CN215494710U - Crop seedling phenotype inspection robot - Google Patents
Crop seedling phenotype inspection robot Download PDFInfo
- Publication number
- CN215494710U CN215494710U CN202122168007.2U CN202122168007U CN215494710U CN 215494710 U CN215494710 U CN 215494710U CN 202122168007 U CN202122168007 U CN 202122168007U CN 215494710 U CN215494710 U CN 215494710U
- Authority
- CN
- China
- Prior art keywords
- crop seedling
- module
- inspection robot
- steering engine
- phenotype
- 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.)
- Expired - Fee Related
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 21
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 11
- 235000011034 Rubus glaucus Nutrition 0.000 claims abstract description 11
- 235000009122 Rubus idaeus Nutrition 0.000 claims abstract description 11
- 230000007613 environmental effect Effects 0.000 claims abstract description 10
- 238000013016 damping Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 241000196324 Embryophyta Species 0.000 claims abstract description 5
- 238000010521 absorption reaction Methods 0.000 claims description 4
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims description 4
- 229910052782 aluminium Inorganic materials 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000033001 locomotion Effects 0.000 claims description 4
- 230000035939 shock Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009418 agronomic effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008654 plant damage Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Guiding Agricultural Machines (AREA)
Abstract
The utility model relates to a crop seedling phenotype inspection robot which comprises a crawler-type chassis, an image acquisition device and a crop seedling phenotype detection module. The crawler-type chassis comprises a damping structure, an STM32 control circuit, a raspberry pi 4B +, a driving device, a power device, a navigation module and an environmental information acquisition module; the navigation module consists of a laser tracking module and an ultrasonic module; the damping structure consists of a bearing, a stud, a fixing frame, a spring, a clamping groove and a track; the image acquisition device consists of a vertical rod, a horizontal rod, a steering engine, a RealSense depth camera and an RGB camera. The utility model uses the laser tracking module to realize routing inspection in the greenhouse according to the designated route, detects obstacles through the ultrasonic module, monitors road conditions through the RGB camera, acquires image information of different angles of greenhouse crops through the RealSense depth camera, collects environmental information such as temperature, humidity, light intensity and the like in real time, and sends crop seedling images to the computer end to calculate phenotypic parameters such as the number of leaves, the area, the plant height and the like.
Description
Technical Field
The utility model relates to the technical field of intelligent agricultural equipment, in particular to a crop seedling phenotype inspection robot.
Background
The traditional agronomic character measurement of crop seedlings adopts an artificial mode, and has the defects of low efficiency, strong subjectivity, poor repeatability, plant damage, incomplete measurement and the like. The crop phenotypic character quantitative determination based on computer vision overcomes the defects, and can analyze complete phenotypic parameters such as plant structure, form, color, texture and the like at one time. In order to realize automatic and high-flux phenotype measurement, an image acquisition assembly line is usually required to be built, and the mode requires manual feeding and discharging, so that the working strength is high, and the growth of crops is interfered. An image sensor carried by the robot is adopted to shoot the image of the in-situ growing crop seedling and calculate the phenotype parameters, so that the defect of the assembly line type detection can be effectively overcome. The robot has the advantages of automation, comprehensiveness, accuracy, low cost and the like, and is expected to become a powerful assistant for scientific research personnel.
Disclosure of Invention
Technical problem to be solved
In order to solve the problem of information acquisition of the existing agricultural intelligent greenhouse, the utility model aims to design a crop seedling phenotype inspection robot, which can realize automatic information acquisition under greenhouse conditions, realize intelligent regulation and control of greenhouse environment and detection of growth conditions of greenhouse crops, reduce manual operation and ensure normal operation of the greenhouse.
(II) technical scheme
The utility model provides the following technical scheme for solving the technical problem.
