CN104918007A - Computer vision-based large field pest situation monitoring sampling device and sampling method - Google Patents
Computer vision-based large field pest situation monitoring sampling device and sampling method Download PDFInfo
- Publication number
- CN104918007A CN104918007A CN201510251109.7A CN201510251109A CN104918007A CN 104918007 A CN104918007 A CN 104918007A CN 201510251109 A CN201510251109 A CN 201510251109A CN 104918007 A CN104918007 A CN 104918007A
- Authority
- CN
- China
- Prior art keywords
- worm
- insect
- computer vision
- land
- transparent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Catching Or Destruction (AREA)
Abstract
The invention discloses a computer vision-based large field pest situation monitoring sampling device and a sampling method. The sampling device includes a pest killing device, a transparent pest carrying board for carrying dead pests from the pest killing device, two cameras which are located at the upper side and the lower side of the transparent pest carrying board respectively and are used for acquiring images of the dead pests, and a terminal used for receiving the images from the cameras and recognizing the images. With the device of the invention adopted, the problem of the stacking of the bodies of the pests in an automatic sampling process, and the problem of precision drop of a recognition model which is caused by difficult recognition of the images of the abdomens of the bodies of the pests can be solved.
Description
Technical field
The present invention relates to Precision Agriculture Technology field, particularly relate to a kind of land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision and the method for sampling.
Background technology
China is a large agricultural country, and the monitoring of agricultural pests, the statistical fluctuation work of insect pest situation disaster are very important.If monitoring and prediction is accurately and timely, just can early Control pests, reduce pesticide dosage, avoid crops to suffer heavy losses.Be generally by experienced peasant and classification of insect expert, insect is identified in conventional method, but manual identified labour intensity is large, efficiency is low.
Therefore, develop some intelligent wireless insect remote automatic monitoring devices, by contributing to the accuracy rate and the efficiency that improve insect identification and counting, reduce the loss that insect pest brings, and then promote the enforcement of precision agriculture, improve the science popularization level of insect knowledge.
In prior art, be generally on the basis that insect is traped, realize identification to insect and remote monitoring.At present, the kind of domestic and international pest trap is a lot, and it catches the biological nature such as phototaxis, the sense of taste that principle mainly utilizes insect, adopts revulsive, light source, information source etc. to carry out trapping pests.
The Chinese patent literature being CN2867873Y as notification number discloses a kind of pest trap, it is by upper cover, funnel seat, lure core and pest catcher composition, the passage that the worm inlet bottom of this pest trap or inner side one i.e. worm inlet lead to conical surface funnel or pest catcher is provided with is prevented escaping that line forms puts release apparatus by elasticity, 1 ~ 6 block of gear worm plate is housed under described upper cover, when insect is lured wicking to draw to fly to trapper, first bump against with gear worm plate and fall downwards, encounter thin and smooth, can not support insect weight upper anti-escape line after fall in funnel seat, rely on the weight of itself to rush open and anti-escape line down, fall into concentrator.This pest trap utilizes upper anti-escapes line and lower anti-line of escaping stops insect to escape from trapper.
But this pest trap can only carry out the trapping of insect, cannot, to the insect information be entrapped, cause being difficult to carry out identification and any type of monitoring to insect.
Notification number is the system that the Chinese patent literature of CN202566059U discloses a kind of real-time remote monitoring insect, comprising: trapper, storage storage, dynamical system and analytical system; Trap interior places different pheromone attractant, the porch installation infrared line robot scaler of trapper, this Infrared Automatic Counting Equipment records quantity and the time that insect enters trapper automatically, and by the information transmission of collection to storage storage (gsm module), gsm module can record the information of Infrared Automatic Counting Equipment collection and be transferred to analytical system further, and analytical system analyzes the probability that insect may be broken out.
This trapper is merely able to gather the T/A information that insect enters trapper, is unfavorable for identifying the kind of insect and analyzing.
