Indoor biological control method and device
Through the camera, video is collected and similarity matched, the activity area and hazard level of the target organism are identified, and biological control strategies are generated, which solves the problems of low efficiency and high cost of biological control in the existing technology, and achieves a more efficient and scientific indoor organism. Prevention and control.
Patent Information
- Application Number
- CN202411059075.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-22
AI Technical Summary
In the existing technology, in indoor biological control, the training cost of image recognition models when detecting organisms is high and the detection effect is difficult to meet the needs. The efficiency and effect of mouse-catching devices are uncertain, and there is a lack of scientific basis, resulting in uneven prevention and control effects.
The camera is used to collect surveillance videos, match the similarity between the pre-stored reference images and the frame images, determine the activity area, activity time and hazard level of the target organism, and generate corresponding biological control strategies, including deploying trapping or repelling devices in the target area. And set the inspection frequency according to the hazard level.
It improves the speed of image information processing, automatically completes cumbersome matching tasks, reduces detection complexity, significantly improves the accuracy and prevention and control efficiency of biometrics, reduces unnecessary manpower and material resources, and enhances indoor biocontrol capabilities.
Smart Images

Figure CN119007245A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of biological control technology, and in particular to an indoor biological control method and device. Background Art
[0002] In the daily operation of power supply enterprises, daily inspections and special inspections are not only the cornerstone of team work, but also the key link to ensure the safe and stable operation of power equipment such as transformers. Given the potential threat of various creatures, especially rats, to power equipment, they tend to build nests in warm and dry environments, such as inside running power equipment. Their gnawing behavior not only directly damages the lines and components inside the equipment, but may also induce major safety accidents such as fires, posing a serious threat to the safety of the equipment and even the entire power system.
[0003] Therefore, effective prevention and control of biological infestations has become an important part of the team's work. At present, two main strategies have been adopted: one is to fully block the pipe gaps around the equipment to prevent the entry of small animals by physical isolation; the other is to strategically arrange mouse stickers and mouse cages on site. However, both methods face challenges. Blocking measures are limited by the durability of materials (such as the aging of glue in harsh environments) and the comprehensiveness of operations (it is difficult to ensure that all gaps are not missed). Mousetraps rely on the active behavior of mice, and their efficiency and effectiveness are uncertain. In addition, there are limitations such as the lack of scientific basis for the number of arrangements and passive effects, resulting in uneven prevention and control effects.
[0004] Faced with this situation, the power industry has an increasingly urgent need to introduce new and advanced technologies. Innovative means are needed to improve the accuracy and efficiency of inspections, while enhancing the ability to prevent and control indoor organisms, to ensure equipment safety in a more scientific and efficient manner, and to reduce unnecessary consumption of manpower and material resources.
[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0006] The embodiments of the present application provide an indoor biological control method and device to at least solve the technical problems in the related art that when using image recognition models to detect organisms, the training cost is high and the detection effect is difficult to meet the requirements.
[0007] According to one aspect of an embodiment of the present application, a method for indoor biological control is provided, comprising: obtaining at least one surveillance video captured by at least one camera indoors; for each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video captured by the camera, and determining that an image that does not match the reference image is a target image that includes the target organism, wherein the reference image is an image captured by the camera that does not include the target organism; determining the activity area, activity time and hazard level of the target organism based on the field of view area of the camera corresponding to each target image, the capture time of each target image and the total number of target images; and generating a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
[0008] Optionally, the process of acquiring the reference image includes: for each camera, acquiring multiple frames of first images captured by the camera; performing Gaussian filtering on the multiple frames of first images to obtain multiple frames of second images; sending the multiple frames of second images to the target object, and determining the reference image from the multiple frames of second images according to the selection instruction of the target object.
[0009] Optionally, before performing similarity matching on each frame image in the surveillance video captured by the camera using a pre-stored reference image corresponding to the camera, the method also includes: for each surveillance video, performing quality detection on the surveillance video, wherein the content of the quality detection includes at least one of the following: clarity detection, smoothness detection, resolution detection, screen jitter detection, brightness detection, and contrast detection; if the surveillance video fails the quality detection, deleting the surveillance video; if the surveillance video passes the quality detection, continuing to perform similarity matching on each frame image in the surveillance video.
