WO2019165611A1

WO2019165611A1 - Method and device for detecting water ripple of image, and unmanned aerial vehicle and storage device

Info

Publication number: WO2019165611A1
Application number: PCT/CN2018/077658
Authority: WO
Inventors: 林家荣; 唐克坦; 张培科
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2018-02-28
Filing date: 2018-02-28
Publication date: 2019-09-06
Also published as: CN110651299A

Abstract

A method for detecting a water ripple of an image, comprising: obtaining an image (301) obtained by photographing an image calibration device (20), wherein the image calibration device (20) comprises a plurality of calibration objects (302); detecting an image object of each calibration object in the image; matching the detected image object of the calibration object with the calibration object in the image calibration device; and determining whether a water ripple exists in the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device. In this way, intelligent detection of water ripples can be realized, and the detection efficiency is improved. Also disclosed is a water ripple detection device, an unmanned aerial vehicle, and a storage device.

Description

Image water ripple detecting method and device thereof, drone and storage device

[Technical Field]

The present application relates to the field of image processing technologies, and in particular, to a water ripple detecting method and device thereof for an image, a drone, and a storage device.

【Background technique】

A drone is equipped with a photographing device, which has been widely used to perform shooting tasks. During the flight of the drone, the fuselage will vibrate, and the vibration of the fuselage will be transmitted directly or indirectly to the camera. Thus, when the photographing device vibrates, a relative displacement occurs between the lines in the image captured by the photographing device. At this time, the image obtained by the shooting will be distorted, and the water ripple deformation, that is, the jelly effect, is observed by the naked eye, which affects the image quality of the image. At present, the detection of water ripples for images is usually judged manually, the detection efficiency is low, and the professional requirements of the operator are high.

[Summary of the Invention]

The technical problem mainly solved by the present application is to provide an image water ripple detecting method and device thereof, a drone and a storage device, which can realize intelligent detection of water ripple and improve detection efficiency.

In order to solve the above technical problem, a first aspect of the present application provides a water ripple detecting method for an image, comprising: acquiring an image captured by an image calibration device, wherein the image calibration device includes a plurality of calibration objects; and detecting the An image object of the object in the image; matching the image object of the detected calibration object with a calibration object in the image calibration device; according to a position of the image object in the image and matching with the image object The position of the calibration object in the image calibration device determines if there is a water ripple in the image.

In order to solve the above technical problem, a second aspect of the present application provides a water ripple detecting apparatus including a processor and a memory, wherein the memory is configured to store program instructions, and the processor executes the program instructions for use in Acquiring an image captured by the image calibration device, wherein the image calibration device includes a plurality of calibration objects; detecting an image object of the calibration object in the image; and detecting the image object of the detected calibration object The calibration object in the image calibration device performs matching; determining whether there is a water ripple in the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device.

In order to solve the above technical problem, a third aspect of the present application provides a water ripple detecting system including a photographing apparatus and the above-described water ripple detecting apparatus, wherein the photographing apparatus is configured to photograph an image calibration apparatus.

In order to solve the above technical problem, a fourth aspect of the present application provides a drone, including the above-described water ripple detecting system.

In order to solve the above technical problem, a fifth aspect of the present application provides a storage device storing program instructions, and when the program instructions are executed on a processor, performing the method described in the first aspect.

In the above solution, the image obtained by the image calibration device is detected to obtain an image object of the calibration object, and whether the water ripple exists in the image according to the position of the image object in the image and the position of the corresponding matching calibration object at the image calibration device The intelligent detection of the image water ripple is realized, and no manual detection is needed, thereby improving the detection efficiency and reducing the false detection rate.

[Description of the Drawings]

1 is a schematic flow chart of an embodiment of a water ripple detecting method of an image of the present application;

2a is a schematic diagram of an image calibration apparatus used in an application scenario of the present application;

2b is a schematic diagram of an image calibration apparatus used in another application scenario of the present application;

3 is a schematic diagram of an image captured in an application scenario and an image object therein;

4 is a schematic diagram of a matching relationship between a calibration object and an image object in an application scenario of the present application;

5 is a schematic flow chart of the step S14 in another embodiment of the water ripple detecting method of the image of the present application;

6 is a schematic diagram of a group of image objects selected in an application scenario of the present application;

7 is a schematic flow chart of the step S14 in still another embodiment of the water ripple detecting method of the image of the present application;

8 is a schematic diagram showing a positional relationship between a projected position of an image and a position of a matching calibration object in an application scenario of the present application;

9 is a schematic structural view of an embodiment of a water ripple detecting device of the present application;

10 is a schematic structural view of an embodiment of a water ripple detecting system of the present application;

Figure 11 is a schematic structural view of an embodiment of the drone of the present application;

FIG. 12 is a schematic structural diagram of an embodiment of a storage device of the present application.

【Detailed ways】

The technical solutions in the embodiments of the present invention will be clearly described with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

It should be noted that when a component is referred to as being "fixed" to another component, it can be directly on the other component or the component can be present. When a component is considered to "connect" another component, it can be directly connected to another component or possibly a central component.

All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. The terminology used in the description of the present invention is for the purpose of describing particular embodiments and is not intended to limit the invention. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

Please refer to FIG. 1. FIG. 1 is a schematic flow chart of an embodiment of a water ripple detecting method of an image of the present application, wherein the method can be applied to an unmanned aerial vehicle, and is specifically used for an image taken by a shooting device configured on the drone. Is there a water ripple? Specifically, the following steps are included:

S11: Acquire an image captured by the image calibration device.

Specifically, the execution body of the method of the embodiment may be a water ripple detecting device, and further, the executing body may be a processor of the water ripple detecting device, wherein the processor may be a general-purpose or dedicated processor, wherein The processor may be one or more, and is not specifically limited herein. The water ripple detecting device may be disposed on the drone, and in the process of detecting the water ripple of the image, the photographing device disposed on the drone may photograph the image calibration device and output the captured image, wherein the water is The ripple detecting device can acquire the image.

The image calibration device may be any calibration device having an image calibration function, wherein a plurality of calibration objects are included, and accordingly, the captured image includes an image object of the calibration object, and the image object is represented in the image. The image area of the calibration object.

