Infrared super-temporal biological detection method and system based on computer vision

Abstract

A computer vision-based infrared super-phase organism detection method and system relates to the field of computer vision technology. In this method, the technical solution provided by this application is implemented. Based on image data captured by an acquisition device in a preset area, a super-phase image of the preset area is obtained. Target images within a preset range are extracted from the super-phase image of the preset area. The target images within the preset range include a first target image, a second target image, and a third target image. First labels are obtained for several organisms based on the first target image. Second labels are obtained for several organisms based on the second and third target images. A determination is made as to whether the second labels correspond to the first labels of the several organisms. If so, the preset area is determined to be the activity area of ​​the organisms corresponding to the labels. This method can effectively improve the accuracy of the detected actual activity areas of the organisms.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to an infrared super-phase biological detection method and system based on computer vision. Background Art

[0002] Nowadays, with the continuous development of science and technology, computer vision technology has become indispensable in many fields such as daily life, scientific research, and military. Because computer vision technology can significantly improve the level of military intelligence, it can be widely used in the military field.

[0003] In the military, it's often necessary to detect the ranges of biological activity so that precise, targeted strikes can be carried out against those within those ranges. However, due to the large number of organisms and their wide ranges, coupled with the limitations of the detection area, it's difficult for researchers to conduct on-site surveys of the ranges, resulting in low accuracy in the detected ranges.

[0004] Therefore, the inventors believe that there is an urgent need for an infrared super-phase biological detection method and system based on computer vision. Summary of the Invention

[0005] The present application provides a computer vision-based infrared super-phase biological detection method and system, which can effectively improve the accuracy of the actual activity area of ​​the detected organisms.

[0006] In the first aspect, the present application provides an infrared super-phase biological detection method based on computer vision, the method comprising: obtaining a super-phase image of a preset area based on image data collected by an acquisition device in the preset area; extracting a target image within a preset range from the super-phase image of the preset area; the target images within the preset range include a first target image, a second target image and a third target image; obtaining a first label of several organisms based on the first target image; obtaining a second label of several organisms based on the second target image and the third target image; judging whether the second label corresponds to the first label of the several organisms; and if so, determining that the preset area is the activity area of ​​the organisms corresponding to the label.

[0007] By adopting the above technical solution, image data in a preset area is collected by an acquisition device, and a super-phase image is obtained after processing, so that the acquired image accuracy can be made higher, thereby making the extracted first target image, second target image and third target image clearer, and making the extracted first label and second label more accurate; by judging whether the second label corresponds to the first labels of several organisms, it is determined whether the information in the first target image, the second target image and the third target image can correspond one to one, so that the activity area of ​​the organism corresponding to the label can be determined more accurately.

[0008] Optionally, after determining that the preset area is the activity area of ​​the organism corresponding to the label, the method also includes: extracting several first sub-labels based on the first target image and the first label; obtaining the corresponding first target image according to the several first sub-labels, and determining the first overtime phase image; determining the set position of the first acquisition device corresponding to the first overtime phase image; constructing a position relationship diagram of the first acquisition device based on the set position of the first acquisition device; wherein, each of the first acquisition devices corresponds to each node in the position relationship diagram of the first acquisition device, and the arrangement relationship between each of the first acquisition devices corresponds to the connection relationship between each of the nodes; determining the first area range based on the position relationship diagram of the first acquisition device; the first area range is the activity area of ​​the organisms corresponding to several of the first sub-labels.

[0009] By adopting the above technical solution, based on the first target image and the first label, several first sub-labels are extracted, that is, the activity ranges of the organisms corresponding to the several first sub-labels are more finely distinguished; and by constructing a position relationship diagram of the first acquisition device, the actual activity areas of various types of organisms can be determined more clearly and intuitively.

