A method and device for grid-based species monitoring and identification

Abstract

A method and device for grid-based species monitoring and identification, relating to the technical field of monitoring and protecting species. In the method, a species identification request sent by a user is received; the monitored area is grid-divided, and a first photographed image corresponding to a first grid area at a first time point is obtained; the first photographed image is judged to determine that the first photographed image is in an abnormal state; the second grid area is determined according to the first grid area; a second photographed image corresponding to a second grid area at a second time point is obtained; the first photographed image is combined with the second photographed image to obtain a first combined image; the first combined image is identified to obtain first target species information; if the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area so as to be displayed to the user. The technical solution provided by the present application is implemented to solve the problem of inaccurate species identification.

Description

Technical Field

[0001] The present application relates to the technical field of monitoring and protecting species, and in particular to a method and device for grid-based species monitoring and identification. Background Art

[0002] Through systematic monitoring activities, researchers can deeply analyze the population dynamics of species, the evolution of distribution patterns, and their needs for specific habitats, thereby revealing the key parameters and potential mechanisms that affect population dynamics. This not only helps to deepen the understanding of species biological characteristics and ecological adaptability, but also provides a scientific basis for the protection of biodiversity and the sustainable management of the ecological environment. Species monitoring is an important means of assessing the threats and risks to ecosystems, and provides data support for the formulation of effective ecological risk management measures.

[0003] In order to improve the accuracy of species identification and monitoring, customized biodiversity monitoring projects are carried out for different geographical areas. The monitoring objects include biological communities such as animals and plants. By deploying fixed photography equipment within the monitoring area, real-time image data of species in the area can be collected. Species identification depends on the clarity and completeness of the species in the image, so that the species can be accurately identified. However, when the images obtained by fixed photography equipment are blurred or incomplete, it may lead to inaccurate species identification, which in turn affects the detection results.

[0004] Therefore, there is an urgent need for a grid-based species monitoring and identification method and device that can solve the above-mentioned technical problems. Summary of the invention

[0005] The present application provides a method and device for grid-based species monitoring and identification. The method identifies species in a monitored area through grid-based identification, effectively solving the problem of inaccurate species identification caused by blurry or incomplete images acquired by inherent photographic equipment.

[0006] In a first aspect, the present application provides a method for grid-based species monitoring and identification, which is applied to a species monitoring platform, and the method includes: receiving a species identification request sent by a user, the species identification request being a request for species monitoring and identification of a monitored area; dividing the monitored area into grids to obtain a plurality of grid areas; obtaining a first captured image corresponding to a first grid area at a first time point, the first captured image being an image captured by a first capturing device, the first capturing device being a capturing device installed in the first grid area, and the first grid area being any one of the plurality of grid areas; judging the first captured image to determine that the first captured image is in an abnormal state, the abnormal state indicating that the species information existing in the first captured image cannot be identified; and determining the first captured image based on the first grid area. A second grid area is determined, where the second grid area is adjacent to the first grid area; a second captured image corresponding to the second grid area at a second time point is obtained, where the second time point is later than the first time point, and the second captured image is an image captured by a second shooting device, and the second shooting device is a shooting device installed in the second grid area; the first captured image is combined with the second captured image to obtain a first combined image; the first combined image is identified to obtain first target species information; it is determined whether the first target species information is the same as the preset first species information; when the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area so as to be displayed to the user, and the first species is an animal species.

[0007] By adopting the above technical solution, a species identification request for a to-be-monitored area sent by a user is received, the to-be-monitored area is divided into a plurality of grid areas, an independent photographing device is configured for each grid area, the coverage of species monitoring is improved through a distributed monitoring method, a first photographed image corresponding to a first grid area is obtained, if the first photographed image is in an abnormal state, the abnormal state indicates an unclear image, a second photographed image corresponding to a second grid area adjacent to the first grid area is obtained, and since the images of adjacent grid areas may capture different parts of the same species, the first photographed image is combined with the second photographed image to obtain a first combined image, the first combined image contains more species characteristic information, so that subsequent species identification is more accurate, and then the first combined image is identified to obtain first target species information, the first target species information is compared with the preset first species information, and the existence of the first species can be confirmed, the accuracy of species identification can be further improved through comparison, and the first species existing in the first grid area can be displayed to the user, effectively solving the problem of inaccurate species identification caused by incomplete images obtained by fixed photographic equipment.

[0008] Optionally, after judging the first captured image and determining that the first captured image is in an abnormal state, the method also includes: extracting features from the first captured image to obtain target image features; judging whether the target image features are the same as preset first image features, the preset first image features being image features corresponding to the animal; when the target image features are the same as the preset first image features, confirming that the second grid area is determined based on the first grid area.

[0009] By adopting the above technical solution, the features of the first captured image are extracted to obtain the target image features. When judging whether the target image features are the same as the preset first image features, it can be quickly judged whether the first captured image contains animal species. When the target image features are the same as the preset first image features, it is confirmed that the first captured image cannot identify the animal species, and a second grid area adjacent to the first grid area can be obtained, and an image captured by the second grid area can be obtained to further identify the species that appear, thereby reducing the need for manual intervention and improving monitoring efficiency.

[0010] Optionally, after determining whether the target image feature is the same as the preset first image feature, the method also includes: if the target image feature is not the same as the preset first image feature, determining whether the target image feature is the same as the preset second image feature, the preset second image feature being the image feature corresponding to the plant; when the target image feature is the same as the preset second image feature, confirming that a third captured image corresponding to the first grid area is at a third time point, the third time point being separated from the first time point by a first preset time period; combining the first captured image with the third captured image to obtain a second combined image; identifying the second combined image to obtain second target species information; determining whether the second target species information is the same as the preset second species information; when the second target species information is the same as the preset second species information, confirming that the second species exists in the first grid area, marking the second species in the first grid area so as to display it to the user, and the second species is a plant species.

[0011] By adopting the above technical solution, when the target image feature is different from the preset first image feature, it is further determined whether the target image feature is the same as the preset second image feature. When the target image feature is the same as the preset second image feature, it is confirmed that the plant species cannot be identified in the first captured image, and a third captured image corresponding to the first grid area at a third time point can be obtained. The first captured image and the third captured image are combined to obtain a second combined image, and the second combined image is identified to obtain second target species information, and the second target species information is compared with the preset second species information. When the second target species information is the same as the preset second species information, it is confirmed that the second species exists in the first grid area, and the second species is displayed to the user, which helps the user to better understand the species distribution in the first grid area.

