Unmanned aerial vehicle acquisition method and system for drought images

Abstract

The invention is suitable for the technical field of image acquisition, and particularly relates to an unmanned aerial vehicle acquisition method and system for drought images, and the method comprises the steps: importing a drought monitoring map, and dividing a drought monitoring region; path planning is carried out based on the edge path of the drought monitoring map, and a scanning itinerant path is generated; scanning and shooting are carried out on the scanning itinerant path through the unmanned aerial vehicle to obtain a scanning exposure image, and real-time positioning is carried out to obtain scanning position data; based on the scanning position data and the scanning exposure image, drought image acquisition points are generated in a drought monitoring map, image acquisition is carried out on the drought image acquisition points, and a drought image is obtained. According to the invention, the image acquisition device is used for continuous shooting, and the unmanned aerial vehicle can fly quickly and scan the drought monitoring area within a short time due to no requirement on the speed of the shutter, so that the position where drought image acquisition needs to be carried out is determined, and the efficiency and accuracy of drought image acquisition are greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of image acquisition, and in particular relates to a method and system for acquiring drought images using an unmanned aerial vehicle. Background Art

[0002] Drought monitoring refers to the process of monitoring and evaluating drought conditions in a region through various technologies and methods, so as to timely understand and predict the development trend of drought and provide a scientific basis for drought relief and disaster reduction. Drought images usually refer to pictures or maps used to show drought conditions. Such images are very important for monitoring, evaluating and understanding the impact of drought. They can be satellite remote sensing images, meteorological data analysis charts, ground truth photos or data visualization charts.

[0003] When drought occurs, drought images are an important source of information for understanding the current development of the drought. However, when collecting drought images, it is necessary to collect images in key drought areas, such as drought areas in large-scale planting areas. The existing drought image collection mainly relies on manual collection or manually controlled drones for collection. Since it is impossible to quickly know the key drought areas, the collection efficiency is low and the image collection of key drought areas cannot be completed quickly. Summary of the invention

[0004] The purpose of the present invention is to provide a method for collecting drought images using a drone, aiming to solve the problem that the prior art cannot quickly obtain key drought areas, resulting in low collection efficiency and inability to quickly complete image collection of key drought areas.

[0005] The present invention is implemented as follows: a method for collecting drought images using an unmanned aerial vehicle, the method comprising: Import drought monitoring maps and divide drought monitoring areas based on the drought monitoring maps; Perform path planning based on the edge path of the drought monitoring map to generate a scanning patrol path; The UAV is used to scan and shoot on the scanning patrol path to obtain a scanning exposure image, and the UAV is positioned in real time during the scanning and shooting process to obtain scanning position data; Based on the scanning position data and the scanning exposure image, drought image collection points are generated in the drought monitoring map, and the drought image collection points are collected by the drone to obtain drought images.

[0006] Preferably, the step of performing path planning based on the edge path of the drought monitoring map to generate a scanning and patrolling path specifically includes: A two-dimensional coordinate system is constructed based on the drought monitoring map, and the drought monitoring map is grid-divided to obtain a plurality of grid units; Determine the coordinates of each grid cell, extract the edge path of the drought monitoring map, and determine the scan width based on the shooting parameters of the drone for image acquisition; A plurality of equidistant scanning bands are constructed based on the scanning width and the edge path, and the equidistant scanning bands are connected based on the scanning starting point to obtain a scanning circuit path.

[0007] Preferably, the step of performing scanning and photographing by a drone on a scanning and patrolling path to obtain a scanning exposure image, and performing real-time positioning of the drone during the scanning and photographing process to obtain scanning position data specifically includes: Set multiple path points on the scanning patrol path, number the path points, and the drone traverses each path point based on the number; Retrieving the flight parameters and image acquisition parameters of the drone, determining the flight speed of the drone, controlling the drone to fly at a constant speed at the flight speed, and performing continuous image acquisition through the image acquisition device; The collected scanning exposure images are obtained. When each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

[0008] Preferably, the step of generating drought image acquisition points in the drought monitoring map based on the scanned position data and the scanned exposure image, and acquiring images of the drought image acquisition points by using a drone to obtain drought images specifically includes: Retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, and classify each pixel into abnormal pixels and normal pixels; Divide the scanned exposure image into multiple pixel bands, calculate the abnormal pixel ratio of each pixel band, and determine whether the current image acquisition area is a key area; Drought image collection points are determined from key areas, and images are collected at the drought image collection points by using drones to obtain drought images.

[0009] Preferably, after the drought image is obtained, the drought monitoring map is marked to generate a drought sample map, and the drought image is marked on each drought image collection point.