At present, based in the land for growing field crops insect pest situation monitoring of computer vision, the insect object often for individuality single in trap lamp identifies, during insect polypide face to face to overlap, then lacks effective means of identification.In addition, current Agriculture field pests model of cognition often can only identify for insect back image, and when in the face of insect abdomen images, then causes performance degradation because of the low discrimination of belly.
The category identification of the large Tanaka insect of these defective effects and quantity statistics, make timely, the effective prevention for land for growing field crops insect pest be difficult to accomplished.
Summary of the invention
For the deficiency that prior art exists, the object of the present invention is to provide a kind of land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision, this device can solve the problem of insect polypide overlap in automatic sampling process effectively, and polypide abdomen images is difficult to the problem identifying the model of cognition precise decreasing caused.
For achieving the above object, the invention provides following technical scheme:
Based on a land for growing field crops insect pest situation monitoring sampling apparatus for computer vision, comprising:
Insect-killing device;
Transparently hold worm plate, for accepting the dead worm from insect-killing device;
Two cameras, lay respectively at transparent both sides up and down of holding worm plate, for gathering the image of dead worm;
Terminating machine, identifies for the image that receives from each camera.
As preferably, described insect-killing device is trap lamp, is provided with for holding to transparent the flexible pipe that worm plate guides dead worm bottom trap lamp.
The present invention is killed off the insect pests by insect-killing device trapping, dead worm is arrived by flexible pipe transparently to be held on worm plate, be positioned at transparent two cameras holding the upper and lower both sides of worm plate and carry out IMAQ to the transparent dead worm held on worm plate respectively, the image collected finally is undertaken identifying and counting by terminating machine.
As preferably, the land for growing field crops insect pest situation that the present invention is based on computer vision is monitored sampling apparatus in real time and is also provided with brace table, two cameras through the Bracket setting of correspondence on brace table.
In order to prevent dead worm overlapped, pile up, as preferably, the described transparent worm plate that holds is movably arranged on brace table, brace table is provided with for driving transparent the first driving mechanism holding the shake of worm plate.First driving mechanism drives and transparently holds the shake of worm plate, disperses dead worm, the mutual circumstance of occlusion of dead worm is reduced and makes the attitude of the dead worm of adjustment, is convenient to that the dead worm of camera collection is multi-faceted, the image of multi-pose, is conducive to identification and the counting of dead worm kind.
Described first driving mechanism comprises:
First motor;
With the bent axle of described first motor linkage;
The connecting rod hinged with described bent axle;
One end and rod hinge connection, the other end and the transparent pull bar holding worm plate and fix;
For guiding the reciprocating location notch of pull bar.
As preferably, what the described transparent end face holding worm plate was slidably matched pushes away worm plate, and described brace table is provided with and pushes away reciprocating second driving mechanism of worm plate for driving.
After camera terminates the transparent dead worm collection image held on worm plate, the second driving mechanism drives and pushes away the motion of worm plate, clears away the transparent dead worm held on worm plate, so that the collection to the dead worm image of next group.
Described second driving mechanism is cylinder or slider-crank mechanism.
Camera collection to the image transmitting of dead worm to carry out identification and the counting of pest species to terminating machine.
Terminating machine and each camera radio communication.
As preferably, of the present inventionly also comprise controller, for controlling the work of camera, the first driving mechanism, the second driving mechanism based on above-mentioned land for growing field crops insect pest situation monitoring sampling apparatus.
Present invention also offers a kind of method of sampling based on above-mentioned land for growing field crops insect pest situation monitoring sampling apparatus, comprising:
Utilize described insect-killing device insect-killing trapping;
Dead worm drops down onto describedly transparently to be held on worm plate;
By the image of described two dead worms of camera collection;
Described terminating machine receives the image from each camera and identifies.
