Termite nest searching method, device, equipment, storage medium and product

Abstract

The present application relates to termite protection technical field, especially termite nest nest seeking method, device, equipment, storage medium and product, through the camera site periodic collection of dam area to be detected several termite site images, according to the equipment number of each camera site, each termite site image is numbered, obtain several target termite site images, according to each target termite site image, through the trained termite activity sign recognition model, termite behavior recognition is carried out, and the target termite site image existing termite activity sign is marked, the collection time of each target termite site image is determined, according to the termite activity sign and collection time of each target termite site image and the position information of target camera site, the position of termite nest is determined, the termite activity area on dam is reduced, and the nest positioning is carried out according to the collection time of the termite site image existing termite activity sign and the position of each site, so as to reduce the range where the termite nest may exist.

Description

Technical Field

[0001] This invention relates to the field of termite protection technology, and in particular to methods, devices, equipment, storage media, and products for locating termite nests. Background Technology

[0002] Termites are one of the most significant dam-damaging animals in southern regions. Termites build nests, tunnels, and reproduce on dikes. They also nest and reproduce within the main body of water conservancy projects, constructing extensive tunnels that can easily lead to seepage, collapses, and other dangerous situations. In severe cases, they can even cause dam collapses or dike breaches. Termites pose a major biological hazard to the safety of water conservancy projects such as reservoirs, dams, and dikes, and bring significant risks to the safe operation of these projects.

[0003] Traditional termite monitoring methods mainly rely on manual surveys, which have many limitations. Manual surveys are extremely time-consuming and labor-intensive, especially when monitoring large areas or multiple locations is required, which significantly increases the difficulty and cost of implementation.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, equipment, storage medium, and product for locating termite nests, aiming to solve the technical problem of low efficiency in manually searching for termite nest locations in the prior art.

[0006] To achieve the above objectives, the present invention provides a method for locating termite nests, the method comprising the following steps: Images of several termite sites in the dam area to be inspected are periodically collected using camera stations. The images of each termite site are numbered according to the equipment number of each camera site, resulting in several target termite site images; Based on the images of each target termite site, termite behavior is identified using a trained termite activity sign recognition model, and the images of target termite sites showing signs of termite activity are marked. Determine the acquisition time for images of each target termite site; The location of termite nests was determined based on the signs of termite activity and the time of collection in the images of each target termite site, as well as the location information of the target camera sites.

[0007] Optionally, the signs of termite activity include at least mud blankets, mud lines, and swarming holes; The process of determining the location of termite nests based on termite activity signs and collection time in images of each target termite site, as well as the location information of the target camera sites, includes: The area of ​​the dam to be detected is divided into equal parts, and the target activity area is determined based on the location information of the target camera station; The occurrence times of mud blankets, mud lines, fly vents, and excrement are determined based on the collection time. A marker is generated based on the termite activity signs and the time of their appearance; The target activity area is marked according to the marked identifier; By using a time-series analysis model to trace activity patterns in the marked target activity areas, the location of termite nests can be determined.

[0008] Optionally, the step of tracing activity signs in the marked target activity area using a time-series analysis model to determine the location of termite nests includes: Based on the target activity area, adjacent activity areas are determined in the dam area to be tested. The adjacent activity areas are those areas that are adjacent to the target activity area when the dam area to be tested is divided into regions and show signs of termite activity. Extract the markers from the adjacent active areas; The time interval is calculated based on the termite activity signs and corresponding occurrence times recorded in the markings and the occurrence times of termite activity signs in the target activity area; When the time interval is less than a preset time interval, the target activity area and the adjacent activity area are merged to obtain a temporary activity area; The termite activity path is fitted based on the relative orientation of activity signs in the temporary activity area; By integrating the termite activity paths corresponding to each temporary activity area, the location of the termite nest can be determined.

[0009] Optionally, the step of integrating the termite activity paths corresponding to each temporary activity area to determine the location of the termite nest includes: The termite activity path is derived bidirectionally; The region where the statistical path intersections fall within the standard range the most; The current location within the standard range is taken as the location of the termite nest.