[0010] Optionally, after determining the first area range, the method also includes: obtaining the number of occurrences of the first sub-tag within the first area range within a preset time period; when the number of occurrences of the first sub-tag is less than a preset first threshold, determining the disturbance area in the first area range based on a preset first method; judging whether the disturbance area is the activity area of ​​the organism corresponding to the first sub-tag based on a preset third method; if not, re-determining the second area range; the second area range is the precise activity area of ​​several organisms corresponding to the first sub-tags.

[0011] By adopting the above technical solution, by determining whether the number of first subtags appearing within a first area within a preset time period is less than a preset first threshold, and setting a disturbance area, the actual activity area of ​​a certain organism can be more accurately detected by re-determining whether the disturbance area is the activity area of ​​the organism corresponding to the first subtag.

[0012] Optionally, the method of determining the disturbance area within the first area range based on a preset first method specifically includes: determining a first node; the first node is a plurality of boundary nodes in a position relationship diagram of the first acquisition device; determining a second node; the second node is a node with the shortest connection line path to the first node in the position relationship diagram of the first acquisition device; and constructing a plurality of disturbance areas based on the first node and the second node.

[0013] By adopting the above technical solution, several disturbance areas are constructed based on the positional relationship between the first node and the second node, taking into account the possibility that the detection ranges of the collection devices may overlap.

[0014] Optionally, the method of determining whether the disturbance area is the activity area of ​​the organism corresponding to the first sub-tag based on a preset third method specifically includes: extracting a second sub-tag based on the second target image and the third target image within the disturbance area; determining the occurrence frequency of the second sub-tag; and when the occurrence frequency is greater than a preset second threshold, determining that the disturbance area is the activity area of ​​the organism corresponding to the first sub-tag.

[0015] By adopting the above technical solution, the second sub-tag is extracted through the second target image and the third target image in the disturbance area, and when the occurrence frequency of the second sub-tag is greater than the second threshold, the disturbance area can be determined to be the activity area of ​​the organism corresponding to the first sub-tag.

[0016] Optionally, constructing several disturbance areas based on the first node and the second node specifically includes: connecting each first node with its corresponding second node to obtain several disturbance areas; determining a third node; the third node is a second node whose number of connected first nodes is a preset third threshold; and connecting the third nodes to obtain several disturbance areas.

[0017] Optionally, after determining whether the second tag corresponds to the first tags of the plurality of organisms, the method further includes: if not, determining the activity area of ​​the organism corresponding to the second tag based on a preset second method.

[0018] By adopting the above technical solution, if it is determined that the second tag does not correspond to the first tag, it is determined that there may be a problem with the collection device position setting of the detection scheme, and the collection device position is redesigned and the actual activity area of ​​the organism is re-detected.

[0019] In a second aspect of the present application, an infrared super-phase biological detection system based on computer vision is provided, the system comprising: an image processing module, a judgment module and an area division module; the image processing module is used to obtain a super-phase image of a preset area based on image data collected by an acquisition device in the preset area; the image processing module is also used to extract target images within a preset range from the super-phase image of the preset area; the target images within the preset range include a first target image, a second target image and a third target image; the image processing module is also used to obtain a first label of several organisms based on the first target image; obtain a second label of several organisms based on the second target image and the third target image; the judgment module is used to determine whether the second label corresponds to the first label of the several organisms; the area division module is used to determine that the preset area is the activity area of ​​the organisms corresponding to the label when the second label corresponds to the first label of the several organisms.

[0020] In the third aspect of the present application, an electronic device is provided, including 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 the electronic device executes any method as described in the first aspect of the present application.

[0021] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program that can be loaded by a processor and execute the method as described in any one of the first aspects of the present application.

[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0023] 1. By using an acquisition device to capture image data in a preset area and processing it to obtain a super-phase image, the acquired image accuracy can be improved, thereby making the extracted first target image, second target image, and third target image clearer and the extracted first and second labels more accurate. By determining whether the second label corresponds to the first label of multiple organisms, it is determined whether the information in the first target image, second target image, and third target image can be one-to-one matched, thereby more accurately determining the activity area of ​​the organism corresponding to the label;

[0024] 2. Based on the first target image and the first label, a plurality of first sub-labels are extracted, thereby more precisely distinguishing the activity ranges of the organisms corresponding to the plurality of first sub-labels. Furthermore, by constructing a position relationship diagram of the first acquisition device, the actual activity areas of each species of organism can be more clearly and intuitively determined.