[0010] Optionally, a pre-stored reference image corresponding to the camera is used to perform similarity matching on each frame image in the surveillance video captured by the camera, including: for each surveillance video, performing frame extraction processing on the surveillance video according to a preset frame extraction interval to obtain multiple frames of third images; performing Gaussian filtering on the multiple frames of third images to obtain multiple frames of fourth images; determining the similarity between each frame of the fourth image and the reference image to obtain a similarity matching result.
[0011] Optionally, the similarity between each frame of the fourth image and the benchmark image is determined to obtain a similarity matching result, including: for each frame of the fourth image, calculating a structural similarity index between the fourth image and the benchmark image, and comparing the structural similarity index with a preset index threshold; if the structural similarity index is not less than the preset index threshold, determining that the fourth image matches the benchmark image; if the structural similarity index is less than the preset index threshold, determining that the fourth image does not match the benchmark image.
[0012] Optionally, the activity area, activity time and hazard level of the target organism are determined based on the field of view area of the camera corresponding to each target image, the acquisition time of each target image and the total number of target images, including: grouping all target images according to the corresponding cameras, and determining the field of view area of the camera whose number of corresponding target images is greater than a first preset threshold as the activity area of the target organism; determining multiple time intervals, and determining the time interval corresponding to the acquisition time of each target image, grouping all target images according to the corresponding time intervals, and determining the time interval whose number of corresponding target images is greater than a second preset threshold as the activity time of the target organism; comparing the total number of target images with multiple preset threshold intervals, and determining the hazard level of the target organism based on the comparison result, wherein different threshold intervals correspond to different hazard levels.
[0013] Optionally, the generated biological control strategy includes at least one of the following: placing a target number of trapping devices in the activity area of the target organism, wherein the target number corresponds to the hazard level; placing repelling devices in the activity area of the target organism, wherein the repelling devices work during the activity time of the target organism and standby at other times; determining an inspection frequency corresponding to the hazard level, and instructing inspection personnel to inspect key areas indoors according to the inspection frequency, wherein the key areas include at least one of the following: pipe openings, vents, ground cracks, and wall cracks.
[0014] According to another aspect of an embodiment of the present application, an indoor biological control device is also provided, including: an acquisition module, used to acquire at least one surveillance video captured by at least one camera indoors; a matching module, used to, for each camera, use a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video captured by the camera, and determine that the image that does not match the reference image is a target image including the target organism, wherein the reference image is an image captured by the camera but does not include the target organism; a determination module, used to determine the activity area, activity time and hazard level of the target organism based on the field of view area of the camera corresponding to each target image, the capture time of each target image and the total number of target images; a generation module, used to generate a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
[0015] According to another aspect of an embodiment of the present application, a computer program product is further provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned indoor biological control method is implemented.
[0016] According to another aspect of an embodiment of the present application, an electronic device is further provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned indoor biological control method through the computer program.
[0017] In the embodiment of the present application, the pre-stored reference image is used to perform similarity matching on each frame image in the surveillance video collected by the corresponding camera, and the image that does not match the reference image is accurately identified as the target image containing the target organism; then, according to the field of view area of the camera corresponding to each target image, the acquisition time and the total number of target images, the activity area, activity time and hazard level of the target organism are further determined; finally, a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism is generated. This process greatly improves the processing speed of image information, automatically completes the tedious matching task, does not require complex data annotation and model training in traditional image recognition, significantly reduces the complexity of implementation, and thus solves the technical problem that the training cost is high and the detection effect is difficult to meet the requirements when using image recognition models to detect organisms in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0019] Figure 1 is a schematic flow chart of an optional indoor biological control method according to an embodiment of the present application;
[0020] Figure 2 is a schematic structural diagram of an optional indoor biological control device according to an embodiment of the present application;
[0021] Figure 3 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 without creative work should fall within the scope of protection of the present application.