[0012] Optionally, the first captured image and the second captured image are combined to obtain a first combined image; specifically including: preprocessing the first captured image to obtain a first feature point; preprocessing the second captured image to obtain a second feature point; performing coordinate transformation on the first feature point and the second feature point to obtain multiple target coordinates; and splicing the multiple target coordinates in a preset manner to obtain the first combined image.

[0013] By adopting the above technical solution, the first captured image and the second captured image are preprocessed respectively to obtain the first feature point and the second feature point, which contain important information of the first captured image, and the second feature point contains important information of the second captured image. The first feature point and the second feature point are transformed into coordinates to obtain multiple target coordinates, and then the multiple target coordinates are evaluated in a preset manner to obtain a first combined image. The first combined image can show a wider field of view and a complete scene, enhance the coherence and integrity of the image, help to more accurately identify species, and reduce misjudgments or missed judgments.

[0014] Optionally, when the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area for display to the user. The method also includes: obtaining target sound data corresponding to the first grid area in a second preset time period; processing the target sound data to obtain multiple sound information; inputting the target sound information into a preset sound database for matching to obtain third target species information, the third target species is the animal corresponding to the first species, and the target sound information is any one of the multiple sound information.

[0015] By adopting the above technical solution, the target sound data corresponding to the first grid area is obtained, and the target sound data is processed to obtain multiple sound information. The sound characteristics emitted by different species are different. The target sound information is input into the preset sound database for matching to obtain the third target species information. The sound data is not limited by line of sight. The multi-dimensional recognition method can more comprehensively reflect the characteristics and distribution of the species. Through subsequent matching of the preset sound database, the species information corresponding to the sound can be quickly identified, thereby improving the efficiency of species recognition.

[0016] Optionally, when the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area for display to the user. The method also includes: obtaining the target shooting number corresponding to the first grid area, the target shooting number is the total number corresponding to the first shooting device installed in the first grid area; obtaining the number of species corresponding to the first grid area, and determining the preset shooting number based on the number of species; judging whether the target shooting number is equal to the preset shooting number; when the target shooting number is not equal to the preset shooting number, confirming the use of a processing method to adjust the first shooting device in the first grid area, and the processing method includes an increase method or a decrease method.

[0017] By adopting the above technical solution, the target shooting number corresponding to the first grid area is obtained, and then the species number corresponding to the first grid area is obtained, the preset shooting number is determined according to the species number, and the target shooting number is compared with the preset shooting number. When the target shooting number is not equal to the preset shooting number, the monitoring of the first grid area is adjusted by using appropriate processing methods, which helps to improve the real-time and accuracy of monitoring.

[0018] Optionally, after obtaining the number of target shots corresponding to the first grid area, the method also includes: obtaining environmental information corresponding to the first grid area, and determining the target survival level based on the environmental information; judging whether the target survival level is less than or equal to a preset survival level; and when the target survival level is greater than the preset survival level, confirming to increase the number of first shooting devices in the first grid area.

[0019] By adopting the above technical solution, the environmental information corresponding to the first grid area is obtained, the target survival level is determined according to the environmental information, and it is judged whether the target survival level is less than or equal to the preset survival level. When the target survival level is equal to the preset survival level, the number of first shooting devices is increased in the first grid area, which can achieve more accurate monitoring and protection of species activities and ensure that shooting resources can be reasonably allocated.

[0020] In a second aspect of the present application, a device for grid-based species monitoring and identification is provided, the device is a species monitoring platform, the species monitoring platform includes an acquisition unit, a processing unit and a confirmation unit; the acquisition unit receives a species identification request sent by a user, the species identification request is a request for species monitoring and identification of a monitored area; acquires a first captured image corresponding to a first grid area at a first time point, the first captured image is an image captured by a first capturing device, the first capturing device is a capturing device installed in the first grid area, and the first grid area is any one of a plurality of grid areas; acquires a second captured image corresponding to a second grid area at a second time point, the second time point is later than the first time point, the second captured image is an image captured by a second capturing device, the second capturing device is a capturing device installed in the second grid area a processing unit, which divides the monitored area into grids to obtain a plurality of grid areas; judges the first captured image to determine that the first captured image is in an abnormal state, where the abnormal state indicates that the species information existing in the first captured image cannot be identified; determines the second grid area according to the first grid area, where the second grid area is adjacent to the first grid area; combines the first captured image with the second captured image to obtain a first combined image; identifies the first combined image to obtain first target species information; judges whether the first target species information is the same as the preset first species information; and a confirmation unit, which confirms that the first species exists in the first grid area when the first target species information is the same as the preset first species information, and marks the first species in the first grid area so as to display it to the user, where the first species is an animal species.

[0021] Optionally, the processing unit is used to extract features from the first captured image to obtain target image features; determine whether the target image features are the same as preset first image features, the preset first image features are image features corresponding to the animal; and the confirmation unit is used to confirm that the second grid area is determined based on the first grid area when the target image features are the same as the preset first image features.

[0022] Optionally, the processing unit is used to determine whether the target image feature is the same as a preset second image feature if the target image feature is not the same as the preset first image feature, and the preset second image feature is the image feature corresponding to the plant; the confirmation unit is used to confirm that a third captured image corresponding to the first grid area is at a third time point when the target image feature is the same as the preset second image feature, and the third time point is separated from the first time point by a first preset time period; the processing unit is used to combine the first captured image with the third captured image to obtain a second combined image; identify the second combined image to obtain second target species information; determine whether the second target species information is the same as the preset second species information; the confirmation unit is used to confirm that the second species exists in the first grid area when the second target species information is the same as the preset second species information, and mark the second species in the first grid area for display to the user, and the second species is a plant species.

[0023] Optionally, the processing unit is used to preprocess the first captured image to obtain a first feature point; preprocess the second captured image to obtain a second feature point; perform coordinate transformation on the first feature point and the second feature point to obtain multiple target coordinates; and splice the multiple target coordinates in a preset manner to obtain a first combined image.

[0024] Optionally, the acquisition unit is used to acquire target sound data corresponding to the first grid area in a second preset time period; the processing unit is used to process the target sound data to obtain multiple sound information; the target sound information is input into a preset sound database for matching to obtain third target species information, the third target species is the animal corresponding to the first species, and the target sound information is any one of the multiple sound information.

