoring section 1 may further include a turnover motor 17; the lower bottom plate of pest collector 12 is a movable turning plate 16; the lower bottom plate of the pest collector is connected with the rotating shaft of the overturning motor 17; after the data collection part 2 drives the image collection device 3 located in the pest collector 12 to take a picture to obtain a target image, it further includes: the turnover motor 17 is driven to turn over the lower base plate of the pest collector.
Specifically, the movable flap 16 is a background plate for acquiring a target image related to pests, and is connected to the turning motor 17, and the pest collector 12 is divided into an upper part and a lower part by the movable flap 16. After the pests fall into the channel 14, the pests are placed on the movable turning plate 16, and the image acquisition device 3 acquires the target image; after the collection is completed, the data collection part 2 drives the overturning motor 17 to drive the movable overturning plate 16 to overturn, pests are dumped into the lower half part which is of a closed structure, and pest carcasses are cleared when manual inspection is carried out.
The overturning motor 17 can use a speed reducing motor, and can ensure the stability of the whole structure in the process of driving the movable overturning plate 16 to slowly rotate.
Further, a limit switch is provided at a position where pest collector 12 is exactly fitted with movable flap 16 to ensure that the limit switch is triggered after 180 degrees of rotation is achieved in each turning cycle of movable flap 16 to send a turning completion signal to data collection portion 2. The data acquisition section 2 stops driving of the speed reduction motor after receiving the overturn completion signal.
According to the pest real-time detection counting system provided by the invention, the movable turning plate divides the pest collector into the upper part and the lower part, the upper part is used as a pest shooting section, the movable turning plate is used as a pest image acquisition background, the lower part is used as a pest corpse storage section of the pest collector, and the shot pests are isolated at the lower part of the pest collector, so that the pest which has acquired the target image is prevented from being mixed again and influencing the monitoring result.
Based on the above-described embodiments, as an alternative embodiment, as shown in fig. 2, the pest monitoring section 1 further includes a light supplement lamp 18; the light supplement lamp 18 is driven while the data collection portion 2 drives the image collection device 3 to take a picture.
Specifically, the camera of the image acquisition device 13 and the light supplementing lamp 18 are built in the pest collector 12, the pest collector 12 is a closed environment, isolated from the external environment, and natural light cannot enter. When the target image is acquired, the intensity of the light supplementing light 18 is kept consistent, so that the consistency of the background environment of the acquired target image can be ensured, the accuracy of pest identification is improved, and the pest identification difficulty is reduced.
Based on the content of the above-described embodiment, as an alternative embodiment, as shown in fig. 4, the pest real-time detection counting system further includes a power management section 4.
Optionally, the power management part 4 is composed of a storage battery, a solar controller and a solar panel, and is used for supplying power to the pest real-time detection counting system.
The main content of the power management part 4 comprises a 12V20Ah storage battery, a 10A solar controller and a 50W solar panel, and is responsible for supplying power to the whole terminal equipment and guaranteeing the power consumption condition in the field.
The pest real-time detection and counting system provided by the invention is often placed in an outdoor environment, and is often difficult to realize by adopting an external power supply mode. Therefore, the invention can effectively improve the applicability of the system to complex working environments by adding the power management part 4 which is powered by solar energy in the system.
Based on the above-mentioned embodiments, as an alternative embodiment, the data acquisition section 2 further includes a data storage module for storing the weather information, the pest number information, the image information, the weather information, the time information, and the geographical position information acquired in each of the sampling periods, and storing them in the txt text.
Specifically, the data acquisition section 2 is responsible for coordinating the operation of the entire system. Wherein pest trapping data collected by the photoelectric counting device, meteorological data collected by the environment monitoring part, time information and geographical position information collected by the GNSS module, hosts, storage data and the like are all operated by the photoelectric counting device.
The data storage module can use a micro sd card with large capacity as a data storage unit to store weather information, pest quantity information, image information, weather information, pest quantity information, time information and the like, and specifically store the weather information, the pest quantity information, the time information and the like in txt texts, and the images are named as 'time when the images are acquired + sequence number', so that no duplication phenomenon of the image information is ensured.
Based on the above-described embodiments, as an alternative embodiment, the data acquisition section 2 may further include a network transmission module, as shown in fig. 4, which connects to a remote server.
The network transmission module is responsible for connecting a remote server to transmit the acquired data such as the meteorological information, the pest quantity information, the image information and the like to the server end for the user to check.
The data acquisition part 2 has a low power consumption mode, for example, when the acquired air temperature is too low, the low power consumption mode is entered, the system power consumption is reduced, and the electric quantity loss is reduced.
Fig. 5 is a schematic structural diagram of an upper computer software system provided by the invention, and as shown in fig. 5, the upper computer software system is mainly used for checking, automatic identification and manual identification and downloading data acquired by the system.