[0023] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0024] Example 1
[0025] According to an embodiment of the present application, a method for indoor biological control is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0026] Figure 1 is a flow chart of an indoor biological control method provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:
[0027] Step S102, obtaining at least one surveillance video collected by at least one indoor camera;
[0028] Step S104, for each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video captured by the camera, and determining that an image that does not match the reference image is a target image that includes the target organism, wherein the reference image is an image captured by the camera that does not include the target organism;
[0029] Step S106, determining the activity area, activity time and hazard level of the target organism according to the field of view of the camera corresponding to each target image, the acquisition time of each target image and the total number of target images;
[0030] Step S108, generating a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
[0031] The following describes the various steps of the indoor biological control method in conjunction with the specific implementation process.
[0032] Optionally, the indoor biological control method of the embodiment of the present application is applicable to a variety of indoor occasions, such as power rooms, machine rooms, factories, warehouses, etc., which are usually equipped with multiple cameras to monitor different areas in the room. Considering that the field of view of each camera is relatively fixed, and the frame images in the surveillance video collected by it are basically similar, the embodiment of the present application proposes a solution of first determining a reference image that does not contain the target organism, and then comparing the frame images in each surveillance video with the reference image for similarity to screen out the target image containing the target organism. Using this solution instead of the traditional target detection algorithm can also obtain accurate recognition effect while reducing the consumption of computing resources.
[0033] As an optional implementation, the following process can be adopted to obtain the reference image: first, for each camera, obtain multiple frames of first images collected by the camera, and then perform Gaussian filtering on the multiple frames of first images to effectively remove random noise and tiny details in the image, and generate clearer and more stable multiple frames of second images; then, send the multiple frames of second images to the target object, determine the reference image from the multiple frames of second images according to the selection instruction of the target object, and store the reference image. Among them, the target object can be an inspection personnel, who can select the most representative image from the multiple frames of second images as the reference image of the camera through intuitive comparison and other means according to actual needs and environmental characteristics. This process ensures that each reference image is the best environmental snapshot under the perspective of a specific camera without interference from the target organism, providing a reliable reference benchmark for subsequent target organism detection.
[0034] During the actual detection process, multiple surveillance videos collected by various cameras in the room within a preset time period can be obtained. In order to accurately analyze the activity patterns of the target organisms, the preset time period can be set to a longer period, such as one week, half a month, etc. Each camera collects one or more surveillance videos.
[0035] It is understandable that before using the pre-stored reference image to perform similarity matching on each frame image in the surveillance video captured by the camera, as an important step to improve efficiency and accuracy, it is indispensable to perform a preliminary quality test on the video image captured by the camera, wherein the content of the quality test covers at least one of the following: clarity test, fluency test, resolution test, screen jitter test, brightness test, and contrast test. When performing quality testing on each surveillance video, if the surveillance video fails the quality test, the surveillance video is deleted; if the surveillance video passes the quality test, the subsequent steps are continued to perform similarity matching on each frame image in the surveillance video.
[0036] Optionally, for each surveillance video that passes the quality inspection, when performing similarity matching, the surveillance video can be frame-sampled according to a preset frame sampling interval to obtain multiple frames of third images, each third image has an acquisition timestamp, which is convenient for subsequent analysis of the activity time of the target organism. Subsequently, the multiple frames of the third images are Gaussian filtered to eliminate noise and enhance image quality to obtain multiple frames of fourth images. Next, the similarity between each frame of the fourth image and the reference image is determined to obtain a similarity matching result.
[0037] Among them, when determining the similarity between the fourth image of each frame and the reference image, SSIM (Structural Similarity) can be used as an evaluation criterion. Specifically, the value range of SSIM is [0,1]. When the SSIM value is close to 0, it means that the similarity between the two images is low; when the SSIM value is close to 1, it means that the similarity between the two images is high. SSIM not only takes into account the brightness and contrast of the image, but also the structural information of the image, so it can more comprehensively evaluate the similarity between images. The calculation formula of the SSIM value is as follows:
[0038]
[0039] In the formula, x and y represent the two pixels to be compared; μ x , μ y represent the means of x and y respectively; Represents the variance of x and y respectively; σ xy represents the covariance of x and y; c1 and c2 are constants added for stability, usually set to (k1l) 2 and (k2s) 2 , where l is the range of pixels, k1 and k2 are constants less than 1, which can be set to: k1 = 0.01, k2 = 0.03.
