CN112307856A - Personnel state tracking method and device - Google Patents
Personnel state tracking method and device Download PDFInfo
- Publication number
- CN112307856A CN112307856A CN201910741740.3A CN201910741740A CN112307856A CN 112307856 A CN112307856 A CN 112307856A CN 201910741740 A CN201910741740 A CN 201910741740A CN 112307856 A CN112307856 A CN 112307856A
- Authority
- CN
- China
- Prior art keywords
- portrait
- file
- archive
- information
- prompt
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to a personnel state tracking method and a device, wherein the personnel state tracking method comprises an acquisition step of acquiring an image to be compared and a portrait archive, wherein the portrait archive has archive level information; a comparison step, namely obtaining a first similarity according to the characteristic value of the image to be compared and the characteristic value of the portrait file, and if the first similarity is greater than a first threshold value, executing a reminding step; and a reminding step, namely generating a prompt message, and determining the time for sending the prompt message according to the file level information of the portrait file. By the method, on one hand, timely reminding of the presence and absence state of personnel can be completed in a non-dynamic control mode, and control resources are saved; on the other hand, the prompt information can be sent according to the priority, and the prompt information can be sent in a notification mode of real-time, timing and the like according to the attention level of the important attention personnel.
Description
Technical Field
The present disclosure relates to the field of people tracking technologies, and in particular, to a method and an apparatus for tracking a person status.
Background
In order to be able to grasp the dynamic state of some key personnel, the state of the relevant personnel is often required to be tracked. At present, people's state is tracked by adopting a personnel control mode in the industry. Namely, a control library is set, the portrait shot by the camera is compared with the portrait in the control library, and when the portrait shot by the camera belongs to the portrait in the control library, the system gives an alarm. Because the tracking of the states of the personnel is realized through personnel control, on one hand, the space requirement on a control library is higher, and the space occupation cost is further increased; on the other hand, the personnel state tracking is realized by establishing a dynamic control task, when key attention personnel appear, the system can only immediately touch the network for alarming, and can not send alarm information according to the actual requirement, so that the alarm information of the key attention personnel with higher attention level is easily submerged in the alarm information of general attention personnel with lower attention level.
Disclosure of Invention
In order to overcome the problems in the prior art, the present disclosure provides a method and an apparatus for tracking a person status.
In a first aspect, an embodiment of the present disclosure provides a method for tracking a person status, including an obtaining step of obtaining an image to be compared and a portrait archive, where the portrait archive has archive level information; a comparison step, namely obtaining a first similarity according to the characteristic value of the image to be compared and the characteristic value of the portrait file, and if the first similarity is greater than a first threshold value, executing a reminding step; and a reminding step, namely generating a prompt message, and determining the time for sending the prompt message according to the file level information of the portrait file.
In one example, the comparing step further comprises: if the first similarity is larger than the first threshold value, the image to be compared is classified into the portrait archive.
In one example, before the obtaining step, the personnel state tracking method further comprises a grading step of obtaining a personnel static library, wherein the personnel static library comprises personnel images, and the personnel images have attention level information; and obtaining a second similarity according to the characteristic value of the personnel image and the characteristic value of the personnel image file, and determining the file level information of the personnel image file according to the attention level information of the personnel image if the second similarity is greater than a second threshold value.
In one example, the personnel state tracking method further comprises a file generation step, wherein a plurality of portrait pictures are obtained, and are clustered to generate a portrait file; generating a portrait archive characteristic value according to all portrait pictures in the portrait archive; or, one portrait picture in the portrait archive is taken as a main picture, and the characteristic value of the main picture is taken as the characteristic value of the portrait archive.
In one example, the step of ranking further comprises: and if the second similarity is larger than a second threshold value, taking the personnel image as a main image of the personnel file, and taking the characteristic value of the personnel image as the characteristic value of the personnel file.
In one example, the step of ranking further comprises: and if the second similarity is smaller than or equal to the second threshold, determining the file level information of the portrait file according to the user instruction.
In one example, the archive tier information includes a first tier, a second tier, or a third tier; the reminding step comprises that if the file level information of the portrait file is a first level, the prompt information is sent immediately; if the file level information of the portrait file is a second level, the prompt message is sent when the user logs in; and if the file level information of the portrait file is the third level, the prompt message is sent at a timing.