[0010] Optionally, the step of identifying termite behavior based on images of each target termite site using a trained termite activity sign recognition model, and marking target termite site images showing signs of termite activity, includes: Extract local image features from images of each target termite site; The local image features are enhanced to obtain the target local image features; The termite activity signs are identified by using a trained termite activity sign recognition model to identify termite activity signs in the target local image features, thereby determining the termite activity sign category of the activity sign segmented sub-image.

[0011] Optionally, the step of performing feature enhancement on the local image features to obtain target local image features includes: The local image features are compressed using the convolutional layer of a pre-trained termite activity sign recognition model to obtain intermediate features; The intermediate features are encoded to obtain the encoded features; The encoded features are upsampled to obtain the target encoded features; The target encoded features are enhanced by using a preset image processing window to obtain the target local image features.

[0012] Furthermore, to achieve the above objectives, the present invention also proposes a termite nest locating device, the termite nest locating device comprising: The acquisition module is used to periodically acquire images of several termite sites in the dam area to be inspected through camera stations; The numbering module is used to number the images of each termite site according to the equipment number of each camera site, thereby obtaining several target termite site images; The identification module is used to identify termite behavior based on images of each target termite site using a trained termite activity sign recognition model, and to mark the target termite site images showing signs of termite activity. The determination module is used to determine the acquisition time of images for each target termite site; The nest-finding module is used to determine the location of termite nests based on the signs of termite activity and the collection time in the images of each target termite site, as well as the location information of the target camera site.

[0013] In addition, to achieve the above objectives, the present invention also proposes a termite nest finding device, which includes: a memory, a processor, and a termite nest finding program stored in the memory and executable on the processor, wherein the termite nest finding program is configured to implement the steps of the termite nest finding method described above.

[0014] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a termite nest finding program, which, when executed by a processor, implements the steps of the termite nest finding method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the termite nest locating method described above.

[0016] This invention periodically collects images of several termite sites in a dam area to be inspected using camera stations; assigns a number to each termite site image based on the device number of each camera station, resulting in several target termite site images; identifies termite behavior using a trained termite activity sign recognition model based on each target termite site image, and marks the target termite site images showing termite activity signs; determines the acquisition time of each target termite site image; and determines the location of termite nests based on termite activity signs, acquisition time, and location information of the target camera stations. By performing behavior recognition on several termite site images collected by various camera stations on the dam to be inspected, the area of ​​termite activity on the dam is narrowed down, and nests are located based on the acquisition time and location of termite site images showing termite activity signs, thereby narrowing down the possible range of termite nests and avoiding the low efficiency problem of manual nest location in existing technologies. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the termite nest locating method of the present invention; Figure 2 This is a flowchart illustrating the second embodiment of the termite nest locating method of the present invention; Figure 3 This is a flowchart illustrating the third embodiment of the termite nest locating method of the present invention; Figure 4 This is a structural block diagram of the first embodiment of the termite nest locating device of the present invention; Figure 5 This is a schematic diagram of the termite nest finding device in the hardware operating environment involved in the embodiments of the present invention.

[0020] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] Based on this, embodiments of the present invention provide a method for locating termite nests, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a termite nest locating method according to the present invention.

[0024] In this embodiment, the termite nest locating method includes: Step S10: Periodically collect images of several termite sites in the dam area to be inspected using camera stations.

[0025] Step S20: Number the termite site images according to the device number of each camera site to obtain several target termite site images.

[0026] Step S30: Based on the images of each target termite site, use the trained termite activity sign recognition model to identify termite behavior and mark the target termite site images that show signs of termite activity.

[0027] Step S40: Determine the acquisition time of images for each target termite site.

[0028] Step S50: Determine the location of the termite nest based on the signs of termite activity and the collection time of the images of each target termite site, as well as the location information of the target camera site.

[0029] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or control computer capable of performing the above functions. The following description uses a control computer as an example to illustrate this embodiment and the subsequent embodiments.

