Remote sensing monitoring equipment for tropical crop planting
By using multiple band sensors and data processing modules in tropical crop monitoring equipment, the biometric remote sensing group is constructed, which solves the problem of image distortion in existing equipment when light changes, and improves monitoring accuracy and energy efficiency by optimizing the flight path of the drone.
Patent Information
- Application Number
- CN202510144505.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-10
- Publication Date
- 2025-05-13
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing tropical crop monitoring equipment has distorted images when the light intensity changes, which affects the accuracy of the detection results. At the same time, the long flight time of the drone leads to large energy consumption and affects the motor life.
A remote sensing monitoring equipment for tropical crop planting is designed, including remote sensing drones and ground operation stations. The remote sensing drones are loaded with red light bands, near-infrared bands and vision sensors. Data connections, data processing and path planning modules are installed in the ground operation station. Through the multi-spectral drone image splicing and the construction of biometric remote sensing groups, the coverage, health, growth conditions and chlorophyll content of tropical crops can be monitored.
The equipment can quickly and accurately monitor the growth status and chlorophyll content of tropical crops, reduce the impact of light, improve the accuracy of detection results, and save energy and extend the service life of the drone motor by optimizing the flight path of the drone.
Smart Images
Figure CN119985335A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of remote sensing monitoring equipment, in particular to remote sensing monitoring equipment for tropical crop planting. Background Art
[0002] Tropical crops refer to special cash crops planted in tropical areas. These crops usually require high temperature and high humidity environmental conditions, have a long growing season, a wide variety of species and varieties, are tropical, and have perennial habits. They are usually produced in plantations, planted once and harvested for many years, but there is a long non-production period in the early stage. The world's tropical crops are mainly distributed in South Asia, Southeast Asia, Africa (except North Africa and parts of South Africa), Latin America (except Argentina and most of Chile) and Oceania (except central and southern Australia and New Zealand). In China, tropical crops are mainly distributed in Hainan and parts of Guangdong, Guangxi, Yunnan, Fujian, Hunan, Sichuan, Guizhou, Tibet, and Taiwan. Among them, Hainan Island and Xishuangbanna are the most suitable areas for the growth of tropical crops.
[0003] Currently, monitoring of tropical crops is usually carried out using drones equipped with high-definition cameras. However, the cameras are easily affected by the light intensity in the shooting environment, causing image deformation and distortion, which in turn affects the accuracy of the drone's detection results. At the same time, during use, the longer the drone flies, the more energy it needs to carry, and carrying a large load will affect the life of the drone's motor. Summary of the invention
[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a remote sensing monitoring device for tropical crop planting to solve the problems existing in the above-mentioned background technology.
[0005] The present invention provides the following technical solution: a remote sensing monitoring device for tropical crop planting, comprising a remote sensing unmanned aerial vehicle and a ground operating station, characterized in that: the remote sensing unmanned aerial vehicle is arranged on the top of the ground operating station, and the remote sensing unmanned aerial vehicle is loaded with a remote sensing monitoring sensor component, including a red light band sensor, a near infrared band sensor and a visual sensor, the visual sensor is arranged at the top position of the remote sensing unmanned aerial vehicle, and the red light band sensor and the near infrared band sensor are arranged at the bottom center position of the remote sensing unmanned aerial vehicle, the remote sensing monitoring sensor component is used to monitor the coverage, health status, growth status and chlorophyll content of tropical crops, the ground operating station is internally provided with a data connection module, a data processing module and a path planning module, the data connection module is used for timely transmission and reception of data between the remote sensing unmanned aerial vehicle and the ground operating station, the data processing module is used for analyzing and processing data information of the remote sensing monitoring sensor component, and then constructing a biological feature remote sensing group, and the path planning module automatically plans the operation path of the unmanned aerial vehicle for the identified planting area, thereby achieving growth monitoring of tropical crops.
[0006] Furthermore, the sensitive band of the red light band sensor used is 660nm±26nm, the sensitive band of the near-infrared band sensor used is 820nm±26nm, and the visual sensor used is a CCD sensor. In vegetation remote sensing, the red light band is often used to evaluate the chlorophyll content and growth status of vegetation. Chlorophyll is a key pigment for photosynthesis in plants. It has strong absorption characteristics in the red light band. By monitoring the reflectivity changes in the red light band, the growth status and chlorophyll content of vegetation can be indirectly understood. The cell structure and water content inside the leaves of vegetation strongly reflect near-infrared light. The near-infrared band is often used to evaluate the coverage, biomass and health of vegetation.