In one example, the instant sending of the prompt message is performed at the time, and if the prompt message is generated in the reminding step, the prompt message is synchronized to the message list in real time; and/or sending the prompt information when the user logs in, wherein if the prompt information is generated in the prompting step, the prompt information is pushed to a message list when the user logs in the system; and/or the timing of sending the prompt message is sending regularly, if the prompt message is generated in the prompting step, the prompt message is pushed to the message list when the preset time for sending the prompt message is reached.
In one example, the prompting step further comprises the step of determining the display sequence of the prompt information in the message list according to the file level information and/or the prompt time of the portrait file corresponding to the prompt information, wherein the prompt time is the time for generating the prompt information.
In one example, the prompt message is used to prompt the user that the person corresponding to the portrait file has a new trend; the prompt message at least comprises one of the following items: a person corresponding to the portrait file presents a new trend portrait picture, the portrait file generates prompt time of prompt information, and a portrait file aggregation list; the portrait archive aggregation list is a summary list of all the portrait archives with archive level information, in the portrait archive aggregation list, portrait pictures of people corresponding to the portrait archives, in which the new trend appears, are displayed in the portrait archives in a marked manner, and the portrait archives are displayed in the portrait archive clustering list in a marked manner.
In one example, after the user views the reminder, the reminder will no longer appear in the message list.
In one example, after the user checks the portrait picture with the new trend of the person corresponding to the portrait file, the portrait picture with the new trend of the person corresponding to the portrait file is displayed in the portrait file in an unmarked form, and the portrait file is displayed in the portrait file clustering list in an unmarked form.
In one example, the personnel state tracking method further comprises a collecting step of collecting the portrait files according to the user instruction; the comparison step also comprises the step of obtaining a third similarity according to the characteristic value of the image to be compared and the characteristic value of the collected portrait file, and if the third similarity is greater than a third threshold value, the reminding step is executed.
In a second aspect, an embodiment of the present disclosure provides a person state tracking device, which has a function of implementing the person state tracking method according to the first aspect. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.
In one example, a personnel state tracking device comprises an acquisition module, a comparison module and a comparison module, wherein the acquisition module is used for acquiring an image to be compared and a portrait archive, and the portrait archive has archive level information; the comparison module is used for obtaining a first similarity according to the characteristic value of the image to be compared and the characteristic value of the portrait file, and if the first similarity is larger than a first threshold value, reminding is executed; and the reminding module is used for executing reminding, generating reminding information and determining the time for sending the reminding information according to the file level information of the portrait file.
In a third aspect, an embodiment of the present disclosure provides an electronic device, where the electronic device includes: a memory to store instructions; and a processor for invoking the memory-stored instructions to perform the person state tracking method of the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, perform the person tracking status method of the first aspect.
The present disclosure provides a person tracking state method and apparatus, wherein the person tracking method sets a portrait archive having archive level information as a portrait archive of a person of major concern. And comparing the portrait file serving as a reference library with the image to be compared, if the similarity between the portrait file and the image to be compared exceeds a set threshold, considering the image to be compared as the image of the key attention personnel, generating prompt information according to the image to be compared, prompting the key attention personnel to update the state, and determining the time for sending the prompt information according to the difference of the file level information of the portrait file. By the method, on one hand, timely reminding of the absence state of the personnel can be completed in a non-dynamic control mode, and control resources are saved; on the other hand, the prompt information can be sent according to the priority, and the prompt information can be sent in a notification mode of real-time, timing and the like according to the attention level of the important attention personnel.
Drawings
The above and other objects, features and advantages of the embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 is a schematic diagram illustrating a method for tracking a person status according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating another method for tracking a person status provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating another method for tracking a person status provided by an embodiment of the present disclosure;
FIG. 4 is a schematic diagram illustrating another method for tracking a person status provided by an embodiment of the present disclosure;
FIG. 5 is a schematic diagram illustrating a person state tracking device provided by an embodiment of the present disclosure;
fig. 6 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.
Detailed Description
The principles and spirit of the present disclosure will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present disclosure, and are not intended to limit the scope of the present disclosure in any way.
It should be noted that, although the expressions "first", "second", etc. are used herein to describe different modules, steps, data, etc. of the embodiments of the present disclosure, the expressions "first", "second", etc. are merely used to distinguish between different modules, steps, data, etc. and do not indicate a particular order or degree of importance. Indeed, the terms "first," "second," and the like are fully interchangeable.