The utility model provides a robot is patrolled and examined to crop seedling phenotype which characterized in that: comprises a crawler-type chassis and an image acquisition device; the crawler-type chassis comprises a damping structure, an STM32 control circuit, a raspberry pi 4B +, a driving device, a power device, a navigation module and an environmental information acquisition module; the shock absorption structure consists of a bearing, a stud, a fixing frame, a spring, a clamping groove and a track, the STM32 control circuit is respectively connected with a raspberry pi 4B + and a driving device, and the driving device is further electrically connected with a power device for robot movement; the power device consists of two direct current speed reducing motors; the image acquisition device consists of a vertical rod, a transverse rod, a steering engine, a RealSense depth camera and an RGB camera, wherein the RGB camera is arranged in the middle of the vertical rod, and the steering engine is arranged on the transverse rod; a RealSense depth camera is arranged on the steering engine, the RealSense depth camera and the RGB camera are connected with a raspberry pie 4B +, and the steering engine is electrically connected with an STM32 control circuit.
Preferably, the environment information acquisition module comprises a light intensity sensor, a temperature and humidity sensor, an air quality sensor and a GPS; the environmental information acquisition module is connected with the STM32 control circuit, is arranged outside the chassis and is used for acquiring the current environmental condition and the position information.
Preferably, the navigation module consists of four laser tracking sensors and an ultrasonic sensor, is connected with an STM32 control circuit, is arranged in front of the chassis and is used for line walking navigation and obstacle avoidance.
Preferably, the bearing in the damping structure is connected with a fixed frame, the fixed frame is connected with a spring, and the spring is connected with a bolt on the side surface of the chassis; the track is supported by a bearing and is powered by a direct current speed reducing motor.
Preferably, the vertical rods and the crawler-type chassis are reinforced by four oblique 45-degree aluminum profiles, are connected with the cross rods by a 90-degree angle connector, and are reinforced by an oblique 45-degree aluminum profile.
Preferably, the RealSense depth camera is fixed on the steering engine, and the STM32 circuit adjusts the shooting angle of view of RealSense by controlling the steering engine to rotate.
Preferably, the crop seedling phenotype detection module consists of a high-performance computer, an image shot by the inspection robot is transmitted to a computer terminal through a TCP/IP protocol, phenotype data including leaf area, plant height, stem thickness, leaf number and leaf perimeter are measured by combining a three-dimensional reconstruction and deep learning technology, and the phenotype data are synchronized to a cloud server database.
(III) advantageous effects
Compared with the prior art, the utility model has the following technical advantages: the crawler-type chassis design is adopted, so that the greenhouse can adapt to different greenhouse environments; the damping structure composed of the bearing, the spring, the fixing frame and the like ensures that the inspection robot keeps the body stable when pressing the obstacle; the sensing capability of the environment is enhanced by adopting various environment information sensors; the RealSense depth camera is controlled by a steering engine, can acquire multi-view greenhouse crop image information and carries out all-dimensional monitoring on greenhouse crops; based on a TCP/IP protocol, pictures shot by the inspection robot are quickly transmitted to a computer terminal, and a series of crop seedling phenotype data are measured by combining a computer vision technology.
Drawings
Fig. 1 is an overall structural view of the present invention.
Wherein the reference numbers and the names of the corresponding parts are respectively 1-RealSense depth camera, 2-steering engine, 3-cross rod supporting rod, 4-cross rod, 5-vertical rod, 6-RGB camera, 7-vertical rod supporting rod, 8-upper cover plate, 9-crawler belt, 10-fixing frame, 11-bearing, 12-spring, 13-stud, 14-side plate, 15-DC speed reducing motor, 16-ship type switch, 17-clamping groove, 18-laser tracking module and 19-ultrasonic sensor
Detailed Description
The utility model provides a crop seedling phenotype inspection robot for solving the technical problem. The technical scheme of the utility model is further concretely explained by the specific implementation mode through combining with a plurality of figures in the specification.