[0025] Optionally, the acquisition unit is used to obtain the target shooting number corresponding to the first grid area, and the target shooting number is the total number corresponding to the first shooting device installed in the first grid area; the acquisition unit is used to obtain the species number corresponding to the first grid area, and determine the preset shooting number according to the species number; the processing unit is used to determine whether the target shooting number is equal to the preset shooting number; the confirmation unit is used to confirm that when the target shooting number is not equal to the preset shooting number, a processing method is used to adjust the first shooting device in the first grid area, and the processing method includes an increase method or a decrease method.

[0026] Optionally, the acquisition unit is used to obtain environmental information corresponding to the first grid area and determine the target survival level based on the environmental information; the processing unit is used to determine whether the target survival level is less than or equal to a preset survival level; and the confirmation unit is used to confirm to increase the number of first shooting devices in the first grid area when the target survival level is greater than the preset survival level.

[0027] In a third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory, so that an electronic device executes any one of the methods described above in the present application.

[0028] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any one of the above methods of the present application is executed.

[0029] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0030] 1. Receive a species identification request for a monitored area from a user, divide the monitored area into multiple grid areas, configure an independent shooting device for each grid area, improve the coverage of species monitoring through distributed monitoring, obtain a first shot image corresponding to a first grid area, if the first shot image is in an abnormal state, the abnormal state indicates an unclear image, obtain a second shot image corresponding to a second grid area adjacent to the first grid area, because the images of adjacent grid areas may capture different parts of the same species, combine the first shot image with the second shot image to obtain a first combined image, the first combined image contains more species feature information, so that subsequent species identification is more accurate, and then identify the first combined image to obtain first target species information, compare the first target species information with the preset first species information, and confirm the existence of the first species. The comparison can further improve the accuracy of species identification, and show the first species existing in the first grid area to the user, effectively solving the problem of inaccurate species identification caused by incomplete images obtained by fixed photographic equipment.

[0031] 2. Perform feature extraction on the first captured image to obtain target image features. When determining whether the target image features are the same as the preset first image features, it is possible to quickly determine whether the first captured image contains animal species. When the target image features are the same as the preset first image features, it is confirmed that the first captured image cannot identify the animal species. A second grid area adjacent to the first grid area can be obtained, and an image captured in the second grid area can be obtained to further identify the species that appear, thereby reducing the need for manual intervention and improving monitoring efficiency.

[0032] 3. Obtain the target sound data corresponding to the first grid area, and process the target sound data to obtain multiple sound information. Different species have different sound characteristics. Input the target sound information into the preset sound database for matching to obtain the third target species information. The sound data is not limited by line of sight. The multi-dimensional recognition method can more comprehensively reflect the characteristics and distribution of the species. Through subsequent matching of the preset sound database, the species information corresponding to the sound can be quickly identified, thereby improving the efficiency of species recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flowchart of a method for grid-based species monitoring and identification provided in an embodiment of the present application;

[0034] Figure 2 This is a schematic diagram of a first scenario of a grid-based species monitoring and identification method provided in an embodiment of the present application;

[0035] Figure 3 This is a schematic diagram of a second scenario of a grid-based species monitoring and identification method provided in an embodiment of the present application;

[0036] Figure 4 It is a structural schematic diagram of a grid-based species monitoring and identification device provided in an embodiment of the present application;

[0037] Figure 5 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0038] Explanation of the reference numerals: 401, acquisition unit; 402, processing unit; 403, confirmation unit; 500, electronic device; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. DETAILED DESCRIPTION

[0039] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0040] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0041] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0042] Through ecological monitoring technology, researchers conduct in-depth research on species population dynamics, geographical distribution, habitat requirements, etc., in order to reveal the key parameters and ecological mechanisms that affect population changes. This not only helps to deepen the understanding of species biological characteristics and ecological adaptability, but also provides a scientific basis for the protection of biodiversity and the sustainable management of the ecological environment. Species monitoring is an important means of assessing the threats and risks to ecosystems, and provides data support for the formulation of effective ecological risk management strategies.

[0043] In order to improve the accuracy of species identification and monitoring, it is recommended to carry out customized biodiversity monitoring projects for different geographical areas. The monitoring objects include biological communities such as animals and plants. By deploying fixed photography equipment in the monitoring area, real-time image data of species in the area can be collected. Species identification depends on the clarity and completeness of the species in the image, so ensuring image quality is a prerequisite for accurate species identification. If the image is blurred or incomplete, it will directly affect the accuracy of species identification.

[0044] Therefore, how to solve the problem that the images obtained by fixed photography are blurred or incomplete, resulting in inaccurate species identification is an urgent problem to be solved. The present application provides a grid-based species monitoring and identification method, which is applied to a species monitoring platform. The species monitoring platform of the present application can be a platform that provides species identification services for scientific researchers. Figure 1 is a flow chart of a method for grid-based species monitoring and identification provided in an embodiment of the present application, with reference to Figure 1 The method includes the following steps S101-S109.

[0045] S101: receiving a species identification request sent by a user, where the species identification request is a request for monitoring and identifying species in a monitoring area.

[0046] In the above S101, the user can send a species identification request through the interface of the species monitoring platform. The user mentioned in this article may refer to a scientific researcher or a species investigator, etc. The species monitoring platform receives the species identification request sent by the user. The species identification request sent by the user is a request for species monitoring and identification of the monitored area. The monitored area refers to the geographical location and range corresponding to the species monitoring area to be carried out this time. Species is the basic unit of biological taxonomy, referring to a group of individuals that can mate and reproduce, but cannot mate with other organisms, cannot have sexual intercourse, or the hybrids produced after mating can no longer reproduce. Species can be divided into the animal kingdom, plant kingdom, fungal kingdom, etc. This application is mainly to monitor and identify the animal kingdom or plant kingdom in the monitored area.

[0047] S102: Divide the area to be monitored into grids to obtain a plurality of grid areas.

[0048] In the above S102, after determining the ground position and area corresponding to the area to be monitored, a geographic information system or similar tool can be used to divide the area to be monitored into multiple grid areas of equal or unequal size. Each grid area has a unique identifier and thus location information. Figure 2 As shown, the monitored area b can be divided into multiple grid areas with the same geographical area according to the geographical location, and each grid area is numbered in sequence based on the location information, thereby obtaining multiple grid areas, and the multiple grid areas are marked according to the numbers, such as 1, 2, 3, 4, 5 and 6 grid areas.

