Target object detection method, device, equipment and storage medium

Abstract

Embodiments of the present invention disclose a target object detection method, apparatus, device, and storage medium. The method includes obtaining first position information of a first target object, determining a detection area for a second target object based on the first position information, target object setting parameters, and a preset angular direction, detecting the second target object within the detection area, determining whether to generate a second target object based on the detection result, and detecting the next target object. This solution achieves automatic detection of target objects with high detection accuracy and good recognition effect.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of unmanned equipment operation, and in particular to a target object detection method, apparatus, device, and storage medium. Background Art

[0002] With the development of unmanned equipment technology, using unmanned equipment to operate in the work area has become one of the mainstream operation methods. For the work area, how to accurately and efficiently determine the target objects contained in it is an essential part of the operation process.

[0003] In the existing technology, when detecting target objects in the working area, relevant conclusions and opinions are mostly given through manual subjective judgment, and there is a lack of a reasonable and efficient detection mechanism. Summary of the Invention

[0004] The embodiments of the present invention provide a target object detection method, device, equipment and storage medium, which solve the problems of low target object detection efficiency and inability to realize automated detection in the prior art, and realize automatic detection of target objects with high detection accuracy and good recognition effect.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting a target object, the method comprising:

[0006] Acquire first position information of a first target object, and determine a detection area of ​​a second target object according to the first position information, target object setting parameters, and a preset angle direction;

[0007] performing detection of a second target object in the detection area;

[0008] Based on the detection result, it is determined whether to generate a second target object, and the next target object is detected.

[0009] In a second aspect, an embodiment of the present invention further provides a target object detection system, the system comprising:

[0010] an area generation module, configured to obtain first position information of a first target object, and determine a detection area for a second target object based on the first position information, target object setting parameters, and a preset angle direction;

[0011] The detection processing module is used to detect the second target object in the detection area, determine whether to generate the second target object based on the detection result, and detect the next target object.

[0012] In a third aspect, an embodiment of the present invention further provides a target object detection device, the device comprising:

[0013] one or more processors;

[0014] a storage device for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the target object detection method described in the embodiment of the present invention.

[0016] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer-executable instructions, which, when executed by a computer processor, are used to execute the target object detection method described in the embodiment of the present invention.

[0017] In an embodiment of the present invention, by obtaining the first position information of the first target object, the detection area of ​​the second target object is determined according to the first position information, the target object setting parameters and the preset angle direction, and then the second target object is detected in the detection area. Based on the detection result, it is determined whether to generate the second target object, and the next target object is detected, thereby realizing automatic detection of the target object with high detection accuracy and good recognition effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a target object detection method provided by an embodiment of the present invention;

[0019] Figure 2 A flowchart of a method for determining a detection area of ​​a second target object provided by an embodiment of the present invention;

[0020] Figure 3 A first plane geometric diagram for determining a second target object detection area provided by an embodiment of the present invention;

[0021] Figure 4 A second plane geometric diagram for determining a second target object detection area provided by an embodiment of the present invention;

[0022] Figure 5 A flowchart of another target object detection method provided by an embodiment of the present invention;

[0023] Figure 6 A digital orthophoto map of the working area provided by an embodiment of the present invention;

[0024] Figure 7 The green leaf index image after band calculation processing provided by the embodiment of the present invention;

[0025] Figure 8 A schematic diagram of an identified seedling outline and target object provided by an embodiment of the present invention;

[0026] Figure 9A schematic diagram of a module of a target object detection device provided by an embodiment of the present invention;

[0027] Figure 10 A schematic structural diagram of a target object detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0029] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0030] The target object detection method provided in the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0031] Figure 1 This is a flow chart of a target object detection method provided by an embodiment of the present invention. This embodiment can realize automatic detection and identification of target objects in an operation area. The method can be implemented by a device with computing capabilities, such as an unmanned device, a mobile phone, a remote control, a customized handheld device, a desktop computer, a tablet computer, or a laptop. The method specifically includes the following steps:

[0032] Step S101: Acquire first position information of a first target object, and determine a detection area for a second target object according to the first position information, target object setting parameters, and a preset angle direction.

