Method and device for monitoring epidemic diseases in public places and electronic equipment

Abstract

The invention provides a public place epidemic disease monitoring method and device and electronic equipment. The method comprises the following steps: acquiring video data acquired by different cameras respectively, and extracting a key frame sequence from the video data; for each key frame sequence, performing individual detection and feature extraction on the key frame sequence, and performing individual association and tracking based on extracted individual features to obtain first trajectory data of an individual; fusing the first trajectory data of the same individual among the key frame sequences to obtain second trajectory data of the individual; and determining contact information between different individuals according to the second trajectory data of the individuals. Therefore, according to the scheme, efficient and automatic contact individual identification is realized, all individuals in a public place can be comprehensively covered, the accuracy and reliability of contact individual identification are remarkably improved, high-risk identification is carried out based on the contact information, and the accuracy of disease screening is improved.

Description

Technical Field

[0001] The present application relates to the technical field of public health and epidemiology, and in particular to a method, device and electronic equipment for monitoring epidemic diseases in public places. Background Art

[0002] Supermarkets, shopping malls and other public places have large flow of people, complex personnel composition and frequent contact, becoming key nodes for disease transmission. In the process of disease transmission and prevention and control management, it is crucial to quickly and accurately track and trace the source of the disease and conduct close contact screening in public places, which can effectively curb the spread of the virus.

[0003] In the existing close contact screening scheme, all visitors to places visited by confirmed patients are considered close contacts. Not only is the screening task arduous and difficult to quickly and accurately identify individuals with a high risk of transmission, but it also ignores the impact of contact frequency and duration in public places on the risk of infection, resulting in a large number of low-frequency, short-term non-continuous contacts and visitors who may not have infection risks being considered close contacts for prevention and control management, which not only increases the pressure of prevention and control, but also affects the normal activities of personnel and the operation of the social economy. In addition, the existing technology mainly relies on manual passive screening, lacks intelligent active identification, screening, and early warning methods for high-frequency short-term contacts in public places, resulting in low screening efficiency, time lag, and inability to dynamically adjust prevention and control strategies. Summary of the invention

[0004] The purpose of this application is to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of the present application is to propose a method for monitoring epidemic diseases in public places to achieve efficient and automated contact individual identification and improve the accuracy and reliability of contact individual identification.

[0006] The second objective of the present application is to provide a monitoring device for epidemic diseases in public places.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first aspect of the present application proposes a method for monitoring epidemic diseases in public places, including: obtaining video data collected by different cameras, and extracting key frame sequences from the video data; for each key frame sequence, performing individual detection and feature extraction on the key frame sequence, and performing individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual; fusing the first trajectory data of the same individual between the key frame sequences to obtain second trajectory data of the individual; and determining contact information between different individuals based on the second trajectory data of the individual.

[0011] To achieve the above-mentioned purpose, the second aspect of the present application proposes a monitoring device for epidemic diseases in public places, including: an extraction module, used to obtain video data collected by different cameras and extract key frame sequences from the video data; a generation module, used to perform individual detection and feature extraction on each key frame sequence, and associate and track individuals based on the extracted individual features to obtain first trajectory data of the individual; a fusion module, used to fuse the first trajectory data of the same individual between the key frame sequences to obtain second trajectory data of the individual; a determination module, used to determine contact information between different individuals based on the second trajectory data of the individual.

[0012] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor; and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor can execute the method for monitoring epidemic diseases in public places described in the first aspect embodiment above.

[0013] To achieve the above objectives, the fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer instructions are used to enable the computer to execute the method for monitoring epidemic diseases in public places described in the first aspect of the present application.

[0014] To achieve the above objectives, a fifth embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the method for monitoring epidemic diseases in public places described in the first embodiment above.

[0015] The method, device and electronic device for monitoring epidemic diseases in public places provided by the present application obtain key frame sequences from video data collected by a camera, and extract individual features from the key frame sequences to obtain the first trajectory data of the individual based on the individual features. Furthermore, the first trajectory data of the same individual in different key frame sequences are fused to obtain the second trajectory data of the individual, so as to determine the contact information between different individuals based on the second trajectory data. Individuals are automatically identified based on the collected video data, and efficient and automated contact individual identification is achieved. It can comprehensively cover all individuals in public places, significantly improve the accuracy and reliability of contact individual identification, perform high-risk identification based on contact information, and improve the accuracy of disease screening.

[0016] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0018] Figure 1 A flow chart of a method for monitoring epidemic diseases in public places provided in an embodiment of the present application;

[0019] Figure 2 A schematic flow chart of another method for monitoring epidemic diseases in public places provided in an embodiment of the present application;

[0020] Figure 3 A schematic flow chart of another method for monitoring epidemic diseases in public places provided in an embodiment of the present application;

[0021] Figure 4 A schematic flow chart of another method for monitoring epidemic diseases in public places provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the structure of a monitoring device for epidemic diseases in public places provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0024] The following describes the method and device for monitoring epidemic diseases in public places according to the embodiments of the present application with reference to the accompanying drawings.