[0025] 3. By determining whether the number of occurrences of the first subtag within the first area within a preset time period is less than a preset first threshold, and setting a disturbance area, the actual activity area of ​​a certain organism can be more accurately detected by re-determining whether the disturbance area is the activity area of ​​the organism corresponding to the first subtag. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a computer vision-based infrared super-phase biological detection method provided in an embodiment of the present application;

[0027] Figure 2 It shows the position relationship of a collection device provided in an embodiment of the present application. Figure 1 ;

[0028] Figure 3 It shows the position relationship of a collection device provided in an embodiment of the present application. Figure 2 ;

[0029] Figure 4 This is a schematic diagram of the structure of an infrared super-phase biological detection system based on computer vision disclosed in an embodiment of the present application;

[0030] Figure 5 This is a structural diagram of an electronic device disclosed in an embodiment of the present application.

[0031] Explanation of the accompanying drawings: 1. Image processing module; 2. Judgment module; 3. Area division module; 500. Electronic device; 501. Processor; 502. Communication bus; 503. User interface; 504. Network interface; 505. Memory. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art 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.

[0033] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0034] In the description of the embodiments of the present application, the term "multiple" means 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 are not to 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 "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0035] Infrared hyperphase, also known as infrared multi-temporal phase, uses satellites, aircraft, or ground-based infrared cameras to capture multiple images of the same area over a specific timeframe. This data is then stitched together into a single, high-precision, high-resolution image using image processing techniques.

[0036] This application provides an infrared super-phase biological detection method based on computer vision, referring to Figure 1 , which shows a flow chart of a computer vision-based infrared super-phase biological detection method provided in an embodiment of the present application. The method includes steps S101-S107, which are as follows:

[0037] Step S101: obtaining a time-lapse image of a preset area based on image data collected by an acquisition device in the preset area.

[0038] In the above steps, the server obtains a time-lapse image of the preset area based on the image data collected by the collection device in the preset area.

[0039] Specifically, in this technical solution, the preset area is the military targeted strike area. In the embodiments of this application, organisms are defined as bionic organisms and humans; bionic organisms include various types of bionic robots, such as large dog robots. Collection equipment includes but is not limited to satellites, aircraft, drones, or ground-based infrared cameras. The collection equipment collects image data of objects, and the hyperphase technology uses computer vision technology to process and analyze the collected image data to achieve automatic recognition and recording of biological behavior. In the hyperphase image, the traces of the organisms can be clearly seen, including the routes they have traveled, the places they have stayed, etc.

[0040] The key to super-phase technology lies in determining the timeout window—the interval and length of the monitoring period. This depends on the researcher's specific needs. For example, a capture device with a frame rate of 30 frames per second captures 30 images per second. Since the organisms being monitored in this application are biomimetic organisms and humans, a sampling interval of 0.5 seconds is sufficient to capture the vast majority of biomimetic and human motion image data.

[0041] Step S102: extracting target images within a preset range from the super-temporal image of a preset area; the target images within the preset range include a first target image, a second target image, and a third target image.

[0042] In the above steps, the server extracts the target image within a preset range from the super-phase image of the preset area.

[0043] Specifically, the server uses computer vision to extract the target image from the hyperphase image. First, the hyperphase image is preprocessed, that is, grayscale processing, denoising, and image enhancement are performed on the hyperphase image to improve the accuracy and effect of subsequent feature extraction. Then, a target detection algorithm, such as an object detection algorithm based on deep learning, is used to detect the target in the hyperphase image. In this application, the first target image, the second target image, and the third target image are detected in the hyperphase image. Feature extraction is then performed on the detected biological target image to extract characteristic feature information that can be represented, such as appearance shape, color, etc. The feature information is then converted into a feature image, that is, the extracted feature information is presented in the form of an image. Traditional image processing methods can be used, such as those based on filters, transformations, and projections. Finally, the feature images are classified. Machine learning and deep learning algorithms can be used for classification to classify the feature images into different categories.