Being fallen within by the insect that insect-killing device is trapped and killed transparently holds on worm plate, the transparent camera holding the upper and lower both sides of worm plate gathers the transparent image held before and after the shake of worm plate respectively, the insect image gathered after compression, radio to terminating machine and carry out image procossing, the identification of pest species and various types of number statistical are carried out to image.
Image procossing comprises the following steps:
(1) degree of depth convolutional neural networks model of Agriculture field pests image is set up in advance;
(1-1) set up the degree of depth convolutional neural networks model of Agriculture field pests image in advance, degree of depth convolutional neural networks structure is: an input layer, five convolutional layers, three pond layers, two full articulamentums and output layers;
(1-2) be input layer before five convolutional layers, three maximum pond layers (max pooling) lay respectively at first, second, after the 5th convolutional layer, two full articulamentums are at the 3rd between maximum pond layer and output layer.Output layer adopts softmax to be grader;
(1-3) input layer accepts the image input of 227 × 227.The pixel size of the convolution filter of five convolutional layers is respectively 13 × 13,5 × 5,3 × 3,3 × 3,6 × 6, and the number of convolution filter is respectively 128,256,512,512,256, and convolution step-length is 4.In three maximum pond layers (max pooling), pond area size is 3 × 3, and pond step-length is 2.Two full articulamentum nodes are 4096.Output layer nodal point number is determined according to concrete pest species number to be identified.
(2) thresholding process is carried out to the original image that upside camera is taken before holding worm plate and shaking, obtain each insect region, in these regions of original image, calculate SIFT feature point, and record coordinate;
(3) to upside camera take in hold worm plate shake after original image carry out thresholding process, obtain each insect region, in these regions of original image, calculate SIFT feature point, and record coordinate;
(4) (matching criterior is: the Euclidean distance between two same characteristic features points on image is no more than 200 pixels for the front image of coupling shake and all SIFT feature points after shaking on image, two same characteristic features points are no more than 0.1 at the Euclidean distance of its feature space), moving direction is calculated to the characteristic point meeting matching criterior, and calculated direction histogram, determine to shake the insect number in front image in each insect region according to direction histogram entry number;
(5) degree of depth convolutional neural networks set up is utilized to identify the object in regional in image before shake, several recognition results that the probability choosing respective number according to insect number determined in this region is the highest, obtain the kind of each insect in regional, then the number obtaining transparent kind and correspondence thereof of holding all insects on worm plate (holds the insect abdomen images that on the upside of worm plate, image can not identify for transparent, then by transparent hold image on the downside of worm plate complete its back identify, improve recognition result).
Beneficial effect of the present invention is:
When camera collection image by transparent shake of holding worm plate, the insect on it is disperseed, can effectively overcome because insect polypide is overlapped and cause cannot the problem of accurate metering and category identification; Simultaneously, adopt the image of upper and lower two camera collection insects, when upside camera collection is to insect abdomen images during None-identified, the corresponding insect back image utilizing downside camera to gather is identified, improves the precision to pest species identification of the present invention.
Accompanying drawing explanation
Fig. 1 is the structural representation of the land for growing field crops insect pest situation monitoring sampling apparatus that the present invention is based on computer vision;
Fig. 2 is the structural representation of crankshaft connecting rod system of the present invention.
Wherein: 1, trap lamp; 2, flexible pipe; 3, transparently worm plate is held; 4, upside camera; 5, downside camera; 6, worm plate is pushed away; 7, brace table; 8, image processing terminal; 9, the first driving mechanism; 10, the second driving mechanism; 91, bent axle; 92, first connecting rod; 93, second connecting rod; 94, location notch.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail, it is pointed out that the following stated embodiment is intended to be convenient to the understanding of the present invention, and any restriction effect is not play to it.
As shown in Figure 1, a kind of monitoring of the land for growing field crops insect pest situation based on computer vision sampling apparatus, comprises trap lamp 1, transparently holds worm plate 3, lays respectively at transparent the upside camera 4 and downside camera 5, the image processing terminal 8 that hold the upper and lower both sides of worm plate.