Further, the image calibration device can be a calibration plate, and the calibration object is a calibration point on the calibration plate. For example, as shown in FIG. 2a, the image calibration device is a checkerboard calibration plate 20, and the calibration object is a corner point 201 on the checkerboard calibration plate; or the image calibration device is a random point calibration plate, as shown in FIG. 2b, the punctuation The object is a random point on the calibration plate 21, which may be a circle or other shape, and the size of the calibration object on the calibration plate 20 may be the same, and in some cases, at least two of the calibration objects on the calibration plate 20 are included. The size of the calibration object, that is, the calibration object including at least two different sizes, for convenience of description, is schematically illustrated here by two different sizes of calibration objects 211 and 212: the image calibration device includes a carrier device and is disposed in the At least two size types of calibration objects on the carrier device. Further, the image calibration device may further include a textured image disposed on the carrier device as a background image of the calibration object. The carrier device can be a substrate. Optionally, the outer ring and the outer ring of the calibration object of the at least one of the at least one size type of the at least two size types are different in color, for example, the outer ring is black, and the outer ring is white inside; or The outer ring is white and the inner part of the outer ring is black. Optionally, the color of the center portion of the calibration object of the at least one of the at least one size type of the calibration object of the at least two size types is different from the color of the center portion of the calibration object of the other size type of the calibration object of the at least two size types . Compared with the checkerboard calibration board, the overall shooting is required to achieve the matching between the corner points and the image objects in the image. The random point calibration plate can be uniquely identified because of the random point distribution around each random point, so the calibration board can be Partial shooting allows for a match between random points and image objects in the image.

S12: Detect an image object of the calibration object in the image.

Specifically, after acquiring the image captured by the image calibration device, the water ripple detecting device identifies an image object of the calibration object from the image, wherein the image object is the captured calibration object in the image. Image area. Since the calibration object on the image calibration device is an object with obvious features, the water ripple detecting device can recognize the image object of the calibration object from the image according to the feature of the calibration object. For example, for the checkerboard calibration plate, the water ripple detecting device can extract the corner points in the image by using the corner extraction algorithm. For the random point calibration plate, the water ripple detecting device can extract the image in the image by using a blob detector algorithm. Random point. Among them, the dot extraction algorithm has higher precision than the checkerboard corner point algorithm. Therefore, in S11, the image calibration device with the calibration object is circular, and the detection accuracy of the image object can be improved.

For convenience of explanation, the image calibration device will be taken as an example for the checkerboard of the checkerboard. As shown in FIG. 3, the water ripple detecting device acquires an image 301 taken on the checkerboard of the checkerboard, and then can be extracted from the image 301. A plurality of corner points 302 are drawn.

S13: Match the detected image object of the calibration object with the calibration object in the image calibration device.

Specifically, after detecting the image object of the calibration object in the image, it is necessary to establish a matching relationship between the detected image object and the calibration object on the image calibration device, that is, determining that the detected image object corresponds to the image calibration device. Which one of the calibration objects. For example, as shown in FIG. 4, for the image captured by the checkerboard 401, a plurality of corner points 402 may be extracted from the image, and each of the corner points 402 may be aligned with a corner point in the checkerboard 401. Matching, after the matching is completed, each of the corner points 402 establishes a one-to-one correspondence with the checkerboard 401.

In some embodiments, the matching the detected image object of the calibration object with the calibration object in the image calibration device comprises: determining a position feature parameter of the detected image object according to a position of the image object in the image, according to The determined position feature parameter and the pre-stored position feature parameter of the calibration object match the detected image object of the calibration object with the calibration object in the image device. In addition, the water ripple detecting device may pre-store the position feature parameter of the calibration object in the image calibration device, wherein the position feature parameter may indicate the position of the image object or the calibration object relative to the other one or more image objects and the calibration object, respectively. The relationship, in particular, the position feature parameter may be a feature vector, and the detected image object of the calibration object is matched with the calibration object in the image device according to the determined position feature parameter and the pre-stored position feature parameter of the calibration object. Optionally, when the location feature parameter of the image object is the same as or similar to the pre-stored location feature parameter of the calibration object, it may be determined that the image object matches the calibration object.

S14: Determine whether there is a water ripple in the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device.

Specifically, the water ripple detecting device may determine the position of the image object in the image, that is, the position of the image object in the image, wherein the position of the image object in the image may be the coordinate of the image object in the image coordinate system. . In addition, the water ripple detecting means can determine the position of the calibration object matching the image object in the image calibration device. For convenience of explanation, the calibration object matching the image object can be simply referred to as the target calibration object. The position of the calibration object in the image calibration device may be pre-existing in the water ripple detecting device. After the target calibration object matching the image object is determined, the target calibration object may be obtained from the position of the pre-stored calibration object in the image calibration device. The position on the image calibration device. For example, when the image calibration device is a checkerboard calibration plate, the position of the image object in the image may be the coordinate of the image region of the corner point in the image coordinate system, and the position of the target calibration object on the image calibration device may be Is the position of the corner point on the checkerboard.

After the position of the image object in the image and the position of the target calibration object on the image calibration device are obtained, whether the image exists in the image may be determined according to the position of the image object in the image and the position of the target calibration object on the image calibration device. Water ripples.

In this embodiment, the image captured by the image calibration device is detected to obtain an image object of the calibration object, and whether the image is present in the image according to the position of the image object in the image and the position of the corresponding matching calibration object at the image calibration device The water ripple realizes the intelligent detection of the image water ripple, and does not require manual detection, thereby improving the detection efficiency. The intelligent detection method can reduce the occurrence of false detection or missed detection and improve the detection accuracy.

Please refer to FIG. 5. FIG. 5 is a schematic flow chart of the step S14 in another embodiment of the water ripple detecting method of the image of the present application. In this embodiment, the geometric parameters of the image object and the geometric parameters of the matching calibration object are used to determine whether the calibration object on the image calibration device and the corresponding image object satisfy the projective invariance, thereby determining whether the image has water ripple. Specifically, compared with the embodiment shown in FIG. 1, S14 of the method of the embodiment further includes the following sub-steps:

S541: Determine a geometric parameter of the image object according to the position of the image object in the image.

Specifically, the image calibration device is photographed, that is, the calibration target on the image device is projected onto the plane of the image sensor of the imaging device. After determining the position of the image object in the image, the geometric parameters of the image object may be determined according to the position, wherein the geometric parameter includes a projective invariant parameter, and the projective invariant parameter is a feature of the projective transformation, and the graphic is a graphic A parameter that does not change after any projective transformation.