[0010] Another object of the present invention is to provide a drone collection system for drought images, the system comprising: A map import module is used to import drought monitoring maps and divide drought monitoring areas based on drought monitoring maps; A scanning path construction module is used to perform path planning based on the edge path of the drought monitoring map and generate a scanning tour path; The scanning and positioning module is used to scan and shoot with the UAV on the scanning and patrolling path to obtain the scanning exposure image, and to locate the UAV in real time during the scanning and shooting process to obtain the scanning position data; The image acquisition module is used to generate drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and to acquire drought images by using a drone to acquire images of the drought image acquisition points.

[0011] Preferably, the scanning path building module includes: A map division unit is used to construct a two-dimensional coordinate system based on the drought monitoring map, and to divide the drought monitoring map into grids to obtain a plurality of grid units; A scanning parameter calculation unit is used to determine the coordinates of each grid cell, extract the edge path of the drought monitoring map, and determine the scanning width based on the shooting parameters of the drone for image acquisition; The path generation unit is used to construct a plurality of equidistant scanning bands based on the scanning width and the edge path, and to connect the equidistant scanning bands based on the scanning starting point to obtain a scanning circuit path.

[0012] Preferably, the scanning and positioning module includes: A path parsing unit is used to set multiple path points on the scanning patrol path, number the path points, and the drone traverses each path point based on the number; A continuous scanning unit is used to retrieve the flight parameters and image acquisition parameters of the UAV, determine the flight speed of the UAV, control the UAV to fly at a constant speed at the flight speed, and perform continuous image acquisition through the image acquisition device; The device positioning unit is used to obtain the collected scanning exposure images. When each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

[0013] Preferably, the image acquisition module includes: A pixel information extraction unit is used to retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, and classify each pixel into abnormal pixels and normal pixels; An image segmentation unit is used to divide the scanned exposure image into multiple pixel bands, calculate the abnormal pixel ratio of each pixel band, and determine whether the current image acquisition area is a key area; The fixed-point acquisition unit is used to determine the drought image acquisition points in the key areas, and acquire drought images by using drones to acquire images of the drought image acquisition points.

[0014] Preferably, after the drought image is obtained, the drought monitoring map is marked to generate a drought sample map, and the drought image is marked on each drought image collection point.

[0015] The present invention provides a method for collecting drought images using a drone. The method controls the drone to fly quickly over a drought monitoring area by constructing a scanning patrol path. During this process, an image acquisition device is used to perform continuous shooting. Since there is no requirement for shutter speed, the drone can fly quickly and can complete the scanning of the drought monitoring area in a short time, thereby determining the location where drought images need to be collected, thereby greatly improving the efficiency and accuracy of drought image collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for collecting drought images using a drone provided by an embodiment of the present invention; Figure 2 A flowchart of the steps of performing path planning based on the edge path of a drought monitoring map and generating a scanning and patrolling path provided in an embodiment of the present invention; Figure 3 A flowchart of the steps of performing scanning and shooting on a scanning and patrolling path by a drone provided in an embodiment of the present invention to obtain a scanning exposure image, and performing real-time positioning of the drone during the scanning and shooting process to obtain scanning position data; Figure 4 A flowchart of the steps of generating drought image acquisition points in a drought monitoring map based on scan position data and scan exposure images, and acquiring drought images at the drought image acquisition points by using a drone, provided in an embodiment of the present invention; Figure 5 An architecture diagram of a drone collection system for drought images provided by an embodiment of the present invention; Figure 6 An architectural diagram of a scan path construction module provided by an embodiment of the present invention; Figure 7 An architecture diagram of a scanning and positioning module provided in an embodiment of the present invention; Figure 8 An architecture diagram of an image acquisition module provided by an embodiment of the present invention; Fig. 9 A working schematic diagram of a method for collecting drought images using a drone provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0019] like Figure 1 FIG. 1 is a flowchart of a method for collecting drought images using a drone provided by an embodiment of the present invention, the method comprising: S100, importing a drought monitoring map, and dividing drought monitoring areas based on the drought monitoring map.

[0020] In this step, a drought monitoring map is imported. For areas that need drought monitoring, the local map is directly retrieved. The drought monitoring map contains all target types that need to be monitored, such as rice-growing areas and wheat-growing areas. The present invention takes the rice-growing area as an example, and divides the areas that need to be monitored in the drought monitoring map. Specifically, the drought monitoring areas are divided by lines.

[0021] S200, performing path planning based on the edge path of the drought monitoring map to generate a scanning patrol path.