Trap lamp 1 bottom is connected with flexible pipe 2, and the insect killed by trap lamp by flexible pipe 2 is directed to transparent holding on worm plate 3.
Two cameras respectively by the support installing of correspondence on brace table 7.
In order to prevent dead worm to hold overlapping on worm plate 3, accumulation transparent, affect the sample effect of camera, the transparent worm plate 3 that holds of the present embodiment is movably arranged on brace table 7, and the transparent worm plate 3 that holds is driven by the first driving mechanism 9.First driving mechanism 9 is servomotor, is connected transparently hold worm plate 3 by crankshaft connecting rod system.As shown in Figure 2, crankshaft connecting rod system comprises bent axle 91 hinged successively, first connecting rod 92, second connecting rod 93, and the junction of first connecting rod 92 and second connecting rod 93 is provided with location notch 94, to ensure that second connecting rod 93 can reciprocating motion stably.The other end of second connecting rod 93 is screwed to connect and transparently holds worm plate 3.The transparent worm plate 3 that holds can back and forth be shaken under the drive of servomotor, disperses the dead worm on it, avoids dead worm overlapping, and dead worm also can be made to convert attitude simultaneously, makes camera can photograph the image of the different attitude of insect.
The transparent end face holding worm plate 3 is sliding combined with and pushes away worm plate 6, and push away reciprocating second driving mechanism 10 of worm plate 6 for drive and be arranged on brace table 7, the second driving mechanism 10 can be cylinder, also can be slider-crank mechanism.After camera terminates the transparent dead worm collection image held on worm plate 3, the second driving mechanism 10 drive pushes away worm plate 6 and moves, and clears away the transparent dead worm held on worm plate, so that the collection to the dead worm image of next group.
The sampling apparatus of the present embodiment also comprises controller, for controlling the work of camera, the first driving mechanism, the second driving mechanism.
The method of sampling based on above-mentioned sampling apparatus is:
Trap lamp is utilized to trap and kill Agriculture field pests, being fallen within by flexible pipe 2 by the insect trapped and killed transparently holds on worm plate 3, the transparent camera holding the upper and lower both sides of worm plate gathers the transparent image held before and after the shake of worm plate respectively, the insect image gathered after compression, radio to image processing terminal 8 and carry out image procossing, the identification of pest species and various types of number statistical are carried out to image.
Image procossing comprises the following steps:
(1) degree of depth convolutional neural networks model of Agriculture field pests image is set up in advance;
(1-1) set up the degree of depth convolutional neural networks model of Agriculture field pests image in advance, degree of depth convolutional neural networks structure is: an input layer, five convolutional layers, three pond layers, two full articulamentums and output layers;
(1-2) be input layer before five convolutional layers, three maximum pond layers (max pooling) lay respectively at first, second, after the 5th convolutional layer, two full articulamentums are at the 3rd between maximum pond layer and output layer.Output layer adopts softmax to be grader;
(1-3) input layer accepts the image input of 227 × 227.The pixel size of the convolution filter of five convolutional layers is respectively 13 × 13,5 × 5,3 × 3,3 × 3,6 × 6, and the number of convolution filter is respectively 128,256,512,512,256, and convolution step-length is 4.In three maximum pond layers (max pooling), pond area size is 3 × 3, and pond step-length is 2.Two full articulamentum nodes are 4096.Output layer nodal point number is determined according to concrete pest species number to be identified.