[0025] Figure 1 is a flow chart of a method for monitoring epidemic diseases in public places provided in an embodiment of the present application, such as Figure 1 As shown, the method for monitoring epidemic diseases in public places of the embodiment of the present application includes but is not limited to the following steps:

[0026] S101, obtaining video data collected by different cameras respectively, and extracting key frame sequences from the video data.

[0027] It should be noted that the execution subject of the method for monitoring epidemic diseases in public places provided in the embodiment of the present application is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a personal computer (PC), a television, etc. The embodiment of the present application is not specifically limited.

[0028] In some implementations, video data collected in real time by multiple different cameras in a public place may be obtained, and key frames may be extracted from the video data according to a time interval for extracting key frames, and then a key frame sequence may be generated based on the extracted key frames.

[0029] In some implementations, in order to improve image quality and facilitate accurate identification of individuals from a key frame sequence, image enhancement processing may be performed on the extracted key frames before generating the key frame sequence, so as to generate a key frame sequence based on the enhanced key frames.

[0030] Optionally, the key frame quality can be improved by performing brightness adjustment, contrast enhancement, noise removal, etc. on the key frame. For example, the brightness and contrast of each key frame can be enhanced by adaptive histogram equalization to adapt the key frame to different lighting conditions. Gaussian filtering can be used to remove high-frequency noise in the key frame.

[0031] S102 , for each key frame sequence, performing individual detection and feature extraction on the key frame sequence, and performing individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual.

[0032] In some implementations, a deep learning algorithm can be used to detect individual features of each key frame in a key frame sequence, and then similarity calculations are performed in adjacent key frames based on the individual features to achieve individual association and tracking.

[0033] Optionally, the key frames in the key frame sequence can be used as input parameters and input into the deep learning algorithm to perform individual detection and feature extraction on the individuals. During the individual detection and feature extraction process, a confidence threshold can be set to filter valid detection results, for example, the threshold is set to 0.5. An intersection over union (IOU) threshold can be set to suppress duplicate detection boxes, for example, the threshold is set to 0.5. It is also possible to retain only the categories of interest (such as "person") and filter out other irrelevant categories according to the needs of the detection scenario.

[0034] In some implementations, individual features can be associated and tracked based on the identification information of the individual. For example, an identifier can be assigned to the individual in the first key frame in the key frame sequence, and the similarity between the individual features in the first key frame and the second key frame is calculated. If the similarity is greater than a similarity threshold, it is determined that the individuals in the first key frame and the second key frame are the same individual, and the same identifier is assigned to the individual in the second key frame. Otherwise, a new identifier is assigned until all key frames in the key frame sequence have been assigned.

[0035] Furthermore, the trajectory data of the individual identifiers can be generated according to the timestamps of the key frames as the first trajectory data of the individual, wherein the first trajectory data includes the position changes of each individual identifier at different times.

[0036] S103, fusing the first trajectory data of the same individual between the key frame sequences to obtain the second trajectory data of the individual.

[0037] In some implementations, since individuals may move to different locations in a public place, individuals identified by different cameras may belong to the same individual. The first trajectory data of the same individual in different key frame sequences may be fused to obtain the second trajectory data of the individual.

[0038] In some implementations, the similarity between the individuals in each key frame sequence can be calculated to determine whether the two individuals are the same individual. Optionally, if the similarity is greater than a set threshold, it is determined that the two individuals are the same individual, and the first trajectory data of the two individuals are fused to obtain the second trajectory data of the individual.

[0039] Optionally, the fused trajectory data may be deduplicated by timestamps, and the final second trajectory data of the individual may be obtained by removing trajectory point data with duplicate timestamps.

[0040] S104: Determine contact information between different individuals based on the second trajectory data of the individuals.

[0041] It is understandable that the contact information between different individuals can be a contact event between individuals, and a contact event is considered to be a continuous period of time in which the distance between individuals is always within a certain distance range. By setting the parameters of the contact event, including the minimum contact time threshold (such as 30 consecutive seconds) and the maximum spatial distance threshold (such as no more than 80 cm), it is determined that there is a contact event between individuals.

[0042] In some implementations, the distance between individuals can be calculated based on the second trajectory data of different individuals, and when the distance is less than or equal to the maximum spatial distance threshold, the contact time between the individuals is determined; if the contact time is greater than the minimum contact time threshold, it is determined that there is a contact event between the individuals, and then the individual identifier of the contact event is determined, and the number of contacts is counted as contact information between different individuals.

[0043] In some implementations, the spatial coordinates of the individuals can be obtained from the second trajectory data, and the distances between the individuals can be calculated based on the spatial coordinates of the different individuals. Alternatively, the spatial coordinates of the individuals can be obtained by converting the image coordinates in the second trajectory data into a world coordinate system.