[0040] Specifically, when performing similarity matching, for each frame of the fourth image, the SSIM value between the fourth image and the baseline image can be calculated, and the SSIM value can be compared with a preset indicator threshold; if the SSIM value is not less than the preset indicator threshold, it is determined that the fourth image matches the baseline image, that is, the environment in the fourth image remains stable without abnormal changes, and does not contain the target organism; if the SSIM value is less than the preset indicator threshold, it is determined that the fourth image does not match the baseline image, and it is inferred that the frame image may contain the target organism, and is then marked as a target image.
[0041] As an optional implementation, the similarity matching scheme of the embodiment of the present application can also be used in combination with image feature recognition technology. For example, on the basis of acquiring the target image, the automatic learning mechanism is inherited, and the target image features are continuously analyzed to automatically learn and recognize different types of target organisms. This function not only improves the recognition accuracy of the system, but also enables it to have the ability to adapt to new biological species and environmental changes. In addition, it is possible to further integrate dynamic tracking and recognition technology, consider the characteristics of the target biological movement, and design a dynamic tracking and recognition technology. Aiming at the complex movement characteristics of the target organism, its position and posture changes are captured in real time, and the movement trajectory and unique features are combined for accurate recognition, thereby further improving the recognition efficiency and accuracy, and providing more powerful technical support for biological detection and protection.
[0042] After acquiring the target image, the activity area, activity time and hazard level of the target organism can be determined by analyzing the field of view area, acquisition time and total number of target images of the camera corresponding to each target image. The specific process can be carried out in the following manner: First, all target images are grouped according to the corresponding cameras. If the number of target images under a certain camera exceeds the first preset threshold, its field of view area is identified as the activity area of the target organism. Secondly, multiple time intervals can be pre-divided, such as dividing a 24-hour day into 24 intervals on average, and the target images are classified into corresponding intervals according to the acquisition time. If the number of target images in a certain interval exceeds the second preset threshold, it is determined that the time period is the activity time of the target organism. Finally, the total number of target images is compared with multiple preset hazard level threshold intervals. Different threshold intervals correspond to different hazard levels. The hazard level of the target organism is determined based on the comparison result, so as to accurately evaluate the impact of the target organism on the monitoring area.
[0043] Furthermore, based on the activity areas, activity times and hazard levels of the target organisms obtained above, corresponding biological control strategies can be generated, including but not limited to: deploying a target number of trapping devices matching the hazard level as needed in the activity areas of the target organisms to capture the target organisms; at the same time, deploying repelling devices such as sound wave stimulation and natural enemy sound simulation in the activity areas of the target organisms to repel the target organisms. Considering that the operating costs of these devices may be high, they can only work during the activity time of the target organisms and be on standby at other times to save energy and reduce the impact on indoor equipment; in addition, a reasonable inspection frequency can be set according to the hazard level, and inspectors can be instructed to conduct regular inspections of high-risk areas such as pipe openings, vents, ground and wall cracks according to the inspection frequency to ensure that potential biological invasion problems are discovered and dealt with in a timely manner, and to fully protect environmental safety.
[0044] In the embodiment of the present application, the pre-stored reference image is used to perform similarity matching on each frame image in the surveillance video collected by the corresponding camera, and the image that does not match the reference image is accurately identified as the target image containing the target organism; then, according to the field of view area of the camera corresponding to each target image, the acquisition time and the total number of target images, the activity area, activity time and hazard level of the target organism are further determined; finally, a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism is generated. This process greatly improves the processing speed of image information, automatically completes the tedious matching task, does not require complex data annotation and model training in traditional image recognition, significantly reduces the complexity of implementation, and thus solves the technical problem that the training cost is high and the detection effect is difficult to meet the requirements when using image recognition models to detect organisms in related technologies.