In some embodiments, the geometric parameter can include a cross ratio parameter, and further, the projective invariant parameter includes a cross ratio parameter. The step S13 includes the following substeps: selecting at least one set of image objects from the detected image objects, wherein the set of image objects includes 5 image objects, and determining the at least one set of image objects Matching at least one set of image calibration devices in the calibration device. Determining the cross ratio parameter of the image object according to the position of the image object in the image comprises: determining a cross ratio parameter of each group of image objects according to a position of each set of the image objects in the image in the at least one group . Specifically, as shown in FIG. 6, five image objects A, B, C, D, and E may be selected from a plurality of detected image objects to form a group of image objects, and at least one image object exists between different groups of image objects. Different image objects. The number of selected image objects can be adjusted according to actual needs. Generally, in an application scenario requiring high detection accuracy, the number of selected groups is large, and the selected image objects are distributed in different regions of the image.

Further, determining the cross-parameter parameter of each group of image objects according to a position of each group of the image objects in the at least one group may include: selecting each group of image objects according to the at least one group The position in the image determines the area of the four intersecting triangles corresponding to each group of image objects; and the intersection ratio parameter of each group of image objects is determined according to the area of each of the group of image objects corresponding to the four intersecting triangles. Continuing to refer to FIG. 6, a set of image objects includes five image objects A, B, C, D, and E, and four intersecting triangles can be formed by the five image objects, and the set of images is obtained by using the areas of the four intersecting triangles. The cross-parameter parameter of the image object is S _ΔABC S _ΔADE /S _ΔABD S _ΔACE .

Optionally, in order to ensure the accuracy of the cross ratio parameter determined in this step, it may be first determined whether the area of the intersecting triangle of each set of calibration objects satisfies the area requirement, and the area of the intersecting triangle is used to determine the cross ratio when determining the area requirement is determined. parameter. Optionally, it can be determined whether the cross ratio parameter obtained according to the area of the triangle satisfies the cross ratio requirement, and the cross ratio parameter is determined to be selected when the cross ratio requirement is met.

Specifically, after determining the area of the four intersecting triangles corresponding to each group of image objects, determining whether each of the areas of the four intersecting triangles corresponding to each group is greater than or equal to a preset area threshold; Determining the cross-parameter parameter of each group of image objects according to the area of each of the four intersecting triangles of each group of images includes: when each of the areas of the corresponding four intersecting triangles of each group is greater than or equal to the pre- When the area threshold is set, the cross-parameter parameter of each group of image objects is determined according to the area of the four intersecting triangles corresponding to each set of images. When one or more of the areas of the corresponding four intersecting triangles of each group are smaller than the preset area threshold, then a group of image objects are reselected, and the step ratio parameter of the group of image objects is determined by using this step.

In addition, after determining the cross ratio parameter of the group of image objects, it may be determined whether the cross ratio parameter is greater than a set cross ratio threshold, and if yes, determining to select the cross ratio parameter for use in subsequent steps, otherwise reselecting a set of graphs Like the object, and use this step to determine the cross-reference parameters of the set of image objects.

S542: Determine a geometric parameter of the calibration object that matches the image object according to the position of the calibration object matching the image object in the image calibration device.

Specifically, after determining the position of the target calibration object in the image calibration device, the geometric parameters of the target calibration object may be determined according to the position. As described above, the geometric parameters include projective invariant parameters.

In some embodiments, the geometric parameter can include a cross ratio parameter. Specifically, the determining, according to the position of the calibration object matching the image object in the image calibration device, the geometric parameter of the calibration object matching the image object comprises: calibrating the image according to the calibration object in the at least one set of image calibration devices The position of the device determines the cross-reference parameters for each set of calibration objects.

Specifically, in the same manner as the cross-parameter parameter determining manner of each of the group of image objects, the determining the intersection of each set of calibration objects according to the position of the image calibration device according to the calibration object in the at least one set of image calibration devices The ratio parameter includes: determining, according to the position of the image calibration device, the area of the four intersecting triangles corresponding to each group of calibration objects according to the calibration object in the at least one set of image calibration devices, according to each of the set of calibration objects The area of the intersecting triangles determines the cross-reference parameters for each set of calibration objects. The specific method is similar to the method for determining the cross-parameter parameter of each group of image objects in the foregoing part, and details are not described herein again.

S543: Determine whether there is a water ripple in the image according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object.

Specifically, according to the principle of projecting, when there is no water ripple in the image, the geometric parameters of the image object and the geometric parameters of the calibration object matching the image object should be the same, so according to the geometric parameters of the image object and The geometric parameters of the calibration object that the image object matches determine whether there is a water ripple in the image. Further, the geometric parameter difference may be determined according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object, thereby determining whether there is a water ripple in the image according to the difference.

As described above, the geometric parameter includes a cross ratio parameter, and step S543 includes: a difference between the cross ratio parameter of each set of image objects in the at least one set and the cross ratio parameter of the corresponding set of calibration objects Determine if there are water ripples in the image. Specifically, based on the principle of invariance of the projective transformation, since the calibration object in the image calibration device and the image matching the image are in a projective transformation relationship, when the image does not have water ripple, the intersection parameter and image of the image object in the image The cross-correlation parameters of the corresponding calibration objects on the calibration device are equal or have small errors. When there is a water ripple image, the intersection ratio parameters and images of the image objects in the image region where the water ripple exists in the image due to the distortion of the image The cross-correlation parameters of the corresponding calibration objects on the calibration device have a large difference, so whether the image has water ripple can be determined by comparing the cross-reference parameters of the image object and the calibration object.

Further, when the number of groups of image objects selected in step S13 is at least two, the ratio parameter according to each group of image objects in the at least one group and the ratio parameter to a corresponding group of calibration objects Determining whether there is a water ripple in the image may include: determining an average cross ratio difference according to the difference, and determining that there is water ripple in the image when the average cross ratio difference is greater than or equal to a preset threshold When the average cross ratio difference is less than a preset threshold, it is determined that there is no water ripple in the image. For example, the number of groups of image objects is 10 groups, and the intersection ratio parameters of 10 sets of image objects and the cross-parameter parameters of the corresponding 10 sets of calibration objects are respectively calculated by the above steps S541 and S542, and the intersection of each group of image objects is calculated. Comparing the difference between the parameter and the cross-parameter parameter of the corresponding calibration object to obtain 10 difference values, performing arithmetic average on the 10 difference values to obtain an average cross ratio difference, and the average cross-ratio difference value and a preset threshold value A comparison can be made to determine if there is a water ripple in the image.

Please refer to FIG. 7. FIG. 7 is a schematic flow chart of the step S14 in another embodiment of the water ripple detecting method of the image of the present application. The embodiment is based on the geometric distance error, that is, using the image object in the image calibration device to calibrate the projecting position on the plane where the object is located, and determining whether the projecting position of the image object and the position of the corresponding calibration object in the image calibration device satisfy the positional consistency. It is then determined whether there is a water ripple in the image. Specifically, compared with the embodiment shown in FIG. 1, S14 of the method of the embodiment further includes the following sub-steps:

S741: Projectively transform the position of the image object in the image to a plane where the calibration object is located in the image calibration device to obtain a projecting position of the image object.