(2) to upside camera take in transparent hold worm plate 3 shake before original image carry out thresholding process, obtain each insect region, in these regions of original image, calculate SIFT feature point, and record coordinate;
(3) to upside camera take in transparent hold worm plate shake after original image carry out thresholding process, obtain each insect region, in these regions of original image, calculate SIFT feature point, and record coordinate;
(4) (matching criterior is: the Euclidean distance between two same characteristic features points on image is no more than 200 pixels for the front image of coupling shake and all SIFT feature points after shaking on image, two same characteristic features points are no more than 0.1 at the Euclidean distance of its feature space), moving direction is calculated to the characteristic point meeting matching criterior, and calculated direction histogram, determine to shake the insect number in front image in each insect region according to direction histogram entry number;
(5) degree of depth convolutional neural networks set up is utilized to identify the object in regional in image before shake, several recognition results that the probability choosing respective number according to insect number determined in this region is the highest, obtain the kind of each insect in regional, then the number obtaining transparent kind and correspondence thereof of holding all insects on worm plate (holds the insect abdomen images that on the upside of worm plate, image can not identify for transparent, then by transparent hold image on the downside of worm plate complete its back identify, improve recognition result).
Above-described embodiment has been described in detail technical scheme of the present invention and beneficial effect; be understood that and the foregoing is only specific embodiments of the invention; be not limited to the present invention; all make in spirit of the present invention any amendment, supplement and equivalent to replace, all should be included within protection scope of the present invention.
Claims (9)
1., based on a land for growing field crops insect pest situation monitoring sampling apparatus for computer vision, it is characterized in that, comprising:
Insect-killing device;
Transparently hold worm plate, for accepting the dead worm from insect-killing device;
Two cameras, lay respectively at transparent both sides up and down of holding worm plate, for gathering the image of dead worm;
Terminating machine, identifies for the image that receives from each camera.
2. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 1, it is characterized in that, described insect-killing device is trap lamp, is provided with for holding to transparent the flexible pipe that worm plate guides dead worm bottom trap lamp.
3. the monitoring of the land for growing field crops insect pest situation based on computer vision sampling apparatus according to claim 1, is characterized in that, be also provided with brace table, two cameras through the Bracket setting of correspondence on brace table.
4. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 3, it is characterized in that, the described transparent worm plate that holds is movably arranged on brace table, brace table is provided with for driving transparent the first driving mechanism holding the shake of worm plate.
5. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 4, it is characterized in that, described first driving mechanism comprises:
First motor;
With the bent axle of described first motor linkage;
The connecting rod hinged with described bent axle;
One end and rod hinge connection, the other end and the transparent pull bar holding worm plate and fix;
For guiding the reciprocating location notch of pull bar.
6. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 3, it is characterized in that, what the described transparent end face holding worm plate was slidably matched pushes away worm plate, and described brace table is provided with and pushes away reciprocating second driving mechanism of worm plate for driving.
7. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 7, it is characterized in that, described second driving mechanism is cylinder or slider-crank mechanism.
8. the land for growing field crops insect pest situation monitoring sampling apparatus based on computer vision according to claim 1, is characterized in that, terminating machine and each camera radio communication.
