Similarity-based anti-agricultural spraying smoke interference processing method, device and medium

Abstract

The present invention provides a similarity-based anti-agricultural spraying smoke interference processing method, device and medium, which are applied to forest fire smoke alarm and relate to the field of forest fire monitoring, including: S1: obtaining a suspected smoke feature area; S2: obtaining and storing the coordinate information (X, Y) of each pixel point in the upper half of the suspected smoke feature area; S3: compressing the suspected smoke feature area in the upper half vertically, that is, counting the number of rows of each column of pixels, and obtaining a statistical array Q; S4: dividing the statistical array Q into a statistical array Q1 and a statistical array Q2 according to symmetry points; S5: compressing the statistical array Q1 and the statistical array Q2 horizontally, that is, summing all statistical values in the statistical array Q1 and the statistical array Q2 respectively to obtain a row total value 1 and a row total value 2; S6: judging whether the current suspected smoke feature area meets the requirements of drone operation smoke based on the similarity of the row total value 1 and the row total value 2.

Description

Technical Field

[0001] The present invention relates to the field of forest fire prevention and monitoring, and in particular to a similarity-based anti-agricultural spraying smoke interference processing method, device and medium. Background Art

[0002] Forest fire prevention technology typically uses video surveillance to identify each frame. If smoke is detected, an alarm is issued, thereby providing early warning of non-open flames. Within the monitored areas, operators often use general-purpose drones for agricultural pesticide spraying. These drones generate large amounts of agricultural smoke, which is often detected by fire prevention systems and can lead to frequent alarms.

[0003] Typically, existing systems display this type of alarm directly on screen, requiring the user to manually determine whether the alarm is a fire or non-fire, thereby turning off the alarm. Consequently, this often results in users having to make selections to turn off the alarm.

[0004] Among them, the drone used for agricultural drug spraying operations is generally a drone with two spray holes. The drone will perform drug spraying operations through two symmetrical spray holes. Therefore, the spraying smoke generated by the drone will show a kind of symmetry as a whole. How to use this symmetry to achieve anti-interference processing of this phenomenon is the technical problem that the present invention needs to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide a similarity-based anti-agricultural spraying smoke interference processing method, device and medium. The similarity-based anti-agricultural spraying smoke interference processing method can utilize the overall central symmetry of the spraying operation smoke generated by the drone to achieve anti-interference processing of this phenomenon.

[0006] In order to solve the above technical problems, the present invention adopts the following solutions:

[0007] A similarity-based anti-agricultural spray smoke interference processing method is applied to forest fire smoke alarms, the method comprising:

[0008] S1: Obtain the suspected smoke feature area by using background subtraction method on the Nth frame image and the background frame image;

[0009] S2: Pre-process the suspected smoke feature area horizontally to obtain the upper half of the suspected smoke feature area, and store the coordinate information (X, Y) of each pixel point in the upper half of the suspected smoke feature area, where X represents the column number of the horizontal coordinate of the pixel point in its image, and Y represents the row number of the vertical coordinate of the pixel point in its image;

[0010] S3: Compress the suspected smoke feature area in the upper half longitudinally, that is, count the number of rows of each column of pixels and obtain a statistical array Q{t1, t2, ..., tn}, where "t1, t2, ..., tn" is a statistical value representing the number of rows;

[0011] S4: Obtain symmetrical points of the upper half of the suspected smoke feature area, and divide the statistical array Q into statistical array Q1 and statistical array Q2 based on the symmetrical points;

[0012] S5: horizontally compressing the statistical array Q1 and the statistical array Q2, that is, summing all statistical values in the statistical array Q1 and the statistical array Q2 to obtain row total value 1 and row total value 2;

[0013] S6: Determine whether the current suspected smoke feature area meets the requirements of UAV operation smoke based on the similarity between the total row value 1 and the total row value 2. If so, do not display an alarm for the current suspected smoke feature area and eliminate the alarm.