As shown in fig. 1, a crop seedling phenotype inspection robot comprises a crawler-type chassis and an image acquisition device; the crawler-type chassis comprises a damping structure, an STM32 control circuit, a raspberry pi 4B +, a driving device, a power device, a navigation module and an environmental information acquisition module; the shock absorption structure consists of a crawler 9, a fixing frame 10, a bearing 11, a spring 12, a stud 13 and a clamping groove 17, the STM32 control circuit is respectively connected with a raspberry pi 4B + and a driving device, and the driving device is further electrically connected with a power device for robot movement; the power device consists of two direct current speed reducing motors 15; the image acquisition device consists of a RealSense depth camera 1, a steering engine 2, a cross rod 4, a vertical rod 5 and an RGB camera 6, wherein the RGB camera is arranged in the middle of the vertical rod, and the steering engine is arranged on the cross rod; a RealSense depth camera is arranged on the steering engine, the RealSense depth camera and the RGB camera are connected with a raspberry pie 4B +, and the steering engine is electrically connected with an STM32 control circuit.
The navigation module consists of four laser tracking sensors 18 and an ultrasonic sensor 19, is connected with an STM32 control circuit and is arranged in front of the chassis. The laser tracking sensor is used for detecting laid black lines, and an STM32 control circuit makes a motion decision to ensure that the inspection robot walks along the black lines; when the ultrasonic sensor detects a front obstacle, the STM32 control circuit controls the driving device to stop the robot according to the level change.
The bearing 11 in the damping structure is connected with a fixed frame 10 and sleeved on a stud 13, the fixed frame is connected with a spring 12, and the spring is connected on a bolt on the side surface of the chassis; the caterpillar band 9 is supported by a bearing and is powered by a direct current speed reducing motor 15. When the robot presses an obstacle, the bearing 11 moves upwards to drive the fixed frame 10 to extend the spring 12, so that the chassis is prevented from inclining; after the obstacle is crossed, the fixed frame 10 and the bearing 11 are restored to the original positions under the action of the elastic force of the spring.
The vertical rod 5 and the crawler-type chassis are reinforced by four oblique 45-degree aluminum profiles 7, are connected with the cross rod 4 by a 90-degree angle code, and are reinforced by an oblique 45-degree profile 3, so that the image acquisition device is kept stable in the running process of the robot.
The RealSense depth camera 1 is fixed on the steering engine 2, and the STM32 circuit adjusts the shooting angle of RealSense through controlling the steering engine rotation, obtains the crop picture information of different visual angles, carries out picture save and transmission by raspberry group 4B +. The crop seedling phenotype detection module receives picture information sent by the inspection robot, measures phenotype data including leaf area, plant height, stem thickness, leaf number and leaf perimeter through three-dimensional reconstruction and deep learning technology, and synchronizes to the cloud server database.
The embodiments described in this application are only intended to illustrate the main idea of the utility model. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the utility model as defined in the appended claims.
Claims (7)
1. The utility model provides a robot is patrolled and examined to crop seedling phenotype which characterized in that: comprises a crawler-type chassis and an image acquisition device; the crawler-type chassis comprises a damping structure, an STM32 control circuit, a raspberry pi 4B +, a driving device, a power device, a navigation module and an environmental information acquisition module; the shock absorption structure consists of a bearing, a stud, a fixing frame, a spring, a clamping groove and a track, the STM32 control circuit is respectively connected with a raspberry pi 4B + and a driving device, and the driving device is further electrically connected with a power device for robot movement; the power device consists of two direct current speed reducing motors; the image acquisition device consists of a vertical rod, a transverse rod, a steering engine, a RealSense depth camera and an RGB camera, wherein the RGB camera is arranged in the middle of the vertical rod, and the steering engine is arranged on the transverse rod; a RealSense depth camera is arranged on the steering engine, the RealSense depth camera and the RGB camera are connected with a raspberry pie 4B +, and the steering engine is electrically connected with an STM32 control circuit.
2. The crop seedling phenotype inspection robot according to claim 1, wherein the environmental information collection module includes a light intensity sensor, a temperature and humidity sensor, an air quality sensor and a GPS; the environmental information acquisition module is connected with the STM32 control circuit, is arranged outside the chassis and is used for acquiring the current environmental condition and the position information.
3. The crop seedling phenotype inspection robot according to claim 1, wherein the navigation module consists of four laser tracking sensors and an ultrasonic sensor, is connected with an STM32 control circuit, is arranged in front of the chassis, and is used for line inspection navigation and obstacle avoidance.