[0044] In some implementations, after obtaining contact information between different individuals, dynamic risk assessment and classification of the contacted individuals can be performed based on the contact information. For example, a threshold for high-frequency contact (such as 3 times) can be set based on the characteristics of disease virus transmission and human virus infection. That is to say, in public places, the risk of disease transmission and infection is low for individual contacts below the threshold, and the risk of disease transmission and infection is high for individual contacts above the threshold.

[0045] Optionally, when it is determined that there is individual contact above the frequency threshold, a high-risk personnel warning can be issued in a timely manner, and appropriate prevention and control measures can be recommended, which will help to block the disease transmission chain in a timely manner and reduce the risk of disease transmission in public places.

[0046] In the method for monitoring epidemic diseases in public places provided in an embodiment of the present application, a key frame sequence is obtained from the video data collected by the camera, and individual features are extracted from the key frame sequence to obtain the first trajectory data of the individual based on the individual features. Furthermore, the first trajectory data of the same individual in different key frame sequences are fused to obtain the second trajectory data of the individual, so as to determine the contact information between different individuals based on the second trajectory data. Individuals are automatically identified based on the collected video data, and efficient and automated contact individual identification is achieved. All individuals in public places can be comprehensively covered, which significantly improves the accuracy and reliability of contact individual identification, and high-risk identification is performed based on contact information, thereby improving the accuracy of disease screening.

[0047] Figure 2 is a flow chart of a method for monitoring epidemic diseases in public places provided in an embodiment of the present application, such as Figure 2 As shown, the method for monitoring epidemic diseases in public places of the embodiment of the present application includes but is not limited to the following steps:

[0048] S201, obtaining video data collected by different cameras respectively, and extracting key frame sequences from the video data.

[0049] In some implementations, key frames may be extracted from the video data according to a set time interval and number of frames. Optionally, key frames may also be extracted based on the video frame rate of the video data in combination with the set time interval and number of frames. The extraction formula is as follows:

[0050] frame n =n×(FPS×T)(1)

[0051] Among them, frame n represents key frame, T represents time interval, n represents number of frames, and FPS represents video frame rate.

[0052] For example, if the FPS of the video data is 30, T is 1 second, the extracted image frame numbers are 30, 60, 90, 120, . . .

[0053] For example, if there are two cameras, and the video data collected by each camera are Video1 and Video2 respectively, then based on the above formula (1), the key frame sequence composed of the key frames extracted from Video1 is L1=[frame 1-1 ,frame 1-2 ,frame 1-3 ,...], then the timestamp corresponding to the key frame sequence L1 is T1 = [Timestamp 1-1 ,Timestamp 1-2 ,Timestamp 1-3,...), the key frame sequence composed of the key frames extracted from Video2 is L2=[frame 2-1 ,frame 2-2 ,frame 2-3 ,...], then the timestamp corresponding to the key frame sequence L2 is T2 = [Timestamp 2-1 ,Timestamp 2-2 ,Timestamp 2-3 ,...).

[0054] In some implementations, in order to calibrate the time difference between different video data, a benchmark camera and remaining cameras can be determined from different cameras, and the time difference between the remaining cameras and the benchmark camera can be obtained, so as to perform time calibration on the key frame sequences corresponding to the remaining cameras based on the time difference to obtain the key frame sequences of the remaining cameras.

[0055] Optionally, the time difference between the remaining cameras and the reference camera can be calculated based on the timestamp of the key frame sequence, and the timestamp of the key frame sequence can be adjusted according to the time difference to achieve time calibration of the key frame sequences corresponding to the remaining cameras based on the time difference, thereby obtaining the key frame sequences of the remaining cameras.

[0056] For example, the camera corresponding to the key frame sequence L1 can be determined as the reference camera, and then the time difference between the key frame sequence L1 and the key frame sequence L2 can be calculated to adjust the timestamp of the key frame sequence L2. The calibrated timestamp is: T′2=[Timestamp 2-1 -Δt,Timestamp 2-2 -Δt,Timestamp 2-3 -Δt,...).

[0057] In some implementations, the extracted key frames may be subjected to image enhancement processing, and a key frame sequence may be obtained based on the enhanced key frames. Optionally, the image quality may be improved by enhancement methods such as brightness adjustment, contrast enhancement, and noise removal.

[0058] Optionally, each key frame may be enhanced in brightness and contrast by adaptive histogram equalization to adapt to different lighting conditions. For example, enhancement may be performed based on a cumulative distribution function (CDF). The key frame may be enhanced by enhancing each pixel in the key frame. The formula for calculating the enhanced pixel value is as follows:

[0059]

[0060] Among them, I'(x,y) represents the enhanced pixel value, CDF(I(x,y)) represents the cumulative distribution function of the original pixel point, and CDFmin Represents the non-zero minimum value in the cumulative distribution function of all pixels, M×N is the total number of pixels, and L is the grayscale level (usually 256).