[0014] Furthermore, in S3, the specific formula for counting the number of rows of pixels in each column is: max -Y min +1.

[0015] Furthermore, in S4, the following steps are specifically included:

[0016] S41: traverse the statistical array Q, and subtract the total number of rows of two adjacent pixel cells. When making the subtraction, keep the subtraction direction consistent, that is, always keep the latter term minus the former term, to obtain a difference array, which represents the relative relationship between the difference values of the two adjacent items;

[0017] S42: traverse the difference array, mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 1, then mark the total number of pixel rows for which the previous difference value is less than 0 and the next difference value is greater than or equal to 0 as a minimum value, and then mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 2;

[0018] S43: Record the minimum value as the symmetric point of the suspected smoke feature area, and perform longitudinal shearing processing based on the symmetric point.

[0019] Furthermore, in S43, the specific process of performing longitudinal shearing processing according to the symmetry point is: dividing according to the position of the total number of rows of pixel cells corresponding to the symmetry point in the pixel array, that is, recording the first half of the total number of rows of corresponding pixel cells as statistical array Q1, and recording the second half of the total number of rows of corresponding pixel cells as statistical array Q1.

[0020] Furthermore, both the Nth frame image and the background frame image establish a rectangular coordinate system XY with pixels as the unit based on the upper left corner of the image as the origin, and the horizontal coordinate X and vertical coordinate Y of the pixel point are the column number and row number in the image respectively.

[0021] Furthermore, in S6, the specific process of determining whether the suspected smoke feature area meets the requirements of drone operation smoke based on the similarity between the total row value 1 and the total row value 2 is as follows:

[0022] If the absolute value of the difference between the total row value 1 and the total row value 2 does not exceed the threshold, it is determined that the current suspected smoke feature area meets the requirements of drone operation smoke.

[0023] Furthermore, the Nth frame image and the background frame image are images taken from the same viewing angle in the forest fire prevention monitoring video, and the background frame image is an image that is manually calibrated to be free of smoke.

[0024] Furthermore, the smoke confirmation judgment includes: a color feature inspection and confirmation method and / or a morphological feature inspection and confirmation method and / or a motion feature detection and confirmation method.

[0025] Furthermore, the drone operation smoke is the spraying operation water mist generated when the drone performs a spraying operation.

[0026] Similarity-based anti-agricultural spraying smoke interference treatment device, including:

[0027] a processor, and a memory communicatively connected to the processor;

[0028] The memory stores computer-executable instructions;

[0029] The processor executes the computer-executable instructions stored in the memory to implement the similarity-based anti-agricultural spraying smoke interference processing method.

[0030] A computer-readable storage medium stores computer-executable instructions, which are used to implement the similarity-based anti-agricultural spraying smoke interference processing method when executed by a processor.

[0031] Beneficial effects of the present invention:

[0032] The present invention provides a similarity-based anti-agricultural spraying smoke interference processing method, which is applied to forest fire smoke alarms. The interference processing method is based on the fact that the spraying smoke generated by drones will show a kind of symmetry as a whole, so by judging whether the smoke has symmetry, the effect of anti-agricultural spraying smoke interference in the forest method system is achieved.

[0033] The present invention mainly adopts the technical means of longitudinal compression and transverse compression. The suspected smoke characteristic area is longitudinally compressed to find the symmetry point, and the suspected smoke characteristic area is divided into suspected smoke characteristic area 1 and suspected smoke characteristic area 2 according to the symmetry point. The suspected smoke characteristic area 1 and the suspected smoke characteristic area 2 are transversely compressed to obtain the total number of rows of the suspected smoke characteristic area 1 and the suspected smoke characteristic area 2. By judging the similarity of the two row number totals, it is determined whether the suspected smoke characteristic area meets the requirements of drone operation smoke. When the two row number totals are similar, it means that the suspected smoke characteristic area 1 and the suspected smoke characteristic area 2 are symmetrical about the symmetry point, so that the suspected smoke characteristic area can be excluded from the forest fire prevention system without generating an alarm, thereby achieving the purpose of removing the interference of drone operation smoke without causing missed reports. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention.