4. The crop seedling phenotype inspection robot according to claim 1, wherein a bearing in the shock absorption structure is connected with a fixed frame, the fixed frame is connected with a spring, and the spring is connected to a bolt on the side face of the chassis; the track is supported by a bearing and is powered by a direct current speed reducing motor.
5. The crop seedling phenotype inspection robot according to claim 1, wherein the vertical rods and the crawler-type chassis are reinforced by four oblique 45-degree aluminum profiles, are connected with the cross rods by a 90-degree angle code, and are reinforced by an oblique 45-degree profile.
6. The crop seedling phenotype inspection robot according to claim 1, wherein the RealSense depth camera is fixed to a steering engine, and an STM32 circuit adjusts the shooting angle of RealSense by controlling the steering engine to rotate.
7. The crop seedling phenotype inspection robot according to claim 1, wherein the crop seedling phenotype detection module is composed of a high-performance computer, images shot by the inspection robot are transmitted to a computer end through a TCP/IP protocol, phenotype data including leaf area, plant height, stem thickness, leaf number and leaf perimeter are measured by combining a three-dimensional reconstruction and deep learning technology, and are synchronized to a cloud server database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202122168007.2U CN215494710U (en) | 2021-09-02 | 2021-09-02 | Crop seedling phenotype inspection robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202122168007.2U CN215494710U (en) | 2021-09-02 | 2021-09-02 | Crop seedling phenotype inspection robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN215494710U true CN215494710U (en) | 2022-01-11 |
Family
ID=79768586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202122168007.2U Expired - Fee Related CN215494710U (en) | 2021-09-02 | 2021-09-02 | Crop seedling phenotype inspection robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN215494710U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115061168A (en) * | 2022-06-27 | 2022-09-16 | 安徽农业大学 | Mobile inspection type crop growth monitoring system and method |
-
2021
- 2021-09-02 CN CN202122168007.2U patent/CN215494710U/en not_active Expired - Fee Related
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115061168A (en) * | 2022-06-27 | 2022-09-16 | 安徽农业大学 | Mobile inspection type crop growth monitoring system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109773788B (en) | Fruit and vegetable picking robot and control method thereof | |
US11397174B2 (en) | Suspension slide rail platform-based greenhouse information automatic monitoring method | |
KR101547560B1 (en) | Management control system for growing plants using moving robot based on image processing | |
CN107486834B (en) | Greenhouse crop growth inspection robot | |
CN109526441A (en) | A kind of topping machine | |
CN103699095A (en) | Greenhouse plant growth posture monitoring system based on binocular stereo vision and greenhouse plant growth posture monitoring method based on binocular stereo vision | |
CN111633660A (en) | Intelligent inspection robot | |
CN215494710U (en) | Crop seedling phenotype inspection robot | |
CN108279678A (en) | A kind of field automatic travelling device and its ambulation control method for detecting plant growth condition | |
CN114080905A (en) | Picking method based on digital twins and cloud picking robot system | |
CN109494617A (en) | One kind is removed obstacles crusing robot and its method of removing obstacles | |
CN114355942B (en) | Plant inspection robot | |
CN113965727A (en) | Plant growth full-period-oriented mobile phenotype information acquisition platform and method | |
CN209343202U (en) | A kind of agricultural environment information collection trolley | |
CN115407771A (en) | Crop monitoring method, system and device based on machine vision | |
CN116117807A (en) | Chilli picking robot and control method | |
CN113114766B (en) | Potted plant information detection method based on ZED camera | |
CN114931112B (en) | Sow body ruler detection system based on intelligent inspection robot | |
CN114290313B (en) | Inspection robot, automatic navigation inspection robot system and control method | |
CN113498639B (en) | Weeding device and weeding method | |
CN114012758A (en) | Novel aquaculture water environment intelligent monitoring robot | |
CN104503468B (en) | A kind of heliogreenhouse surrounding three-dimensional stereoscopic monitoring and Image-forming instrument | |
CN220180924U (en) | Cross-ridge type detection trolley | |
CN115119644B (en) | Field management device based on bionic travelling mechanism | |
CN220384096U (en) | Laser weeding is mirror system that shakes for robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220111 |