[0044] Among them, the first target image is the biological image; the second target image is the biological trace image, such as the biological footprint; the third target image is other images of the biological, such as the activity traces produced by the biological.

[0045] Step S103: obtaining first labels of several organisms based on the first target image.

[0046] In the above steps, the server obtains first tags of several organisms based on the first target image.

[0047] Specifically, in this technical solution, the first label is the classification label of the organism, such as the bionic organism label and the human label, which distinguishes the organisms into bionic organisms and humans. The server will extract features in the organism image based on computer vision and classify the organisms with labels.

[0048] Step S104: obtaining second labels of several organisms based on the second target image and the third target image.

[0049] In the above steps, the server obtains second tags of several creatures based on the second target image and the third target image.

[0050] Specifically, in this technical solution, the second label has the same meaning as the first label: a bionic creature label and a human label. Because bionic creatures and humans leave different tracks and produce different activity traces, the server uses computer vision to extract features such as footprint shape, size, and form from bionic trace images, as well as features such as activity traces from other images of the organism, to classify the organisms.

[0051] Step S105: Determine whether the second tag corresponds to the first tags of several organisms.

[0052] In the above steps, the server determines whether the second tag corresponds to the first tags of several creatures.

[0053] Step S106: If yes, determine that the preset area is the activity area of ​​the organism corresponding to the tag.

[0054] In the above steps, when the server determines that the second tag corresponds to the first tags of several creatures, it determines the preset area as the activity area of ​​the creatures corresponding to the tags.

[0055] Specifically, in this technical solution, when the first label extracted from the first target image in the preset area corresponds one-to-one with the second label extracted from the second target image and the third target image, the preset area is judged to be the activity area of ​​the organism corresponding to the label.

[0056] In one possible implementation, refer to Figure 1 After step S105, the method further includes step S107: when the second tag does not correspond to the first tags of the plurality of creatures, determining the activity area of ​​the creature corresponding to the second tag based on a preset second method.

[0057] In the above steps, when the server determines that the second tag does not correspond to the first tags of the plurality of creatures, the server determines the activity area of ​​the creature corresponding to the second tag based on a preset second method.

[0058] Specifically, in this technical solution, there may be a situation where the creature fails to capture the image, resulting in a mismatch between the first label and the second label. Therefore, the second method is used to determine that the researcher repositions the acquisition device, expands the scope of the preset area, and re-executes steps S101-S105.

[0059] In a possible implementation, after step S106, the method further includes the following steps:

[0060] Based on the first target image and the first label, a plurality of first sub-labels are extracted.

[0061] In the above steps, the server extracts a plurality of first sub-tags based on the first target image and the first tag.

[0062] Specifically, the first sub-label is the category of the organism. For example, for human labels, humans are distinguished into military personnel and ordinary people based on the first target image. For bionic organism labels, bionic organisms are distinguished into specific types based on the first target image, such as a certain type of bionic robot. Based on the distinguishing feature points of each organism in the first target image, the server extracts characteristic information that can characterize the organism and generates several first sub-labels. For human labels, humans are distinguished into military personnel and ordinary people based on distinguishing feature points such as whether they are equipped with military equipment; for bionic organism labels, bionic organisms are distinguished into various types of bionic robots based on their shape, structure, color, etc.

[0063] It should be noted that distinguishing humans into military personnel and civilians is used to accurately identify the military personnel of the target forces to be attacked, avoiding inadvertent attacks on the civilian population. Distinguishing biomimetic organisms by their specific types is used to more accurately identify the military forces of the target forces to be attacked, facilitating subsequent experts' accurate assessment of the battle situation.

[0064] According to the plurality of first sub-labels, a corresponding first target image is obtained, and a first overtime phase image is determined.