The user can access the software system by means of a client such as a computer, a mobile terminal and the like which can be connected with the Internet, and after logging in through the logging in 51 interface, the user can access the real-time monitoring 52 function interface, and all the devices in the whole pest real-time detection counting system are presented on the interface. Other functional interfaces can be respectively accessed through the selection of the functional frames, including a pest data statistics 53 interface, a pest image identification 54 interface, a historical data viewing 55 interface and the like.
The upper computer software system can be loaded in the image recognition part 3, and after receiving the picture, the upper computer software system can automatically detect target pests in the picture and perform identification. The automatic identification result can be viewed on the pest image identification 54 interface, and the user can manually modify the result and correct the identification result.
For example: the user can view the target image shot by the image acquisition device 13 through the interface of the pest image identification 54, and can perform independent identification on each image so as to judge whether target pests fall into the acquired target image or not, and mark identification in the figure so as to correct the number of the pests detected by the photoelectric counting device.
According to the pest real-time detection counting system, the data and the images detected by the whole system are displayed through the upper computer software system, so that the user can manually identify the development of work, the false triggering condition generated in the photoelectric counting device is corrected, and meanwhile, the counting phenomenon caused by the fact that non-target pests fall into the trapper can be eliminated, so that the counting value is more accurate. And the data of the upper computer software system is checked and the image identification function provides visual monitoring results for staff, and the image and the data are combined to avoid specific deviation caused by single data.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A pest real-time detection counting system, characterized by comprising: the pest monitoring device comprises a data acquisition part, a pest monitoring part and an image recognition part; the pest monitoring part at least comprises a photoelectric counting device, a pest collector and an image acquisition device;
The data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency;
In the case that it is determined that there is a pest entering the pest collector according to the detection signal, the data collection part drives an image collection device located in the pest collector to take a picture to obtain a target image;
The image recognition part recognizes the target image to determine a detection count result of the target pest according to the recognition result;
The photoelectric counting device comprises a linear light source and a silicon photocell array which takes the linear light source as a circle center and is arranged in an arc shape; the linear light source and the silicon photocell arrays are arranged on two sides of the pest falling channel; the detection signals collected each time comprise multipath silicon photocell signals;
The data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency and then further comprises:
constructing a two-dimensional array based on the multi-channel silicon photocell signals acquired in each sampling period;
Carrying out gray image processing on the two-dimensional array to obtain a two-dimensional array gray image;
And adopting an edge detection operator to carry out edge detection on the two-dimensional array gray level diagram so as to judge whether pests enter the pest collector through the pest falling channel in the sampling period.
2. The pest real-time detection and counting system according to claim 1, wherein the data collection part further includes: a satellite navigation module;
Under the condition that the data acquisition part drives the photoelectric counting device to acquire detection signals according to a preset working frequency or the data acquisition part drives the image acquisition device positioned in the pest collector to take photos, the data acquisition part also acquires time information and geographic position information through the satellite navigation module.
3. The pest real-time detection and counting system according to claim 1, further comprising: an environment monitoring section;
The environment monitoring part comprises an air temperature and humidity sensor, a wind direction sensor, an illumination sensor and a rainfall sensor.
4. The pest real-time detection and counting system according to claim 1, wherein the pest monitoring part further includes a pest trapping unit;
the pest trapping unit communicates with the pest collector through the pest falling channel for trapping pests.
5. The pest real-time detection and counting system according to claim 1, wherein the pest monitoring section further includes a turnover motor; the lower bottom plate of the pest collector is a movable turning plate; the lower bottom plate of the pest collector is connected with the rotating shaft of the overturning motor;
The data acquisition part drives an image acquisition device positioned in the pest collector to take a picture so as to acquire a target image, and then the pest collector further comprises:
The overturning motor is driven to drive the lower bottom plate of the pest collector to overturn.
6. The pest real-time detection and counting system according to claim 1, wherein the pest monitoring section further includes a light supplement lamp; and driving the light supplementing lamp while the data acquisition part drives the image acquisition device to take a picture.
7. The pest real-time detection and counting system according to claim 1, further comprising a power management section;
The power management part is composed of a storage battery, a solar controller and a solar panel and is used for supplying power to the pest real-time detection counting system.
8. The pest real-time detection and counting system according to claim 1, wherein the data collection part further comprises a data storage module for storing weather information, pest number information, image information, weather information, time information and geographical position information collected in each of the sampling periods, and storing the same in txt text.