Specifically, as described above, when there is no water ripple in the image, the image object in the image has a relationship of projective transformation with the calibration object in the image calibration device, that is, the position of the image object in the image corresponds to the image. There is a projective transformation relationship of the position of the matched calibration object in the image calibration device. The water ripple detecting device may project the position of the image object in the image to a plane on which the calibration object is located in the image calibration device, and further, according to the position of the image object in the image and the calibration object matching the image object Positioning the image object in the image to project a position of the image object in the image to a plane in which the calibration object is located in the image calibration device to obtain a projecting position of the image object, so that the image object can be acquired on the image calibration device Projective position.

In some embodiments, the projective parameter between the image object of the first preset area in the image and the matching calibration object may be determined first, and then the projective position of the image object is determined by using the projective parameter. Specifically, the projective parameter is determined according to a position of the image object of the first preset area in the image in the image and a position of the calibration object matching the image object of the first preset area in the image calibration apparatus, wherein The projective parameter may be a transformation parameter that transforms the image object of the first region at a position of the image into a position of the calibration object matching the image object in the image calibration device, wherein the image object of the first region is known in the image The projective parameter may be calculated on the premise that the position of the calibration object matching the image object of the first preset area is in the image calibration device, wherein the projective parameter may be a homography matrix. The position of the image object in the image may then be projectively transformed according to the projective parameter to a plane in which the calibration object is located in the image calibration device to obtain a projecting position of the image object.

In some embodiments, the projecting the position of the image object in the image to the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device Determining, in the calibration device, the plane in which the object is located to acquire the projective position of the image object comprises: arranging the image according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device The position of the image object in the second preset area in the image is projectively transformed to the plane in which the calibration object is located in the image calibration device to acquire the projecting position of the image object. Specifically, the water ripple detecting device selects an image of the second preset area from the image, determines a projecting position of the image object of the second preset area, and then determines an image according to the projecting position of the image object in the second preset area. Whether there is water ripple in the middle.

Further, the position of the image object in the image and the position of the calibration object matching the image object in the image calibration apparatus include: the image object according to the first preset area in the image is in the image And a position of the calibration object matching the image object of the first preset area in the image calibration device determines a projective parameter, and the image object in the second preset area of the image is in the image according to the projective parameter The position projecting is transformed to the plane in which the calibration object is located in the image calibration device to obtain the projective position of the image object.

Optionally, the first preset area and the second preset area may be set as areas that do not completely overlap. For example, the first predetermined area is an area near one or more of the four corners of the image. In the actual situation, the probability of water ripples in the four corners of the image is low, and the water ripple generally exists in the center of the image or in the vicinity of the center. Therefore, the position of the image object in the first preset area in the image is selected and Calculating the photographic parameters by the position of the calibration object matching the image object of the first preset area in the image calibration apparatus can effectively improve the calculation accuracy of the photographic parameters. Optionally, the center of the second preset area is the center of the image, that is, the second preset area is located in a central area of the image.

S742: Determine whether there is a water ripple in the image according to the projecting position of the image object.

Specifically, when there is no water ripple in the image, the projecting position of the image object and the calibration object matching the image object should be the same or only a small error in the image calibration device. When there is a water ripple in the image, there should be a large error in the projecting position of the image object and the position of the calibration object matching the image object in the image calibration device, according to the projecting position of the image object and the calibration object matching the image object. The position in the image calibration device determines if there is a water ripple in the image.

Optionally, when the image object that acquires the projecting position is in the second preset area, the image is calibrated according to the projecting position of the image object and the calibration object that matches the image object in the second preset area of the image. The position in the device determines if there is a water ripple in the image.

Alternatively, it may be determined whether the image has water ripple by comparing the obtained projective position and the position of the corresponding calibration object. For example, the difference between the projective position of the image object and the position of the calibration object matching the image object in the image calibration device is first determined; and whether there is a water ripple in the image is determined based on the difference.

Optionally, determining whether the water ripple exists in the image according to the difference value may specifically include: determining, according to the difference, a distance between a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device Determining whether there is a water ripple in the image based on the distance. For example, when the distance is higher than the preset distance threshold preset distance threshold, it is determined that there is water ripple in the image, otherwise it is determined that there is no water ripple in the image. When a plurality of image objects are obtained at the projecting position, a plurality of distances may be correspondingly obtained. At this time, the plurality of distances are sorted, and the median value is selected to be compared with the preset distance threshold value; or, the plurality of distances are compared. The distance is compared with the preset distance threshold respectively, and as long as there is a distance higher than the preset distance threshold, it is determined that there is water ripple in the image, and if all the distances are lower than the preset distance threshold, it is determined that there is no water ripple in the image.

Optionally, in order to improve the accuracy of the water ripple detection, the position of each calibration object in the image calibration device may be determined according to the projection position of the image object in each frame image of the multi-frame image captured by the image calibration device. A distance vector cluster between the corresponding projecting positions determines whether there is a water ripple in the image according to the area enclosed by the distance vector cluster.

Wherein, when there are a plurality of image objects for obtaining the projecting position in each frame of image, there are also a plurality of corresponding calibration objects, so that distance vector clusters of the plurality of calibration objects can be obtained. At this time, the average or median of the plurality of distance vector clusters may be selected to be compared with the preset area threshold. For example, determining whether the water ripple exists in the image according to the area enclosed by the distance vector cluster may specifically include: determining an average value of the area enclosed by the distance vector cluster; when the average value of the area is greater than a preset area At the threshold value, it is determined that there is water ripple in the image, otherwise it is determined that there is no water ripple in the image; or, the median value in the determined area surrounded by the plurality of distance vector clusters; when the median value is greater than the preset area threshold, the image is determined There is a water ripple in it, otherwise it is determined that there is no water ripple in the image.

For ease of understanding, the following examples are given.

In an application scenario, the video captured by the imager of the drone is acquired, and the water ripple detection is performed on the video. First, the multi-frame image on the video is extracted, assuming that three images captured by the image calibration device are acquired, and after the matching between the image object on each frame image and the calibration object on the image calibration device is completed, each frame image is selected. The image object that is closest to each of the four corners of the image as the image object of the first preset area, according to the position X' ₁ of the image object of the first preset area in each frame image on the image The projection parameter H corresponding to each frame image is calculated by the position X ₁ of the calibration object corresponding to the image object of the first preset area. Specifically, the projective parameter H can be fitted and calculated according to the equation X ₁ =HX′ ₁ . Then, according to the corresponding projective parameter H of each frame, the position X′ ₂ of the image object in the second preset area in each frame image is projectively transformed into the plane where the calibration object is located in the image calibration device to obtain the projective position. X" ₂ = HX' ₂ . The second preset area can be a quarter of the area of the image.