[0045] Example 2
[0046] According to an embodiment of the present application, an indoor biological control device for implementing the indoor biological control method in embodiment 1 is also provided, such as Figure 2 As shown, the indoor biological control device at least includes: an acquisition module 21, a matching module 22, a determination module 23 and a generation module 24, wherein:
[0047] An acquisition module 21 is used to acquire at least one surveillance video collected by at least one indoor camera;
[0048] A matching module 22 is used for, for each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video collected by the camera, and determining that an image that does not match the reference image is a target image that includes the target organism, wherein the reference image is an image collected by the camera that does not include the target organism;
[0049] A determination module 23, for determining the activity area, activity time and hazard level of the target organism according to the field of view area of the camera corresponding to each target image, the acquisition time of each target image and the total number of target images;
[0050] The generation module 24 is used to generate a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
[0051] The functions of each module of the indoor biological control device are described below in conjunction with a specific implementation process.
[0052] Optionally, the indoor biological control device of the embodiment of the present application is applicable to a variety of indoor occasions, such as power rooms, machine rooms, factories, warehouses, etc., which are usually equipped with multiple cameras to monitor different areas in the room. Considering that the field of view of each camera is relatively fixed, and the frame images in the surveillance video collected by it are basically similar, the embodiment of the present application proposes a solution of first determining a reference image that does not contain the target organism, and then comparing the frame images in each surveillance video with the reference image for similarity to screen out the target image containing the target organism. Using this solution instead of the traditional target detection algorithm can also obtain accurate recognition effect while reducing the consumption of computing resources.
[0053] As an optional implementation, the indoor biological control device of the embodiment of the present application also includes an interactive module for acquiring a reference image in the following manner: first, for each camera, multiple frames of first images captured by the camera are acquired, and then the multiple frames of first images are subjected to Gaussian filtering to effectively remove random noise and tiny details in the image, and generate multiple frames of second images that are clearer and more stable; then, the multiple frames of second images are sent to the target object, and a reference image is determined from the multiple frames of second images according to the selection instruction of the target object, and the reference image is stored. Among them, the target object can be an inspection personnel, who can select the most representative image from the multiple frames of second images as the reference image of the camera through intuitive comparison and other means according to actual needs and environmental characteristics. This process ensures that each reference image is the best environmental snapshot under the perspective of a specific camera without interference from the target organism, providing a reliable reference benchmark for subsequent target organism detection.
[0054] During the actual detection process, the acquisition module can obtain multiple surveillance videos collected by each camera in the room within a preset time period. In order to accurately analyze the activity patterns of the target organisms, the preset time period can be set longer, such as one week, half a month, etc. Each camera collects one or more surveillance videos.
[0055] It is understandable that before the matching module uses the pre-stored reference image to perform similarity matching on each frame image in the surveillance video captured by the camera, as an important step to improve efficiency and accuracy, it is indispensable to perform a preliminary quality test on the video image captured by the camera, wherein the content of the quality test covers at least one of the following: clarity test, fluency test, resolution test, screen jitter test, brightness test, and contrast test. When performing quality testing on each surveillance video, if the surveillance video fails the quality test, the surveillance video is deleted; if the surveillance video passes the quality test, the subsequent steps are continued to perform similarity matching on each frame image in the surveillance video.
[0056] Optionally, for each surveillance video that passes the quality inspection, the matching module can perform frame extraction on the surveillance video according to a preset frame extraction interval when performing similarity matching to obtain multiple frames of third images, each third image having an acquisition timestamp to facilitate subsequent analysis of the activity time of the target organism. Subsequently, the multiple frames of the third images are subjected to Gaussian filtering to eliminate noise and enhance image quality to obtain multiple frames of fourth images. Next, the similarity between each frame of the fourth image and the reference image is determined to obtain a similarity matching result.
[0057] Among them, when determining the similarity between each frame of the fourth image and the reference image, SSIM can be used as an evaluation criterion. Specifically, for each frame of the fourth image, the SSIM value between the fourth image and the reference image can be calculated, and the SSIM value can be compared with a preset index threshold; if the SSIM value is not less than the preset index threshold, it is determined that the fourth image matches the reference image, that is, the environment in the fourth image remains stable without abnormal changes and does not contain the target organism; if the SSIM value is less than the preset index threshold, it is determined that the fourth image does not match the reference image, and it is inferred that the frame image may contain the target organism, and is then marked as a target image.