9., based on a real-time monitoring method of sampling for the land for growing field crops insect pest situation monitoring sampling apparatus described in any one of claim 1 ~ 8, it is characterized in that, comprising:
Utilize described insect-killing device insect-killing trapping;
Dead worm drops down onto describedly transparently to be held on worm plate;
By the image of described two dead worms of camera collection;
Described terminating machine receives the image from each camera and identifies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510251109.7A CN104918007B (en) | 2015-05-15 | 2015-05-15 | Crop field insect pest situation monitoring sampling apparatus and the method for sampling based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510251109.7A CN104918007B (en) | 2015-05-15 | 2015-05-15 | Crop field insect pest situation monitoring sampling apparatus and the method for sampling based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104918007A true CN104918007A (en) | 2015-09-16 |
| CN104918007B CN104918007B (en) | 2017-10-27 |
Family
ID=54086662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510251109.7A Active CN104918007B (en) | 2015-05-15 | 2015-05-15 | Crop field insect pest situation monitoring sampling apparatus and the method for sampling based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104918007B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107333098A (en) * | 2016-04-28 | 2017-11-07 | 浙江托普云农科技股份有限公司 | A kind of device for detecting and reporting pest information |
| CN107333731A (en) * | 2016-04-28 | 2017-11-10 | 浙江托普云农科技股份有限公司 | A kind of measuring and reporting system and its method filtered based on polypide with borer population and category identification |
| CN108782492A (en) * | 2018-05-18 | 2018-11-13 | 仲恺农业工程学院 | Pest control method based on pest control equipment |
| CN109118001A (en) * | 2018-08-09 | 2019-01-01 | 成都天地量子科技有限公司 | A kind of mountain fire monitoring method and system based on satellite remote sensing date |
| CN110122449A (en) * | 2019-05-29 | 2019-08-16 | 重庆工程职业技术学院 | Intelligent insecticidal lamp with artificial intelligence prediction pest |
| 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 |
| CN110326593A (en) * | 2019-06-19 | 2019-10-15 | 仲恺农业工程学院 | Pest capture system, method, computer device, and medium |
| CN111011325A (en) * | 2019-12-04 | 2020-04-17 | 济南祥辰科技有限公司 | Image acquisition device and insect pest situation forecast lamp of two discernments of taking photograph |
| CN111202035A (en) * | 2019-09-17 | 2020-05-29 | 浙江农林大学暨阳学院 | Automatic pest collecting device and method for agriculture and forestry pest prediction |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050097021A1 (en) * | 2003-11-03 | 2005-05-05 | Martin Behr | Object analysis apparatus |
| CN102239793A (en) * | 2011-04-18 | 2011-11-16 | 浙江大学 | Real-time classification method and system of rice pests |
| CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
| CN103299969A (en) * | 2013-06-09 | 2013-09-18 | 浙江大学 | Pest trapping device and long-distance remote pest recognizing and monitoring system |
| CN203243847U (en) * | 2013-04-18 | 2013-10-23 | 浙江托普仪器有限公司 | Automatic recognizing and counting device for lamplight trapping |
| US20130293710A1 (en) * | 2010-10-29 | 2013-11-07 | Commonwealth Scientific And Industrial Research Organisation | Real-time insect monitoring device |
| US20150085100A1 (en) * | 2013-09-26 | 2015-03-26 | Micholas Raschella | System for detection of animals and pests |
-
2015
- 2015-05-15 CN CN201510251109.7A patent/CN104918007B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050097021A1 (en) * | 2003-11-03 | 2005-05-05 | Martin Behr | Object analysis apparatus |
| US20130293710A1 (en) * | 2010-10-29 | 2013-11-07 | Commonwealth Scientific And Industrial Research Organisation | Real-time insect monitoring device |
| CN102239793A (en) * | 2011-04-18 | 2011-11-16 | 浙江大学 | Real-time classification method and system of rice pests |
| CN203243847U (en) * | 2013-04-18 | 2013-10-23 | 浙江托普仪器有限公司 | Automatic recognizing and counting device for lamplight trapping |
| CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
| CN103299969A (en) * | 2013-06-09 | 2013-09-18 | 浙江大学 | Pest trapping device and long-distance remote pest recognizing and monitoring system |
| US20150085100A1 (en) * | 2013-09-26 | 2015-03-26 | Micholas Raschella | System for detection of animals and pests |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107333098A (en) * | 2016-04-28 | 2017-11-07 | 浙江托普云农科技股份有限公司 | A kind of device for detecting and reporting pest information |