[0007] Furthermore, after receiving the image data acquired by the remote sensing UAV, the data processing module performs radiation correction, atmospheric correction and geometric correction on the acquired remote sensing image data, and adopts a multispectral UAV image stitching method based on RANSAC to obtain remote sensing images of tropical crop sample fields. Thereafter, the remote sensing images of tropical crop sample fields are analyzed based on the biological characteristics of tropical crops and current phenological conditions to construct a biological characteristic remote sensing group.
[0008] Furthermore, the biometric remote sensing group includes the normalized difference vegetation index (NDVI), the ratio vegetation index (RVI), the difference environmental index (DVI), texture features and morphological features. The calculation formula of the normalized difference vegetation index (NDVI) is NDVI=(NIR-RED) / (NIR+RED), the calculation formula of the ratio vegetation index (RVI) is RVI=NIR / RED, the calculation formula of the difference environmental index (DVI) is DVI=NIR-RED, the texture features include canopy structure and leaf morphology, and the morphological features include plant height and crown width. The generated NDVI, RVI and DVI image maps are visualized and analyzed to understand the vegetation coverage, growth status and ecological environment changes.
[0009] Furthermore, the data processing module uses correlation analysis technology on the biological feature remote sensing group to analyze the correlation between different crops and different features, eliminates redundant features with high correlation, reduces the dimension of the feature set, and uses a machine learning algorithm - random forest to evaluate the importance of features. According to the crop growth cycle, the remote sensing image data is labeled with classification labels from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal, and an image feature set from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal of tropical crops is constructed. At the same time, a recurrent neural network (RNN) model is constructed, and the model is trained using the constructed image feature set to obtain a classification model. The classification model can be used to quickly determine the type and status of the currently scanned plant when used.
[0010] Furthermore, the data processing module uses QGIS (Quantum GIS) to stitch and crop the collected remote sensing images to obtain a complete image map of the patrol area, and at the same time, it outlines and classifies the plots on the image map to distinguish different crop planting areas.
[0011] Furthermore, after the data processing module obtains the complete patrol area image map, the path planning module performs rasterization processing on the patrol area. The grid is divided into a large grid and a small grid. The large grid is the same size as the inscribed square of the sensor sensing range in the remote sensing monitoring sensor assembly at the normal patrol height of the remote sensing UAV. The size of the small grid is one-ninth or one-sixteenth of the large grid and is distributed inside the large grid at the edge of the planting area. Then, according to the results of the rasterization processing, the actual crop planting area can be accurately located through the large and small grids. At the same time, the edge position can also be used when formulating the flight route, and the area of each crop planting area is calculated using QGIS (Quantum GIS).
[0012] Furthermore, the path planning module can also plan the motion path of the remote sensing UAV based on the results of rasterization processing, splice each grid with a random adjacent grid, connect the center points of the spliced grids, and form several lines from these points. The Dijkstra algorithm is used to select two different routes in the optimal solution of the path between the patrol starting point and the patrol end point, one for the patrol route and one for the return route. Round-trip scanning and taking different routes can improve the accuracy of the scanning results, and enable the remote sensing UAV to scan tropical crops in all planting areas with the most reasonable flight route, which is conducive to saving energy, thereby reducing the load of the UAV and increasing the service life of the UAV motor.
[0013] Beneficial effects:
[0014] 1. The remote sensing monitoring equipment for tropical crop planting is provided with a remote sensing monitoring sensor component and a data processing module. The actual crop image data is obtained through the remote sensing monitoring sensor component, and the data processing module is used to process the data, stitch the images and analyze the data, thereby constructing a biometric remote sensing group. During use, the current growth period and growth status of the crop can be quickly understood, which is convenient for maintenance and management. The scanning results are not easily affected by light, and the scanning results are more accurate than those of high-definition cameras.
[0015] 2. The remote sensing monitoring equipment for tropical crop planting is equipped with a path planning module, which can automatically plan the UAV operation path for the identified planting area, and enable the remote sensing UAV to scan the tropical crops in all planting areas with the most reasonable flight route, which is conducive to saving energy, thereby reducing the load of the UAV and increasing the service life of the UAV motor. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a schematic diagram of the structure of a remote sensing monitoring device for tropical crop planting proposed by the present invention;
[0017] Figure 2 This is a module structure diagram of a remote sensing monitoring device for tropical crop planting proposed by the present invention.