[0035] Figure 2 Schematic diagram of the current suspected smoke feature area obtained by background subtraction method.

[0036] Figure 3 Schematic diagram of the suspected smoke feature area in the upper half of the present invention.

[0037] Figure 4 Schematic diagram of the coordinate information of the suspected smoke feature area in the upper half of the present invention.

[0038] Figure 5 Schematic diagram of the statistical array Q corresponding to the suspected smoke feature area in the upper half of the present invention.

[0039] Figure 6 Schematic diagram of the difference array corresponding to the suspected smoke feature area in the upper half of the present invention.

[0040] Figure 7 Schematic diagram of the suspected smoke feature area 1 and the corresponding statistical array Q1 in the present invention.

[0041] Figure 8 Schematic diagram of the suspected smoke feature region 2 and the corresponding statistical array Q2 in the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] Unless otherwise specifically stated, the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention.

[0044] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0045] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness. Those skilled in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0046] Technologies, methods and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods and equipment should be considered part of the authorization specification.

[0047] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0048] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments:

[0049] Example 1

[0050] The similarity-based anti-agricultural spray smoke interference processing method is applied to forest fire smoke alarm. Figure 1 As shown, the interference processing method includes:

[0051] S1: Obtain the suspected smoke feature area by using background subtraction method on the Nth frame image and the background frame image;

[0052] S2: Pre-process the suspected smoke feature area horizontally to obtain the upper half of the suspected smoke feature area, and store the coordinate information (X, Y) of each pixel point in the upper half of the suspected smoke feature area, where X represents the column number of the horizontal coordinate of the pixel point in its image, and Y represents the row number of the vertical coordinate of the pixel point in its image;

[0053] S3: Compress the suspected smoke feature area in the upper half longitudinally, that is, count the number of rows of each column of pixels and obtain a statistical array Q{t1, t2, ..., tn}, where "t1, t2, ..., tn" is a statistical value representing the number of rows;

[0054] S4: Obtain symmetrical points of the upper half of the suspected smoke feature area, and divide the statistical array Q into statistical array Q1 and statistical array Q2 based on the symmetrical points;

[0055] S5: horizontally compressing the statistical array Q1 and the statistical array Q2, that is, summing all statistical values in the statistical array Q1 and the statistical array Q2 to obtain row total value 1 and row total value 2;

[0056] S6: Determine whether the current suspected smoke feature area meets the requirements of UAV operation smoke based on the similarity between the total row value 1 and the total row value 2. If so, do not display an alarm for the current suspected smoke feature area and eliminate the alarm.

[0057] Preferably, in S3, the specific formula for counting the number of rows of pixels in each column is: max -Y min +1.

[0058] Preferably, in S4, the following steps are specifically included:

[0059] S41: traverse the statistical array Q, and subtract the total number of rows of two adjacent pixel cells. When making the subtraction, keep the subtraction direction consistent, that is, always keep the latter term minus the former term, to obtain a difference array, which represents the relative relationship between the difference values of the two adjacent items;

[0060] S42: traverse the difference array, mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 1, then mark the total number of pixel rows for which the previous difference value is less than 0 and the next difference value is greater than or equal to 0 as a minimum value, and then mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 2;

[0061] S43: Record the minimum value as the symmetric point of the suspected smoke feature area, and perform longitudinal shearing processing based on the symmetric point.

[0062] Preferably, in S43, the specific process of performing longitudinal shearing processing according to the symmetry point is: dividing according to the position of the total number of rows of pixel cells corresponding to the symmetry point in the pixel array, that is, recording the first half of the total number of rows of corresponding pixel cells as statistical array Q1, and recording the second half of the total number of rows of corresponding pixel cells as statistical array Q1.