As shown in FIG. 8 , for convenience of description, here is an example of a calibration object that matches an image object in a second preset area, and for the one calibration object, if the position of the calibration object in the image calibration apparatus is a position A, the projection positions B, C, and D of the image objects matching the calibration object A in the three-frame image are acquired as described above, and the vector clusters AB, AC, and AD can be acquired. Further, the vector cluster can be determined. The area S _ΔBCD , wherein the area enclosed by the vector cluster can be realized by a convex hull algorithm. When the area S _{ΔBCD is} large, it indicates that there is water ripple in the image, that is, according to the area enclosed by the distance vector cluster. Determine if the image has water ripples. Further, by using the method as described above, an area surrounded by a plurality of distance vector clusters can be acquired, and an area surrounded by the plurality of distance vector clusters can be sorted, and an area enclosed by the distance vector clusters at the intermediate value is selected. The preset area threshold is compared, and if it is greater than the preset area threshold, it is determined that the video has water ripple.

Please refer to FIG. 9. FIG. 9 is a schematic structural diagram of an embodiment of a water ripple detecting device of the present application. In the present embodiment, the water ripple detecting device 900 includes a processor 91 and a memory 92 that are connected to each other.

Memory 901 can include read only memory and random access memory and provides instructions and data to processor 902. A portion of the memory 901 may also include a non-volatile random access memory.

The processor 902 may be a central processing unit (CPU), and the processor may be another general-purpose processor, a digital signal processor (DSP), or an application specific integrated circuit (ASIC). ), a Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, and the like. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

The memory 901 is used to store program instructions.

The processor 902, the program instruction is called, when the program instruction is executed, used to:

Acquiring an image captured by the image calibration device, wherein the image calibration device includes a plurality of calibration objects;

Detecting an image object of the calibration object in the image;

Matching the detected image object of the calibration object with the calibration object in the image calibration device;

Whether or not there is a water ripple in the image is determined according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device.

In some embodiments, when the processor 902 determines whether there is a water ripple in the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device, the processor 902 is specifically configured to: Determining a geometric parameter of the image object according to a position of the image object in the image; determining a geometric parameter of the calibration object matching the image object according to a position of the calibration object matching the image object in the image calibration device; according to the image object The geometric parameters and the geometric parameters of the calibration object that match the image object determine if there is a water ripple in the image.

Further, when the processor 902 determines whether there is a water ripple in the image according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object, the processor 902 may be specifically configured to: according to the geometric parameter and the image object The geometric parameters of the calibration object that the image object matches determine a geometric parameter difference; based on the difference, it is determined whether there is a water ripple in the image.

Wherein, the geometric parameter may include a cross ratio parameter.

In some embodiments, when the image object of the detected calibration object is matched with the calibration object in the image calibration device, the processor 902 is specifically configured to: select at least one of the detected image objects. a set of image objects, wherein the set of image objects includes 5 image objects; determining a calibration object in at least one set of image calibration devices that match the at least one set of image objects;

The determining, by the processor 902, the geometric parameters of the image object according to the position of the image object in the image, specifically, determining, according to the position of each group of the image objects in the at least one group, the image of each group of images The ratio parameter of the object;

The processor 902 is specifically configured to: according to the calibration object in the at least one set of image calibration devices, when determining a geometric parameter of the calibration object that matches the image object according to a position of the calibration object matching the image object in the image calibration device Determining a cross ratio parameter of each set of calibration objects at a position of the image calibration device;

The determining, by the processor 902, the geometric parameter difference according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object, specifically, determining: a cross ratio of each group of the image objects in the at least one group The difference between the parameter and the cross-parameter parameter of the corresponding set of calibration objects;

The processor 902 is configured to determine, according to the difference, whether there is a water ripple in the image, according to: a cross ratio parameter of each group of the image objects in the at least one group and a cross ratio parameter of the corresponding set of calibration objects The difference between the two determines if there is a water ripple in the image.

Further, the processor 902 determines whether there is a water ripple in the image according to a difference between a cross ratio parameter of each set of image objects in the at least one group and a cross ratio parameter of the corresponding set of calibration objects. Specifically, the average cross ratio difference is determined according to the difference; when the average cross ratio difference is greater than or equal to a preset threshold, determining that there is a water ripple in the image.

In some embodiments, when determining, according to the position of each group of image objects in the image, the intersection ratio parameter of each group of image objects, the processor 902 is specifically configured to: according to the at least one The position of each group of image objects in the group in the image determines the area of the four intersecting triangles corresponding to each group of image objects; each group of maps is determined according to the area of each of the group of image objects corresponding to four intersecting triangles Like the cross-reference parameter of the object;

The processor 902 is specifically configured to: according to the at least one set of image calibration devices, when determining, according to the calibration object in the at least one set of image calibration devices, the intersection ratio parameter of each group of calibration objects at the position of the image calibration device The calibration object in the image calibration device determines the area of the four intersecting triangles corresponding to each group of calibration objects; and determines the intersection ratio parameter of each group of calibration objects according to the area of each of the four calibration triangles corresponding to each calibration object .

Further, the processor 902 is further configured to: determine whether each of the areas of the corresponding four triangles of each group is greater than or equal to a preset area threshold;

The processor 902 is specifically configured to: when the cross-parameter parameter of each group of image objects is determined according to the area of the four intersecting triangles of each set of images, when the area of each of the four corresponding triangles is When each one is greater than or equal to the preset area threshold, the cross-parameter parameter of each group of image objects is determined according to the area of the four intersecting triangles corresponding to each set of images.

In some embodiments, when the processor 902 determines whether there is a water ripple in the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device, the processor 902 is specifically configured to: Converting a position of the image object in the image to a plane in which the calibration object is located in the image calibration device according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device Obtaining a projecting position of the image object; determining whether there is a water ripple in the image according to a projecting position of the image object.

Further, the processor 902 projectively transforms the position of the image object in the image to the image calibration device according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device. When the plane in which the object is located is obtained to obtain the projecting position of the image object, the method is specifically configured to: match the position of the image object in the image according to the first preset area in the image and the image object of the first preset area; The position of the calibration object in the image calibration device determines a projective parameter; according to the projective parameter, the position of the image object in the image is projectively transformed to a plane in which the calibration object is located in the image calibration device to obtain a projecting position of the image object.