[0018] In the picture: 1. Remote sensing drone; 2. Ground operation station. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] Embodiment 1
[0021] See also Figure 1-Figure 2 A remote sensing monitoring device for tropical crop planting includes a remote sensing UAV 1 and a ground operating station 2, characterized in that: the remote sensing UAV 1 is arranged on the top of the ground operating station 2, and the remote sensing UAV 1 is loaded with a remote sensing monitoring sensor component, including a red light band sensor, a near infrared band sensor and a visual sensor, the visual sensor is arranged at the top position of the remote sensing UAV 1, and the red light band sensor and the near infrared band sensor are arranged at the bottom center position of the remote sensing UAV 1, and the remote sensing monitoring sensor component is used to monitor the coverage, health status, growth status and chlorophyll content of tropical crops, and the ground operating station 2 is internally provided with a data connection module, a data processing module and a path planning module, the data connection module is used for timely transmission and reception of data between the remote sensing UAV 1 and the ground operating station 2, the data processing module is used for analyzing and processing the data information of the remote sensing monitoring sensor component, and then constructing a biometric remote sensing group, and the path planning module automatically plans the UAV operation path for the identified planting area, so as to achieve growth monitoring of tropical crops.
[0022] The red light band sensor used has a sensitive band of 660nm±26nm, the near-infrared band sensor used has a sensitive band of 820nm±26nm, and the visual sensor used is a CCD sensor. In vegetation remote sensing, the red light band is often used to evaluate the chlorophyll content and growth status of vegetation. Chlorophyll is a key pigment for photosynthesis in plants. It has strong absorption characteristics in the red light band. By monitoring the reflectivity changes in the red light band, we can indirectly understand the growth status and chlorophyll content of vegetation. The cell structure and water content inside the leaves of vegetation strongly reflect near-infrared light. The near-infrared band is often used to evaluate the coverage, biomass and health of vegetation.
[0023] After receiving the image data acquired by the remote sensing UAV 1, the data processing module performs radiation correction, atmospheric correction and geometric correction on the acquired remote sensing image data, and adopts a multispectral UAV image stitching method based on RANSAC to obtain remote sensing images of tropical crop sample fields. Then, the remote sensing images of tropical crop sample fields are analyzed based on the biological characteristics of tropical crops and current phenological conditions to construct a biological characteristic remote sensing group.
[0024] The biological characteristic remote sensing group includes the normalized difference vegetation index (NDVI), the ratio vegetation index (RVI), the difference environmental index (DVI), texture characteristics and morphological characteristics. The calculation formula of the normalized difference vegetation index (NDVI) is NDVI = (NIR-RED) / (NIR+RED), the calculation formula of the ratio vegetation index (RVI) is RVI = NIR / RED, and the calculation formula of the difference environmental index (DVI) is DVI = NIR-RED. The texture characteristics include canopy structure and leaf morphology, and the morphological characteristics include plant height and crown width. The generated NDVI, RVI and DVI image maps are visualized and analyzed to understand the vegetation coverage, growth status and ecological environment changes.
[0025] The data processing module uses correlation analysis technology on the biological feature remote sensing group to analyze the correlation between different crops and different features, eliminate redundant features with high correlation, reduce the dimension of the feature set, and use the machine learning algorithm - random forest to evaluate the importance of features. According to the crop growth cycle, the remote sensing image data is labeled with classification labels from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal, and an image feature set of tropical crops from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal is constructed. At the same time, a recurrent neural network (RNN) model is constructed, and the model is trained using the constructed image feature set to obtain a classification model. The classification model can be used to quickly determine the type and status of the currently scanned plant when used.
[0026] Embodiment 2
[0027] See also Figure 1-Figure 2,The data processing module uses QGIS (Quantum GIS) to stitch and crop the collected remote sensing images to obtain a complete ,image map of the patrol area, and at the same time plots are delineated and ,classified on the image map to distinguish different crop planting areas.
[0028] After the data processing module obtains the complete patrol area image map, the path planning module rasterizes the patrol area. The grid is divided into a large grid and a small grid. The large grid is the same size as the inscribed square of the sensor sensing range in the remote sensing monitoring sensor assembly of the remote sensing UAV 1 at the normal patrol height. The size of the small grid is one-ninth or one-sixteenth of the large grid and is distributed inside the large grid at the edge of the planting area. Then, according to the results of the rasterization processing, the actual crop planting area can be accurately located through the large and small grids. At the same time, the edge position can also be used when formulating the flight route. The area of each crop planting area is calculated using QGIS (Quantum GIS).
[0029] The path planning module can also plan the motion path of the remote sensing UAV 1 according to the results of rasterization processing, splice each grid with a random adjacent grid, connect the center points of the spliced grids, and form several lines from these points. The Dijkstra algorithm is used to select two different routes from the optimal solution of the path between the patrol starting point and the patrol end point, one for the patrol route and one for the return route. Round-trip scanning and taking different routes can improve the accuracy of the scanning results, and enable the remote sensing UAV 1 to scan tropical crops in all planting areas with the most reasonable flight route, which is conducive to saving energy, thereby reducing the load of the UAV and increasing the service life of the UAV's motor.