[0061] Optionally, Gaussian filtering can be used to remove high-frequency noise in keyframes, with the following formula:

[0062]

[0063] Among them, I'(x,y) represents the pixel value at the position (x,y) after processing, G(i,j) represents the value of the Gaussian kernel at the position (i,j), I(x+i,y+j) represents the pixel value of the original image at the position (x+i,y+j), k is the radius of the kernel, and k=2 can be taken.

[0064] Optionally, the formula for calculating the value G(i,j) of the Gaussian kernel at position (i,j) is as follows:

[0065]

[0066] Here, σ represents the standard deviation, which is used for the width of the Gaussian distribution, and σ=1.0.

[0067] S202: for each key frame sequence, perform individual detection and feature extraction on the key frame sequence to obtain individual features.

[0068] In the embodiment of the present application, the implementation method of step S202 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0069] S203, starting from the first key frame, obtaining the similarity between the first individual in key frame i-1 and the second individual in key frame i according to individual characteristics, where i is an integer greater than or equal to 1.

[0070] In some implementations, the individual features of the first individual in key frame i-1 are obtained as the first feature vector, and the individual features of the second individual in key frame i are obtained as the second feature vector, and then the similarity between the first feature vector and the second feature vector is calculated as the similarity between the first individual in key frame i-1 and the second individual in key frame i.

[0071] Optionally, the formula for calculating similarity is as follows:

[0072]

[0073] Among them, A and B are the eigenvectors of individuals respectively.

[0074] That is, by substituting the first eigenvector and the second eigenvector into the above formula (5), the similarity between the first individual in key frame i-1 and the second individual in key frame i can be calculated.

[0075] S204: In response to the similarity between the first individual and the second individual being greater than or equal to a first set similarity threshold, the first individual and the second individual are associated as the same individual, and inherit the individual identification ID of the first individual in key frame i-1.

[0076] In some implementations, by setting a similarity threshold and determining whether the first individual and the second individual are the same individual, it can be determined whether the first individual and the second individual are the same individual. Optionally, if the similarity between the first individual and the second individual is greater than or equal to the first similarity threshold, the first individual and the second individual are associated as the same individual.

[0077] Exemplarily, the first similarity threshold is set to Threshold_C, and Threshold_C=0.8. When the Cosine Similarity of the feature vectors of the first individual and the second individual>Threshold_C, it is determined that the first individual and the second individual belong to the same individual.

[0078] In some implementations, if key frame i-1 is the first key frame, an identity document (ID) can be assigned to the individual detected in the first key frame, and when it is determined that the first individual in key frame i-1 and the second individual in key frame i are the same individual, the individual identification ID of the first individual in key frame i-1 can be inherited.

[0079] Optionally, when it is determined that the first individual in key frame i-1 and the second individual in key frame i are not the same individual, a new individual ID may be assigned to the second individual. That is, in response to the similarity between the second individual and each of the previous individuals being less than a first set similarity threshold, the second individual is determined to be a new individual, and a new individual ID is assigned to the second individual.

[0080] S205, after the individual association is completed, the key frame associated with each individual is obtained.

[0081] S206, determining the timestamp of the key frame and the position of the individual in the key frame, and generating first trajectory data of the individual according to the timestamp of the key frame and the position of the individual in the key frame.

[0082] In some implementations, after associating the individuals in each key frame in the key frame sequence, the first trajectory sequence of the individuals can be generated based on the timestamp of the key frame sequence. Optionally, by obtaining the key frame associated with each individual, and determining the timestamp corresponding to the key frame according to the key frame sequence in which the key frame is located, and further determining the position of the individual in the key frame, the first trajectory data is generated according to the timestamp and position. The position of the individual in the first trajectory data changes at different times.

[0083] S207, fusing the first trajectory data of the same individual between the key frame sequences to obtain the second trajectory data of the individual.

[0084] In the embodiment of the present application, the implementation method of step S207 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0085] S208: Determine contact information between different individuals based on the second trajectory data of the individuals.

[0086] In the embodiment of the present application, the implementation method of step S208 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0087] In the method for monitoring epidemic diseases in public places provided in an embodiment of the present application, a key frame sequence is obtained from the video data collected by the camera, and individual features are extracted from the key frame sequence to determine whether the individuals in adjacent key frames are the same based on the individual features, and the same ID is assigned to the individual in the same case. Further, the first trajectory data of the individual is generated according to the position and timestamp of the individual in the key frame. Further, the first trajectory data of the individual in different key frame sequences are fused to obtain the second trajectory data of the individual, so as to determine the contact information between different individuals based on the second trajectory data. Individuals are automatically identified based on the collected video data, and efficient and automated contact individual identification is realized, which can comprehensively cover all individuals in public places, significantly improve the accuracy and reliability of contact individual identification, and perform high-risk identification based on contact information, thereby improving the accuracy of disease screening.