[0033] The first target object may be a target object set by a user or an object selected from an image after image processing according to a preset rule. In one embodiment, the first target object is used to represent the location of crops in the operation area, such as the location of seedling holes for crop seedlings in a farmland.

[0034] The first location information is used to represent the location of the first target object. This location information can be a specific geographic location in the actual operation area or a virtual coordinate location determined according to a set coordinate system. The target object setting parameters are parameters related to the target object. In one embodiment, taking crops in a farmland as an example, the target object setting parameters include crop spacing, crop row spacing, and a set threshold value. The crop spacing is the distance between the front and back crops in a row of continuously planted crops, the crop row spacing is the distance between rows of each crop row, and the threshold value is a variable parameter set by the user. Specifically, in this embodiment, the target object setting parameters include a first setting parameter value, a second setting parameter value, and a threshold parameter value. The first setting parameter value is the crop spacing, the second setting parameter value is the crop row spacing, and the threshold parameter value is illustratively one-tenth of the crop spacing. Of course, the first setting parameter can also be set to twice the crop spacing, and the second setting parameter can also be set to twice the crop row spacing. The specific distance setting can be adaptively adjusted according to different crop types and target object detection requirements. Similarly, the threshold parameter value can also be adaptively adjusted, such as adjusted to one-fifth of the crop spacing. The first and second setting parameters can be adjusted proportionally or non-proportionally. For example, the first setting parameter is twice the crop spacing, and the second setting parameter is 1.5 times the crop row spacing. By default, the crop row spacing is greater than the crop plant spacing. That is, when the crop plant spacing is used as the first setting parameter and the crop row spacing is used as the second setting parameter, the parameter value of the second setting parameter is greater than the parameter value of the first setting parameter.

[0035] In one embodiment, the preset angle direction refers to a direction pointing toward another area with the location of the first target object as a reference point. Taking the established horizontal and vertical coordinate system as an example, this can be a preset direction that forms a preset angle with the horizontal or vertical axis. The second target object is a target object, distinct from the first target object, whose presence in the detection area needs to be determined. The detection area is an area determined based on the first location information, the target object setting parameters, and the preset angle direction.

[0036] Figure 2 A flowchart of a method for determining a detection area for a second target object provided by an embodiment of the present invention is provided. The method uses a first target object as a reference object and determines a detection area for the second target object based on target object setting parameters and a preset angle direction. For example, the position information of the first target object is a first coordinate, and the target object setting parameters include a first setting parameter value, a second setting parameter value, and a threshold parameter value. The specific process for determining the detection area is as follows:

[0037] Step S1011: With the first coordinate as the center, the sum and difference of the first parameter value and the threshold parameter as the radius, and a first semicircular area and a second semicircular area are generated in a preset angle direction.

[0038] like Figure 3 As shown, Figure 3 A schematic diagram of a first plane geometry for determining a second target object detection area is provided in an embodiment of the present invention. The first coordinate is represented by O1, which is the coordinate origin. Taking the target object as a crop seedling as an example, the coordinate represents the seedling hole location of the crop seedling. The first parameter value representing the crop plant spacing is recorded as a, and the threshold parameter value is recorded as c. With the first coordinate O1 as the center, the sum and difference of the first parameter value and the threshold parameter, i.e., a+c and ac, are used as radii to determine a first semicircular area S1 and a second semicircular area S2. The determination of the first and second semicircular areas S1 and S2 is based on a preset angle direction. Specifically, taking the crop plant absence detection scene as an example, the coordinate system uses the first coordinate O1 as the origin, the y-axis of the vertical coordinate is parallel to the plant spacing direction, and the x-axis of the horizontal coordinate is rotated 90° clockwise to the direction of the x-axis. The direction of the y-axis of the vertical coordinate is the preset angle direction, i.e., the first and second semicircular areas S1 and S2 are semicircular areas with the preset angle direction as the axis of symmetry.

[0039] In another embodiment, taking the second parameter value as the crop row spacing denoted as b as an example, the first semicircular area S1 can also be a first semicircular area determined by taking the first coordinate O1 as the center and b+c as the radius, and the second semicircular area S2 is correspondingly a second semicircular area determined by taking the first coordinate O1 as the center and bc as the radius.