The first preset area may be an area close to one or more of the four corners of the image.

In some embodiments, the processor 902 projectively transforms the position of the image object in the image according to the position of the image object in the image and the position of the calibration object in the image calibration device that matches the image object to When the plane of the calibration object is located in the image calibration device to obtain the projecting position of the image object, specifically, according to the position of the image object in the image and the calibration object matching the image object in the image calibration device Positioning the position of the image object in the second preset area in the image in the image to the plane of the calibration object in the image calibration device to obtain the projecting position of the image object;

The processor 902 is configured to determine whether there is a water ripple in the image according to a projecting position of the image object in the second preset area when determining whether there is a water ripple in the image according to the projecting position of the image object.

The center of the second preset area may be the center of the image.

In some embodiments, when determining whether there is a water ripple in the image according to the projecting position of the image object, the processor 902 is specifically configured to: determine a projecting position of the image object and a calibration object matching the image object in the image calibration device. The difference between the positions; the presence or absence of water ripple in the image based on the difference.

Further, the processor 902 is configured to determine, according to the difference, whether there is a water ripple in the image, according to the difference, determining, according to the difference, a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device. The distance between the two is determined based on the distance to determine whether there is a water ripple in the image.

In some embodiments, when determining, according to the projecting position of the image object, whether the water ripple exists in the image, the processor 902 is specifically configured to: according to the image in each frame image of the multi-frame image captured by the image calibration device The projecting position of the object determines a distance vector cluster between the position of each calibration object in the image calibration device and the corresponding projecting position; and determining whether there is a water ripple in the image according to the area enclosed by the distance vector cluster.

In some embodiments, when determining, according to the area enclosed by the distance vector clusters, the processor 902 determines whether there is a water ripple in the image, specifically, determining an average value of an area enclosed by the distance vector clusters; When the average of the area is greater than the preset area threshold, it is determined that there is water ripple in the image.

In some embodiments, when determining, according to an area enclosed by the distance vector cluster, whether the water ripple exists in the image, the processor 902 is specifically configured to: determine a median value among the plurality of distance vector clusters; When the median value is greater than the preset area threshold, it is determined that there is a water ripple in the image.

In some embodiments, the projective parameter is a homography matrix.

In some embodiments, when the image object of the detected calibration object is matched with the calibration object in the image device, the processor 902 is specifically configured to: determine a feature parameter of the detected image object; according to the determined feature The parameter and the characteristic parameter of the pre-stored calibration object in the image calibration device match the detected image object of the calibration object with the calibration object in the image device.

The device in this embodiment may be used to implement the technical solution of the foregoing method embodiment of the present application, and the implementation principle and the technical effect are similar, and details are not described herein again.

Please refer to FIG. 10. FIG. 10 is a schematic structural diagram of an embodiment of a water ripple detecting system of the present application. The detection system 1000 includes a photographing device 1001 and a water ripple detecting device 1002 that are connected to each other. The imaging device 1001 is configured to capture an image by the image calibration device. The water ripple detecting device 1002 is the water ripple detecting device described in the above embodiment, and will not be described herein.

Please refer to FIG. 11. FIG. 11 is a schematic structural diagram of an embodiment of the drone of the present application. In this embodiment, the unmanned aerial vehicle includes a water ripple detecting system, wherein the water ripple detecting system may specifically include the water ripple detecting device 1101 and the photographing device 1002 as described in the above system embodiment.

Further, the drone may further include a carrying device 1103, wherein the carrying device 1103 is configured to carry the photographing device 1002. In some embodiments, the drone is a rotor drone, and the camera 1002 can be a main camera of the drone. The carrier device 1103 can be a two-axis or three-axis pan/tilt.

Optionally, the drone is further provided with a function circuit such as a visual sensor and an inertial measurement device according to actual needs.

Please refer to FIG. 12. FIG. 12 is a schematic structural diagram of an embodiment of a storage device of the present application. In this embodiment, the storage device 1200 stores the program instruction 1201. When the program instruction 1201 is run on the processor, the technical solution of the foregoing method embodiment of the present application is executed.

The storage device 1200 may specifically be a medium that can store computer instructions, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Alternatively, it may be a server storing the program instructions, and the server may send the stored program instructions to other devices for running, or may also run the stored program instructions.

In the several embodiments provided by the present application, it should be understood that the disclosed methods and apparatus may be implemented in other manners. For example, the device implementations described above are merely illustrative. For example, the division of modules or units is only one logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

An integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, can be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, which can store program instructions. .

The above is only the embodiment of the present application, and thus does not limit the scope of patents of the present application, and the equivalent structure or equivalent process transformation made by using the specification and the contents of the drawings, or directly or indirectly applied to other related technical fields, The same is included in the scope of patent protection of this application.

Claims

An image water ripple detecting method, comprising:

Acquiring an image captured by the image calibration device, wherein the image calibration device includes a plurality of calibration objects;

Detecting an image object of the calibration object in the image;

Matching the detected image object of the calibration object with the calibration object in the image calibration device;

Whether or not there is a water ripple in the image is determined according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device.
The method of claim 1 wherein

Determining whether there is a water ripple in the image according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device includes:

Determining a geometric parameter of the image object according to a position of the image object in the image;

Determining a geometric parameter of the calibration object that matches the image object according to a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the geometric parameters of the image object and the geometric parameters of the calibration object that match the image object.
The method of claim 2 wherein:

Determining whether there is a water ripple in the image according to the geometric parameter of the image object and the geometric parameter of the calibration object matching the image object includes:

Determining a geometric parameter difference according to a geometric parameter of the image object and a geometric parameter of the calibration object matching the image object;

A water ripple is determined in the image based on the difference.
The method of claim 3 wherein:

The geometric parameters include cross ratio parameters.
The method of claim 4 wherein:

The matching the image object of the detected calibration object with the calibration object in the image calibration device comprises:

Selecting at least one set of image objects from the detected image objects, wherein the set of image objects includes 5 image objects;

Determining a calibration object in at least one set of image calibration devices that match the at least one set of image objects;

Determining the geometric parameters of the image object according to the position of the image object in the image includes:

Determining a cross-parameter parameter of each set of image objects according to a position of each set of image objects in the at least one set in the image;

Determining, according to the position of the calibration object matching the image object in the image calibration device, the geometric parameters of the calibration object that match the image object include:

Determining a cross-parameter parameter of each set of calibration objects according to a position of the image calibration device in the calibration object in the at least one set of image calibration devices;

Determining the geometric parameter difference according to the geometric parameter of the image object and the geometric parameter of the calibration object matching the image object includes:

Determining a difference between a cross ratio parameter of each of the at least one set of image objects and a cross ratio parameter of the corresponding set of calibration objects;

Determining whether there is a water ripple in the image according to the difference comprises:

A water ripple is determined in the image based on a difference between a cross ratio parameter of each of the at least one set of image objects and a cross ratio parameter of the corresponding set of calibration objects.
The method according to claim 5, wherein said determining an image based on a difference between a cross ratio parameter of each of said at least one set of image objects and a cross ratio parameter of a corresponding set of calibration objects Whether there are water ripples in it includes:

Determining an average cross ratio difference based on the difference;

When the average cross ratio difference is greater than or equal to a preset threshold, it is determined that there is a water ripple in the image.
Method according to claim 5 or 6, characterized in that

Determining, according to the position of each set of the image objects in the at least one group, the cross-parameter parameters of each group of image objects comprises:

Determining an area of four intersecting triangles corresponding to each group of image objects according to a position of each group of image objects in the at least one group;

Determining a cross-parameter parameter of each group of image objects according to an area of each of the set of image objects corresponding to four intersecting triangles;

Determining, according to the position of the image calibration device, the calibration target of the calibration object in the at least one set of image calibration devices includes:

Determining, according to the position of the image calibration device, the area of the four intersecting triangles corresponding to each group of calibration objects according to the calibration object in the at least one set of image calibration devices;

The cross ratio parameter of each set of calibration objects is determined according to the area of each of the set of calibration objects corresponding to 4 intersecting triangles.
The method of claim 7, wherein the method further comprises:

Determining whether each of the areas of the corresponding four triangles of each group is greater than or equal to a preset area threshold;

The determining, according to the area of the four intersecting triangles of each set of images, the cross-parameter parameters of each group of image objects includes:

When each of the areas of the corresponding four triangles of each group is greater than or equal to the preset area threshold, determining the cross ratio of each group of image objects according to the area of the four intersecting triangles of each set of images parameter.
The method of claim 1 wherein

Determining whether there is a water ripple in the image according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device includes:

Converting a position of the image object in the image to a plane in which the calibration object is located in the image calibration device according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device Obtaining a projecting position of the image object;

Whether or not there is a water ripple in the image is determined according to the projecting position of the image object.
The method of claim 9 wherein:

Converting the position of the image object in the image to the position of the calibration object in the image calibration device according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device The plane to obtain the projective position of the image object includes:

Determining a projective parameter according to a position of the image object of the first preset area in the image in the image and a position of the calibration object matching the image object of the first preset area in the image calibration apparatus;

And projecting the position of the image object in the image to the plane of the calibration object in the image calibration device according to the projective parameter to obtain a projecting position of the image object.
The method of claim 10 wherein:

The first predetermined area is an area close to one or more of the four corners of the image.
A method according to any one of claims 9-11, wherein

Converting the position of the image object in the image to the position of the calibration object in the image calibration device according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device The plane to obtain the projective position of the image object includes:

Transforming the position of the image object in the second preset area in the image into the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device Defining a plane in which the object is located in the calibration device to obtain a projecting position of the image object;

Determining whether there is a water ripple in the image according to the projecting position of the image object comprises:

Determining whether there is a water ripple in the image according to a projecting position of the image object in the second preset area.
The method of claim 12 wherein:

The center of the second preset area is the center of the image.
A method according to any one of claims 9-13, wherein

Determining whether there is a water ripple in the image according to the projecting position of the image object comprises:

Determining a difference between a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the difference.
The method according to claim 14, wherein the determining whether there is a water ripple in the image according to the difference comprises:

Determining, according to the difference, a distance between a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the distance.
A method according to any one of claims 9-13, wherein

Determining whether there is a water ripple in the image according to the projecting position of the image object comprises:

Determining a distance vector cluster between a position of each calibration object in the image calibration device and a corresponding projecting position according to a projecting position of the image object in each frame image of the multi-frame image captured by the image calibration device;

The presence or absence of water ripple in the image is determined based on the area enclosed by the distance vector clusters.
The method of claim 16 wherein:

Determining whether there is a water ripple in the image according to an area enclosed by the distance vector cluster includes:

Determining an average of the area enclosed by the distance vector clusters;

When the average of the areas is greater than the preset area threshold, it is determined that there is a water ripple in the image.
The method of claim 16 wherein:

Determining whether there is a water ripple in the image according to an area enclosed by the distance vector cluster includes:

Determining a median of the areas enclosed by the plurality of distance vector clusters;

When the median is greater than the preset area threshold, it is determined that there is a water ripple in the image.
The method of claim 10 wherein said projective parameter is a homography matrix.
The method of claim 1 wherein

The matching of the detected image object of the calibration object with the calibration object in the image device includes:

Determining a position feature parameter of the detected image object according to a position of the image object in the image;

And matching the detected image object of the calibration object with the calibration object in the image device according to the determined position feature parameter and the pre-stored position feature parameter of the calibration object.
A water ripple detecting device, comprising: a processor and a memory, wherein

The memory is configured to store program instructions;

The processor executing the program instructions for:

Acquiring an image captured by the image calibration device, wherein the image calibration device includes a plurality of calibration objects;

Detecting an image object of the calibration object in the image;

Matching the detected image object of the calibration object with the calibration object in the image calibration device;

Whether or not there is a water ripple in the image is determined according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device.
The device according to claim 21, wherein

And determining, by the processor, whether there is a water ripple in the image according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device, specifically for:

Determining a geometric parameter of the image object according to a position of the image object in the image;

Determining a geometric parameter of the calibration object that matches the image object according to a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the geometric parameters of the image object and the geometric parameters of the calibration object that match the image object.
The device according to claim 22, wherein

The processor is configured to determine whether there is a water ripple in the image according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object, specifically for:

Determining a geometric parameter difference according to a geometric parameter of the image object and a geometric parameter of the calibration object matching the image object;

A water ripple is determined in the image based on the difference.
The device according to claim 23, wherein

The geometric parameters include cross ratio parameters.
The device according to claim 24, wherein

The processor is specifically configured to: when the image object of the detected calibration object is matched with the calibration object in the image calibration device,

Selecting at least one set of image objects from the detected image objects, wherein the set of image objects includes 5 image objects;

Determining a calibration object in at least one set of image calibration devices that match the at least one set of image objects;