[0022] In this step, path planning is performed based on the edge path of the drought monitoring map. In the drought monitoring map, the areas that need to be monitored have been marked, and the edges of the areas that need to be monitored are identified. A set of scanning and patrol paths are generated with the edges as boundaries. When flying, the drone can fly along the scanning and patrol paths. During the flight, the image acquisition device mounted on the drone performs image acquisition.

[0023] S300, the UAV performs scanning and shooting on the scanning patrol path to obtain a scanning exposure image, and the UAV is positioned in real time during the scanning and shooting process to obtain scanning position data.

[0024] In this step, the drone performs scanning and shooting on the scanning and patrolling path. After obtaining the scanning and patrolling path, the drone can fly along the scanning and patrolling path. The drone is equipped with an image acquisition device. The flight altitude of the drone is fixed. During the flight, continuous shooting is performed for drought monitoring below. However, unlike the conventional image acquisition process, in the present invention, the image acquisition device is installed on the drone. In order to quickly complete the scanning and patrolling path, the drone adopts a high-speed flight mode. During this process, the image acquisition device mounted on the drone continuously takes pictures to obtain a scanning exposure image. In the present invention, the performance requirements for the image acquisition device are relatively low. As for the image acquisition device, in order to take clear images, it is necessary to keep the image acquisition device stable under the focusing condition until the shutter time ends, so that a set of clear images can be obtained. In the present invention, since the drone flies at a high speed, the drone will drive the image acquisition device to move a certain distance within the shutter time, that is, the scanned exposure image is not an image collected at a fixed point. Therefore, the scanned exposure image is an image with "smear". This is because during the scanning process, image details are not required. It is only necessary to determine whether there is drought in the area based on the color information in the photographed area. When shooting, the position information of each drone at each time is recorded to obtain the scanning position data.

[0025] S400, generating drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and acquiring images of the drought image acquisition points by using a drone to obtain drought images.

[0026] In this step, drought image acquisition points are generated in the drought monitoring map based on the scanning position data and the scanning exposure image. For the scanning exposure image, the content recorded is actually the superposition of under-exposed images of multiple locations in the drought monitoring area. The color information of each pixel in the current scanning exposure image is extracted and compared with the preset value, so that the pixels are divided into abnormal pixels and normal pixels. The abnormal pixels are the areas where drought may occur. Specifically, they can be divided according to the RGB color value range. After the division is completed, the scanning exposure image is divided into multiple pixel bands. The area where drought exists can be further located based on the position of the pixel band, so as to determine the drought acquisition point, control the drone carrying the image acquisition device to fly to the drought acquisition point for close-range fixed-point acquisition, and obtain the drought image. Then, the drought image will clearly record the actual appearance of the location.

[0027] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of performing path planning based on the edge path of the drought monitoring map and generating a scanning and patrolling path specifically includes: S201, constructing a two-dimensional coordinate system based on the drought monitoring map, and dividing the drought monitoring map into grids to obtain a plurality of grid units.

[0028] In this step, a two-dimensional coordinate system is constructed based on the drought monitoring map, the drought monitoring map is imported into the two-dimensional coordinate system as an image, any point in the drought monitoring map is used as the origin of the two-dimensional coordinate system, and the drought monitoring map is divided. Specifically, a pixel point in the drought monitoring map can be used as a grid unit.

[0029] S202, determining the coordinates of each grid unit, extracting the edge path of the drought monitoring map, and determining the scanning width based on the shooting parameters of the drone for image acquisition.

[0030] In this step, the coordinates of each grid unit can be determined, and the simplified GPS positioning coordinates of each grid unit can be determined. The GPS positioning coordinates are two-dimensional coordinate points and do not include altitude data. Therefore, during the flight of the drone, the GPS positioning coordinates of the drone can be directly determined from the two-dimensional coordinate system.

[0031] S203, constructing a plurality of equidistant scanning bands based on the scanning width and the edge path, and connecting the equidistant scanning bands based on the scanning starting point to obtain a scanning circuit path.

[0032] In this step, multiple equidistant scanning belts are constructed based on the scanning width and edge path, and the flight altitude of the UAV is set. The higher the flying altitude of the UAV, the larger the corresponding image acquisition range, but details are more likely to be lost. Under the premise of ensuring scanning efficiency and accuracy, the flight altitude of the UAV can be set to 50 meters. The image acquisition device takes a bird's-eye view from top to bottom. Since the image acquisition angle of the image acquisition device is known, it can be determined that the image acquisition width that can be covered at a height of 50 meters can be determined. This width is the scanning width. Multiple equidistant lines are constructed according to the edge path. The distance between the equidistant lines is the scanning width. The annular range between adjacent equidistant lines is the equidistant scanning belt. The center line of the equidistant scanning belt is the flight path of the UAV. Adjacent equidistant scanning belts are connected by straight lines to obtain a complete scanning patrol path. The UAV can complete a rapid scan of the entire drought monitoring area by flying according to the above scanning patrol path.