| CN107333731A (en) * | 2016-04-28 | 2017-11-10 | 浙江托普云农科技股份有限公司 | A kind of measuring and reporting system and its method filtered based on polypide with borer population and category identification |
| CN108782492A (en) * | 2018-05-18 | 2018-11-13 | 仲恺农业工程学院 | Pest control method based on pest control equipment |
| CN108782492B (en) * | 2018-05-18 | 2021-03-02 | 仲恺农业工程学院 | Pest control method based on pest control equipment |
| CN109118001A (en) * | 2018-08-09 | 2019-01-01 | 成都天地量子科技有限公司 | A kind of mountain fire monitoring method and system based on satellite remote sensing date |
| CN110122449A (en) * | 2019-05-29 | 2019-08-16 | 重庆工程职业技术学院 | Intelligent insecticidal lamp with artificial intelligence prediction pest |
| CN110122449B (en) * | 2019-05-29 | 2021-07-30 | 重庆工程职业技术学院 | Intelligent insecticidal lamp with artificial intelligence forecasts pest |
| CN110326593A (en) * | 2019-06-19 | 2019-10-15 | 仲恺农业工程学院 | Pest capture system, method, computer device, and medium |
| 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 |
| CN110235873B (en) * | 2019-06-26 | 2021-11-26 | 北京农业智能装备技术研究中心 | Automatic monitoring and forecasting system for insect pest situation of agricultural and forestry harmful insects |
| CN111202035A (en) * | 2019-09-17 | 2020-05-29 | 浙江农林大学暨阳学院 | Automatic pest collecting device and method for agriculture and forestry pest prediction |
| CN111011325A (en) * | 2019-12-04 | 2020-04-17 | 济南祥辰科技有限公司 | Image acquisition device and insect pest situation forecast lamp of two discernments of taking photograph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104918007B (en) | 2017-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104918007B (en) | Crop field insect pest situation monitoring sampling apparatus and the method for sampling based on computer vision | |
| CN103299969B (en) | Pest trapping device and long-distance remote pest recognizing and monitoring system | |
| CN110235873B (en) | Automatic monitoring and forecasting system for insect pest situation of agricultural and forestry harmful insects | |
| CN107711762A (en) | Intelligent Insect infestation monitoring method and intelligent Insect infestation monitoring device | |
| CN205390083U (en) | Intelligence plant diseases and insect pests monitoring and early warning system | |
| CN105941365A (en) | Automatic monitoring and prevention system for target pests | |
| CN206005625U (en) | A kind of Insect infestation monitoring device for fall webworms | |
| CN114201636A (en) | Forest pest disaster occurrence prediction method based on big data analysis | |
| CN104902228A (en) | Insect real-time monitoring device and method based on computer vision | |
| CN205567561U (en) | Pest situation lamp that can shoot automatically | |
| CN105454193A (en) | Insect collecting and capturing device | |
| CN113693041B (en) | Insect pest prevention and control device and method applied to pollution-free vegetables | |
| CN108462855A (en) | A kind of trapping lamp long-distance video monitoring system that can observe desinsection situation in real time | |
| CN114868714A (en) | Forestry plant diseases and insect pests monitoring system | |
| CN210642086U (en) | 5G solar energy formula insecticidal check out test set that shakes frequently | |
| CN212279561U (en) | Solar insect killing device for insect pest situation measurement and control | |
| CN111202035B (en) | Automatic pest collecting device and method for agriculture and forestry pest prediction | |
| CN116593461A (en) | Agricultural pest monitoring system and method based on artificial intelligence | |
| CN218389472U (en) | Orchard pest trapping and living body shooting recognition device | |
| CN115443960A (en) | Method and device based on live insect photographing identification | |
| KR102519804B1 (en) | Mosquito automatic analyzer with mesh-type electrode plate | |
| CN115024298B (en) | Counting insecticidal lamp based on lightweight neural network and counting method | |
| CN213074115U (en) | Agricultural insect trapping and catching device with periodic clearing function | |
| CN216533394U (en) | Insect pest situation observation and report lamp | |
| CN221152610U (en) | Intelligent remote insect pest killing and identifying integrated machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20150916 Assignee: Yongkang power Polytron Technologies Inc Assignor: Zhejiang University Contract record no.: 2018330000030 Denomination of invention: Computer vision-based large field pest situation monitoring sampling device and sampling method Granted publication date: 20171027 License type: Common License Record date: 20180328 |
|
| EE01 | Entry into force of recordation of patent licensing contract |