[0040] In another embodiment, during the generation of the first semicircular area S1 and the second semicircular area S2, the radius thereof may be determined independently of the threshold parameter value. Specifically, taking the case where the target object setting parameters include a first setting parameter value (denoted as a) and a second setting parameter value (denoted as b) as an example, the radius of the first semicircular area determined based on the first setting parameter value may be 1.2*a, and the radius of the second semicircular area determined based on the first setting parameter value may be 0.8*a.

[0041] Step S1012: With the first coordinate as the center, the first parameter value as the minor axis of the ellipse, and the second parameter value as the major axis of the ellipse, a semi-ellipse area is generated in the preset angle direction.

[0042] in, Figure 3 The semi-elliptical region S3 in the geometric image shown is determined by taking the first coordinate O1 as the center, the first parameter value a as the minor axis of the ellipse, and the second parameter value b as the major axis of the ellipse. Similarly, the semi-elliptical region is also determined based on the above-mentioned predetermined angle direction, using it as the axis of symmetry.

[0043] Step S1013: Determine a first intersection point and a second intersection point between the first semicircular area and the semi-elliptical area, and generate a sector-shaped area based on the first intersection point, the second intersection point, and the first coordinates.

[0044] Among them, such as Figure 3 As shown, the first intersection point of the first semicircular area S1 and the semi-elliptical area S3 is recorded as P1, the first intersection point of the second semicircular area S2 and the semi-elliptical area S3 is recorded as P2, and the fan-shaped area determined based on the first intersection point P1 and the second intersection point P2 and the first coordinate O1 is recorded as S4.

[0045] Step S1014 : Subtract the overlapping area between the first semicircular area and the second semicircular area from the overlapping area between the fan-shaped area and the first semicircular area to obtain a detection area for the second target object.

[0046] Figure 4 A second plane geometric diagram for determining a second target object detection area provided by an embodiment of the present invention. Figure 4 As shown, after determining the sector area S4, the overlapping area between the first semicircular area S1 and the second semicircular area S2 is subtracted from the overlapping area between the sector area S4 and the first semicircular area S1 to obtain the detection area S5 of the second target object, that is, S5 = (S1-S2)∩S4.

[0047] Step S102: Detect a second target object in the detection area.

[0048] In one embodiment, after determining a detection area for a second target object based on the first target object, the second target object is detected in the detection area to determine whether the second target object is detected. Taking crop seedling deficiency detection as an example, to determine whether there are any seedling deficiency signs in the current crop area, the first target object is used as a reference object and a reasonable detection area for the second target object is determined. If the second target object is detected, it means that there is no seedling deficiency in the area where the first target object is located, under the premise that the current first target object is used as the reference object. Otherwise, there is a seedling deficiency, thereby achieving seedling deficiency detection.

[0049] Step S103: Determine whether to generate a second target object based on the detection result, and detect the next target object.

[0050] In the process of detecting the target object, the next detection process is determined based on whether the second target object is detected in the detection area of ​​the second target object to complete the corresponding detection.

[0051] Specifically, if the second target object is not detected in the detection area, a second target object is generated in the detection area, and the third target object is detected with the second target object as a reference object; if the second target object is detected in the detection area, the third target object is detected with the second target object as a reference object. Figure 4 As shown, during the detection process of the second target object O2, if it is not in the detection area S5, a second target object T1 is generated in the detection area S5, and subsequently T1 is used as a new reference object. For example, the above process of generating a semicircular area, an elliptical area, and a sector area is performed with the coordinates of the position of T1 as the center of the circle, and then the detection area is determined to further determine whether there is a third target object in the newly generated detection area, and so on until the detection of missing crop seedlings in the row is completed.

[0052] Optionally, if the second target object is not detected in the detection area S5, when generating a new second target object T1, the position point of the second target object T1 can be any point on the intersection line of the detection area S5 and the vertical coordinate axis y, such as the midpoint of the intersection line segment as the position coordinate of the second target object T1.