[0030] In this embodiment, multiple camera stations, such as high-definition cameras, 2D or 3D cameras, will be deployed in the area of ​​the dam to be inspected. The image acquisition device will be powered by an independent power module. Some initial termite station images may show signs of termite activity, while others may not. Therefore, termite activity identification needs to be performed on all termite station images. In addition, in order to improve the accuracy of termite nest location, this embodiment will periodically detect termite activity signs in the termite station images, thereby achieving long-term and accurate identification of termite activity signs.

[0031] It should be understood that, in order to avoid situations where signs of termite activity are identified but the specific location cannot be pinpointed, this embodiment takes advantage of the fixed installation location of the camera stations, assigns numbers to the camera stations, and assigns corresponding numbers to the termite station images based on the device numbers of the camera stations. For example, images collected by camera station A are sequentially labeled as A1, A2, A3, A4, etc., and images collected by camera station B are sequentially labeled as B1, B2, B3, B4, etc. This embodiment does not impose specific limitations on this.

[0032] The trained termite activity sign recognition model can be a trained neural network model with feature recognition or data classification capabilities. By identifying termite activity signs in termite site images, it can accurately determine the areas in the images where termite activity traces exist. However, since termite activity traces are small and there is limited research in this field, resulting in a small number of training samples and low recognition accuracy of the trained model, this embodiment can iterate the termite activity sign recognition model based on historical termite site images before inputting the image into the trained model, thereby improving the model's recognition accuracy.

[0033] Termite activity signs include at least mud sheets, mud lines, and swarming holes. Due to the small size of termites, these activity signs are relatively difficult to identify. In order to ensure the reliability of termite site images in the subsequent termite activity sign identification process and improve identification efficiency, this embodiment can perform image enhancement on the initial termite site images before performing termite activity sign identification, thereby improving the accuracy of subsequent termite activity sign identification.

[0034] The acquisition time of images of each target termite site can be output by the camera site. Although termite site images are acquired periodically in this embodiment, due to the high acquisition frequency and relatively short period of the camera site, there may be slight differences in the time of images showing signs of termite activity. Therefore, by identifying the occurrence time of activity signs in images of different target termite sites, this embodiment can deduce the approximate range and path of termite activity and realize the location of termite nests.

[0035] This embodiment periodically collects images of several termite sites in the embankment area to be inspected using camera stations; each termite site image is numbered according to the device number of each camera station, resulting in several target termite site images; termite behavior is identified using a trained termite activity sign recognition model based on each target termite site image, and target termite site images showing termite activity signs are marked; the acquisition time of each target termite site image is determined; the location of termite nests is determined based on the termite activity signs, acquisition time, and location information of the target camera stations in each target termite site image. By performing behavior recognition on several termite site images collected by each camera station on the embankment to be inspected, the area of ​​termite activity on the embankment is narrowed down, and nest location is determined based on the acquisition time and location of each termite site image showing termite activity signs, thereby narrowing down the possible range of termite nests and avoiding the technical problem of low efficiency in manually searching for termite nests in the prior art.

[0036] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S50 includes: Step S501: Divide the dam area to be detected into equal regions, and determine the target activity area based on the location information of the target camera station.

[0037] Step S502: Determine the occurrence time of mud blanket, mud line, fly spit, and excrement based on the collection time.

[0038] Step S503: Generate a marker based on the termite activity signs and the time of occurrence.

[0039] Step S504: Mark the target activity area according to the marker identifier.

[0040] Step S505: Use a time series analysis model to trace the activity signs of the marked target activity area and determine the location of the termite nest.

[0041] It should be noted that since each camera station is installed in a fixed location, if an image of a termite site collected by a certain camera station is identified as showing signs of termite activity, the target activity area on the embankment to be inspected can be determined based on the location of that camera station.