[0033] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of scanning and photographing by a drone on a scanning and patrolling path to obtain a scanning exposure image, positioning the drone in real time during the scanning and photographing process to obtain scanning position data specifically include: S301, multiple path points are set on the scanning patrol path, the path points are numbered, and the drone traverses each path point based on the number.

[0034] In this step, multiple path points are set on the scanning patrol path. In order to facilitate navigation and control of the UAV, multiple path points are set according to the preset path step length. The distance between adjacent path points is equal to the path step length. By numbering the path points, the flight path of the UAV can be controlled. The path step length is determined according to the flight speed v of the UAV, the shutter time t of the image acquisition device and the scanning length L. The scanning length L is the actual distance corresponding to the side length of the scanning exposure image in the flight direction of the UAV, and the scanning width W is the actual distance corresponding to the side length of the scanning exposure image perpendicular to the flight direction of the UAV. For example, if the scanning width is 100 meters and the scanning length is 200 meters, then within a single shutter time, the area scanned by the image acquisition device is v*t+W*L, and the path step length is set to v*t+W*L.

[0035] S302, retrieve the flight parameters and image acquisition parameters of the UAV, determine the flight speed of the UAV, control the UAV to fly at a constant speed at the flight speed, and perform continuous image acquisition through the image acquisition device.

[0036] S303, acquiring the collected scanning exposure images, positioning the drone once when each group of scanning exposure images is generated, and obtaining scanning position data, wherein the scanning position data corresponds to the scanning exposure images one by one.

[0037] In this step, the flight parameters and image acquisition parameters of the UAV are retrieved. First, the image acquisition parameters are determined. The image acquisition parameters include shutter time t, image acquisition angle range, detection length L1 and detection width L2 of a single image. The area scanned by a single image is v*t+W*L, then L2= W, and v*t+W*L= L1* L2. The scanning width W and scanning length L are determined according to the flight altitude of the UAV and the image acquisition angle range. The scanning width W and scanning length L corresponding to a single image, then no matter what the flight altitude of the UAV is, the ratio of W to L is a constant (the aspect ratio of the scanning exposure image is a constant), the flight speed of the UAV is calculated according to v*t+W*L= L1* L2, the flight altitude of the UAV is determined according to W and L, so that the UAV flies according to the above-mentioned flight altitude and flight speed, and the image acquisition device continuously performs image acquisition in this process to obtain the acquired scanning exposure images, and when each group of scanning exposure images is generated, the UAV is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

[0038] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of generating drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and acquiring images of the drought image acquisition points by using a drone to obtain drought images specifically include: S401, retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, classify each pixel, and divide it into abnormal pixels and normal pixels.

[0039] In this step, the scanned exposure images are retrieved based on the generation time sequence. For the drought monitoring area, if the crop planted is rice, the color value range of normal rice in the image is determined by performing image acquisition in advance. For example, in the RGB channel, the range of the R channel is set to (30-145), the range of the G channel is set to (150-220), and the range of the B channel is set to (40-139). Then, when the color value of the pixel point completely falls into the above range, it is classified as a normal pixel point, otherwise it is an abnormal pixel point.

[0040] S402, dividing the scanned exposure image into a plurality of pixel bands, calculating the abnormal pixel ratio of each pixel band, and determining whether the current image acquisition area is a key area.

[0041] In this step, the scanned exposure image is divided into multiple pixel bands. The number of pixels of the scanned exposure image in the scanning length direction is M, and the number of pixels of the scanned exposure image in the scanning width direction is N. Then the number of pixels in the width of the pixel band is N, and the number of pixels in the length of the pixel band is at least 1. Specifically, it can be set to m, then the number of pixels contained in the pixel band is m*N, and the entire scanned exposure image will be divided into M / m pixel bands, such as Fig. 9 As shown, the image acquisition area corresponding to the scanned exposure image is divided into multiple image acquisition area units. Each pixel band corresponds to an image acquisition area unit. The pixel points in the pixel band are counted, and the abnormal pixel ratio in the pixel band is counted. In the pixel band, the number of normal pixel points is P1, and the number of abnormal pixel points is P2. Then the abnormal pixel ratio is P2 / (P1+P2). If the abnormal pixel ratio is greater than the preset value, it is determined that there is an abnormal area in the image acquisition area unit, and the abnormal area is the key area. Fig. 9 As shown, the color information recorded in each pixel band comes from the corresponding image acquisition area unit. Therefore, the crop growth conditions in the corresponding image acquisition area unit can be analyzed based on the color information in the pixel band. The color of the crops will change, such as turning yellow, at the location where drought occurs.