[0049] S103: Acquire a first captured image corresponding to the first grid area at a first time point, where the first captured image is an image acquired by a first capturing device, and the first capturing device is a capturing device installed in the first grid area.

[0050] In the above S103, after the monitored area is divided into grids, multiple grid areas are obtained, and then the first grid area is obtained from the multiple grid areas, and the first grid area is any one of the multiple grid areas. When determining to monitor the species in the first grid area, it is necessary to check whether the first shooting device (such as a camera, drone, etc.) in the first grid area is online and working normally. If the first shooting device is online and in normal operation, the species monitoring platform sends a shooting request to the first shooting device, and based on the shooting request, the first shooting device shoots an image corresponding to the first time point, and sends the first shot image to the species monitoring platform. At this time, the first time point represents the current time point.

[0051] S104: judging the first captured image and determining that the first captured image is in an abnormal state, where the abnormal state means that species information existing in the first captured image cannot be identified.

[0052] In the above S104, after acquiring the first captured image, the species monitoring platform may use image processing technology (such as a deep learning model) to analyze the first captured image. If the first captured image is of poor quality (such as blurry, overexposed or underexposed, etc.) and the corresponding species information in the first captured image cannot be identified, the first captured image is judged to be in an abnormal state, and the abnormal state means that the corresponding species information in the first captured image cannot be identified, and the first captured image is marked as an abnormal state.

[0053] In addition, when confirming that the first captured image is in an abnormal state, it is necessary to determine what species classification the unrecognizable species in the first captured image corresponds to, that is, whether the unrecognizable species is an animal or a plant. Based on the species classification corresponding to the unrecognizable species in the first captured image, different methods are selected for subsequent processing. When the unrecognizable species in the first captured image corresponds to an animal, other grid areas adjacent to the first grid area can be determined according to the movement characteristics of the animal, and other captured images corresponding to the other grid areas can be obtained. On the basis of the first captured image, the other captured images are combined to further identify the animal species appearing in the first captured image. How to perform animal classification judgment on the unrecognizable species in the first captured image specifically includes: extracting features from the first captured image to obtain target image features; judging whether the target image features are the same as the preset first image features, and the preset first image features are image features corresponding to the animal; when the target image features are the same as the preset first image features, confirming that the second grid area is determined according to the first grid area. Specifically, before extracting features from the first captured image, it is usually necessary to preprocess the first captured image to improve image quality and reduce noise interference. It includes operations such as image denoising, contrast enhancement, and size normalization. Feature extraction is the process of extracting meaningful information from the first captured image. This information can be color, shape, texture, etc. Common feature extraction methods include local feature extraction algorithms such as scale-invariant feature transform (SIFT), accelerated robust features (SURF), ERIEF with direction, or global features extracted by deep learning algorithms such as convolutional neural network (CNN). If you choose to use a traditional local feature extraction algorithm, you will first detect key points in the image (such as corner points, edge points, etc.), and then calculate the feature descriptors around these key points. If a deep learning algorithm is used, the image is usually input into a pre-trained neural network model, and the global feature vector of the image is obtained through the forward propagation of the model. The target image feature obtained in the end is usually a vector or a group of vectors, which represent the key information in the image. Determine whether the target image feature is the same as the preset first image feature. The preset first image feature is defined in advance. The preset first image feature is the image feature corresponding to the animal. These features may come from known animal sample images or feature representations obtained by training an animal recognition model. Matching the extracted target image features with the preset first image features usually involves calculating the distance between the two feature vectors (such as Euclidean distance or cosine similarity, etc.), and then judging whether they are the same or similar based on the size of the distance. If judging whether two features are the same or similar, a threshold needs to be set. If the distance between the two features is less than this threshold, they are confirmed to be the same; otherwise, they are considered different. Based on the feature matching results, it is judged whether there is the same species as the preset animal image in the target image.When the target image feature is the same as the preset first image feature, it is confirmed that the animal species existing in the first captured image cannot be accurately identified. Therefore, when there are unrecognizable animal species according to the first captured image, other grid areas that are adjacent to the first grid area can be obtained, and the captured images corresponding to the other grid areas are obtained, and the images captured by the first grid area and the other grid areas are combined, so as to accurately identify the animal species, and then determine the name and detailed content corresponding to the animal species appearing in the first grid area.

[0054] S105: Determine a second grid area according to the first grid area, where the second grid area and the first grid area are adjacent areas.

[0055] In the above S105, when it is determined that the target image feature in the first captured image is the same as the preset first image feature, it is confirmed that the second grid area is determined based on the first grid area. When the monitored area is gridded, each grid will have an adjacent grid. This can usually be determined by a geographic information system or a grid data structure. When the first captured image taken into the first grid area fails to identify the corresponding animal species, the second grid area adjacent to the first grid area will be found based on the identifier or location information of the first grid area. Figure 3 As shown, if the number corresponding to the first grid area is A, then other grid areas adjacent to the first grid area are obtained, and the grid areas adjacent to the first grid area A include F, B and D. The captured images corresponding to the F area, the B area and the D area are obtained in sequence, and the captured images are identified to determine whether the species appearing in the first grid area A appears in the three adjacent grid areas. The captured images of the adjacent grid areas can be identified in sequence to determine the information that the species appears in the next grid area. The next grid area can be understood as the information that the species moves from the first grid area to the current grid area. At this time, the current grid area can be understood as the second grid area. If there is species information in the image captured by the F area, it is confirmed that the species moves from the first grid area A to the second grid area F, and then the image captured by the shooting device in the second grid area F is obtained, that is, the second captured image.

[0056] S106: Acquire a second captured image corresponding to the second grid area at a second time point, where the second time point is later than the first time point, and the second captured image is an image acquired by a second shooting device, which is a shooting device installed in the second grid area.

[0057] In the above S106, after determining the second grid area, the species monitoring platform will repeat the previous operation, that is, obtain the second captured image corresponding to the second grid area at the second time point, the second captured image is an image obtained by the second shooting device installed in the second grid area, and the second time point is after the first time point, that is, the first time point indicates that the animal species is first photographed by the preset shooting device. Since it is impossible to accurately identify the animal species, it is necessary to determine the second time point based on the distance between the first shooting device and the second shooting device, and divide the distance by the average speed of the animal's movement to obtain the required time. At this time, the required time can be understood as the interval time between the first time point and the second time point. The required time is added to the first time point to obtain the second time point. The second time point is later than the first time point.