The processor is specifically configured to: when determining a geometric parameter of the image object according to a position of the image object in the image:

Determining a cross-parameter parameter of each set of image objects according to a position of each set of image objects in the at least one set in the image;

The processor is specifically configured to: when determining, according to a position of the calibration object matching the image object in the image calibration device, a geometric parameter of the calibration object that matches the image object, specifically:

Determining a cross-parameter parameter of each set of calibration objects according to a position of the image calibration device in the calibration object in the at least one set of image calibration devices;

The determining, when determining the geometric parameter difference according to the geometric parameter of the image object and the geometric parameter of the calibration object that matches the image object, is specifically used to:

Determining a difference between a cross ratio parameter of each of the at least one set of image objects and a cross ratio parameter of the corresponding set of calibration objects;

The processor is configured to: when determining whether there is a water ripple in the image according to the difference,

A water ripple is determined in the image based on a difference between a cross ratio parameter of each of the at least one set of image objects and a cross ratio parameter of the corresponding set of calibration objects.
The apparatus according to claim 25, wherein said processor is in accordance with a difference between a cross-parameter parameter of each set of image objects in said at least one group and a cross-parameter parameter of a corresponding set of calibration objects When the value determines whether there is water ripple in the image, it is specifically used to:

Determining an average cross ratio difference based on the difference;

When the average cross ratio difference is greater than or equal to a preset threshold, it is determined that there is a water ripple in the image.
Device according to claim 25 or 26, characterized in that

The processor is specifically configured to: when determining a cross-parameter parameter of each group of image objects according to a position of each group of image objects in the image in the at least one group:

Determining an area of four intersecting triangles corresponding to each group of image objects according to a position of each group of image objects in the at least one group;

Determining a cross-parameter parameter of each group of image objects according to an area of each of the set of image objects corresponding to four intersecting triangles;

The processor is specifically configured to: when determining, according to the calibration object in the at least one set of image calibration devices, the intersection ratio parameter of each group of calibration objects at the position of the image calibration device:

Determining, according to the position of the image calibration device, the area of the four intersecting triangles corresponding to each group of calibration objects according to the calibration object in the at least one set of image calibration devices;

The cross ratio parameter of each set of calibration objects is determined according to the area of each of the set of calibration objects corresponding to 4 intersecting triangles.
The device according to claim 27, wherein the processor is further configured to:

Determining whether each of the areas of the corresponding four triangles of each group is greater than or equal to a preset area threshold;

The processor is specifically configured to: when determining, according to the area of the four intersecting triangles of each group of images, the intersection ratio parameter of each group of image objects:

When each of the areas of the corresponding four triangles of each group is greater than or equal to the preset area threshold, determining the cross ratio of each group of image objects according to the area of the four intersecting triangles of each set of images parameter.
The device according to claim 21, wherein

And determining, by the processor, whether there is a water ripple in the image according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device, specifically for:

Converting a position of the image object in the image to a plane in which the calibration object is located in the image calibration device according to a position of the image object in the image and a position of the calibration object matching the image object in the image calibration device Obtaining a projecting position of the image object;

Whether or not there is a water ripple in the image is determined according to the projecting position of the image object.
The device according to claim 29, wherein

Converting, by the processor, the position of the image object in the image to the image calibration device according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device When the plane of the object is located to obtain the projective position of the image object, it is specifically used to:

Determining a projective parameter according to a position of the image object of the first preset area in the image in the image and a position of the calibration object matching the image object of the first preset area in the image calibration apparatus;

And projecting the position of the image object in the image to the plane of the calibration object in the image calibration device according to the projective parameter to obtain a projecting position of the image object.
The device of claim 30 wherein:

The first predetermined area is an area close to one or more of the four corners of the image.
A device according to any of claims 29-31, characterized in that

Converting, by the processor, the position of the image object in the image to the image calibration device according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device When the plane of the object is located to obtain the projective position of the image object, it is specifically used to:

Transforming the position of the image object in the second preset area in the image into the image according to the position of the image object in the image and the position of the calibration object matching the image object in the image calibration device Defining a plane in which the object is located in the calibration device to obtain a projecting position of the image object;

The processor is configured to: when determining whether there is a water ripple in the image according to the projecting position of the image object, specifically:

Determining whether there is a water ripple in the image according to a projecting position of the image object in the second preset area.
The device of claim 32, wherein

The center of the second preset area is the center of the image.
Device according to any of claims 29-33, characterized in that

The processor is configured to: when determining whether there is a water ripple in the image according to the projecting position of the image object, specifically:

Determining a difference between a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the difference.
The device according to claim 34, wherein the processor is configured to: when determining whether there is a water ripple in the image according to the difference, specifically:

Determining, according to the difference, a distance between a projecting position of the image object and a position of the calibration object matching the image object in the image calibration device;

A water ripple is determined in the image based on the distance.
Device according to any of claims 29-33, characterized in that

The processor is configured to: when determining whether there is a water ripple in the image according to the projecting position of the image object, specifically:

Determining a distance vector cluster between a position of each calibration object in the image calibration device and a corresponding projecting position according to a projecting position of the image object in each frame image of the multi-frame image captured by the image calibration device;

The presence or absence of water ripple in the image is determined based on the area enclosed by the distance vector clusters.
The device of claim 36, wherein

The processor is configured to determine whether there is a water ripple in the image according to an area enclosed by the distance vector clusters, specifically for:

Determining an average of the area enclosed by the distance vector clusters;

When the average of the areas is greater than the preset area threshold, it is determined that there is a water ripple in the image.
The device of claim 36, wherein

The processor is configured to determine whether there is a water ripple in the image according to an area enclosed by the distance vector clusters, specifically for:

Determining a median of the areas enclosed by the plurality of distance vector clusters;

When the median is greater than the preset area threshold, it is determined that there is a water ripple in the image.
The apparatus of claim 30 wherein said projective parameter is a homography matrix.
The device according to claim 21, wherein

When the processor matches the detected image object of the calibration object with the calibration object in the image device, the processor is specifically configured to:

Determining a position feature parameter of the detected image object according to a position of the image object in the image;

And matching the detected image object of the calibration object with the calibration object in the image device according to the determined position feature parameter and the pre-stored position feature parameter of the calibration object.
A water ripple detecting system, comprising: a photographing device and a water ripple detecting device according to any one of claims 21 to 40, wherein

The photographing device is configured to photograph an image calibration device.
A drone characterized by comprising the water ripple detecting system of claim 41.
A storage device, characterized in that the storage device stores program instructions, and when the program instructions are run on a processor, performs the method of any one of claims 1-20.