[0042] In practice, since termites are small in size and the activity signs they form are relatively small compared to the area represented by the entire image, the target activity area occupies a relatively small area in the entire image. In order to successfully trace the source of the activity signs, this embodiment will mark the areas where there are termite activity signs, thereby distinguishing the categories and times of different activity signs and improving the accuracy of tracing the source of the activity signs.

[0043] Furthermore, the step of tracing activity patterns in the marked target activity area using a time-series analysis model to determine the location of termite nests includes: Based on the target activity area, adjacent activity areas are determined in the dam area to be tested. The adjacent activity areas are those areas that are adjacent to the target activity area when the dam area to be tested is divided into regions and show signs of termite activity. Extract the markers from the adjacent active areas; The time interval is calculated based on the termite activity signs and corresponding occurrence times recorded in the markings and the occurrence times of termite activity signs in the target activity area; When the time interval is less than a preset time interval, the target activity area and the adjacent activity area are merged to obtain a temporary activity area; The termite activity path is fitted based on the relative orientation of activity signs in the temporary activity area; By integrating the termite activity paths corresponding to each temporary activity area, the location of the termite nest can be determined.

[0044] It should be understood that since termites move randomly rather than linearly during their activities, this embodiment requires joint judgment of each target activity area and any adjacent activity area to form a short-term termite activity path. Finally, the short-term termite activity paths in all temporary activity areas are integrated to improve the reliability of termite nest location. After verification, the accuracy of this scheme reached 63%.

[0045] Furthermore, the process of integrating the termite activity paths corresponding to each temporary activity area to determine the location of the termite nest includes: The termite activity path is derived bidirectionally; The region where the statistical path intersections fall within the standard range the most; The current location within the standard range is taken as the location of the termite nest.

[0046] In a specific embodiment, because termite activity is relatively small and far less significant than that of an ant nest or the entire dam area, its reliability in location is relatively low. This embodiment innovatively uses the termite activity area as the endpoint and the line connecting the target activity area with the adjacent activity area as the termite activity path, thereby reducing the impact of the magnitude difference on location.

[0047] Since the direction of termite movement and the location of the termite nest are unknown, this embodiment uses a two-way derivation of the line connecting the target activity area and adjacent activity areas to form a straight line within the dam area. By statistically analyzing the intersections of the path of each termite activity showing signs of activity, the area with the highest density is taken as the location of the termite nest. This provides a feasible termite nest location scheme and reduces the location error caused by the difference in size between termites and the dam area.

[0048] This embodiment divides the dam area to be detected into equal regions and determines the target activity area based on the location information of the target camera station; it determines the appearance time of mud, mud lines, swarming holes, and excrement based on the collection time; it generates markers based on the termite activity signs and appearance time; it marks the target activity area based on the markers; and it uses a time-series analysis model to trace the activity signs in the marked target activity area to determine the location of the termite nest. By tracing the areas with termite activity signs, the location of the termite nest can be determined, thus improving the nest location efficiency.

[0049] Based on the second embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S30 includes: Step S301: Extract local image features from the images of each target termite site.

[0050] Step S302: Perform feature enhancement on the local image features to obtain the target local image features.

[0051] Step S303: Use the trained termite activity sign recognition model to identify termite activity signs in the target local image features to determine the termite activity sign category of the activity sign segmented sub-image.

[0052] It should be noted that there are certain differences between the activity area of ​​termites and their environment. However, considering the influence of termite size, in this embodiment, in order to improve the accuracy of image recognition, we can first identify local images in the image. That is, we select an appropriate size to segment the target termite site image first, and then identify it based on the features of the segmented sub-images. At the same time, since some environmental features will be discarded during the segmentation process, feature enhancement is performed on the local image features to improve the recognition rate of features that are different from environmental features.

[0053] Further, the step of performing feature enhancement on the local image features to obtain target local image features includes: The local image features are compressed using the convolutional layer of a pre-trained termite activity sign recognition model to obtain intermediate features; The intermediate features are encoded to obtain the encoded features; The encoded features are upsampled to obtain the target encoded features; The target encoded features are enhanced by using a preset image processing window to obtain the target local image features.