[0063] Preferably, in S6, the specific process of determining whether the suspected smoke feature area meets the requirements of drone operation smoke based on the similarity between the total row value 1 and the total row value 2 is as follows:

[0064] If the absolute value of the difference between the total row value 1 and the total row value 2 does not exceed the threshold, it is determined that the current suspected smoke feature area meets the requirements of drone operation smoke.

[0065] Preferably, both the Nth frame image and the background frame image establish a rectangular coordinate system XY with pixels as the unit based on the lower left corner of the image as the origin, and the horizontal coordinate X and vertical coordinate Y of the pixel point are the column number and row number in the image respectively.

[0066] Preferably, the smoke confirmation judgment includes: a color feature inspection and confirmation method and / or a morphological feature inspection and confirmation method and / or a motion feature detection and confirmation method.

[0067] Specifically, such as Figure 2-Figure 8 As shown,

[0068] In order to better understand the technical concept of the present invention, this embodiment will be analyzed as follows in conjunction with the accompanying drawings:

[0069] First of all, the drone operation smoke defined in the present invention generally includes but is not limited to the spraying operation water mist generated when the drone performs a spraying operation. At present, when using drones for drug spraying operations, the liquid substance is atomized and then sprayed out. The sprayed water mist is similar to the smoke produced by the burning of the substance, and it is very easy to identify using the background subtraction method.

[0070] Among them, the drone used for agricultural drug spraying operations is generally a drone with two spray holes. The drone will perform drug spraying operations through two spray holes that are symmetrical about the center point. Therefore, the overall spraying smoke generated by the drone will show a kind of symmetry. This symmetry will make the smoke generated by the two symmetrical spray holes on the left and right symmetrical about the center point. By judging whether the smoke generated by the two symmetrical spray holes on the left and right are similar, it can be obtained whether the overall spraying smoke is symmetrical.

[0071] Therefore, based on this symmetrical overall spraying operation smoke, the present invention provides an anti-agricultural spraying smoke interference processing method based on similarity, which is applied to forest fire smoke alarm, and the suspected smoke feature area is longitudinally compressed and the symmetrical point of the suspected smoke feature area is found. According to the symmetrical point, the suspected smoke feature area is divided into suspected smoke feature area 1 and suspected smoke feature area 2, and then the suspected smoke feature area 1 and the suspected smoke feature area 2 are horizontally compressed to obtain the total pixel value of the suspected smoke feature area 1 and the suspected smoke feature area 2. By judging the similarity of the two total values, it is determined whether the suspected smoke feature area meets the requirements of drone operation smoke.

[0072] Based on the above principles, the present invention is further elaborated:

[0073] like Figure 2 As shown, Figure 2 This is a schematic diagram of the current suspected smoke feature area obtained by background subtraction. The current suspected smoke feature area is pre-processed by horizontal shearing to obtain the suspected smoke feature area in the upper half, as shown in Figure 3 As shown, this step can eliminate some interference and make the calculation process of the present invention more convenient.

[0074] The present invention establishes a rectangular coordinate system XY with pixels as the unit based on the lower left corner of the image as the origin, and the horizontal coordinate X and the vertical coordinate Y of the pixel point are the column number and the row number of the pixel point in the image respectively.

[0075] like Figure 4 As shown in , we can get the coordinate information of the pixel cells occupied by the suspected smoke feature area in the upper half. Figure 5 As shown, the pixel cells occupied by the suspected smoke feature area in the upper half are vertically compressed to obtain the statistical array Q {4, 5, 6, 6, 6, 6, 12, 12, 12, 5, 4, 7, 9, 11, 11, 11, 4, 4, 4, 3, 1}. A pixel value in the statistical array Q is the total number of rows in a column of pixel cells, and the position order of the pixel values in the pixel array is fixed and sorted in ascending order according to the horizontal coordinate information.