[0088] Figure 3 is a flow chart of a method for monitoring epidemic diseases in public places provided in an embodiment of the present application, such as Figure 3 As shown, the method for monitoring epidemic diseases in public places of the embodiment of the present application includes but is not limited to the following steps:

[0089] S301, obtaining video data collected by different cameras respectively, and extracting key frame sequences from the video data.

[0090] In the embodiment of the present application, the implementation method of step S301 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0091] S302 : For each key frame sequence, perform individual detection and feature extraction on the key frame sequence, and perform individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual.

[0092] In the embodiment of the present application, the implementation method of step S302 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0093] S303: For any first key frame sequence and any second key frame sequence in the key frame sequence, obtain the similarity between the individual x in the first key frame sequence and the individual y in the second key frame sequence.

[0094] In some implementations, since individuals may move to different locations in a public place, individuals identified by different cameras may belong to the same individual. Optionally, the similarity between individual x in the first key frame sequence and individual y in the second key frame sequence may be calculated to determine whether individual x and individual y are the same individual.

[0095] Optionally, the above formula (5) can be used to calculate the similarity between individual x and individual y. The similarity between individual x and individual y can be calculated by extracting the feature vector of any key frame in the first trajectory data corresponding to individual x and extracting the feature vector of any key frame in the first trajectory data corresponding to individual y, and then substituting them into formula (5).

[0096] S304: In response to the similarity being greater than the second set similarity threshold, determining that individual x and individual y are the same individual, and merging the first trajectory data of individual x and the first trajectory data of individual y to obtain third trajectory data of the same individual.

[0097] In some implementations, it may be determined whether individual x and individual y are the same individual based on a set similarity threshold. If the similarity is greater than a second set similarity threshold, it is determined that individual x and individual y are the same individual, and the first trajectory data of individual x and the first trajectory data of individual y may be merged to obtain third trajectory data, otherwise it is determined that individual x and individual y are not the same individual.

[0098] In some implementations, the individual trajectories are merged by determining whether all individuals identified in the first key frame sequence and the second key frame sequence are the same individual. By fusing the detection results of different cameras, the complete trajectory data of any individual can be determined.

[0099] S305 , performing trajectory deduplication on the third trajectory data of the same individual to obtain the second trajectory data of the same individual.

[0100] In some implementations, since different cameras have overlapping coverage areas, it is necessary to deduplicate the third trajectory data of an individual, and finally obtain the second trajectory data of the individual. It is possible to determine whether the third trajectory data is repeated based on the timestamp, and obtain the second trajectory data by identifying the repeated timestamps of the third trajectory data and deduplicating the trajectory points with the repeated timestamps.

[0101] S306: Determine contact information between different individuals based on the second trajectory data of the individuals.

[0102] In the embodiment of the present application, the implementation method of step S306 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0103] In the method for monitoring epidemic diseases in public places provided in the embodiment of the present application, a key frame sequence is obtained from the video data collected by the camera, and individual features are extracted from the key frame sequence to obtain the first trajectory data of the individual based on the individual features. Furthermore, the first trajectory data of the same individual in different key frame sequences are fused to obtain the third trajectory data, and the third trajectory data is deduplicated to obtain the second trajectory data of the individual, so as to determine the contact information between different individuals based on the second trajectory data. Individuals are automatically identified based on the collected video data, and efficient and automated contact individual identification is achieved, which can comprehensively cover all individuals in public places, significantly improve the accuracy and reliability of contact individual identification, and perform high-risk identification based on contact information, thereby improving the accuracy of disease screening.

[0104] Figure 4 is a flow chart of a method for monitoring epidemic diseases in public places provided in an embodiment of the present application, such as Figure 4 As shown, the method for monitoring epidemic diseases in public places of the embodiment of the present application includes but is not limited to the following steps:

[0105] S401, obtaining video data collected by different cameras respectively, and extracting key frame sequences from the video data.

[0106] In the embodiment of the present application, the implementation method of step S401 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0107] S402 : For each key frame sequence, perform individual detection and feature extraction on the key frame sequence, and perform individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual.

[0108] In the embodiment of the present application, the implementation method of step S402 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0109] S403, fusing the first trajectory data of the same individual between the key frame sequences to obtain the second trajectory data of the individual.

[0110] In the embodiment of the present application, the implementation method of step S403 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0111] S404, acquiring the spatial coordinates of the individual according to the second trajectory data of the individual.

[0112] In some implementations, the depth information of the individual in the physical environment may be determined based on the height information of the individual, so as to convert the coordinates in the image coordinate system to the world coordinate system according to the depth information, thereby obtaining the spatial coordinates of the individual.

[0113] Optionally, the height of the person in the image can be determined based on the second trajectory data of the person, and the depth information of the person can be determined based on the height of the person in the image and the focal length of the camera. The formula for calculating the depth information is as follows:

[0114]

[0115] Among them, Z represents the depth information, h img Indicates the height in the image, H real represents the true average height, f x Indicates the horizontal focal length of the camera.