[0054] In specific implementation, to improve the discernibility of the segmented sub-images of activity signs, this embodiment can perform feature enhancement on the parts where there are differences between the two images, thereby improving the discernibility between termite activity signs and the environment in that area. Specifically, the operation of feature compression of local image features to obtain intermediate features is as follows:

[0055] Where W represents intermediate features, X represents local image features, R represents the real number field, b represents the batch size, cmid represents the number of output channels of the intermediate layer of the network, and h and w represent the height and width of the intermediate feature map.

[0056] The specific steps for enhancing the target's encoded features using a preset image processing window and obtaining the target's local image features are as follows:

[0057] Where scale represents the upsampling factor, kup represents the channel splitting factor, Wenc represents the encoded feature, Wshuffled represents the target encoded feature, h' and w' represent the spatial resolution, Xupsampled represents the feature map, Xunfolded represents the result after feature enhancement, and c represents the number of output channels of the convolutional layer.

[0058] This embodiment extracts local image features from images of each target termite site; enhances these local image features using a trained termite activity sign recognition model to obtain target local image features; and then uses the trained termite activity sign recognition model to identify termite activity signs in the target local image features, thereby determining the termite activity sign category of the activity sign segmented sub-image and improving the recognition accuracy and reliability of termite activity signs.

[0059] This application also provides a termite nest locator; please refer to... Figure 4 The termite nest locating device includes: The acquisition module 10 is used to periodically acquire images of several termite sites in the dam area to be inspected through camera sites.

[0060] The numbering module 20 is used to number the images of each termite site according to the equipment number of each camera site, so as to obtain several target termite site images.

[0061] The identification module 30 is used to identify termite behavior based on the images of each target termite site using a trained termite activity sign identification model, and to mark the target termite site images that show signs of termite activity.

[0062] The determination module 40 is used to determine the acquisition time of each target termite site image and the time interval between the acquisition of target termite site images by the target camera site.

[0063] The nest-finding module 50 is used to determine the location of termite nests based on the signs of termite activity and the collection time of images of each target termite site, as well as the location information of the target camera site.

[0064] This embodiment periodically collects images of several termite sites in the embankment area to be inspected using camera stations; each termite site image is numbered according to the device number of each camera station, resulting in several target termite site images; termite behavior is identified using a trained termite activity sign recognition model based on each target termite site image, and target termite site images showing termite activity signs are marked; the acquisition time of each target termite site image is determined; the location of termite nests is determined based on the termite activity signs and acquisition time of each target termite site image, as well as the location information of the target camera stations. By performing behavior recognition on several termite site images collected by each camera station on the embankment to be inspected, the area of ​​termite activity on the embankment is narrowed down, and nest location is determined based on the acquisition time and location of each termite site image showing termite activity signs, thereby narrowing down the possible range of termite nests.

[0065] In one embodiment, the nest-finding module 50 is further configured to divide the dam area to be detected into equal regions, and determine the target activity area based on the location information of the target camera station; determine the occurrence time of mud cover, mud line, swarming holes and excrement based on the collection time; generate markers based on the termite activity signs and occurrence time; mark the target activity area based on the markers; and trace the activity signs of the marked target activity area through a time series analysis model to determine the location of the termite nest.

[0066] In one embodiment, the nest-finding module 50 is further configured to: determine adjacent activity areas in the dam area to be detected based on the target activity area; the adjacent activity areas are areas adjacent to the target activity area and showing signs of termite activity when the dam area to be detected is divided into regions; extract markers from the adjacent activity areas; calculate a time interval based on the termite activity signs and corresponding occurrence times recorded in the markers and the occurrence times of termite activity signs in the target activity area; when the time interval is less than a preset time interval, merge the target activity area and the adjacent activity areas to obtain a temporary activity area; fit termite activity paths based on the relative orientation of the activity signs in the temporary activity areas; and integrate the termite activity paths corresponding to each temporary activity area to determine the location of the termite nest.