[0042] S403, determining drought image acquisition points from the key areas, and acquiring images of the drought image acquisition points by using a drone to obtain drought images.

[0043] In this step, the position of each abnormal pixel point is identified, a plane coordinate system is constructed according to the pixel band, the coordinates of each abnormal pixel point are determined, the average coordinates of the abnormal pixel point are calculated, the actual coordinates of the abnormal pixel point in the image acquisition area unit are determined based on the average coordinates, and the position of the average coordinates of the abnormal pixel point in the pixel band is calculated, such as (K1*m, K2*N), K1 is the ratio of the horizontal coordinate of the average coordinate to the number of pixels in the length direction of the pixel band, and K2 is the ratio of the vertical coordinate of the average coordinate to the number of pixels in the width direction of the pixel band. After obtaining K1 and K2, the coordinates of each position point in the image acquisition area unit are determined, the coordinates of the position point of the lower left corner are (X1, Y1), and the coordinate point of the support point of the upper right corner is (X2, Y2), then the coordinate point of the drought image acquisition point is (K1 (X1+X2), K2 (Y1+Y2)), and the image acquisition point of the drought image acquisition point is acquired by a drone. The drone carries an image acquisition device and moves to the position to perform fixed-point image acquisition to obtain a clear drought image.

[0044] like Figure 5 As shown, a drone collection system for drought images provided by an embodiment of the present invention includes: The map importing module 100 is used to import a drought monitoring map and divide drought monitoring areas based on the drought monitoring map.

[0045] In this system, the map import module 100 imports the drought monitoring map. For areas that need drought monitoring, the local map is directly retrieved. The drought monitoring map contains all target types that need to be monitored, such as rice planting areas and wheat planting areas. The present invention takes the rice planting area as an example, and divides the areas that need to be monitored in the drought monitoring map. Specifically, the drought monitoring areas are divided by lines.

[0046] The scanning path construction module 200 is used to perform path planning based on the edge path of the drought monitoring map to generate a scanning patrol path.

[0047] In this system, the scanning path construction module 200 performs path planning based on the edge path of the drought monitoring map. In the drought monitoring map, the areas that need to be monitored have been marked, and the edges of the areas that need to be monitored are identified. A set of scanning patrol paths is generated with the edges as boundaries. When flying, the drone can fly along the scanning patrol path. During the flight, the image acquisition device mounted on the drone performs image acquisition.

[0048] The scanning and positioning module 300 is used to perform scanning and shooting on the scanning and patrolling path by using the drone to obtain a scanning exposure image, and to perform real-time positioning of the drone during the scanning and shooting process to obtain scanning position data.

[0049] In this system, the scanning and positioning module 300 performs scanning and shooting on the scanning and patrolling path through the drone. After obtaining the scanning and patrolling path, the drone can fly along the scanning and patrolling path. The drone is equipped with an image acquisition device. The flight altitude of the drone is fixed. During the flight, the drought monitoring below is continuously photographed. However, unlike the conventional image acquisition process, in the present invention, the image acquisition device is installed on the drone. In order to quickly complete the scanning and patrolling path, the drone adopts a high-speed flight mode. During this process, the image acquisition device mounted on the drone continuously takes pictures to obtain a scanning exposure image. In the present invention, the performance requirements for the image acquisition device are as follows: The image acquisition device is relatively low. In order to take clear images, it is necessary to keep the image acquisition device stable under focusing until the shutter time ends to obtain a set of clear images. In the present invention, since the UAV flies at a high speed, the UAV will drive the image acquisition device to move a certain distance within the shutter time, that is, the scanned exposure image is not an image collected at a fixed point. Therefore, the scanned exposure image is an image with "smear". This is because during the scanning process, image details are not required. It is only necessary to determine whether there is drought in the area based on the color information in the photographed area. When shooting, the position information of each UAV at each time is recorded to obtain the scanning position data.

[0050] The image acquisition module 400 is used to generate drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and acquire drought images by using a drone to acquire images of the drought image acquisition points.