[0116] Furthermore, the first coordinates of the human body in the image coordinate system can be determined according to the second trajectory data of the individual, and the second coordinates of the individual in the world coordinate system can be determined according to the first coordinates of the human body, the focal length of the camera and the optical center coordinates of the image.

[0117]

[0118] Among them, (X real ,Y real ) represents the second coordinate, (x img ,y img ) represents the first coordinate, f x With f y represents the focal length in the horizontal and vertical directions, c x With c y represents the optical center coordinates of the image, and Z represents the depth information.

[0119] Furthermore, the spatial coordinates of the individual can be determined based on the second coordinates of the individual in the world coordinates and the depth information. That is, the second coordinates can be used as the X value and Y value of the spatial coordinates, and the depth information can be used as the Z value of the spatial coordinates.

[0120] S405, for any target individual among the different individuals, determine the spatial distance between the target individual and the remaining individuals at different time points according to the spatial coordinates of the target individual and the spatial coordinates of the remaining individuals among the different individuals.

[0121] Optionally, the formula for calculating the spatial distance between the target individual and the remaining individuals at different time points is as follows:

[0122]

[0123] Among them, d represents the spatial distance, (X1, Y1, Z1) represents the spatial coordinates of the target individual, and (X2, Y2, Z2) represents the spatial coordinates of the remaining individuals.

[0124] S406, determining contact information between the target individual and the remaining individuals according to the spatial distances between the target individual and the remaining individuals at different time points.

[0125] In some implementations, the potential contact individuals may be first determined based on the spatial distances between the target individual and the remaining individuals at different time points, and then the contact information between the target individual and the remaining individuals may be further determined based on the potential contact time points corresponding to the potential contact individuals.

[0126] That is, by identifying potential contact time points whose spatial distance is less than or equal to the maximum spatial distance threshold from the spatial distances at different time points. Further, continuous time points are determined from the potential contact time points, and the duration of the continuous time points is counted. The duration can be determined by accumulating the continuous time points.

[0127] Optionally, it can be determined whether the target individual is in contact with the remaining individuals based on the duration and the minimum contact time threshold. In response to the duration being greater than or equal to the minimum contact time threshold, it is determined that the target individual is in contact with the remaining individuals once.

[0128] Furthermore, by counting the number of contacts between the target individual and the remaining individuals, and associating the individual ID of the target individual with the individual IDs of the remaining individuals, the contact information between the target individual and the remaining individuals is obtained.

[0129] In the method for monitoring epidemic diseases in public places provided in the embodiment of the present application, a key frame sequence is obtained from the video data collected by the camera, and individual features are extracted from the key frame sequence to obtain the first trajectory data of the individual according to the individual features. Furthermore, the first trajectory data of the same individual in different key frame sequences are fused to obtain the second trajectory data of the individual, so as to determine the spatial distance between the target individual and the remaining individuals according to the second trajectory data, and determine the potential contact time point according to the spatial distance, and then determine the duration according to the potential contact time point, and count the number of contacts according to the duration to determine the contact information. Automatically identify individuals based on the collected video data, realize efficient and automated contact individual identification, can comprehensively cover all individuals in public places, significantly improve the accuracy and reliability of contact individual identification, perform high-risk identification based on contact information, and improve the accuracy of disease screening.

[0130] Corresponding to the methods for monitoring epidemic diseases in public places proposed in the above-mentioned embodiments, an embodiment of the present application further proposes a device for monitoring epidemic diseases in public places. Since the device for monitoring epidemic diseases in public places proposed in the embodiment of the present application corresponds to the methods for monitoring epidemic diseases in public places proposed in the above-mentioned embodiments, the implementation methods of the above-mentioned methods for monitoring epidemic diseases in public places are also applicable to the device for monitoring epidemic diseases in public places proposed in the embodiments of the present application, and will not be described in detail in the following embodiments.

[0131] In order to implement the above embodiment, the present application also proposes a monitoring device for epidemic diseases in public places.

[0132] Figure 5 A schematic diagram of the structure of a monitoring device for epidemic diseases in public places provided in an embodiment of the present application.

[0133] like Figure 5 As shown, the monitoring device 500 for epidemic diseases in public places includes:

[0134] An extraction module 501 is used to obtain video data collected by different cameras and extract key frame sequences from the video data;

[0135] A generating module 502 is used to perform individual detection and feature extraction on each key frame sequence, and perform individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual;

[0136] A fusion module 503 is used to fuse the first trajectory data of the same individual between key frame sequences to obtain the second trajectory data of the individual;

[0137] The determination module 504 is configured to determine contact information between different individuals based on the second trajectory data of the individuals.