9. The pest real-time detection and counting system according to claim 8, wherein the data collection part further includes a network transmission module, the network transmission module being connected to a remote server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110221101.1A CN112862054B (en) | 2021-02-26 | 2021-02-26 | Real-time pest detecting and counting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110221101.1A CN112862054B (en) | 2021-02-26 | 2021-02-26 | Real-time pest detecting and counting system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862054A CN112862054A (en) | 2021-05-28 |
| CN112862054B true CN112862054B (en) | 2024-05-14 |
Family
ID=75990347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110221101.1A Active CN112862054B (en) | 2021-02-26 | 2021-02-26 | Real-time pest detecting and counting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862054B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113797515A (en) * | 2021-08-31 | 2021-12-17 | 海南翔睿德科技有限公司 | Table tennis service robot capable of automatically counting |
| CN116935017A (en) * | 2023-06-20 | 2023-10-24 | 农芯(南京)智慧农业研究院有限公司 | Automatic pest counting and identifying system and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015228803A (en) * | 2014-06-03 | 2015-12-21 | みこらった株式会社 | Pest insect capture-accommodation device and pest insect insecticidal device |
| CN107711762A (en) * | 2017-10-19 | 2018-02-23 | 上海中信信息发展股份有限公司 | Intelligent Insect infestation monitoring method and intelligent Insect infestation monitoring device |
| JP2018061513A (en) * | 2017-12-25 | 2018-04-19 | みこらった株式会社 | Pest insect exterminating device |
| WO2019092707A1 (en) * | 2017-11-07 | 2019-05-16 | Dr. Eyal Bressler Ltd. | Integrated system for controlling, detecting, monitoring, evaluating and treating crop pests |
| CN110235873A (en) * | 2019-06-26 | 2019-09-17 | 北京农业智能装备技术研究中心 | A kind of agricultural harmful insect insect pest situation automatic monitoring forecast system |
| CN110250123A (en) * | 2019-06-26 | 2019-09-20 | 江苏大学 | Low-density grain storage pest real-time monitoring system based on image recognition |
-
2021
- 2021-02-26 CN CN202110221101.1A patent/CN112862054B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015228803A (en) * | 2014-06-03 | 2015-12-21 | みこらった株式会社 | Pest insect capture-accommodation device and pest insect insecticidal device |
| CN107711762A (en) * | 2017-10-19 | 2018-02-23 | 上海中信信息发展股份有限公司 | Intelligent Insect infestation monitoring method and intelligent Insect infestation monitoring device |
| WO2019092707A1 (en) * | 2017-11-07 | 2019-05-16 | Dr. Eyal Bressler Ltd. | Integrated system for controlling, detecting, monitoring, evaluating and treating crop pests |
| JP2018061513A (en) * | 2017-12-25 | 2018-04-19 | みこらった株式会社 | Pest insect exterminating device |
| CN110235873A (en) * | 2019-06-26 | 2019-09-17 | 北京农业智能装备技术研究中心 | A kind of agricultural harmful insect insect pest situation automatic monitoring forecast system |
| CN110250123A (en) * | 2019-06-26 | 2019-09-20 | 江苏大学 | Low-density grain storage pest real-time monitoring system based on image recognition |
Non-Patent Citations (1)
| Title |
|---|
| 自动监测装置用温室粉虱和蓟马成虫图像分割识别算法;杨信廷;刘蒙蒙;许建平;赵丽;魏书军;李文勇;陈梅香;陈明;李明;;农业工程学报(01);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862054A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112862054B (en) | Real-time pest detecting and counting system | |
| US11650207B1 (en) | Spore state discrimination | |
| CN108189043A (en) | A kind of method for inspecting and crusing robot system applied to high ferro computer room | |
| CN105938571B (en) | Insect identifies number system and method | |
| CN109919796B (en) | Insect pest situation detecting and reporting system | |
| JP6390054B2 (en) | Monitoring system | |
| CN203812266U (en) | Insect trapping and counting device | |
| EP4161258A1 (en) | Insect monitoring system and method | |
| US11175277B2 (en) | Automated profiling of the condition of wood | |
| CN103598171A (en) | Device for trapping, classifying and counting orchard flying injurious insects | |
| CN101701906A (en) | Method and device for detecting stored-grain insects based on near infrared super-spectral imaging technology | |
| CN102256102A (en) | Agricultural condition information real-time monitoring method and system based on remote monitoring | |
| CN106570534A (en) | Automatic small insect trapping detection method and system thereof | |
| CN109063815A (en) | A kind of pest identification statistic device, system and method | |
| CN103125457A (en) | Orchard bactrocera dorsalis insect damage recognition system based on digital signal processing (DSP) and internet of things | |
| US20240040995A1 (en) | Method, apparatus and system for detecting carbon emission-involved gas from ruminant | |
| CN218444524U (en) | Agricultural inspection soil taking robot | |
| CN216351838U (en) | Crop monitoring system | |
| CN206757392U (en) | Agricultural greenhouse inspection managing device based on Internet of Things | |
| JP2019039913A (en) | Monitoring system | |
| CN204989162U (en) | Heavy metal detector | |
| CN109902647B (en) | Portable online bird nest intelligent identification method and system | |
| CN209014477U (en) | A kind of portable Grassland Biomass noninvasive measurement device | |
| CN208421879U (en) | A kind of pest identification statistic device and system | |
| CN115508515A (en) | Data acquisition system and equipment for soil greenhouse gas emission |
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 |