[0058] For example, the time point 10:40 corresponding to the first captured image is obtained. The first time point is 10:40, the animal speed is set to 200 meters per minute, and the distance corresponding to the first grid area and the second grid area is obtained. The distance is 2000 meters. The distance is divided by the animal speed to obtain the required time, which is 10 minutes. The first time point is added to the required time to obtain the second time point, that is, the predicted time when the animal arrives at the second shooting device is 10:50, that is, the second captured image corresponding to the second shooting device at the second time point is obtained. The animal speed mentioned in this article can be set based on the type of animals existing in the monitored area. This is just an example. The actual setting can be selected based on the actual situation, and no further explanation will be given here.

[0059] S107: Combine the first captured image and the second captured image to obtain a first combined image.

[0060] In the above S107, the first captured image is combined with the second captured image to obtain a first combined image. The first captured image and the second captured image may be spliced ​​or superimposed to obtain the first combined image, specifically including: preprocessing the first captured image to obtain a first feature point; preprocessing the second captured image to obtain a second feature point; performing coordinate transformation on the first feature point and the second feature point to obtain a plurality of target coordinates; splicing the plurality of target coordinates in a preset manner to obtain the first combined image. Specifically, the first captured image is preprocessed, and the preprocessing includes image loading, denoising, edge detection, feature point extraction, feature description, and result output. First, the first captured image is loaded, and then the noise in the first captured image is removed, and the denoising algorithm may be used for denoising. Then, an edge detection algorithm is used to find edges or significant features in the first captured image, and these edges usually correspond to the contour or texture changes of the object. A feature point detection algorithm is used to find key points or feature points on the image after edge detection. These points have unique properties, such as scale invariance, rotation invariance, etc., and can be reliably identified under different angles and lighting conditions. For each detected feature point, a feature description information is generated, which is usually a vector, and the extracted feature point is output as the first feature point. According to the processing process of the first captured image, it is applied to the second captured image, and the steps of loading the image, denoising, edge detection, feature point extraction and feature description are repeated, but the same parameter settings may be used. When processing the first captured image and the second captured image, it is necessary to determine that the feature points in the two captured images can be compared in the same coordinate system. Matching the first feature point with the second feature point can be achieved by calculating the distance or similarity between each feature point, and finding the point with the smallest distance or the highest similarity as the matching feature point. Then, based on the matched feature point pairs, a coordinate transformation matrix (such as an affine transformation, a projection transformation or a perspective transformation matrix) is calculated. This matrix describes how to map points in one image to corresponding positions in another image. Using the calculated coordinate transformation matrix, the feature points in the first image are transformed to new coordinate positions to obtain multiple target coordinates. According to the application scenario and image features, select the appropriate stitching method, which includes simple overlay (placing two images side by side), image fusion (using an algorithm to smoothly blend two images together), or feature-based stitching (determining the relative position and angle of the images based on the matching relationship of feature points). According to the selected stitching method, the two images are merged into a combined image. It may be necessary to adjust the image's size, position, angle, brightness and other attributes to ensure that the stitched image looks natural and coherent. Then the stitched combined image is output as the final result, outputting the first combined image.

[0061] S108: Identify the first combined image to obtain first target species information; and determine whether the first target species information is the same as the preset first species information.

[0062] In the above S108, after obtaining the first combined image, the first combined image is identified, and a pre-trained species recognition model can be used to identify the first combined image. The recognition model will output the first target species information present in the first combined image, and the first target species information includes the animal species name and brief introduction information, etc. The identified first target species information is compared with the preset first species information. By comparing the similarity between the first target species information and the preset first species information, it can be determined whether the first target species information is the same as the preset first species information based on the similarity value. When the similarity value is equal to or greater than the preset similarity threshold, it is confirmed that the first target species information is the same as the preset first species information. When the similarity value is less than the preset similarity threshold, it is confirmed that the first target species information is not the same as the preset first species information. The preset first species information can be understood as the species information corresponding to any animal in the preset animal database.

[0063] S109: When the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area to be displayed to the user, and the first species is an animal species.

[0064] In the above S109, when the first target species information is the same as the preset first species information, that is, the similarity value between the first target species information and the preset first species information is greater than or equal to the preset similarity threshold, it is confirmed that the first species exists in the first grid area, and the first species represents an animal species. The detailed information of the first species is marked in the first grid area, and the result of species identification in the first captured image is displayed to the user, so that the user can understand the species appearing in the first captured image, so as to subsequently check the distribution of the first species in the area to be monitored.

[0065] In addition, when the first target species information is different from the preset first species information, the first target species information is confirmed to be compared with the species information of other animals in the preset animal database, thereby accurately identifying the animal name corresponding to the first target species information.

[0066] Further, after determining whether the target image feature is the same as the preset first image feature, the method further includes: if the target image feature is not the same as the preset first image feature, determining whether the target image feature is the same as the preset second image feature, the preset second image feature is an image feature corresponding to a plant; when the target image feature is the same as the preset second image feature, confirming that a third shot image corresponding to the first grid area at a third time point is obtained, the third time point is separated from the first time point by a first preset time period; combining the first shot image with the third shot image to obtain a second combined image; identifying the second combined image to obtain second target species information; determining whether the second target species information is the same as the preset second species information; when the second target species information is the same as the preset second species information, confirming that the second species exists in the first grid area, marking the second species in the first grid area so as to display it to the user, and the second species is a plant species. Specifically, when the target image feature is not the same as the preset first image feature, it means that there is no animal species in the first shot image, comparing the target image feature with the preset second image feature, the preset second image feature is an image feature corresponding to a plant, and the preset second image feature is a predefined plant sample image or a training result of a plant recognition model. The feature matching process is the same as the above-mentioned animal features. By calculating the distance or similarity between the target image feature and the preset second image feature, it is determined whether they are the same or similar. When the target image feature is the same as the preset second image feature, the unrecognizable species in the first captured image of the task is a plant species. In order to further obtain more information, an image corresponding to the first shooting device at the third time point in the first grid area can be obtained, that is, a third captured image. There is a preset time interval between the third time point and the first time point, that is, a first preset time period. The first preset time period is based on the change in the appearance of the plant during the day and at night. The preset first time period can be set according to the actual situation to ensure that enough changes or details are captured. For example, the first preset time period can be set to 12 hours, that is, after the first shooting device is at the first time point to shoot the first captured image, after an interval of 12 hours, the third captured image corresponding to the first shooting device at the third time point is used. After obtaining the third captured image, the first captured image is combined with the third captured image to obtain a second combined image. The combination method can be a simple splicing, or it can be a common algorithm to fuse the two images to provide richer context information. The second combined image is identified using the plant identification model to obtain the second target species information, which includes the name and introduction information of the plant. Then, it is determined whether the second target species information is the same as the preset second species information, which is the information corresponding to any plant species in the preset plant database. The similarity between the second target species information and the preset second species information can be calculated to determine whether they are the same.When the similarity between the second target species information and the preset second species information is greater than the preset similarity threshold, it is confirmed that the second target species information is the same as the preset second species information, and it is confirmed that the second species exists in the first grid area, and the second species represents a plant species. The plant name and information corresponding to the second species are marked in the first grid area, and the information is displayed to the user in an appropriate manner so that the user can view the plant species information corresponding to the first grid area.