[0051] In the present system, the image acquisition module 400 generates drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image. For the scanning exposure image, the content recorded is actually the superposition of under-exposed images of multiple locations in the drought monitoring area. By extracting the color information of each pixel in the current scanning exposure image and comparing it with the preset value, the pixel points are divided into abnormal pixel points and normal pixel points. The abnormal pixel points are the areas where drought may occur. Specifically, they can be divided according to the RGB color value range. After the division is completed, the scanning exposure image is divided into multiple pixel bands. Based on the position of the pixel bands, the area where drought exists can be further located, thereby determining the drought acquisition point, and controlling the drone carrying the image acquisition device to fly to the drought acquisition point for close-range fixed-point acquisition to obtain a drought image. Then, the drought image will clearly record the actual appearance of the location.

[0052] like Figure 6 As shown, as a preferred embodiment of the present invention, the scanning path construction module 200 includes: The map division unit 201 is used to construct a two-dimensional coordinate system based on the drought monitoring map, and to divide the drought monitoring map into grids to obtain a plurality of grid units.

[0053] In this module, the map division unit 201 constructs a two-dimensional coordinate system based on the drought monitoring map, imports the drought monitoring map as an image into the two-dimensional coordinate system, takes any point in the drought monitoring map as the origin of the two-dimensional coordinate system, and divides the drought monitoring map. Specifically, a pixel point in the drought monitoring map can be used as a grid unit.

[0054] The scanning parameter calculation unit 202 is used to determine the coordinates of each grid unit, extract the edge path of the drought monitoring map, and determine the scanning width based on the shooting parameters of the drone for image acquisition.

[0055] In this module, the scanning parameter calculation unit 202 can determine the coordinates of each grid cell and determine the simplified GPS positioning coordinates of each grid cell. The GPS positioning coordinates are two-dimensional coordinate points and do not include altitude data. Therefore, during the flight of the drone, the GPS positioning coordinates of the drone can be directly determined from the two-dimensional coordinate system.

[0056] The path generation unit 203 is used to construct a plurality of equidistant scanning bands based on the scanning width and the edge path, and connect the equidistant scanning bands based on the scanning starting point to obtain a scanning circuit path.

[0057] In this module, the path generation unit 203 constructs multiple equidistant scanning belts based on the scanning width and the edge path, and sets the flight altitude of the drone. The higher the flight altitude of the drone, the larger the corresponding image acquisition range, but details are more likely to be lost. Under the premise of ensuring scanning efficiency and accuracy, the flight altitude of the drone can be set to 50 meters. The image acquisition device shoots from top to bottom. Since the image acquisition angle of the image acquisition device is known, it can be determined that when the height is 50 meters, the image acquisition width that it can cover can be determined. This width is the scanning width. Multiple equidistant lines are constructed according to the edge path. The distance between the equidistant lines is the scanning width. The annular range between adjacent equidistant lines is the equidistant scanning belt. The center line of the equidistant scanning belt is the flight path of the drone. Adjacent equidistant scanning belts are connected by straight lines to obtain a complete scanning patrol path. The drone can complete a rapid scan of the entire drought monitoring area by flying according to the above scanning patrol path.

[0058] like Figure 7 As shown, as a preferred embodiment of the present invention, the scanning and positioning module 300 includes: The path parsing unit 301 is used to set a plurality of path points on the scanning patrol path, number the path points, and the drone traverses each path point based on the number.

[0059] In this module, the path parsing unit 301 sets a plurality of path points on the scanning patrol path. In order to facilitate navigation control of the UAV, a plurality of path points are set according to a preset path step length. The distance between adjacent path points is equal to the path step length. By numbering the path points, the flight path of the UAV can be controlled. The path step length is determined according to the flight speed v of the UAV, the shutter time t of the image acquisition device and the scanning length L. The scanning length L is the actual distance corresponding to the side length of the scanning exposure image in the flight direction of the UAV, and the scanning width W is the actual distance corresponding to the side length of the scanning exposure image perpendicular to the flight direction of the UAV. For example, if the scanning width is 100 meters and the scanning length is 200 meters, then within a single shutter time, the area scanned by the image acquisition device is v*t+W*L, and the path step length is set to v*t+W*L.

[0060] The continuous scanning unit 302 is used to retrieve the flight parameters and image acquisition parameters of the drone, determine the flight speed of the drone, control the drone to fly at a constant speed at the flight speed, and perform continuous image acquisition through the image acquisition device.