[0067] In one embodiment, the nest-finding module 50 is further configured to bidirectionally derive the termite activity path; count the area where the path intersections fall into the standard range interval the most; and take the current position of the standard range interval as the termite nest location.

[0068] In one embodiment, the identification module 30 is further configured to extract local image features of each target termite site image; enhance the local image features using a trained termite activity sign recognition model to obtain target local image features; and perform termite activity sign recognition on the target local image features using the trained termite activity sign recognition model to determine the termite activity sign category of the activity sign segmented sub-image.

[0069] In one embodiment, the recognition module 30 is further configured to compress the local image features through the convolutional layer of a trained termite activity sign recognition model to obtain intermediate features; encode the intermediate features to obtain encoded features; upsample the encoded features to obtain target encoded features; and enhance the target encoded features through a preset image processing window to obtain target local image features.

[0070] This application provides a termite nest finding device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the termite nest finding method in the above embodiment 1.

[0071] The following is for reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing a termite nest finding device according to embodiments of this application. The termite nest finding device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The termite nest finding device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0072] like Figure 5As shown, the termite nest finding device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the termite nest finding device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the termite nest finding device to communicate wirelessly or wiredly with other devices to exchange data. Although termite nest finding devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0073] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0074] The termite nest locating device provided in this application, employing the termite nest locating method described in the above embodiments, can solve the technical problem of termite nest locating. Compared with the prior art, the beneficial effects of the termite nest locating device provided in this application are the same as those of the termite nest locating method provided in the above embodiments, and other technical features of this termite nest locating device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0075] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0076] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0077] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the termite nest finding method in the above embodiments.

[0078] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0079] The aforementioned computer-readable storage medium may be included in the termite nest finding device; or it may exist independently and not be assembled into the termite nest finding device.

[0080] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the termite nest finding device, cause the termite nest finding device to: termite nest finding.

[0081] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0083] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0084] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described termite nest locating method, thereby solving the technical problem of termite nest locating. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the termite nest locating method provided in the above embodiments, and will not be repeated here.

[0085] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the termite nest locating method described above.

[0086] The computer program product provided in this application can solve the technical problem of locating termite nests. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the termite nest locating method provided in the above embodiments, and will not be repeated here.

[0087] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for locating termite nests, characterized in that, The method for locating termite nests includes: Images of several termite sites in the dam area to be inspected are periodically collected using camera stations. The images of each termite site are numbered according to the equipment number of each camera site, resulting in several target termite site images; Based on the images of each target termite site, termite behavior is identified using a trained termite activity sign recognition model, and the images of target termite sites showing signs of termite activity are marked. Determine the acquisition time for images of each target termite site; The location of termite nests was determined based on the signs of termite activity and the time of collection in the images of each target termite site, as well as the location information of the target camera sites. The signs of termite activity include at least mud blankets, mud lines, and swarming holes; The process of determining the location of termite nests based on termite activity signs and collection time in images of each target termite site, as well as the location information of the target camera sites, includes: The area of ​​the dam to be detected is divided into equal parts, and the target activity area is determined based on the location information of the target camera station; The occurrence times of mud blankets, mud lines, fly vents, and excrement are determined based on the collection time. A marker is generated based on the termite activity signs and the time of their appearance; The target activity area is marked according to the marked identifier; By using a time-series analysis model, the activity patterns of the marked target activity areas are traced to determine the location of termite nests; The step of tracing activity patterns in the marked target activity area using a time-series analysis model to determine the location of termite nests includes: Based on the target activity area, adjacent activity areas are determined in the dam area to be tested. The adjacent activity areas are those areas that are adjacent to the target activity area when the dam area to be tested is divided into regions and show signs of termite activity. Extract the markers from the adjacent active areas; The time interval is calculated based on the termite activity signs and corresponding occurrence times recorded in the markings and the occurrence times of termite activity signs in the target activity area; When the time interval is less than a preset time interval, the target activity area and the adjacent activity area are merged to obtain a temporary activity area; The termite activity path is fitted based on the relative orientation of activity signs in the temporary activity area; By integrating the termite activity paths corresponding to each temporary activity area, the location of the termite nest can be determined. The process of integrating the termite activity paths corresponding to each temporary activity area to determine the location of the termite nest includes: The termite activity path is derived bidirectionally; The region where the statistical path intersections fall within the standard range the most; The current location within the standard range is taken as the location of the termite nest.

