Lattice field flatness detection system and method based on unmanned aerial vehicle laser fusion image

Abstract

The invention discloses a lattice field flatness detection system and method based on an unmanned aerial vehicle laser fusion image, and relates to the technical field of flatness detection, and the system comprises a laser array detector, a CMOS image sensor, a positioning system, an embedded microcontroller, a storage chip, a power circuit, and a multi-rotor unmanned aerial vehicle system. The method specifically comprises the following steps: controlling a laser array to emit a detection light signal underwater through an embedded microcontroller, and synchronously controlling a CMOS image sensor to collect a water layer image under laser detection; and an embedded microcontroller is used for carrying out storage, preprocessing, threshold segmentation, morphological processing, light pillar detection and length calculation on the image data to obtain flatness data of the grid field mud surface after water soil preparation. Therefore, by the adoption of the lattice field flatness detection system and method based on the unmanned aerial vehicle laser fusion image, flatness data can be obtained through the underwater imaging light beam, the principle is clear, calculation is simple, and processing and calculation can be conveniently carried out in an edge terminal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of flatness detection, in particular to a check dam flatness detection system and method based on unmanned aerial vehicle laser fusion image. BACKGROUND

[0002] China is a big agricultural country, and rice is an important crop in China. During the growth of rice in the field, irrigation, fertilization, mechanized operation and pest control all have certain requirements for the flatness of the check dam, and it is of great significance to obtain accurate check dam flatness data, especially the flatness detection of the check dam after the water leveling mud is deposited.

[0003] At present, in the check dam flatness detection method, the manual measurement method using the wire drawing method and the level instrument has low precision, is time-consuming and laborious, has large workload and low efficiency, and is not suitable for large-area check dam measurement; the unmanned aerial vehicle carrying a multispectral camera measures the flatness by height, which is greatly affected by the resolution of the sensor and the shooting conditions, and the price is high, and the precision is difficult to guarantee; the measurement range of the measurement method using ultrasonic waves to measure the flatness is limited, and it is easy to be disturbed by the external environment.

[0004] Considering that there is a lot of water in the rice check dam after the water leveling mud is deposited, and the mud is hidden under the water surface after deposition, which brings certain difficulty to the flatness detection, the present application provides a check dam flatness detection method based on unmanned aerial vehicle laser fusion image, which emits laser from the laser array to the check dam. After the laser meets the water layer, different lengths of light columns or light spots will be formed according to the different depths of the water layer, the detection imaging of the laser irradiated to the water surface is photographed in real time by the image sensor, the water layer depth is judged by the length of the laser column in the image, and the flatness of the mud surface under the water is obtained. According to the obtained flatness data, the GPS coordinates and flatness data are provided by combining the airborne GPS sensor, and the flatness heat map is drawn based on the above data relying on ArcGIS, so as to improve the flatness detection accuracy and digital level of the check dam after the water leveling mud is deposited. SUMMARY

[0005] The purpose of the present application is to provide a check dam flatness detection system and method based on unmanned aerial vehicle laser fusion image, which can calculate the flatness data by underwater imaging light column, is suitable for flatness detection of check dam mud surface after water leveling, and has simple calculation and low cost.

[0006] To achieve the above purpose, the present application provides a check dam flatness detection method based on unmanned aerial vehicle laser fusion image, comprising the following steps: S1, control the laser array to emit laser once every 3 seconds by the embedded microcontroller, emit detection light signal to underwater, and control the CMOS image sensor to collect water layer image under laser detection at the same time; S2, using an embedded microcontroller to store, preprocess, threshold segmentation, morphological processing, light column detection and length calculation of image data, get the flatness data of the grid field mud surface after water leveling, and generate a heat map.

[0007] Further, in S2, the preprocessing includes filtering the collected image data to remove noise from the image.

[0008] Further, in S2, the threshold segmentation includes selecting a corresponding threshold value for image segmentation based on the color characteristics of the light column in the HSV color space to obtain a binary image containing the light column.

[0009] Further, in S2, the morphological processing includes morphological erosion and dilation operations, which remove isolated noise points through morphological erosion operations, and restore the original shape of the light column through dilation operations to make the light column area continuous.

[0010] Further, in S2, the light column detection and length calculation includes contour detection and length calculation; Contour detection includes obtaining the light column contour based on the binary image through a corresponding algorithm; Length calculation includes calculating the number of corresponding pixel points for each light column contour and converting it to the actual light column length, and then converting the light column length to the light column depth according to the detection angle of the laser, and then obtaining the flatness data of the grid field mud surface.