[0053] From the above, it can be seen that in the target object detection method of this scheme, the detection area is determined according to the position information of the first target object, the target object setting parameters and the preset angle direction, and then the adjacent target objects are detected and generated to achieve missing seedling detection in the missing seedling detection scenario, thereby realizing automatic detection of target objects without the need for human subjective judgment, and its detection accuracy is high and the recognition effect is good.

[0054] Figure 5 A flowchart of another target object detection method provided by an embodiment of the present invention provides a method for identifying a target object in an operating area, specifically including:

[0055] Step S201: Determine a target object in an operation area based on image data captured by an unmanned device.

[0056] The unmanned equipment may be a drone, and the image data captured by the unmanned equipment is image data captured when the unmanned equipment is flying over the work area. The image data may be a digital orthophoto. Optionally, the method for determining the target object in the work area based on the digital orthophoto includes: obtaining the digital orthophoto captured by the unmanned equipment in the work area, and the digital surface model corresponding to the work area; performing band operation processing on the digital orthophoto to obtain a green leaf index image; performing image segmentation processing on the green leaf index image based on a preset threshold, and superimposing the segmentation processing result with the digital surface model and performing contour recognition to obtain the target object. The digital orthophoto is a set of digital orthophotos generated by digitally differentially correcting and mosaicking high-altitude image photos and cropping them according to a certain map range. It has both map geometric accuracy and image characteristics. A digital surface model refers to a ground elevation model that includes the heights of surface buildings, bridges, trees, crop plants, etc. The GLI image is obtained by performing band arithmetic processing on the digital orthophoto. The calculation formula is exemplarily: GLI = (2*GREEN-RED-BLUE) / (2*GREEN+RED+BLUE). The green leaf index (GLI) in the green leaf index image can be used to identify soil and vegetation areas. It was first proposed by Louhaichi et al. to record the impact of grazing on wheat. The GLI index generates a grayscale image by determining whether the average DN value of the red and blue light bands is greater than the DN value of the green light band. It is then normalized so that the pixel values ​​of the resulting image are between -1 and 1. The preset threshold based on can be exemplarily 0.5. For example, pixel values ​​less than 0.5 are determined to be crop seedling boundaries, and those greater than 0.5 are determined to be soil, thereby achieving image segmentation. After the image segmentation is completed, since there may be a lot of surface debris, the target object cannot be identified. At this time, a step is added to superimpose the segmentation processing results with the digital surface model, that is, the two-dimensional segmentation results are fused with the elevation of the corresponding position points. Since the height of crop seedlings is higher than the height of ground debris such as weeds and gravel, the crop seedling area can be significantly determined after fusion, and contour recognition is performed to finally obtain the target object in the crop area, which is the seedling hole position of the crop seedling.

[0057] In one embodiment, taking the detection of whether there is a shortage of seedlings in the operation area as an example, Figure 6 The digital orthophoto image of the working area provided by the embodiment of the present invention corresponds to the green leaf index image obtained by band operation processing, such as Figure 7 As shown, Figure 7 This is a green leaf index image after band calculation processing provided by an embodiment of the present invention. Figure 8A schematic diagram of an identified seedling outline and target object provided by an embodiment of the present invention, wherein the target object is the area where the roots of the crop seedlings are located, which is determined as the seedling hole location.

[0058] Step S202: Determine a first target object in the image of the working area containing the target object, and obtain first position information of the first target object.

[0059] In one embodiment, the first target object can be manually selected by the user, designating one of the identified multiple target objects as the first target object. Alternatively, the first target object can be determined in the work area image according to a preset first target object selection rule. The first target object selection rule can be to identify horizontal or vertical target objects starting from a corner of the work area image, such as the lower left corner, and determine the first target object identified as the first target object.

[0060] Step S203: determining a detection area for a second target object according to the first position information, target object setting parameters, and a preset angle direction.

[0061] Step S204: Detect a second target object in the detection area, determine whether to generate a second target object based on the detection result, and detect the next target object.

[0062] Accordingly, when determining the detection area for detecting the second target object, it is determined whether the target object identified based on the aforementioned image data falls within the detection area. If so, the detection is determined to be successful; otherwise, the detection is determined to be a failure.