[0065] In the above steps, the server obtains the corresponding first target image according to the plurality of first sub-tags, and determines the first time-out phase image.

[0066] Specifically, in this technical solution, the server will find the corresponding first target image according to the first subtag, that is, find which first target image contains the first subtag, and determine the first time-lapse phase image corresponding to the first target image.

[0067] A set position of a first acquisition device corresponding to the first time-phase image is determined.

[0068] In the above steps, the server determines the set position of the first acquisition device corresponding to the first time-lapse image.

[0069] Specifically, in this technical solution, the first over-time phase image includes multiple over-time phase images; the first acquisition device includes multiple acquisition devices, and the first acquisition device is the acquisition device corresponding to the first over-time phase image. For example, the server extracts a first sub-label of military personnel from a first target image extracted from the multiple over-time phase images, and the multiple over-time phase images are image data acquired by acquisition devices 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11, respectively, and the over-time phase images are obtained after processing.

[0070] Based on the set positions of the first acquisition devices, a position relationship diagram of the first acquisition devices is constructed; wherein each first acquisition device corresponds to each node in the position relationship diagram of the first acquisition devices, and the arrangement relationship between each first acquisition device corresponds to the connection relationship between each node.

[0071] In the above steps, the server constructs a position relationship diagram of the first acquisition device based on the set position of the first acquisition device.

[0072] Specifically, in this technical solution, refer to Figure 2 , which shows the position relationship of a collection device provided in an embodiment of the present application Figure 1 Nodes A, B, C, D, E, F, G, H, I, J, and K correspond to collection devices 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11. The positional relationship between the nodes will be scaled down based on the actual layout of the collection devices, with the scale being set based on the actual range of the preset area. The server will connect nodes A, B, C, D, E, and F corresponding to the outermost first collection device based on the positional relationship of the first collection device.

[0073] Based on the position relationship diagram of the first acquisition device, a first area range is determined; the first area range is the activity area of ​​the organisms corresponding to the plurality of first sub-tags.

[0074] In the above steps, the server determines the first area range based on the position relationship diagram of the first acquisition device.

[0075] Specifically, in this technical solution, refer to Figure 2 The area formed by the connection of nodes A, B, C, D, E, and F is the first area range, that is, the activity area of ​​the organism corresponding to the first sub-label. In the above example, the area formed by the connection of nodes A, B, C, D, E, and F is the activity area of ​​military personnel.

[0076] In a possible implementation, after the step of determining the first area range, the method further includes the following steps:

[0077] Obtain the number of occurrences of the first sub-tag within a preset time period within the first area.

[0078] In the above steps, the server obtains the number of occurrences of the first sub-tag within the first area within a preset time period.

[0079] Specifically, in this technical solution, the preset time period is set by the technician according to the actual situation, and the preset time period can be one week, one month, etc. The specific time period is not too limited in this technical solution.

[0080] When the number of occurrences of the first sub-tag is less than a preset first threshold, the disturbance area in the first area range is determined based on a preset first method.

[0081] In the above steps, when the server determines that the number of occurrences of the first sub-tag is less than a preset first threshold, the server determines the disturbance area in the first area range based on a preset first method.

[0082] Specifically, in this technical solution, the preset first threshold is set at 50% of the peak number of the first subtag detected in the preset time period. The specific percentage will also need to be set based on the actual environment and the battle situation in the preset area, as these factors will affect the number of organisms.

[0083] In a possible implementation, the step of determining the disturbance area within the first area range based on a preset first method specifically includes the following steps:

[0084] Determine a first node; the first node is a plurality of boundary nodes in the position relationship graph of the first acquisition device.

[0085] In the above steps, the server will determine the first node.

[0086] Specifically, in this technical solution, refer to Figure 3 , which shows the position relationship of a collection device provided in an embodiment of the present application Figure 2 . Nodes A, B, C, D, E, and F are the first nodes.

[0087] Determine a second node; the second node is a node in the position relationship diagram of the first acquisition device that has the shortest connection line path with the first node.