[0067] In addition, when the second target species information is different from the preset second species information, the second target species information is confirmed to be compared with the species information of other plants in the preset plant database, thereby accurately identifying the plant name corresponding to the second target species information.

[0068] In a possible implementation, in addition to photographing the animal species in each grid area by the above-mentioned photographing device, and then identifying the photographed image to determine the animal species information appearing in the photographed image, the sound data corresponding to each grid area can also be obtained, and the animal species in each grid area can be identified according to the sound data. Specifically, it includes: obtaining the target sound data corresponding to the first grid area in the second preset time period; processing the target sound data to obtain multiple sound information; inputting the target sound information into the preset sound database for matching to obtain the third target species information, the third target species is the animal corresponding to the first species, and the target sound information is any one of the multiple sound information. Specifically, a sound monitoring device, such as a sound sensor, can be deployed in each grid area to capture the sound data of the area. Taking the acquisition of the sound data of the first grid area as an example, a specific time period can be set as the second preset time period, and the second preset time period can be set based on the activity law of the animal and the environmental characteristics. In the second preset time period, the sound data in the first grid area is continuously collected by the monitoring device. The collected data may include environmental noise, animal calls or sounds generated by human activities. The collected sound data is stored to obtain the target sound data and sent to the species monitoring platform. The species monitoring platform pre-processes the target sound data to remove noise and improve the signal-to-noise ratio, which can be achieved through audio processing technologies such as filtering, noise reduction, and enhancement. Extract features from each sound information, such as time domain features (such as energy, duration), frequency domain features (such as spectrum, fundamental frequency) or other acoustic features. These features will be used for subsequent species identification. According to the extracted features, the sound information can be classified and aggregated to distinguish different types of sounds (such as animal calls, human voices, environmental noise, etc.). This helps to search for the sound of the target species in a specific category in the future. Then establish a sound database with known species sound features. This database can be built by collecting and annotating species sound samples, or using an existing sound recognition database. The target sound information is input into the preset sound database for matching, which can be achieved by calculating the distance between the features. According to the results of feature matching, determine the species that the target sound information is most likely to correspond to, which is usually determined based on the output result of the similarity with the sound features of known species in the preset sound database. The identified species information is output as the third target species information, and the third target species information includes the species name. Through the above steps, animal species in the first grid area are identified based on sound data, providing strong support for species monitoring and ecological research.

[0069] In a possible implementation, after determining the number of species corresponding to each grid area, how to set appropriate shooting equipment according to the number of species corresponding to each grid area, so as to better monitor the species situation in each grid area. Specifically, it includes: obtaining the target shooting number corresponding to the first grid area, the target shooting number is the total number of first shooting devices installed in the first grid area; obtaining the number of species corresponding to the first grid area, and determining the preset shooting number according to the number of species; judging whether the target shooting number is equal to the preset shooting number; when the target shooting number is not equal to the preset shooting number, confirming that the first shooting device in the first grid area is adjusted by a processing method, and the processing method includes an increase method or a decrease method. Specifically, it is necessary to obtain multiple first shooting devices installed in the first grid area, which is usually completed by recording the equipment deployment information of each grid area. Obtaining the information of all first shooting devices in the first grid area, the target shooting number is calculated, that is, the total number of first shooting devices in the first grid area. After identifying the species information corresponding to each grid area according to the above, the species number corresponding to each grid area can be determined, that is, the species number corresponding to the first grid area is obtained, and the species number at this time refers to the sum of the number of animal species and the number of plant species in the first grid area. The preset number of shots corresponding to the first grid area can be determined based on the number of species. The preset number of shots is usually determined based on factors such as the number of species, the range of species activities, and monitoring needs. For example, if the number of species is large and the range of activities is wide, more shooting equipment may be needed to cover the entire area. Determine whether the target shooting number is equal to the preset shooting number. When the target shooting number is not equal to the preset shooting number, it includes two situations. The first situation corresponds to that the target shooting number is less than the preset shooting number, then confirm to increase the number of first shooting devices in the first grid area. The second situation corresponds to that the target shooting number is greater than the preset shooting number, then confirm to reduce the number of first shooting devices in the first grid area. The reduction here can be to turn off the shooting of the first shooting device. After determining the processing method, perform the corresponding operation to adjust the first shooting device in the first grid area. After performing the adjustment operation, the species monitoring platform should recheck the number of shooting devices in the first grid area to ensure that the number of shooting devices meets the requirements of the preset shooting number.

[0070] In addition, when the target shooting number is equal to the preset shooting number, there is no need to adjust the number of first shooting devices in the first grid area.