[0063] From the above, it can be seen that after the image data is captured by unmanned equipment, the target object is identified by combining it with the digital surface model and band operation, and then the target object is detected based on the accurate position of the identified target object to determine whether it meets the requirements. The automatic detection of the target object is realized throughout the process, and its application in the field of seedling shortage detection is effective.

[0064] Based on the above technical solution, after generating the second target object in the detection area, the method further includes: generating a target object operation map based on all generated target objects; and controlling unmanned equipment to perform operations at the locations of the generated target objects in the operation area. Specifically, through the above target object detection method, corresponding target objects, i.e., seedling hole locations, can be generated in an area with a coordinate that meets the requirements. For areas lacking seedlings, unmanned equipment, such as an unmanned vehicle, can perform seedling planting operations at the corresponding target object locations in the operation area, thereby achieving automatic seedling replenishment.

[0065] On the basis of the above technical solution, after obtaining the image data taken by the unmanned equipment, a rough target object detection process is also included, which specifically includes: dividing the image data into blocks to obtain multiple block image data; performing contour recognition on each block image data, and binarizing the recognition result; and determining whether the target object exists in the working area corresponding to each block image data based on the binarization processing result. Specifically, the content of the block image data is roughly identified by binarization processing. If, after binarization processing, a large area of ​​the binarization processing result corresponding to the block image data has the same value, it is determined that the image content of the area is single, that is, there are no target objects (crop seedling holes) arranged alternately, and it is judged to be a seedling-missing area. By combining fine detection and rough detection of target objects, the real-time and accurate target object detection requirements can be met at the same time, and the target object detection mechanism is further improved.

[0066] Figure 8 This is a module diagram of a target object detection device provided by an embodiment of the present invention. The device is used to execute the target object detection method described above and has the corresponding functional modules and beneficial effects of the execution method. Figure 8 As shown, the device specifically includes: a region generation module 101 and a detection processing module 102, wherein:

[0067] The area generation module 101 is configured to obtain first position information of a first target object, and determine a detection area for a second target object based on the first position information, target object setting parameters, and a preset angle direction;

[0068] The detection processing module 102 is configured to detect a second target object in the detection area, determine whether to generate a second target object based on the detection result, and detect the next target object.

[0069] It can be seen from the above scheme that by obtaining the first position information of the first target object, determining the detection area of ​​the second target object according to the first position information, the target object setting parameters and the preset angle direction, and then detecting the second target object in the detection area, determining whether to generate the second target object based on the detection result, and detecting the next target object, automatic detection of the target object is achieved, with high detection accuracy and good recognition effect.

[0070] In a possible embodiment, the detection processing module 102 is specifically configured to:

[0071] If the second target object is not detected in the detection area, generating a second target object in the detection area, and detecting a third target object using the second target object as a reference object;

[0072] If a second target object is detected in the detection area, a third target object is detected using the detected second target object as a reference object.

[0073] In a possible embodiment, the target object generation module 103 is configured to:

[0074] Before obtaining the first position information of the first target object, determining the target object in the operation area according to the image data captured by the unmanned equipment;

[0075] The region generation module 101 is specifically configured to:

[0076] A first target object is determined in the work area image containing the target object, and first position information of the first target object is acquired.

[0077] In a possible embodiment, the target object generation module 103 is specifically configured to:

[0078] Obtaining digital orthophotos taken by unmanned equipment in the operation area and a digital surface model corresponding to the operation area;

[0079] Performing band calculation processing on the digital orthophoto to obtain a green leaf index image;

[0080] The green leaf index image is segmented based on a preset threshold, and the segmentation result is superimposed with the digital surface model and contours are identified to obtain a target object.

[0081] In a possible embodiment, the region generating module 101 is specifically configured to:

[0082] According to a preset first target object selection rule, a first target object is determined in the working area image, and first position information of the first target object is obtained according to set coordinate system information of the working area image.