[0011] The application also provides a grid field flatness detection system based on unmanned aerial vehicle laser fusion image, which comprises a laser array detector, a CMOS image sensor, a positioning system, an embedded microcontroller, a storage chip, a power circuit, and a multi-rotor unmanned aerial vehicle system. The laser array detector is arranged below the unmanned aerial vehicle and is at a 30° angle with the unmanned aerial vehicle plane, and is used to emit laser to the grid field water surface; The CMOS image sensor is arranged at the bottom of the unmanned aerial vehicle and is placed downward, parallel to the unmanned aerial vehicle, and is used to detect the imaging of the laser under the water surface; The positioning system is placed on the unmanned aerial vehicle frame and corresponds to the CMOS image sensor up and down, and is used to detect the current latitude and longitude information; The embedded microcontroller is placed on the unmanned aerial vehicle, and is used to control the laser emission, receive the data collected by the CMOS image sensor, image preprocessing, image threshold segmentation, image morphological processing, light column detection and length calculation, positioning and flatness data storage; The storage chip is connected with the embedded microcontroller, and is used to store the GPS positioning data and the flatness data; The power circuit supplies power to the unmanned aerial vehicle and the detection system; The multi-rotor unmanned aerial vehicle system comprises an unmanned aerial vehicle frame system, an unmanned aerial vehicle power system, an unmanned aerial vehicle flight control system and an unmanned aerial vehicle remote control device, and realizes constant speed cruising through trajectory planning.

[0012] Further, the laser array detector alternative solution includes using a green laser array, and the interval between each laser source is 2cm.

[0013] Further, the power supply circuit alternative solution includes being powered by a lithium battery.

[0014] Therefore, the above-mentioned paddy field flatness detection system and method based on unmanned aerial vehicle laser fusion image have the following technical effects: (1) The detection method principle is clear, the system is simple, and the calculation is easy: since the underwater imaging light column length under the fixed angle of laser inclination is linearly related to the water depth, the flatness data calculated by the method is easy to calculate, and is convenient for processing and calculation in the edge terminal; (2) The detection method has high measurement accuracy: since the basic data for flatness calculation comes from the underwater light column length of the laser, and the length is collected by a high-definition CMOS image sensor, in the calculation process, noise interference removal and other technical means are considered, and the calculation principle is clear, so that the flatness data can be better calculated, and the accuracy is higher; (3) The system is easy to install and maintain: since the sensor is small, the unmanned aerial vehicle does not need to be disassembled and greatly modified, and is convenient for installation, wiring and unloading, and the power supply comes from the on-board battery of the unmanned aerial vehicle, all devices consider waterproof performance, and maintenance is convenient; (4) The laser device, image sensor device, storage chip, microcontroller and other technologies used in the application are mature, low in price, and the system cost is not high.

[0015] The technical solutions of the application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a flowchart of the paddy field flatness detection method based on unmanned aerial vehicle laser fusion image; Figure 2 is a frame schematic diagram of the paddy field flatness detection system based on unmanned aerial vehicle laser fusion image. DETAILED DESCRIPTION

[0017] The application can be explained in more detail through the following examples, and the purpose of disclosing the application is to protect all changes and improvements within the scope of the application, and the application is not limited to the following examples.

[0018] The application provides a check method for the flatness of a check dam based on a laser fusion image of a UAV, and uses a check system for the flatness of a check dam based on a laser fusion image of a UAV, which mainly comprises a laser array detector, a CMOS image sensor, a positioning system, an embedded microcontroller, a storage chip, a power supply circuit, a multi-rotor UAV system and the like, as shown in Figure 2 . .

[0019] The laser array detector is a 16 green laser array, the distance between each laser source is 2 cm, is placed below the UAV, and is at a 30° angle with the plane of the UAV, and is used for emitting green laser to the water surface of the check dam. .

[0020] The CMOS image sensor is placed at the bottom of the UAV and is placed downward and parallel to the UAV, and is used for detecting the imaging of the laser under the water surface. .

[0021] The positioning system is placed on the UAV frame and corresponds to the CMOS image sensor, and is used for detecting the current longitude and latitude information. .

[0022] The embedded microcontroller is placed on the UAV, and is used for controlling the laser emission, receiving the data collected by the CMOS image sensor, image preprocessing, image threshold segmentation, image morphological processing, light column detection and length calculation, positioning and flatness data storage. .

[0023] The storage chip is connected with the embedded microcontroller, and is mainly used for storing the GPS positioning data and the flatness data. .

[0024] The power supply circuit is mainly a lithium battery, which is used for supplying power for the UAV and the detection system. .

[0025] The multi-rotor UAV system comprises a UAV frame system, a UAV power system, a UAV flight control system, a UAV remote control device and the like, and can realize constant speed cruising through trajectory planning. .

[0026] As shown in Figure 1 , the check method for the flatness of a check dam based on a laser fusion image of a UAV comprises the following specific steps: S1, the embedded microcontroller is used for controlling the laser array to emit laser once every 3 seconds to emit a detection light signal under the water. Since the laser emission surface is at a 60° angle with the water surface, after contacting the water surface, a light column with different lengths is formed under the water according to different depths. At this time, the CMOS image sensor is synchronously controlled to collect the water layer image under the laser detection. .

[0027] S2, the embedded microcontroller is used for storing, preprocessing, threshold segmentation, morphological processing, light column detection and length calculation of the image data. .

[0028] The image preprocessing includes filtering the collected image, removing noise in the image through median filtering and Gaussian filtering, and avoiding the influence of noise on the light column detection and length calculation.

[0029] The image threshold segmentation is to segment the green part in the image according to the color feature of the green light column, and the specific steps are as follows: first, the image is converted from the RGB color space to the HSV color space; then, according to the range of green in the HSV space, a suitable threshold is set for segmentation, so as to obtain a binary image; wherein the green light column region is white and the background is black.