[0071] Furthermore, in addition to determining the number of shooting devices by the number of species in each grid area, the survival level can also be determined according to the environment corresponding to each grid area, and the number of shooting devices to be installed can be determined based on the survival level. Specifically, it includes: obtaining the environmental information corresponding to the first grid area, determining the target survival level according to the environmental information; judging whether the target survival level is less than or equal to the preset survival level; when the target survival level is greater than the preset survival level, confirming to increase the number of first shooting devices in the first grid area. Specifically, the species monitoring platform collects environmental information of the first grid area, and the environmental information includes but is not limited to climate data (such as temperature, humidity and precipitation, etc.), geographical data (such as terrain, altitude, vegetation coverage, etc.), ecological data (such as species diversity, population density, food chain structure, etc.), human interference factors (such as human activity frequency, building distribution, traffic conditions, etc.), etc., and the drone shooting equipment can be used to conduct a detailed inspection of the monitored area and output environmental information. The data source of environmental information can be diverse, and the latest data can be obtained regularly or in real time. The collected raw data may need to be cleaned, sorted, converted, etc. for subsequent analysis and evaluation. Determining the target survival level based on environmental information may require an evaluation model for calculating the target survival level based on environmental information. The survival level is a quantitative evaluation of the survival status of species in the area. It can be defined based on factors such as the species' physiological needs, ecological habits, and environmental adaptation. For example, the survival level can be divided into 1-5 levels. Among them, level 1 represents extremely poor and level 5 represents excellent. The evaluation model takes environmental information as input and outputs the target survival level through a series of calculations and analyses. When judging whether the target survival level is less than or equal to the preset survival level, the preset survival level is a threshold used to judge whether the survival status of the species in the area meets the expected standards. The preset survival level can be determined based on actual needs. When the target survival level is less than or equal to the preset survival level, it means that the survival status corresponding to the first grid area is not good. There is no need to adjust the number of first shooting devices in the first grid area, or monitor the species in the first grid area based on the initial installation number. When the target survival level is greater than the preset survival level, it is confirmed that the survival status corresponding to the first grid area is good, and there is a need to increase the number of first shooting devices. The number to be increased can be determined in combination with the number of first shooting devices installed in the first grid area, and it is determined that the number of first shooting devices after the increase can meet the monitoring requirements of the first grid area. After the number of first shooting devices is increased, it is necessary to continuously monitor the environmental information and species activities of the first grid area. The number of first shooting devices can be dynamically adjusted according to the environmental information of the first grid area to better meet the monitoring needs and improve the monitoring effect.

[0072] The present application also provides a grid-based species monitoring and identification device. Figure 4is a schematic diagram of a grid-based species monitoring and identification device provided in an embodiment of the present application, with reference to Figure 4 The device is a species monitoring platform, which includes an acquisition unit 401, a processing unit 402 and a confirmation unit 403.

[0073] An acquisition unit 401 receives a species identification request sent by a user, where the species identification request is a request for species monitoring and identification of a monitored area; acquires a first captured image corresponding to a first grid area at a first time point, where the first captured image is an image captured by a first capturing device, where the first capturing device is a capturing device installed in the first grid area, and where the first grid area is any one of a plurality of grid areas; acquires a second captured image corresponding to a second grid area at a second time point, where the second time point is later than the first time point, where the second captured image is an image captured by a second capturing device, and where the second capturing device is a capturing device installed in the second grid area.

[0074] The processing unit 402 divides the monitored area into grids to obtain a plurality of grid areas; judges the first captured image to determine that the first captured image is in an abnormal state, where the abnormal state indicates that the species information existing in the first captured image cannot be identified; determines a second grid area based on the first grid area, where the second grid area is adjacent to the first grid area; combines the first captured image with the second captured image to obtain a first combined image; identifies the first combined image to obtain first target species information; and judges whether the first target species information is the same as the preset first species information.

[0075] The confirmation unit 403 confirms that the first species exists in the first grid area when the first target species information is the same as the preset first species information, and marks the first species in the first grid area to display it to the user, and the first species is an animal species.

[0076] In one possible implementation, the processing unit 402 is used to perform feature extraction on the first captured image to obtain target image features; determine whether the target image features are the same as the preset first image features, where the preset first image features are image features corresponding to the animal; and the confirmation unit 403 is used to confirm that the second grid area is determined based on the first grid area when the target image features are the same as the preset first image features.

[0077] In a possible implementation, the processing unit 402 is used to determine whether the target image feature is the same as the preset second image feature if the target image feature is not the same as the preset first image feature, and the preset second image feature is the image feature corresponding to the plant; the confirmation unit 403 is used to confirm the acquisition of the third captured image corresponding to the first grid area at the third time point when the target image feature is the same as the preset second image feature, and the third time point is separated from the first time point by a first preset time period; the processing unit 402 is used to combine the first captured image with the third captured image to obtain a second combined image; identify the second combined image to obtain the second target species information; determine whether the second target species information is the same as the preset second species information; the confirmation unit 403 is used to confirm that the second species exists in the first grid area when the second target species information is the same as the preset second species information, and mark the second species in the first grid area so as to display it to the user, and the second species is a plant species.

[0078] In a possible implementation, the processing unit 402 is used to preprocess the first captured image to obtain a first feature point; preprocess the second captured image to obtain a second feature point; perform coordinate transformation on the first feature point and the second feature point to obtain multiple target coordinates; and splice the multiple target coordinates in a preset manner to obtain a first combined image.

[0079] In a possible implementation, the acquisition unit 401 is used to acquire the target sound data corresponding to the first grid area in the second preset time period; the processing unit 402 is used to process the target sound data to obtain multiple sound information; the target sound information is input into a preset sound database for matching to obtain third target species information, the third target species is the animal corresponding to the first species, and the target sound information is any one of the multiple sound information.

[0080] In a possible implementation, the acquisition unit 401 is used to acquire the target shooting number corresponding to the first grid area, where the target shooting number is the total number corresponding to the first shooting devices installed in the first grid area; the acquisition unit 401 is used to acquire the number of species corresponding to the first grid area, and determine the preset shooting number based on the number of species; the processing unit 402 is used to determine whether the target shooting number is equal to the preset shooting number; the confirmation unit 403 is used to confirm that a processing method is used to adjust the first shooting device in the first grid area when the target shooting number is not equal to the preset shooting number, and the processing method includes an increase method or a decrease method.

[0081] In one possible implementation, the acquisition unit 401 is used to acquire environmental information corresponding to the first grid area and determine the target survival level based on the environmental information; the processing unit 402 is used to determine whether the target survival level is less than or equal to a preset survival level; and the confirmation unit 403 is used to confirm increasing the number of first shooting devices in the first grid area when the target survival level is greater than the preset survival level.

[0082] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0083] The present application also discloses an electronic device. Figure 5 , Figure 5 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0084] The communication bus 502 is used to realize the connection and communication between these components.

[0085] The user interface 503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0086] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0087] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application requests; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0088] Among them, the memory 505 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area. Instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. can be stored; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 505 can also be optionally at least one storage device located away from the aforementioned processor 501.