[0088] In the above steps, the server determines the second node.

[0089] Specifically, in this technical solution, the server will calculate the length between each node and determine the node with the shortest distance to each first node except the first node. Figure 3The node with the shortest connection line path to node A is node H; the node with the shortest connection line path to node B is node J; the node with the shortest connection line path to node C is node J; the node with the shortest connection line path to node D is node K; the node with the shortest connection line path to node E is node I; and the node with the shortest connection line path to node F is node H. Therefore, the second node can be determined as nodes J, K, I, and H.

[0090] Based on the first node and the second node, several disturbance regions are constructed.

[0091] In the above steps, the server constructs several disturbance areas based on the first node and the second node.

[0092] Specifically, the divided areas must meet the following requirements: They must be independent of each other, without interference or overlap. Furthermore, the number of biological traces within each small area must be sufficient to ensure that the subsequent classification algorithm can effectively identify and classify them. In this technical solution, the disturbance area refers to the edge area where the collection devices may overlap due to the close spacing between them.

[0093] In a possible implementation, the step is based on the first node and the second node to construct a plurality of disturbance regions, and the method specifically includes the following steps.

[0094] Each first node is connected to its corresponding second node to obtain a plurality of disturbance regions.

[0095] In the above steps, the server connects each first node to its corresponding second node to obtain several disturbance areas

[0096] Specifically, in this technical solution, the server connects the first node and its corresponding second node, and determines whether the first node and its corresponding second node can form a closed area. Figure 3 The first nodes A and F and the second node H with the shortest connection path thereto may form region AFH; the first nodes B and C and the second node J with the shortest connection path thereto may form region BCJ.

[0097] Determine a third node; the third node is a second node whose number of connected first nodes is a preset third threshold.

[0098] In the above steps, the server determines the second node whose number of connected first nodes is the preset third threshold.

[0099] Specifically, in this technical solution, the third threshold is 1. Figure 3 , the first node connected to the second node I is only node E; the first node connected to the second node K is only node D. Therefore, node I and node K are determined to be the third node.

[0100] Connect the third node to obtain several disturbance areas.

[0101] In the above steps, the server connects the third node to obtain several disturbance areas.

[0102] Specifically, in this technical solution, connecting nodes I and K can obtain a closed region IKDE, and thus a disturbed region IKDE. Therefore, in the example of this technical solution, there are three disturbed regions, namely region AFH, region BCJ, and region IKDE.

[0103] determining, based on a preset third method, whether the disturbance area is an activity area of ​​the organism corresponding to the first subtag;

[0104] In the above steps, the server determines whether the disturbance area is the activity area of ​​the organism corresponding to the first sub-tag based on a preset third method.

[0105] In a possible implementation, the step of determining whether the disturbance area is the activity area of ​​the organism corresponding to the first subtag based on a preset third method specifically includes the following steps:

[0106] Based on the second target image and the third target image in the disturbance area, a second sub-tag is extracted; the occurrence frequency of the second sub-tag is determined; when the occurrence frequency is greater than a preset second threshold, the disturbance area is determined to be the activity area of ​​the organism corresponding to the first sub-tag.

[0107] Specifically, in this technical solution, the server extracts a second sub-label based on the second and third target images of the disturbed areas AFH, BCJ, and IKDE. The second sub-label indicates relatively clear biological activity traces. The preset second threshold is 0. If relatively clear biological activity traces appear in a disturbed area, the disturbed area can be determined to be the biological activity area corresponding to the first sub-label.

[0108] If not, the second area range is re-determined; the second area range is the precise activity area of ​​the organisms corresponding to the first sub-tags.

[0109] In the above steps, when the server determines that the disturbance area is not the activity area of ​​the organism corresponding to the first subtag, it re-determines the precise activity areas of the organisms corresponding to the first subtags.