[0030] The image morphological processing includes morphological erosion and dilation operations on the segmented binary image, and the specific steps are as follows: first, some isolated noise points are removed through the erosion operation, and then the dilation operation is performed to restore the original shape of the light column, so that the light column region is more continuous.

[0031] The light column detection and length calculation include two steps of contour detection and length calculation: the contour detection is to use the findContours function to find the contour of the green light column in the binary image; the length calculation is to calculate the number of pixel points for each contour, then convert the number of pixels into the actual physical length according to the image resolution, and then convert the calculated light column length into depth, unit: mm, and the above calculation process is completed within 3 seconds. Wherein, the detection angle is related to the installation angle of the laser sensor, and in the above system setting, the laser emitting surface and the water surface are 60°, in the case that the angle is fixed, the conversion of the light column length and the depth can be realized by using the sine calculation formula, that is, , is the depth, is the light column length, is 60°.

[0032] Then, the calculated flatness data and the current latitude and longitude data are stored in the storage chip. With the aid of airborne GPS data and ArcGIS, a thermal map of the flatness of the paddy field mud surface after water grading is generated, so as to realize the purpose of accurate measurement of the flatness of the paddy field mud surface after water grading.

[0033] Therefore, the paddy field flatness detection system and method based on the unmanned aerial vehicle laser fusion image can obtain flatness data through underwater imaging light column, and the principle is clear and the calculation is simple, which is convenient for processing and calculation in the edge terminal.

[0034] It should be pointed out finally that the above examples are only used to illustrate the technical solutions of the present application but not to limit it, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can still be modified or replaced equivalently, and these modifications or equivalent replacements should not make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for detecting the flatness of grid fields based on UAV laser fusion imagery, characterized in that, Includes the following steps: S1. The laser array is controlled by an embedded microcontroller to emit a laser every 3 seconds to send a detection light signal underwater, and the CMOS image sensor is controlled to acquire images of the water layer under the laser detection at the same time. S2. Using an embedded microcontroller, the image data is stored, preprocessed, thresholded, morphologically processed, and light beams are detected and their lengths are calculated to obtain the flatness data of the mud surface of the gridd land after water leveling, and a heat map is generated.

2. The method for detecting the flatness of grid fields based on UAV laser fusion imagery according to claim 1, characterized in that, In S2, preprocessing includes filtering the acquired image data to remove noise from the image.

3. The method for detecting the flatness of grid fields based on UAV laser fusion imagery according to claim 1, characterized in that, In S2, threshold segmentation involves selecting an appropriate threshold in the HSV color space to segment the image based on the color characteristics of the light pillars, thereby obtaining a binary image containing the light pillars.

4. The method for detecting the flatness of grid fields based on UAV laser fusion imagery according to claim 1, characterized in that, In S2, morphological processing includes morphological erosion and dilation operations. The morphological erosion operation removes isolated noise points, and the dilation operation restores the original shape of the light pillar, making the light pillar area continuous.

5. The method for detecting the flatness of grid fields based on UAV laser fusion imagery according to claim 1, characterized in that, In S2, beam detection and length calculation include contour detection and length calculation; Contour detection involves obtaining the contour of the light column based on a binary image and using appropriate algorithms; The length calculation involves calculating the number of corresponding pixels for each light pillar outline and converting it into the actual light pillar length. Then, based on the laser detection angle, the light pillar length is converted into the light pillar depth, thereby obtaining the flatness data of the grid mud surface.

6. A grid flatness detection system based on UAV laser fusion imagery, used to implement the grid flatness detection method based on UAV laser fusion imagery as described in any one of claims 1-5, characterized in that, This includes laser array detectors, CMOS image sensors, positioning systems, embedded microcontrollers, memory chips, power supply circuits, and multi-rotor unmanned aerial vehicle systems; The laser array detector is positioned below the drone at a 30° angle to the drone's plane and is used to emit lasers toward the surface of the Getian water. The CMOS image sensor is positioned face down on the bottom of the drone, parallel to the drone, and is used to detect the laser image below the water surface; The positioning system is placed on the drone frame, corresponding vertically to the CMOS image sensor, and is used to detect the current latitude and longitude information; An embedded microcontroller is placed on the drone to control laser emission, receive data collected by the CMOS image sensor, perform image preprocessing, image thresholding segmentation, image morphological processing, light pillar detection and length calculation, and location and flatness data storage. The memory chip is connected to the embedded microcontroller and is used to store GPS positioning data and flatness data; The power circuit supplies power to the drone and the detection system; A multi-rotor drone system includes a drone frame system, a drone power system, a drone flight control system, and a drone remote control device, achieving constant speed cruise through trajectory planning.

7. The grid flatness detection system based on UAV laser fusion imagery according to claim 6, characterized in that, The laser array detector options include using a green laser array with a 2cm spacing between each laser source.

8. The grid flatness detection system based on UAV laser fusion imagery according to claim 6, characterized in that, The power supply circuit options include powering via a lithium battery.

Images