2. The termite nest locating method as described in claim 1, characterized in that, The step of identifying termite behavior based on images of each target termite site using a trained termite activity sign recognition model, and marking target termite site images showing signs of termite activity, includes: Extract local image features from images of each target termite site; The local image features are enhanced to obtain the target local image features; The termite activity signs are identified by using a trained termite activity sign recognition model to identify termite activity signs in the target local image features, thereby determining the termite activity sign category of the activity sign segmented sub-image.

3. The termite nest locating method as described in claim 2, characterized in that, The step of enhancing the local image features to obtain the target local image features includes: The local image features are compressed using the convolutional layer of a pre-trained termite activity sign recognition model to obtain intermediate features; The intermediate features are encoded to obtain the encoded features; The encoded features are upsampled to obtain the target encoded features; The target encoded features are enhanced by using a preset image processing window to obtain the target local image features.

4. A termite nest locator, characterized in that, The termite nest locating device includes: The acquisition module is used to periodically acquire images of several termite sites in the dam area to be inspected through camera stations; The numbering module is used to number the images of each termite site according to the equipment number of each camera site, thereby obtaining several target termite site images; The identification module is used to identify termite behavior based on images of each target termite site using a trained termite activity sign recognition model, and to mark the target termite site images showing signs of termite activity. The determination module is used to determine the acquisition time of images for each target termite site; The nest-finding module is used to determine the location of termite nests based on the signs of termite activity and the collection time in the images of each target termite site, as well as the location information of the target camera site. The signs of termite activity include at least mud blankets, mud lines, and swarming holes; The process of determining the location of termite nests based on termite activity signs and collection time in images of each target termite site, as well as the location information of the target camera sites, includes: The area of ​​the dam to be detected is divided into equal parts, and the target activity area is determined based on the location information of the target camera station; The occurrence times of mud blankets, mud lines, fly vents, and excrement are determined based on the collection time. A marker is generated based on the termite activity signs and the time of their appearance; The target activity area is marked according to the marked identifier; By using a time-series analysis model, the activity patterns of the marked target activity areas are traced to determine the location of termite nests; The step of tracing activity patterns in the marked target activity area using a time-series analysis model to determine the location of termite nests includes: Based on the target activity area, adjacent activity areas are determined in the dam area to be tested. The adjacent activity areas are those areas that are adjacent to the target activity area when the dam area to be tested is divided into regions and show signs of termite activity. Extract the markers from the adjacent active areas; The time interval is calculated based on the termite activity signs and corresponding occurrence times recorded in the markings and the occurrence times of termite activity signs in the target activity area; When the time interval is less than a preset time interval, the target activity area and the adjacent activity area are merged to obtain a temporary activity area; The termite activity path is fitted based on the relative orientation of activity signs in the temporary activity area; By integrating the termite activity paths corresponding to each temporary activity area, the location of the termite nest can be determined. The process of integrating the termite activity paths corresponding to each temporary activity area to determine the location of the termite nest includes: The termite activity path is derived bidirectionally; The region where the statistical path intersections fall within the standard range the most; The current location within the standard range is taken as the location of the termite nest.

5. A termite nest locating device, characterized in that, The termite nest finding device includes: a memory, a processor, and a termite nest finding program stored in the memory and executable on the processor, the termite nest finding program being configured to implement the termite nest finding method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium stores a termite nest finding program, which, when executed by a processor, implements the termite nest finding method as described in any one of claims 1 to 3.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the termite nest locating method as described in any one of claims 1 to 3.

Images