[0110] Specifically, in this technical solution, if the server determines that the disturbed area is not the activity area of ​​the organism corresponding to the first subtag, it removes the disturbed area from the original first area range and determines a new second area range. For example, if the disturbed area AHF is not the activity area of ​​military personnel, the second area range is the remaining area after removing area AHF from areas ABCDEF.

[0111] It should be noted that when the server determines that the disturbed area is the activity area of ​​the organism corresponding to the first sub-tag, the disturbed area is retained.

[0112] Reference Figure 4 , which shows a schematic structural diagram of an infrared super-phase biological detection system based on computer vision provided by an embodiment of the present application. The system includes: an image processing module 1, a judgment module 2, and a region division module 3; the image processing module 1 is used to obtain a super-phase image of a preset area based on image data collected by an acquisition device in the preset area; the image processing module 1 is also used to extract target images within a preset range from the super-phase image of the preset area; the target images within the preset range include a first target image, a second target image, and a third target image; the image processing module 1 is also used to obtain a first label of several organisms based on the first target image; and obtain a second label of several organisms based on the second target image and the third target image; the judgment module 2 is used to determine whether the second label corresponds to the first label of several organisms; the region division module 3 is used to determine that the preset area is the activity area of ​​the organisms corresponding to the label when the second label corresponds to the first label of several organisms.

[0113] This application also discloses an electronic device. Figure 5 , Figure 5 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. 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.

[0114] The communication bus 502 is used to implement the connection and communication between these components.

[0115] 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.

[0116] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0117] The processor 501 may include one or more processing cores. Using various interfaces and circuits, the processor 501 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in the memory 505, as well as accesses data stored in the memory 505, to perform various server functions and process data. Optionally, the processor 501 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 501 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented as a separate chip, rather than integrated into the processor 501.

[0118] 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 may store 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.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. Reference Figure 5 , the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program.

[0119] 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 the data input by the user; and the processor 501 can be used to call an application stored in the memory 505. When executed by one or more processors 501, the electronic device 500 executes one or more methods in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the described order of actions, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0120] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, 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 interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0122] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0123] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0124] If the integrated unit is implemented as 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 this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0125] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0126] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A computer vision-based infrared super-temporal biological detection method, characterized in that: The method comprises: Obtaining a super-phase image of the preset area based on image data collected by an acquisition device in the preset area; Extracting target images within a preset range from the super-temporal image of the preset area; the target images within the preset range include a first target image, a second target image, and a third target image; Obtaining first labels of a plurality of organisms based on the first target image; obtaining second labels of a plurality of organisms based on the second target image and the third target image; determining whether the second tag corresponds to the first tags of the plurality of organisms; If so, the preset area is determined to be the activity area of ​​the organism corresponding to the label; after the preset area is determined to be the activity area of ​​the organism corresponding to the label, the method further includes: extracting a plurality of first sub-labels based on the first target image and the first label; obtaining the corresponding first target image according to the plurality of first sub-labels, and determining a first time-lapse image; determining the set position of the first acquisition device corresponding to the first time-lapse image; constructing a position relationship diagram of the first acquisition device based on the set position of the first acquisition device; wherein, each of the first acquisition devices corresponds to each node in the position relationship diagram of the first acquisition device, and the arrangement relationship between each of the first acquisition devices corresponds to the connection relationship between each of the nodes; determining the first area range based on the position relationship diagram of the first acquisition device; the first area range is the activity area of ​​the organism corresponding to the plurality of first sub-labels; after the first area range is determined, the method The method also includes: obtaining the number of occurrences of the first subtag within a preset time period within the first area; when the number of occurrences of the first subtag is less than a preset first threshold, determining the disturbance area in the first area based on a preset first method; the method for determining the disturbance area in the first area based on the preset first method specifically includes: determining a first node; the first node is a plurality of boundary nodes in a position relationship diagram of the first acquisition device; determining a second node; the second node is a node with the shortest connection line path to the first node in the position relationship diagram of the first acquisition device; constructing a plurality of disturbance areas based on the first node and the second node, and judging whether the disturbance area is the activity area of ​​the organism corresponding to the first subtag based on a preset third method; if not, re-determining the second area; the second area is the precise activity area of ​​the organisms corresponding to the plurality of first subtags.