Fig. 1 is a schematic diagram of a method for tracking a person status according to an embodiment of the present disclosure. As shown in fig. 1, the person state tracking method 100 includes an obtaining step S101, a comparing step S102, and a reminding step S103.
As one possible embodiment, the image to be compared and the portrait archive are acquired through the acquisition step S101, wherein the portrait archive may be a portrait archive of a person of interest, the portrait archive is formed by clustering captured portrait pictures, and the portrait archive has archive level information. The portrait archive can also be formed by the identity card portrait of the concerned person directly, one portrait archive corresponds to the identity card portrait of one person, and because the concerned level information of the person can be directly determined through the identity card of the person, the corresponding portrait archive also has the corresponding archive level information.
It should be noted that the image to be compared may be a portrait image acquired by the acquisition device, or a portrait image acquired by other methods; the file level information of the portrait file can be set manually or generated according to a system, and the concerned level of the portrait file can be determined according to the file level information.
In the comparison step S102, a clustering analysis is performed according to the feature value of the image to be compared and the feature value of the portrait archive, so as to obtain a first similarity. The characteristic value of the portrait archive can be obtained by extracting the characteristic according to the portrait picture in the portrait archive. If the first similarity is larger than the first threshold value, the image to be compared is considered to be attached to the portrait archive. Since the portrait file has the attention level, i.e. the file level information, and accordingly, the image to be compared also has the same attention level, which needs to be paid attention, the movement of the image to be compared may represent the movement of the person corresponding to the portrait file, and therefore, the reminding step S103 is executed.
For example, if the image a to be compared is a portrait image captured by the capturing device C1 at the time t1, and the first similarity between the image a to be compared and the portrait archive M is greater than the first threshold, the movement of the image a to be compared may represent the movement of the person corresponding to the portrait archive M. That is, it can be considered that the person corresponding to the portrait archive M appears at the location of the collecting device C1 at time t1, and therefore, this information can be sent to the user to remind the user.
In the reminding step S103, a prompt message is generated to prompt the user that the corresponding portrait in the corresponding portrait file is dynamically updated. Wherein, for the generated prompt message, the timing of sending the prompt message is determined according to the file level information of the corresponding portrait file, namely the concerned level.
The prompt message may include the movement information of the person corresponding to the portrait archive, or a portrait archive label, wherein the portrait archive label may be manually set and determined according to the actual situation of the person corresponding to the portrait archive. For example, it may be a person profile of interest tag. In practical applications, if a person corresponding to a certain person profile is a person of interest, and if the person image corresponding to the person is captured by the capturing device C1 at time t2, it is described that the person of interest is present at the location where the capturing device C1 is located at time t2, the reminding step S103 sends movement information of the person of interest to the user based on the movement information, so as to remind the user.
The person tracking method forms a person image file of a person of major concern by setting the person image file with file level information. And comparing the portrait file serving as a reference library with the image to be compared, if the similarity between the portrait file and the image to be compared exceeds a set threshold value, considering the image to be compared as the image of the concerned person, generating prompt information according to the image to be compared so as to prompt the concerned person to update the state, and determining the time for sending the prompt information according to the difference of the file level information of the portrait file. By the method, on one hand, timely reminding of the absence state of the personnel can be completed in a non-dynamic control mode, and control resources are saved; on the other hand, the prompt information can be sent according to the priority, and the prompt information can be sent by the attention personnel in a notification mode of real time, timing and the like according to the attention degree.
As a possible embodiment, as shown in fig. 2, the person state tracking method 100 further includes a grading step S104 before the acquiring step S101, in addition to the acquiring step S101, the comparing step S102 and the reminding step S103.
In the ranking step S104, a personal static library, i.e., a personal information library having a personal image and personal information of the personal image may be acquired. Through the person information, attention level information of the person image can be determined. The static staff repository may be a reference repository for determining archive level information of the portrait archive acquired in the acquiring step S101, and in practical applications, an aggregate repository of identification cards of corresponding staff may be used as the static staff repository, where an identification card image in the aggregate repository is used as a staff image, and information such as a name and an identification card number is used as staff information.
In practical application, according to the characteristic value of the person image in the person static library and the characteristic value of the person image archive, a second similarity is obtained through comparison calculation, if the second similarity is larger than a second threshold value, the person image in the person image archive and the person image in the person static library are considered to belong to the same person, and then the attention level information of the person image in the person static library is the attention level information of the person image archive. Therefore, the archive level information of the portrait archive is determined based on the attention level information of the portrait image. It should be noted that, in practical applications, the static people library may include a plurality of sub-libraries, where each sub-library is distinguished according to the attention level of the person, and accordingly, images of the person with information of different attention levels are located in different sub-libraries.