[0076] Therefore, the symmetric point of the current suspected smoke feature region is found by using the statistical array Q obtained through longitudinal compression. Since the drone has two symmetrical spray holes, the current suspected smoke feature region must have two maximum points. These maximum points are physically represented by the locations of the spray holes. The minimum point between the two maximum points can be used as the symmetric point in this invention.

[0077] like Figure 6As shown, the pixel values in the statistical array Q are subtracted from each other in pairs, and the subtraction direction is kept consistent, that is, the previous term is always subtracted from the next term, to obtain the difference array {1,1,1,1,1,1,6,0,0,-7,-1,3,2,2,0,0,-7,0,0,-1,-2}, which represents the relative relationship between the difference values of two adjacent values. For example, the previous difference value of pixel value 7 is 3 and the next difference value is 2. Traversing the difference array, it is found that the maximum value 1 is pixel value 12, the previous difference value of pixel value 12 is 6 and the next difference value is 0; the minimum value is pixel value 4, the previous difference value of pixel value 4 is -1 and the next difference value is 3; the maximum value 2 is pixel value 11, the previous difference value of pixel value 11 is 2 and the next difference value is 0.

[0078] Therefore, the pixel value 4 is recorded as the symmetrical point of the current suspected smoke feature area. According to this symmetrical point, the pixel value Q can be divided into the statistical array Q1 {4, 5, 6, 6, 6, 6, 12, 12, 12, 5} and the statistical array Q2 {7, 9, 11, 11, 11, 4, 4, 4, 3, 1}.

[0079] like Figure 7 、 Figure 8 As shown, Figure 7 For the suspected smoke feature area 1 corresponding to the statistical array Q1, Figure 8 The pixel value Q2 corresponds to the suspected smoke feature area 2. Since the drone smoke is symmetrical, it is necessary to determine whether the suspected smoke feature area 1 and the suspected smoke feature area 2 are similar. Therefore, the statistical arrays Q1 and Q2 are horizontally compressed. That is, all the values in the statistical arrays Q1 and Q2 are summed up respectively, and the total value 1 is equal to 82, and the total value 2 is equal to 65.

[0080] Finally, based on the similarity between total value 1 and total value 2, it is determined whether the current suspected smoke feature area meets the requirements of drone operation smoke. If the absolute value of the difference between total value 1 and total value 2 does not exceed the threshold, the alarm will not be displayed for the current suspected smoke feature area and the alarm will be eliminated.

[0081] Based on similarity, the present invention creates a method for implementing anti-interference processing of forest fire smoke alarms. The processing method can be described as follows:

[0082] Step 1: Compress the suspected smoke feature area longitudinally to find the symmetric point of the suspected smoke feature area, and divide the suspected smoke feature area into suspected smoke feature area 1 and suspected smoke feature area 2 based on the symmetric point;

[0083] Step 2: Compress the suspected smoke feature region 1 and the suspected smoke feature region 2 horizontally to obtain the total pixel value of the suspected smoke feature region 1 and the suspected smoke feature region 2;

[0084] Step 3: By judging the similarity of the two total values, it is determined whether the suspected smoke feature area is consistent with drone operation smoke.

[0085] Example 2

[0086] This embodiment provides a computer-readable storage medium, including: one or more processors; a storage unit for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement a method for monitoring floating pollutants in a river in embodiment 1 or embodiment 2.