2. The infrared super-phase biological detection method based on computer vision according to claim 1 is characterized in that: The method for determining whether the disturbance area is an activity area of ​​the organism corresponding to the first subtag based on the preset third method specifically includes: extracting a second sub-label based on the second target image and the third target image within the disturbance area; and determining an occurrence frequency of the second sub-label; When the occurrence frequency is greater than a preset second threshold, the disturbance area is determined to be an activity area of ​​the organism corresponding to the first sub-tag.

3. The infrared super-phase biological detection method based on computer vision according to claim 1 is characterized in that: The step of constructing a plurality of disturbance regions based on the first node and the second node specifically includes: Connecting each of the first nodes to its corresponding second node to obtain a plurality of disturbance regions; Determine a third node; the third node being a second node connected to which the number of the first nodes is a preset third threshold; The third nodes are connected to obtain a plurality of disturbance regions.

4. The infrared super-phase biological detection method based on computer vision according to claim 1 is characterized in that: After determining whether the second tag corresponds to the first tags of the plurality of organisms, the method further includes: If not, the activity area of ​​the organism corresponding to the second tag is determined based on a preset second method.

5. An infrared super-temporal biological detection system based on computer vision, characterized in that: The system comprises: an image processing module (1), a judgment module (2) and a region division module (3); The image processing module (1) is used to obtain a super-phase image of a preset area based on image data collected by an acquisition device in the preset area; The image processing module (1) is further used to extract target images within a preset range from the super-temporal image of the preset area; the target images within the preset range include a first target image, a second target image, and a third target image; The image processing module (1) is further configured to obtain first labels of a plurality of organisms based on the first target image; obtain second labels of a plurality of organisms based on the second target image and the third target image; and the judgment module (2) is configured to judge whether the second labels correspond to the first labels of the plurality of organisms; The area division module (3) is used to determine that the preset area is the activity area of ​​the organism corresponding to the label when the second label corresponds to the first label of the plurality of organisms; after determining that the preset area is the activity area of ​​the organism corresponding to the label, it also includes: extracting a plurality of first sub-labels based on the first target image and the first label; obtaining the corresponding first target image according to the plurality of first sub-labels, and determining a first super-phase image; determining the set position of the first acquisition device corresponding to the first super-phase image; constructing a position relationship diagram of the first acquisition device based on the set position of the first acquisition device; wherein each of the first acquisition devices corresponds to each node in the position relationship diagram of the first acquisition device, and the arrangement relationship between each of the first acquisition devices corresponds to the connection relationship between each of the nodes; determining the first area range based on the position relationship diagram of the first acquisition device; the first area range is the activity area of ​​the plurality of organisms corresponding to the first sub-labels area; after determining the scope of the first area, it also includes: obtaining the number of occurrences of the first sub-tag within a preset time period within the scope of the first area; when the number of occurrences of the first sub-tag is less than a preset first threshold, determining the disturbance area in the scope of the first area based on a preset first method; determining the disturbance area in the scope of the first area based on the preset first method specifically includes: determining a first node; the first node is a number of boundary nodes in the position relationship diagram of the first acquisition device; determining a second node; the second node is a node with the shortest connection line path with the first node in the position relationship diagram of the first acquisition device; based on the first node and the second node, constructing a number of disturbance areas, and judging whether the disturbance area is the activity area of ​​the organism corresponding to the first sub-tag based on a preset third method; if not, re-determining the scope of the second area; the scope of the second area is the precise activity area of ​​the organisms corresponding to the several first sub-tags.

6. An electronic device, characterized in that: The electronic device (500) comprises a processor (501), a memory (505), a user interface (503) and a network interface (504), wherein the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to communicate with other devices, and the processor (501) is used to execute the instructions stored in the memory (505) so that the electronic device (500) executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method steps according to any one of claims 1 to 4 are performed.

Images