[0083] In a possible embodiment, the target object setting parameters include a first setting parameter value, a second setting parameter value, and a threshold parameter value, the second setting parameter value is greater than the first setting parameter value, the first location information includes a first coordinate, and the area generation module 101 is specifically configured to:

[0084] With the first coordinate as the center of the circle, the sum and difference of the first parameter value and the threshold parameter are respectively the radius, and a first semicircular area and a second semicircular area are generated in the preset angle direction; or with the first coordinate as the center of the circle, the sum and difference of the second parameter value and the threshold parameter are respectively the radius, and a first semicircular area and a second semicircular area are generated in the preset angle direction;

[0085] With the first coordinate as the center, the first parameter value as the minor axis of the ellipse, and the second parameter value as the major axis of the ellipse, a semi-ellipse area is generated in the preset angle direction;

[0086] Determine a first intersection point and a second intersection point between the first semicircular area and the semi-elliptical area, and generate a sector-shaped area based on the first intersection point, the second intersection point, and the first coordinate;

[0087] The detection area of ​​the second target object is obtained by subtracting the overlapping area of ​​the first semicircular area and the second semicircular area from the overlapping area of ​​the fan-shaped area and the first semicircular area.

[0088] In a possible embodiment, the detection processing module 102 is specifically configured to:

[0089] It is determined whether a target object determined by the image data exists in the detection area.

[0090] In a possible embodiment, the target object generation module 103 is specifically configured to:

[0091] Dividing the image data into blocks to obtain a plurality of block image data;

[0092] Perform contour recognition on each block of image data and perform binarization processing on the recognition results;

[0093] Determine whether there is a target object in the operation area corresponding to each block image data based on the binarization processing result.

[0094] In a possible embodiment, the device further includes an automatic operation module 104, configured to:

[0095] After generating a second target object in the detection area, generating a target object operation map based on all generated target objects;

[0096] Control the unmanned equipment to operate at the location of the generated target object in the operation area.

[0097] Figure 9 A schematic diagram of the structure of a target object detection device provided by an embodiment of the present invention is shown in FIG. Figure 9 As shown, the device includes a processor 201, a memory 202, an input device 203 and an output device 204; the number of processors 201 in the device can be one or more. Figure 9 In the embodiment, a processor 201 is used as an example; the processor 201, the memory 202, the input device 203 and the output device 204 in the device can be connected by a bus or other means. Figure 9The example of the connection via a bus is taken. The memory 202, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the target object detection method in the embodiment of the present invention. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 202, that is, realizes the above-mentioned target object detection method. The input device 203 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the device. The output device 204 may include a display device such as a display screen.

[0098] An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which may be stored in the form of a server application. When the computer-executable instructions are executed by a computer processor, they are used to perform a target object detection method, the method comprising:

[0099] Acquire first position information of a first target object, and determine a detection area of ​​a second target object according to the first position information, target object setting parameters, and a preset angle direction;

[0100] performing detection of a second target object in the detection area;

[0101] Based on the detection result, it is determined whether to generate a second target object, and the next target object is detected.

[0102] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be an unmanned device, a mobile phone, a computer, a server or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0104] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A target object detection method, characterized in that: include: Acquiring first position information of a first target object, where the first position information is used to represent a position of a crop in an operation area; Determine a detection area for a second target object based on the first position information, target object setting parameters, and a preset angle direction, wherein the target object setting parameters are parameters related to the first target object, the preset angle direction refers to a direction pointing to other areas with the position of the first target object as a reference starting point, the second target object is a target object different from the first target object and its presence needs to be determined in the detection area, the target object setting parameters include a first setting parameter value, a second setting parameter value, and a threshold parameter value, the second setting parameter value is greater than the first setting parameter value, wherein the first setting parameter value is the crop spacing, the second setting parameter value is the crop row spacing, and the detection area is a crop planting area with evenly distributed plant spacing and row spacing; performing detection of a second target object in the detection area; Based on the detection result, it is determined whether to generate a second target object, and the next target object is detected.

2. The target object detection method according to claim 1, characterized in that: The first target object is a reference object, and determining whether to generate a second target object based on the detection result and detecting the next target object includes: If the second target object is not detected in the detection area, generating a second target object in the detection area, and detecting a third target object using the second target object as a reference object; If a second target object is detected in the detection area, a third target object is detected using the detected second target object as a reference object.