[0061] The device positioning unit 303 is used to obtain the collected scanning exposure images. When each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

[0062] In this module, the flight parameters and image acquisition parameters of the drone are retrieved. First, the image acquisition parameters are determined. The image acquisition parameters include shutter time t, image acquisition angle range, detection length L1 and detection width L2 of a single image. The area scanned by a single image is v*t+W*L, then L2= W, and v*t+W*L= L1* L2. The scanning width W and scanning length L are determined according to the flight altitude of the drone and the image acquisition angle range. The scanning width W and scanning length L corresponding to a single image, then no matter how much the flight altitude of the drone is, the ratio of W to L is a constant (the aspect ratio of the scanning exposure image is a constant), the flight speed of the drone is calculated according to v*t+W*L= L1* L2, the flight altitude of the drone is determined according to W and L, so that the drone flies according to the above flight altitude and flight speed, and the image acquisition device continuously performs image acquisition in this process to obtain the acquired scanning exposure images, and when each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

[0063] like Figure 8 As shown, as a preferred embodiment of the present invention, the image acquisition module 400 includes: The pixel information extraction unit 401 is used to retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, and classify each pixel into abnormal pixels and normal pixels.

[0064] In this module, the pixel information extraction unit 401 retrieves the scanned exposure image based on the generation time sequence. For the drought monitoring area, if the crop planted is rice, the color value range of normal rice in the image is determined by performing image acquisition in advance. For example, in the RGB channel, the range of the R channel is set to (30-145), the range of the G channel is set to (150-220), and the range of the B channel is set to (40-139). Then, when the color value of the pixel point completely falls into the above range, it is classified as a normal pixel point, otherwise it is an abnormal pixel point.

[0065] The image segmentation unit 402 is used to divide the scanned exposure image into a plurality of pixel bands, calculate the abnormal pixel ratio of each pixel band, and determine whether the current image acquisition area is a key area.

[0066] In this module, the image segmentation unit 402 divides the scanned exposure image into multiple pixel bands. The number of pixels of the scanned exposure image in the scanning length direction is M, and the number of pixels of the scanned exposure image in the scanning width direction is N. Then the number of pixels in the width of the pixel band is N, and the number of pixels in the length of the pixel band is at least 1. Specifically, it can be set to m, then the number of pixels contained in the pixel band is m*N, and the entire scanned exposure image will be divided into M / m pixel bands, such as Fig. 9 As shown, the image acquisition area corresponding to the scanned exposure image is divided into multiple image acquisition area units. Each pixel band corresponds to an image acquisition area unit. The pixel points in the pixel band are counted, and the abnormal pixel ratio in the pixel band is counted. In the pixel band, the number of normal pixel points is P1, and the number of abnormal pixel points is P2. Then the abnormal pixel ratio is P2 / (P1+P2). If the abnormal pixel ratio is greater than the preset value, it is determined that there is an abnormal area in the image acquisition area unit, and the abnormal area is the key area. Fig. 9 As shown, the color information recorded in each pixel band comes from the corresponding image acquisition area unit. Therefore, the crop growth conditions in the corresponding image acquisition area unit can be analyzed based on the color information in the pixel band. The color of the crops will change, such as turning yellow, at the location where drought occurs.

[0067] The fixed-point acquisition unit 403 is used to determine drought image acquisition points in the key area, and acquire drought images by using a drone to acquire images of the drought image acquisition points.

[0068] In this module, the fixed-point acquisition unit 403 identifies the position of each abnormal pixel point, constructs a plane coordinate system according to the pixel band, determines the coordinates of each abnormal pixel point, calculates the average coordinates of the abnormal pixel point, determines the actual coordinates of the abnormal pixel point in the image acquisition area unit based on the average coordinates, and calculates the position of the average coordinates of the abnormal pixel point in the pixel band, such as (K1*m, K2*N), K1 is the ratio of the horizontal coordinate of the average coordinate to the number of pixels in the length direction of the pixel band, and K2 is the ratio of the vertical coordinate of the average coordinate to the number of pixels in the width direction of the pixel band. After obtaining K1 and K2, the coordinates of each position point in the image acquisition area unit are determined, and the coordinates of the position point at the lower left corner are (X1, Y1), and the coordinate point of the support point at the upper right corner is (X2, Y2). Then the coordinate point of the drought image acquisition point is (K1 (X1+X2), K2 (Y1+Y2)). The image acquisition point of the drought image acquisition point is performed by a drone, and the drone carries an image acquisition device and moves to the position to perform fixed-point image acquisition to obtain a clear drought image.

[0069] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0070] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0071] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for collecting drought images using drones, characterized in that: The method comprises: Import drought monitoring maps and divide drought monitoring areas based on the drought monitoring maps; Perform path planning based on the edge path of the drought monitoring map to generate a scanning patrol path; The UAV is used to scan and shoot on the scanning patrol path to obtain a scanning exposure image, and the UAV is positioned in real time during the scanning and shooting process to obtain scanning position data; Based on the scanning position data and the scanning exposure image, drought image collection points are generated in the drought monitoring map, and the drought image collection points are collected by the drone to obtain drought images.