[0058] After acquiring the target image, the determination module can determine the activity area, activity time and hazard level of the target organism by analyzing the field of view area, acquisition time and total number of target images of the camera corresponding to each target image. The specific process can be carried out in the following manner: First, all target images are grouped according to the corresponding cameras. If the number of target images under a certain camera exceeds the first preset threshold, its field of view area is identified as the activity area of the target organism. Secondly, multiple time intervals can be pre-divided, such as dividing a day of 24 hours into 24 intervals on average, and the target images are classified into corresponding intervals according to the acquisition time. If the number of target images in a certain interval exceeds the second preset threshold, it is determined that the time period is the activity time of the target organism. Finally, the total number of target images is compared with multiple preset hazard level threshold intervals. Different threshold intervals correspond to different hazard levels. The hazard level of the target organism is determined based on the comparison result, so as to accurately evaluate the impact of the target organism on the monitoring area.
[0059] Furthermore, based on the activity area, activity time and hazard level of the target organisms obtained above, the generation module can generate corresponding biological control strategies, which include but are not limited to: deploying a target number of trapping devices matching the hazard level as needed in the activity area of the target organisms to capture the target organisms; at the same time, deploying repelling devices such as sound wave stimulation and natural enemy sound simulation in the activity area of the target organisms to repel the target organisms. Considering that the operating costs of these devices may be high, they can only work during the activity time of the target organisms and be on standby at other times to save energy and reduce the impact on indoor equipment; in addition, a reasonable inspection frequency can be set according to the hazard level, and the inspection personnel can be instructed to conduct regular inspections of high-risk areas such as pipe openings, vents, ground and wall cracks according to the inspection frequency to ensure that potential biological invasion problems are discovered and dealt with in a timely manner to fully protect environmental safety.
[0060] It should be noted that the modules in the indoor biological control device in the embodiment of the present application correspond one-to-one to the implementation steps of the indoor biological control method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1, and will not be repeated here.
[0061] Example 3
[0062] According to an embodiment of the present application, a computer program product is also provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, the indoor biological control method in Example 1 is implemented.
[0063] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the indoor biological control method in Example 1 by running the computer program.
[0064] According to an embodiment of the present application, a processor is also provided, which is used to run a computer program, wherein the indoor biological control method in Example 1 is executed when the computer program is running.
[0065] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the indoor biological control method in Example 1 through the computer program.
[0066] Specifically, the computer program executes the following steps when it is running: obtaining at least one surveillance video captured by at least one camera in the room; for each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video captured by the camera, and determining that the image that does not match the reference image is a target image including the target organism, wherein the reference image is an image captured by the camera but does not include the target organism; determining the activity area, activity time and hazard level of the target organism based on the field of view of the camera corresponding to each target image, the capture time of each target image and the total number of target images; and generating a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
[0067] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 The hardware structure block diagram of an electronic device for implementing an indoor biological control method is shown. Figure 3 As shown, the electronic device 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.
[0068] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the electronic device 30. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0069] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the indoor biological control method in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, to implement the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0070] The transmission device 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 30. In one example, the transmission device 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0071] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .
[0072] The serial numbers of the above embodiments are only for description and do not represent the advantages or disadvantages of the embodiments.
[0073] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.
[0074] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0075] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0076] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.
[0078] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for indoor biological control, It is characterized in that include: Obtain at least one surveillance video collected by at least one indoor camera; For each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video captured by the camera, and determining that an image that does not match the reference image is a target image that includes the target organism, wherein the reference image is an image captured by the camera that does not include the target organism; Determine the activity area, activity time and hazard level of the target organism according to the field of view of the camera corresponding to each target image, the acquisition time of each target image and the total number of the target images; Generate a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
2. The method according to claim 1, It is characterized in that The process of acquiring the reference image includes: For each camera, obtaining a plurality of frames of first images captured by the camera; Performing Gaussian filtering on multiple frames of the first image to obtain multiple frames of second images; The multiple frames of second images are sent to a target object, and the reference image is determined from the multiple frames of second images according to a selection instruction of the target object.