[0087] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide the functions for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0091] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Based on the technical essence of the present invention and within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement of the above embodiment shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A similarity-based anti-agricultural spray smoke interference processing method, applied to forest fire smoke alarm, characterized by: The method comprises: S1: Obtain the suspected smoke feature area by using background subtraction method on the Nth frame image and the background frame image; S2: Pre-process the suspected smoke feature area horizontally to obtain the upper half of the suspected smoke feature area, and store the coordinate information (X, Y) of each pixel point in the upper half of the suspected smoke feature area, where X represents the column number of the horizontal coordinate of the pixel point in its image, and Y represents the row number of the vertical coordinate of the pixel point in its image; S3: Compress the suspected smoke feature area in the upper half longitudinally, that is, count the number of rows of pixels in each column and obtain a statistical array Q{t1, t2, ..., tn}, where "t1, t2, ..., tn" is a statistical value representing the number of rows; S4: Obtain symmetrical points of the upper half of the suspected smoke feature area, and divide the statistical array Q into statistical array Q1 and statistical array Q2 based on the symmetrical points; S5: horizontally compressing the statistical array Q1 and the statistical array Q2, that is, summing all statistical values in the statistical array Q1 and the statistical array Q2 to obtain the row total value 1 and the row total value 2; S6: Determine whether the current suspected smoke feature area meets the requirements of UAV operation smoke based on the similarity between the total row value 1 and the total row value 2. If so, do not display an alarm for the current suspected smoke feature area and eliminate the alarm.

2. The similarity-based anti-agricultural spraying smoke interference treatment method according to claim 1, characterized in that: In S3, the specific formula for counting the number of rows of pixels in each column is: max -Y min +1, Y max is the maximum number of rows, the Y min The minimum number of rows.

3. The similarity-based anti-agricultural spraying smoke interference treatment method according to claim 1, characterized in that: In S4, the following steps are specifically included: S41: traverse the statistical array Q, and subtract the total number of rows of two adjacent pixel cells. When making the subtraction, keep the subtraction direction consistent, that is, always keep the latter term minus the former term, to obtain a difference array, which represents the relative relationship between the difference values of the two adjacent items; S42: traverse the difference array, mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 1, then mark the total number of pixel rows for which the previous difference value is less than 0 and the next difference value is greater than or equal to 0 as a minimum value, and then mark the total number of pixel rows for which the previous difference value is greater than 0 and the next difference value is less than or equal to 0 as a maximum value 2; S43: Record the minimum value as the symmetric point of the suspected smoke feature area, and perform longitudinal shearing processing based on the symmetric point.

4. The similarity-based anti-agricultural spraying smoke interference treatment method according to claim 2, characterized in that: In S43, the specific process of performing longitudinal shearing according to the symmetry point is: dividing the total number of rows of pixel cells corresponding to the symmetry point according to the position in the pixel array, that is, recording the first half of the total number of rows of corresponding pixel cells as statistical array Q1, and recording the second half of the total number of rows of corresponding pixel cells as statistical array Q1.

5. The similarity-based anti-agricultural spraying smoke interference treatment method according to claim 1, characterized in that: The Nth frame image and the background frame image both establish a rectangular coordinate system XY with pixels as the unit based on the upper left corner of the image. The horizontal coordinate X and the vertical coordinate Y of the pixel point are the column number and the row number in the image respectively.

6. The similarity-based anti-agricultural spraying smoke interference treatment method according to claim 1, characterized in that: In S6, the specific process of determining whether the suspected smoke feature area is consistent with the smoke of UAV operation based on the similarity between the total value of the number of rows 1 and the total value of the number of rows 2 is as follows: If the absolute value of the difference between the total row value 1 and the total row value 2 does not exceed the threshold, it is determined that the current suspected smoke feature area meets the requirements of drone operation smoke.

7. The similarity-based method for resisting agricultural spraying smoke interference according to claim 1, characterized in that: The Nth frame image and the background frame image are images from the same perspective in the forest fire monitoring video, and the background frame image is an image that is manually calibrated to have no smoke.

8. The similarity-based method for resisting agricultural spraying smoke interference according to claim 1, characterized in that: The smoke confirmation judgment includes: a color feature inspection and confirmation method and / or a morphological feature inspection and confirmation method and / or a motion feature detection and confirmation method.

9. Similarity-based anti-agricultural spraying smoke interference treatment device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the similarity-based anti-agricultural spraying smoke interference processing method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the similarity-based anti-agricultural spraying smoke interference processing method according to any one of claims 1 to 8.

Images