2. The method for collecting drought images using an unmanned aerial vehicle according to claim 1, characterized in that: The step of performing path planning based on the edge path of the drought monitoring map to generate a scanning and patrolling path specifically includes: A two-dimensional coordinate system is constructed based on the drought monitoring map, and the drought monitoring map is grid-divided to obtain a plurality of grid units; Determine the coordinates of each grid cell, extract the edge path of the drought monitoring map, and determine the scan width based on the shooting parameters of the drone for image acquisition; A plurality of equidistant scanning bands are constructed based on the scanning width and the edge path, and the equidistant scanning bands are connected based on the scanning starting point to obtain a scanning circuit path.

3. The method for collecting drought images using drones according to claim 1, characterized in that: The steps of scanning and photographing by the drone on the scanning and patrolling path to obtain the scanning exposure image, and positioning the drone in real time during the scanning and photographing process to obtain the scanning position data specifically include: Set multiple path points on the scanning patrol path, number the path points, and the drone traverses each path point based on the number; Retrieving the flight parameters and image acquisition parameters of the UAV, determining the flight speed of the UAV, controlling the UAV to fly at a constant speed at the flight speed, and performing continuous image acquisition through the image acquisition device; The collected scanning exposure images are obtained. When each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

4. The method for collecting drought images using drones according to claim 1, characterized in that: The step of generating drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and acquiring images of the drought image acquisition points by using a drone to obtain drought images specifically includes: Retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, and classify each pixel into abnormal pixels and normal pixels; Divide the scanned exposure image into multiple pixel bands, calculate the abnormal pixel ratio of each pixel band, and determine whether the current image acquisition area is a key area; Drought image collection points are determined from key areas, and images are collected at the drought image collection points by using drones to obtain drought images.

5. The method for collecting drought images using drones according to claim 1, characterized in that: After the drought image is obtained, the drought monitoring map is marked to generate a drought sample map, and the drought image is marked on each drought image collection point.

6. A drone collection system for drought images, characterized in that: The system comprises: A map import module is used to import drought monitoring maps and divide drought monitoring areas based on drought monitoring maps; A scanning path construction module is used to perform path planning based on the edge path of the drought monitoring map and generate a scanning tour path; The scanning and positioning module is used to scan and shoot with the UAV on the scanning and patrolling path to obtain the scanning exposure image, and to locate the UAV in real time during the scanning and shooting process to obtain the scanning position data; The image acquisition module is used to generate drought image acquisition points in the drought monitoring map based on the scanning position data and the scanning exposure image, and to acquire drought images by using a drone to acquire images of the drought image acquisition points.

7. The drone collection system for drought images according to claim 6, characterized in that: The scanning path building module comprises: A map division unit is used to construct a two-dimensional coordinate system based on the drought monitoring map, and to divide the drought monitoring map into grids to obtain a plurality of grid units; A scanning parameter calculation unit is used to determine the coordinates of each grid cell, extract the edge path of the drought monitoring map, and determine the scanning width based on the shooting parameters of the drone for image acquisition; The path generation unit is used to construct a plurality of equidistant scanning bands based on the scanning width and the edge path, and to connect the equidistant scanning bands based on the scanning starting point to obtain a scanning circuit path.

8. The drone collection system for drought images according to claim 6, characterized in that: The scanning and positioning module comprises: A path parsing unit is used to set multiple path points on the scanning patrol path, number the path points, and the drone traverses each path point based on the number; A continuous scanning unit is used to retrieve the flight parameters and image acquisition parameters of the UAV, determine the flight speed of the UAV, control the UAV to fly at a constant speed at the flight speed, and perform continuous image acquisition through the image acquisition device; The device positioning unit is used to obtain the collected scanning exposure images. When each group of scanning exposure images is generated, the drone is positioned once to obtain scanning position data, and the scanning position data corresponds to the scanning exposure images one by one.

9. The drone collection system for drought images according to claim 6, characterized in that: The image acquisition module comprises: A pixel information extraction unit is used to retrieve the scanned exposure image based on the generation time sequence, read the RGB color information of each pixel, and classify each pixel into abnormal pixels and normal pixels; An image segmentation unit is used to divide the scanned exposure image into multiple pixel bands, calculate the abnormal pixel ratio of each pixel band, and determine whether the current image acquisition area is a key area; The fixed-point acquisition unit is used to determine the drought image acquisition points in the key areas, and acquire drought images by using drones to acquire images of the drought image acquisition points.

10. The drone collection system for drought images according to claim 6, characterized in that: After the drought image is obtained, the drought monitoring map is marked to generate a drought sample map, and the drought image is marked on each drought image collection point.

Images