It should be noted that the magnitude of the second similarity may be adjusted according to different actual situations and based on the first similarity. In some cases, the second similarity may be the same as the first similarity, and correspondingly, the second threshold may also be the same as the first threshold.
As one possible embodiment, as shown in fig. 3, in addition to the acquiring step S101, the comparing step S102, the reminding step S103 and the ranking step S104, the person state tracking method 100 further includes a profile generating step S105.
Through the archive generation step S105, a plurality of portrait pictures are acquired, the plurality of portrait pictures may be acquired through the acquisition device or may be acquired through other methods, and the clustering analysis is performed according to the acquired feature values of the plurality of portrait pictures to form a portrait archive.
In practical applications, the feature values of the portrait archive can be generated according to all the portrait pictures in the portrait archive, that is, all the portrait pictures already filed in the portrait archive. For example, the characteristic value of the portrait archive can be obtained by taking the average value of the characteristic values of all the archived portrait pictures in the portrait archive; the characteristic value of the portrait archive can be obtained through the fusion characteristic calculation of a plurality of images.
The obtaining of the feature value of the portrait file through the fusion calculation means that if the portrait picture P1 and the portrait picture P2 are portrait pictures belonging to a certain portrait file, for convenience of description, only the portrait picture P1 and the portrait picture P2 are in the portrait file. Wherein, the portrait picture P1 has A, B, C, D four key part information, the portrait picture P2 has B, C, D, E four key part information, and the comprehensive key part of the portrait file includes A, B, C, D, E five key parts (for example, A, B, C, D, E is the outline of the eye, nose, mouth, eyebrow, lip and face, and P1 cannot acquire the information of the key part E because it is a side face image), and the definition of the key part B, C, D commonly owned by the portrait picture P1 and the portrait picture P2 is calculated, and the key part with the highest definition of a same key part in the two portrait pictures is taken as the key part in calculating the comprehensive key part of the portrait file, and then the file characteristic value of the portrait file is acquired from the comprehensive key part of the portrait file. For example, if the clarity of the two key parts B, C in the portrait picture P1 is higher than that of the two key parts B, C in the portrait picture P2, and the clarity of the key part D in the portrait picture P1 is lower than that of the key part D in the portrait picture P2, the comprehensive key parts of the portrait file are a (P1), B (P1), C (P1), D (P2) and E (P2). And then, acquiring the file characteristic value of the portrait file according to the comprehensive key part of the obtained portrait file.
As another possible scenario, a portrait picture with the best picture quality may be selected from the portrait archive as a main picture, and the feature value of the main picture may be used as the feature value of the portrait archive. In the process of selecting the main picture, comprehensive evaluation can be performed from the aspects of the shooting angle, the light condition, the picture definition and the like of the portrait picture.
As a possible example, images of people in static libraries of people tend to have high resolution and are the clearest. Thus, the ranking step S104 further comprises, if the second similarity is greater than the second threshold, then the person in the person profile and the person images in the static pool of persons are considered to belong to the same person. Correspondingly, the person image in the person static library can be selected as the main image of the person image file, and meanwhile, the feature value of the person image is used as the feature value of the person image file, so that the person image is used for calculating the first similarity with the image to be compared in the comparison step S102 in the later period, and whether to execute the reminding step S103 is determined according to the comparison result of the first similarity and the first threshold.
As another possible embodiment, the step S104 of ranking further includes, if the second similarity is less than or equal to the second threshold, then the portrait in the portrait archive is considered not to belong to the same portrait as the portrait in the static library, and accordingly, the archive level information of the portrait archive cannot be determined according to the attention level information of the portrait in the static library.
In this case, the profile level information of the portrait profile may be determined according to the user's instruction, and the timing of sending the prompt information of the portrait profile may be confirmed according to the profile level information. For example, if a certain person image file is not matched with any person image in the static person library, but the person corresponding to the person image file always appears at the attention time or the attention area, the file hierarchy of the person image file can be divided according to the manual instruction. When the first similarity between the new portrait picture appearing again and the portrait file exceeds the first threshold, the reminding step S103 is executed, prompt information is generated, and the timing for sending the prompt information is determined according to the file level information of the portrait file.