[0138] In a possible implementation of the embodiment of the present application, the generation module 502 is also used to: starting from the first key frame, obtain the similarity between the first individual in key frame i-1 and the second individual in key frame i based on individual characteristics, where i is an integer greater than or equal to 1; in response to the similarity between the first individual and the second individual being greater than or equal to a first set similarity threshold, associate the first individual and the second individual as the same individual, and inherit the individual identification ID of the first individual in key frame i-1.

[0139] In a possible implementation of the embodiment of the present application, the generation module 502 is further used to: in response to the similarity between the second individual and each previous individual being less than a first set similarity threshold, determine the second individual as a new individual and assign a new individual ID to the second individual.

[0140] In a possible implementation of an embodiment of the present application, the generation module 502 is further used to: obtain the key frame associated with each individual after the individual association is completed; determine the timestamp of the key frame and the position of the individual in the key frame, and generate the first trajectory data of the individual according to the timestamp of the key frame and the position of the individual in the key frame.

[0141] In a possible implementation manner of the embodiment of the present application, the fusion module 503 is further used to: for any first key frame sequence and second key frame sequence in the key frame sequence, obtain the similarity between the individual x in the first key frame sequence and the individual y in the second key frame sequence; in response to the similarity being greater than a second set similarity threshold, determine that the individual x and the individual y are the same individual, and merge the first trajectory data of the individual x and the first trajectory data of the individual y to obtain the third trajectory data of the same individual; perform trajectory deduplication on the third trajectory data of the same individual to obtain the second trajectory data of the same individual.

[0142] In a possible implementation manner of the embodiment of the present application, the fusion module 503 is further configured to: identify repeated timestamps of the third trajectory data, and perform deduplication processing on trajectory points with repeated timestamps to obtain second trajectory data.

[0143] In a possible implementation manner of an embodiment of the present application, the determination module 504 is further used to: obtain the spatial coordinates of the individual according to the second trajectory data of the individual; for any target individual among the different individuals, determine the spatial distance between the target individual and the remaining individuals at different time points according to the spatial coordinates of the target individual and the spatial coordinates of other remaining individuals among the different individuals; determine the contact information between the target individual and the remaining individuals according to the spatial distance between the target individual and the remaining individuals at different time points.

[0144] In a possible implementation of an embodiment of the present application, the determination module 504 is also used to: identify potential contact time points whose spatial distances are less than or equal to a maximum spatial distance threshold from the spatial distances at different time points; determine continuous time points from the potential contact time points, and count the duration of the continuous time points; in response to the duration being greater than or equal to the minimum contact time threshold, determine that the target individual has one contact with the remaining individuals; count the number of contacts between the target individual and the remaining individuals, and associate the individual ID of the target individual with the individual ID of the remaining individuals.

[0145] In a possible implementation of an embodiment of the present application, the determination module 504 is further used to: determine the height of the human body in the image based on the second trajectory data of the individual, and determine the depth information of the individual based on the height of the human body in the image and the focal length of the camera; determine the first coordinates of the human body in the image coordinate system based on the second trajectory data of the individual, and determine the second coordinates of the individual in the world coordinate system based on the first coordinates of the human body, the focal length of the camera and the optical center coordinates of the image; determine the spatial coordinates of the individual based on the second coordinates of the individual in the world coordinate system and the depth information.

[0146] In a possible implementation of an embodiment of the present application, the extraction module 501 is also used to: extract key frames from the video data according to a set time interval and number of frames; determine a benchmark camera and remaining cameras from different cameras, and obtain the time difference between the remaining cameras and the benchmark camera; and perform time calibration on the key frame sequences corresponding to the remaining cameras based on the time difference to obtain the key frame sequences of the remaining cameras.

[0147] In a possible implementation manner of the embodiment of the present application, the extraction module 501 is further used to: perform image enhancement processing on the extracted key frames, and obtain a key frame sequence based on the enhanced key frames.

[0148] In the monitoring device for epidemic diseases in public places provided in the embodiment of the present application, a key frame sequence is obtained from the video data collected by the camera, and individual features are extracted from the key frame sequence to obtain the first trajectory data of the individual based on the individual features. Furthermore, the first trajectory data of the same individual in different key frame sequences are fused to obtain the second trajectory data of the individual, so as to determine the contact information between different individuals based on the second trajectory data. Individuals are automatically identified based on the collected video data, and efficient and automated contact individual identification is achieved. It can comprehensively cover all individuals in public places, significantly improve the accuracy and reliability of contact individual identification, perform high-risk identification based on contact information, and improve the accuracy of disease screening.

[0149] It should be noted that the above explanations and descriptions of the embodiment of the method for monitoring epidemic diseases in public places are also applicable to the apparatus for monitoring epidemic diseases in public places of this embodiment, and will not be repeated here.

[0150] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0151] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0152] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0153] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0154] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0155] This application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, this application is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of users.