[0089] like Figure 5 As shown, the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application for grid-based species monitoring and identification.

[0090] exist Figure 5In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 501 can be used to call the application for gridded species monitoring and identification stored in the memory 505. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0091] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0092] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0094] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] 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.

[0096] 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 memory. 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 memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0097] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure.

Claims

1. A method for grid-based species monitoring and identification, characterized in that: Applied to a species monitoring platform, the method comprises: Receiving a species identification request sent by a user, wherein the species identification request is a request for species monitoring and identification in a monitoring area; Dividing the area to be monitored into grids to obtain a plurality of grid areas; Acquire a first captured image corresponding to a first grid area at a first time point, where the first captured image is an image acquired by a first capturing device, the first capturing device is a capturing device installed in the first grid area, and the first grid area is any one of the plurality of grid areas; Judging the first captured image, determining that the first captured image is in an abnormal state, where the abnormal state indicates that species information existing in the first captured image cannot be identified; Determine a second grid area according to the first grid area, where the second grid area is adjacent to the first grid area; Acquire a second captured image corresponding to a second grid area at a second time point, where the second time point is later than the first time point, and the second captured image is an image acquired by a second shooting device, where the second shooting device is a shooting device installed in the second grid area; combining the first captured image and the second captured image to obtain a first combined image; Identify the first combined image to obtain first target species information; Determining whether the first target species information is the same as the preset first species information; When the first target species information is the same as the preset first species information, it is confirmed that the first species exists in the first grid area, and the first species is marked in the first grid area to be displayed to the user, and the first species is an animal species.

2. The method according to claim 1, characterized in that After judging the first captured image and determining that the first captured image is in an abnormal state, the method further includes: Performing feature extraction on the first captured image to obtain target image features; Determining whether the target image feature is the same as a preset first image feature, where the preset first image feature is an image feature corresponding to an animal; When the target image feature is the same as the preset first image feature, it is confirmed that the second grid area is determined according to the first grid area.

3. The method according to claim 2, characterized in that After determining whether the target image feature is the same as the preset first image feature, the method further includes: If the target image feature is not the same as the preset first image feature, determining whether the target image feature is the same as the preset second image feature, the preset second image feature being the image feature corresponding to the plant; when the target image feature is the same as the preset second image feature, confirming that a third captured image corresponding to the first grid area at a third time point is obtained, and the third time point is separated from the first time point by a first preset time period; combining the first captured image and the third captured image to obtain a second combined image; Identifying the second combined image to obtain second target species information; Determining whether the second target species information is the same as the preset second species information; When the second target species information is the same as the preset second species information, it is confirmed that the second species exists in the first grid area, and the second species is marked in the first grid area to be displayed to the user, and the second species is a plant species.

4. The method according to claim 1, characterized in that: The step of combining the first captured image with the second captured image to obtain a first combined image specifically includes: Preprocessing the first captured image to obtain a first feature point; performing the preprocessing on the second captured image to obtain second feature points; Performing coordinate transformation on the first feature point and the second feature point to obtain a plurality of target coordinates; The plurality of target coordinates are spliced ​​in a preset manner to obtain the first combined image.

5. The method according to claim 1, characterized in that After confirming that the first species exists in the first grid area when the first target species information is the same as the preset first species information and marking the first species in the first grid area for display to the user, the method further includes: Acquire target sound data corresponding to the first grid area in a second preset time period; Processing the target sound data to obtain multiple sound information; The target sound information is input into a preset sound database for matching to obtain third target species information, wherein the third target species is an animal corresponding to the first species, and the target sound information is any one of the multiple sound information.

6. The method according to claim 3, characterized in that After confirming that the first species exists in the first grid area when the first target species information is the same as the preset first species information and marking the first species in the first grid area for display to the user, the method further includes: Acquire the number of target shooting devices corresponding to the first grid area, where the number of target shooting devices is the total number of the first shooting devices installed in the first grid area; Obtaining the number of species corresponding to the first grid area, and determining the number of preset shooting devices according to the number of species; Determine whether the number of target shooting devices is equal to the preset number of shooting devices; When the target number of shooting devices is not equal to the preset number of shooting devices, it is confirmed to adopt a processing method to adjust the number of the first shooting devices in the first grid area, and the processing method includes an increase method or a decrease method.

7. The method according to claim 6, characterized in that After obtaining the number of target shooting devices corresponding to the first grid area, the method further includes: Acquire environmental information corresponding to the first grid area, and determine a target survival level according to the environmental information; and determine whether the target survival level is less than or equal to a preset survival level; When the target survival level is greater than the preset survival level, it is confirmed to increase the number of devices of the first shooting device in the first grid area.

8. A grid-based species monitoring and identification device, characterized in that: The device is a species monitoring platform, and the species monitoring platform comprises an acquisition unit (401), a processing unit (402) and a confirmation unit (403); the acquisition unit (401) receives a species identification request sent by a user, and the species identification request is a request for species monitoring and identification in a monitored area; Acquire a first captured image corresponding to a first grid area at a first time point, where the first captured image is an image acquired by a first capturing device, the first capturing device is a capturing device installed in the first grid area, and the first grid area is any one of the plurality of grid areas; Acquire a second captured image corresponding to a second grid area at a second time point, where the second time point is later than the first time point, and the second captured image is an image acquired by a second shooting device, where the second shooting device is a shooting device installed in the second grid area; The processing unit (402) divides the area to be monitored into grids to obtain a plurality of grid areas; judges the first captured image to determine that the first captured image is in an abnormal state, wherein the abnormal state indicates that the species information existing in the first captured image cannot be identified; determines a second grid area based on the first grid area, wherein the second grid area is adjacent to the first grid area; combining the first captured image and the second captured image to obtain a first combined image; identifying the first combined image to obtain first target species information; and determining whether the first target species information is the same as the preset first species information; The confirmation unit (403) confirms that the first species exists in the first grid area when the first target species information is the same as the preset first species information, and marks the first species in the first grid area so as to display it to the user, and the first species is an animal species.

9. An electronic device, characterized in that: Includes a processor (501), a memory (505), a user interface (503) and a network interface (504), the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to For communicating with other devices, the processor (501) is used to execute instructions stored in the memory (505) so that the The electronic device (500) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores instructions. When the instruction is executed, the method according to any one of claims 1 to 7 is performed.

Images