As a possible embodiment, the archive level information includes a first level, a second level, or a third level. The first level is a level of major concern, for example, in order to ensure that some important activities take place smoothly, for some persons that may interfere with or affect the activities, the file level corresponding to the persons may be set as the first level; or for managing the community, since the personnel who have privately entered the community and issue the advertisement need to be prohibited, for the community manager, the archive level corresponding to the personnel can be set as the first level. The second level is a level of secondary importance, taking management of the community as an example, for some takeout persons who do not comply with the management order of the community in the community, we need to pay attention to their activity states in and near the community, and accordingly, the file level corresponding to these persons can be set as the second level. The third level is a level of general attention, such as strangers entering the community, who need to pay attention to their dynamics in and near the community, so that the file level corresponding to the strangers can be set as the third level. Therefore, in terms of importance of attention, it can be understood that the degree of attention of the first hierarchy is greater than that of the second hierarchy, and the degree of attention of the second hierarchy is greater than that of the third hierarchy.
Correspondingly, the reminding step S103 comprises that if the file level information of the portrait file is the first level, the prompt message is sent immediately; if the file level information of the portrait file is a second level, the sent prompt information is sent when the user logs in; if the file level information of the portrait file is the third level, the prompt message is sent at a timing time.
In practical applications, if a person corresponding to a certain portrait file is found to have a new movement through the comparison step S102, a prompt message is generated, and the movement changes of the portrait file and the corresponding portrait picture are recorded. And determining the time for sending the prompt message by judging the file level information of the portrait file.
If the portrait file has the first-level file level information, once the personnel corresponding to the portrait file have new movement changes, prompt information is immediately generated in the message center, and is synchronized to the message list in real time, and notification information is generated for the user to check. If the user receives the notification message and checks the corresponding prompt message, the prompt message does not appear in the message list. In addition, the prompt message and/or the notification message can be synchronized to the user terminal so as to be convenient for the user to view.
It should be noted that the generated notification message is used to notify the user that the person corresponding to the portrait archive that needs to be focused has a new trend to appear, so as to prompt the user to view corresponding information. Wherein the generated notification message may appear in the form of a pop-up dialog box accompanied by a prompt sound. For example, when the notification information is presented in the form of a dialog box, it is possible to display: the portrait archive a having the information of the concerned hierarchy is updated and please refer.
The prompt message can further show the specific information of the updated portrait file with the attention level information. For example, a newly captured portrait picture of a portrait archive having information about a level of interest, i.e., an image to be compared belonging to the portrait archive, may be presented, which may characterize a new trend of appearance of a person corresponding to the portrait archive, as well as a time and a place of capture.
If the portrait file has second-level file level information, once the person corresponding to the portrait file has a new trend change, when the user does not log in the system, the prompt information can be generated in the message center and cached in the memory queue, and when the user logs in the system, the prompt information is pushed to the message list and notification information is generated for the user to view. If the user receives the notification message and checks the corresponding prompt message, the prompt message does not appear in the message list. It should be noted that the prompt message and/or the notification message may also be synchronized to the user terminal for the user to view.
If the portrait file has the third-level file level information, once a person corresponding to the portrait file has a new trend change, prompt information can be generated in a message center and cached in an internal storage queue, and when the preset time for sending the prompt information is reached, the prompt information can be pushed to a message list and notification information can be generated for a user to check. If the user receives the notification message and checks the corresponding prompt message, the prompt message does not appear in the message list. Similarly, the prompt message and/or the notification message may be synchronized to the user terminal for viewing by the user.
Further, the reminding step S103 further includes determining a display order of the corresponding prompt information in the message list according to the file level information of the portrait file corresponding to the prompt information and/or the prompt time for generating the prompt information, where the prompt time is the time for generating the prompt information.
For example, if one of the prompt messages J is subordinate to a portrait file having first-level file hierarchy information and the other prompt message K is subordinate to a portrait file having second-level file hierarchy information, the prompt message J may be displayed before the prompt message K for the user to view when the prompt message is displayed in the message list according to the hierarchy information of the corresponding portrait file.
Alternatively, the order of display of the guidance information in the message list may be determined according to the guidance time at which the guidance information is generated. For example, if the prompt message J is generated at time t1 and the prompt message K is generated at time t2, and if t1 is smaller than t2, the prompt message J may be displayed before the prompt message K for the user to view when the prompt message is displayed in the message list.