[0156] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0157] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0158] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0160] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0161] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0163] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for monitoring epidemic diseases in public places, characterized in that: The method comprises: Obtaining video data collected by different cameras, and extracting key frame sequences from the video data; For each key frame sequence, individual detection and feature extraction are performed on the key frame sequence, and individual association and tracking are performed based on the extracted individual features to obtain first trajectory data of the individual; fusing the first trajectory data of the same individual between the key frame sequences to obtain second trajectory data of the individual; Contact information between different individuals is determined according to the second trajectory data of the individuals.

2. The method according to claim 1, characterized in that The process of individual association and tracking includes: Starting from the first key frame, obtaining the similarity between the first individual in key frame i-1 and the second individual in key frame i according to the individual features, where i is an integer greater than or equal to 1; In response to the similarity between the first individual and the second individual being greater than or equal to a first set similarity threshold, the first individual and the second individual are associated as the same individual and inherit the individual identification ID of the first individual in the key frame i-1.

3. The method according to claim 2, characterized in that The method further comprises: In response to the similarity between the second individual and each previous individual being less than the first set similarity threshold, the second individual is determined as a new individual, and a new individual ID is assigned to the second individual.

4. The method according to claim 1, characterized in that: The process of acquiring the first trajectory data includes: After the individual association is completed, the key frame associated with each individual is obtained; The timestamp of the key frame and the position of the individual in the key frame are determined, and first trajectory data of the individual is generated according to the timestamp of the key frame and the position of the individual in the key frame.

5. The method according to claim 1, characterized in that The fusing the first trajectory data of the same individual between the key frame sequences to obtain the second trajectory data of the individual includes: For any first key frame sequence and any second key frame sequence in the key frame sequence, obtaining the similarity between individual x in the first key frame sequence and individual y in the second key frame sequence; In response to the similarity being greater than a second set similarity threshold, determining that the individual x and the individual y are the same individual, and merging the first trajectory data of the individual x and the first trajectory data of the individual y to obtain third trajectory data of the same individual; Deduplication is performed on the third trajectory data of the same individual to obtain second trajectory data of the same individual.

6. The method according to claim 5, characterized in that The performing track deduplication on the third track data of the same individual to obtain the second track data of the same individual includes: Repeated timestamps of the third trajectory data are identified, and the trajectory points of the repeated timestamps are deduplicated to obtain the second trajectory data.

7. The method according to any one of claims 1 to 6, characterized in that The determining, according to the second trajectory data of the individual, contact information between different individuals includes: Acquiring the spatial coordinates of the individual according to the second trajectory data of the individual; For any target individual among the different individuals, determine the spatial distance between the target individual and the remaining individuals at different time points according to the spatial coordinates of the target individual and the spatial coordinates of the remaining individuals among the different individuals; The contact information between the target individual and the remaining individuals is determined according to the spatial distance between the target individual and the remaining individuals at different time points.

8. The method according to claim 7, characterized in that The step of determining contact information between the target individual and the remaining individuals according to the spatial distances between the target individual and the remaining individuals at different time points includes: From the spatial distances at the different time points, identifying a potential contact time point where the spatial distance is less than or equal to a maximum spatial distance threshold; Determine continuous time points from the potential contact time points, and count the duration of the continuous time points; In response to the duration being greater than or equal to a minimum contact time threshold, determining that the target individual has one contact with the remaining individual; The number of contacts between the target individual and the remaining individuals is counted, and the individual ID of the target individual is associated with the individual ID of the remaining individuals.

9. The method according to claim 7, characterized in that: The acquiring the spatial coordinates of the individual according to the second trajectory data of the individual includes: Determine the height of the person in the image according to the second trajectory data of the person, and determine the depth information of the person according to the height of the person in the image and the focal length of the camera; Determine a first coordinate of the human body in the image coordinate system according to the second trajectory data of the individual, and determine a second coordinate of the individual in the world coordinate system according to the first coordinate of the human body, the focal length of the camera and the coordinate of the optical center of the image; The spatial coordinates of the individual are determined according to the second coordinates of the individual in the world coordinates and the depth information.

10. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Extracting key frames from the video data according to a set time interval and frame number; Determine a reference camera and remaining cameras from different cameras, and obtain a time difference between the remaining cameras and the reference camera; The key frame sequences corresponding to the remaining cameras are time-calibrated based on the time difference to obtain the key frame sequences of the remaining cameras.

11. The method according to claim 10, characterized in that The method further comprises: The extracted key frames are subjected to image enhancement processing, and the key frame sequence is obtained based on the enhanced key frames.

12. A monitoring device for epidemic diseases in public places, characterized in that: The device comprises: An extraction module, used to obtain video data collected by different cameras and extract key frame sequences from the video data; A generating module, configured to perform individual detection and feature extraction on each key frame sequence, and perform individual association and tracking based on the extracted individual features to obtain first trajectory data of the individual; a fusion module, configured to fuse the first trajectory data of the same individual between the key frame sequences to obtain second trajectory data of the individual; The determination module is used to determine contact information between different individuals according to the second trajectory data of the individuals.

13. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 11 when being executed by a processor.

Images