3. The target object detection method according to claim 1, characterized in that: Before obtaining the first location information of the first target object, the method further includes: Determine the target object in the operation area based on the image data captured by the unmanned equipment; The obtaining of first location information of the first target object includes: A first target object is determined in the work area image containing the target object, and first position information of the first target object is acquired.

4. The target object detection method according to claim 3, characterized in that: Determining the target object in the operation area based on the image data captured by the unmanned equipment includes: Obtaining digital orthophotos taken by unmanned equipment in the operation area and a digital surface model corresponding to the operation area; Performing band calculation processing on the digital orthophoto to obtain a green leaf index image; The green leaf index image is segmented based on a preset threshold, and the segmentation result is superimposed with the digital surface model and contours are identified to obtain a target object.

5. The target object detection method according to claim 3, characterized in that: The determining the first target object and obtaining the first location information of the first target object includes: According to a preset first target object selection rule, a first target object is determined in the working area image, and first position information of the first target object is obtained according to set coordinate system information of the working area image.

6. The target object detection method according to any one of claims 1 to 5, characterized in that: The first position information includes a first coordinate, and determining a detection area of ​​the second target object according to the first position information, target object setting parameters, and a preset angle direction includes: With the first coordinate as the center of the circle, the sum and difference of the first setting parameter value and the threshold parameter are respectively the radius, and a first semicircular area and a second semicircular area are generated in the preset angle direction; or with the first coordinate as the center of the circle, the sum and difference of the second setting parameter value and the threshold parameter are respectively the radius, and a first semicircular area and a second semicircular area are generated in the preset angle direction; With the first coordinate as the center of the circle, the first setting parameter value as the minor axis of the ellipse, and the second setting parameter value as the major axis of the ellipse, a semi-ellipse area is generated in the preset angle direction; Determine a first intersection point and a second intersection point between the first semicircular area and the semi-elliptical area, and generate a sector-shaped area based on the first intersection point, the second intersection point, and the first coordinate; The detection area of ​​the second target object is obtained by subtracting the overlapping area of ​​the first semicircular area and the second semicircular area from the overlapping area of ​​the fan-shaped area and the first semicircular area.

7. The target object detection method according to claim 3, characterized in that: Detecting a second target object in the detection area includes: It is determined whether a target object determined by the image data exists in the detection area.

8. The target object detection method according to claim 3, wherein: Determining the target object in the operation area based on the image data captured by the unmanned equipment includes: Dividing the image data into blocks to obtain a plurality of block image data; Perform contour recognition on each block of image data and perform binarization processing on the recognition results; Determine whether there is a target object in the operation area corresponding to each block image data based on the binarization processing result.

9. The target object detection method according to claim 2, characterized in that: After generating the second target object in the detection area, the method further includes: generating a target object operation graph according to all generated target objects; Control the unmanned equipment to operate at the location of the generated target object in the operation area.

10. A target object detection device, characterized in that: include: an area generation module, configured to obtain first position information of a first target object, and determine a detection area for a second target object based on the first position information, target object setting parameters, and a preset angle direction, wherein the first position information is used to characterize the position of crops in an operating area, the target object setting parameters are parameters related to the first target object, and the preset angle direction refers to a direction pointing to other areas with the position of the first target object as a reference starting point, the second target object is a target object different from the first target object and its presence in the detection area needs to be determined, the target object setting parameters include a first setting parameter value, a second setting parameter value, and a threshold parameter value, the second setting parameter value being greater than the first setting parameter value, wherein the first setting parameter value is the crop spacing, the second setting parameter value is the crop row spacing, and the detection area is a crop planting area with evenly distributed plant and row spacings; The detection processing module is used to detect the second target object in the detection area, determine whether to generate the second target object based on the detection result, and detect the next target object.

11. A target object detection device, comprising: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the target object detection method according to any one of claims 1 to 9.

12. A storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to perform the target object detection method according to any one of claims 1 to 9 when executed by a computer processor.

Images