3. The method according to claim 1, It is characterized in that Before performing similarity matching on each frame image in the surveillance video captured by the camera using the pre-stored reference image corresponding to the camera, the method further includes: For each surveillance video, perform a quality detection on the surveillance video, wherein the content of the quality detection includes at least one of the following: clarity detection, fluency detection, resolution detection, picture jitter detection, brightness detection, and contrast detection; If the surveillance video fails the quality inspection, deleting the surveillance video; If the surveillance video passes the quality detection, continue to perform similarity matching on each frame image in the surveillance video.
4. The method according to claim 1, It is characterized in that Using the pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video collected by the camera, including: For each surveillance video, frame extraction is performed on the surveillance video according to a preset frame extraction interval to obtain multiple frames of third images; Performing Gaussian filtering on the multiple frames of the third image to obtain multiple frames of fourth images; Determine the similarity between each frame of the fourth image and the reference image to obtain a similarity matching result.
5. The method according to claim 4, It is characterized in that Determining the similarity between each frame of the fourth image and the reference image to obtain a similarity matching result includes: For each frame of the fourth image, calculating a structural similarity index between the fourth image and the reference image, and comparing the structural similarity index with a preset index threshold; If the structural similarity index is not less than the preset index threshold, determining that the fourth image matches the reference image; If the structural similarity index is less than the preset index threshold, it is determined that the fourth image does not match the reference image.
6. The method according to claim 1, It is characterized in that Determining the activity area, activity time and hazard level of the target organism according to the field of view of the camera corresponding to each target image, the acquisition time of each target image and the total number of the target images includes: Grouping all the target images according to the corresponding cameras, and determining the field of view area of the cameras whose number of corresponding target images is greater than a first preset threshold as the activity area of the target organism; Determine multiple time intervals, and determine the time interval corresponding to the acquisition moment of each of the target images, group all the target images according to the corresponding time intervals, and determine the time interval corresponding to the number of target images greater than a second preset threshold as the activity time of the target organism; The total number of the target images is compared with a plurality of preset threshold intervals, and the hazard level of the target organism is determined according to the comparison result, wherein different threshold intervals correspond to different hazard levels.
7. The method according to claim 1, It is characterized in that The generated biological control strategy includes at least one of the following: Placing a target number of trapping devices in the activity area of the target organism, wherein the target number corresponds to the hazard level; Placing a repelling device in the activity area of the target organism, wherein the repelling device works during the activity time of the target organism and is on standby at other times; Determine an inspection frequency corresponding to the hazard level, and instruct inspection personnel to inspect key areas in the room according to the inspection frequency, wherein the key areas include at least one of the following: pipe openings, vents, ground cracks, and wall cracks.
8. An indoor biological control device, It is characterized in that include: An acquisition module, used to acquire at least one surveillance video collected by at least one indoor camera; A matching module is used for, for each camera, using a pre-stored reference image corresponding to the camera to perform similarity matching on each frame image in the surveillance video collected by the camera, and determining that an image that does not match the reference image is a target image that includes a target organism, wherein the reference image is an image collected by the camera that does not include the target organism; A determination module, used to determine the activity area, activity time and hazard level of the target organism according to the field of view area of the camera corresponding to each of the target images, the acquisition time of each of the target images and the total number of the target images; A generation module is used to generate a biological control strategy corresponding to the activity area, activity time and hazard level of the target organism.
9. A computer program product, It is characterized in that include: A computer program, wherein when the computer program is executed by a processor, the indoor biological control method according to any one of claims 1 to 7 is implemented.
10. An electronic device, It is characterized in that include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the indoor biological control method according to any one of claims 1 to 7 through the computer program.
Citation Information
Patent Citations
Method and device for determining activity time period of pests and method for determining pesticide applying time
CN109197273A
Pest prevention and control monitoring method, device and system and storage medium
CN113749067A
Image similarity matching method and device and storage medium
CN114972817A