[0030] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A remote sensing monitoring device for tropical crop planting, comprising a remote sensing drone (1) and a ground operating station (2), characterized in that: The remote sensing drone (1) is arranged on the top of the ground operating station (2). The remote sensing drone (1) is equipped with a remote sensing monitoring sensor assembly, including a red light band sensor, a near infrared band sensor and a visual sensor. The visual sensor is arranged at the top of the remote sensing drone (1). The red light band sensor and the near infrared band sensor are arranged at the bottom center of the remote sensing drone (1). The remote sensing monitoring sensor assembly is used to monitor the coverage, health status, growth status and chlorophyll content of tropical crops. The ground operating station (2) is internally provided with a data connection module, a data processing module and a path planning module. The data connection module is used for timely transmission and reception of data between the remote sensing drone (1) and the ground operating station (2). The data processing module is used for analyzing and processing data information of the remote sensing monitoring sensor assembly, thereby constructing a biometric remote sensing group. The path planning module automatically plans the drone operation path for the identified planting area, thereby achieving growth monitoring of tropical crops.
2. A remote sensing monitoring device for tropical crop planting according to claim 1, characterized in that: The sensitive band of the red light band sensor used is 660nm±26nm, the sensitive band of the near infrared band sensor used is 820nm±26nm, and the visual sensor used is a CCD sensor.
3. A remote sensing monitoring device for tropical crop planting according to claim 1, characterized in that: After receiving the image data acquired by the remote sensing UAV (1), the data processing module performs radiation correction, atmospheric correction and geometric correction on the acquired remote sensing image data, adopts a multispectral UAV image stitching method based on RANSAC, obtains remote sensing images of tropical crop sample fields, and then analyzes the remote sensing images of tropical crop sample fields based on the biological characteristics of tropical crops and current phenological conditions, and constructs a biological characteristic remote sensing group.
4. A remote sensing monitoring device for tropical crop planting according to claim 3, characterized in that: The biological characteristic remote sensing group includes the normalized difference vegetation index (NDVI), the ratio vegetation index (RVI), the difference environmental index (DVI), texture characteristics and morphological characteristics. The calculation formula of the normalized difference vegetation index (NDVI) is NDVI=(NIR-RED) / (NIR+RED), the calculation formula of the ratio vegetation index (RVI) is RVI=NIR / RED, the calculation formula of the difference environmental index (DVI) is DVI=NIR-RED, the texture characteristics include canopy structure and leaf morphology, and the morphological characteristics include plant height and crown width.
5. A remote sensing monitoring device for tropical crop planting according to claim 4, characterized in that: The data processing module uses correlation analysis technology on the biological feature remote sensing group to analyze the correlation between different crops and different features, eliminates redundant features with high correlation, reduces the dimension of the feature set, and uses a machine learning algorithm - random forest to evaluate the importance of features. According to the crop growth cycle, the remote sensing image data is labeled with classification labels from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal, and an image feature set from seed germination, seedling growth, vegetative growth, maturity, flowering and fruiting to aging and renewal of tropical crops is constructed. At the same time, a recurrent neural network (RNN) model is constructed, and the model is trained using the constructed image feature set to obtain a classification model.
6. A remote sensing monitoring device for tropical crop planting according to claim 5, characterized in that: The data processing module uses QGIS (Quantum GIS) to stitch and crop the collected remote sensing images to obtain a complete image map of the patrol area, and at the same time, it delineates and classifies plots on the image map to distinguish different crop planting areas.
7. A remote sensing monitoring device for tropical crop planting according to claim 6, characterized in that: After the data processing module obtains the complete patrol area image map, the path planning module performs raster processing on the patrol area, and the raster is divided into a large raster and a small raster. The large raster is the same size as the inscribed square of the sensor sensing range in the remote sensing monitoring sensor assembly of the remote sensing unmanned aerial vehicle (1) at a normal patrol height. The small raster is one-ninth or one-sixteenth the size of the large raster and is distributed inside the large raster at the edge of the planting area. Then, according to the raster processing result, the area of each crop planting area is calculated using QGIS (Quantum GIS).
8. A remote sensing monitoring device for tropical crop planting according to claim 7, characterized in that: The path planning module can also plan the motion path of the remote sensing drone (1) based on the result of the rasterization processing, splicing each grid with a random grid on its adjacent side, connecting the center points of the spliced grids, and forming a number of routes from these points. The Dijkstra algorithm is used to select two different routes from the optimal solution of the path between the patrol start point and the patrol end point, one for the patrol route and one for the return route.