It should be noted that, when a certain image to be compared is found to belong to the corresponding portrait file that needs to be focused, the reminding step S103 is executed, and the corresponding prompt information is generated. Therefore, it can be understood that the prompt time for generating the prompt message is synchronous with the time for filing the image to be compared in the portrait archive. Further, if the portrait file is updated based on the image to be compared, the update time and the prompt time of the portrait file are synchronized.
Further, since the prompt information is used to prompt the user that the person corresponding to the portrait file has a new movement, the prompt information may be a portrait picture of the person corresponding to the portrait file having the new movement, a prompt time for the portrait file to generate the prompt information, or a displayed portrait file aggregated list.
The prompt message is presented in the form of a portrait archive aggregated list. Since the portrait archive aggregated list is a summary list covering all the portrait archives with archive level information, if it is determined through the comparison step S102 that a new direction of movement occurs to a person corresponding to a certain portrait archive, a portrait picture representing the new direction of movement can be displayed in the portrait archive in a marked form, and the portrait archive is also marked correspondingly. When the user opens the portrait archive aggregated list, the portrait archive can be directly distinguished from the portrait archive aggregated list.
It should be noted that the marks made for the portrait photos and the marks made for the portrait archives may be the same or different. The marking can be realized by labeling different colors, or realized by highlighting the corresponding portrait pictures and/or portrait archives. Further, after the user checks the portrait picture of the new trend of the person corresponding to the portrait archive in the portrait archive, the portrait picture is displayed in the portrait archive in a mark-free form. Correspondingly, after the portrait picture of the person corresponding to the portrait archive showing the new trend is viewed, the portrait archive is also viewed, so that the portrait archive at the moment is also displayed in the portrait archive clustering list in an unmarked form. Thereby indicating that the user viewed the corresponding reminder information.
In practical application, the corresponding prompt information can be displayed in a preview mode, so that a user can more intuitively know and read the prompt information of the corresponding portrait file.
Similarly, taking a person corresponding to a certain person image file as an example of a person concerned, if the person image picture corresponding to the person is acquired by the acquisition device C1 at time t2, it indicates that the person concerned appears at the place where the acquisition device C1 is located at time t2, then the reminding step S103 sends the movement information of the person concerned to the message list in a prompt information manner for the user to view, and may also show other information related to the prompt information, for example, the person image picture corresponding to the person is acquired by the acquisition device C1 at time t2 to the user in a preview manner, so that the user can more intuitively read the prompt information.
As another possible embodiment, as shown in fig. 4, the person state tracking method 100 may further include a collecting step S106, i.e., it may be determined to collect some portrait files according to a user instruction. In practical application, by collecting certain portrait files, the updating condition of the collected portrait files can be checked at any time without being influenced by whether the portrait files have file level information of a first level, a second level or a third level.
Further, the comparing step S102 may further include obtaining a third similarity according to the collected feature value of the image to be compared and the collected feature value, and if the third similarity is greater than a third threshold, executing the reminding step S103. By the embodiment, dynamic tracking of the personnel corresponding to the collected portrait files is achieved.
Correspondingly, the image to be compared, which meets the requirement that the third similarity between the image to be compared and the portrait archive is larger than the third threshold value, can also be included in the collected portrait archive, so that the portrait archive is updated, the archive characteristics of the portrait archive can be closer to the real conditions of corresponding personnel, and the accuracy of the portrait archive is improved.
It should be noted that the magnitude of the third similarity may be adjusted according to different actual situations and based on the first similarity. In some cases, the third similarity may be the same as the first similarity, and correspondingly, the third threshold may also be the same as the first threshold.
As a possible embodiment, the comparing step S102 further includes, if the first similarity is greater than the first threshold, classifying the image to be compared into the portrait file, and updating the portrait file, and accordingly, updating the file feature value of the portrait file correspondingly. The updated portrait archive and the corresponding archive characteristic value can be used as a standard for judging whether the subsequently obtained image to be compared is subordinate to the portrait archive or not. With the continuous update of the portrait archive, the number of the portrait pictures filed in the portrait archive is correspondingly increased, so that the archive characteristics of the portrait archive are closer to the real situation of corresponding personnel, and the accuracy of the portrait archive is improved.
Correspondingly, the prompt message generated in the reminding step S103 may further include portrait picture update information or portrait archive update information. The portrait archive update information may be determined based on the time and place of update of the corresponding updated portrait picture in the portrait archive. For example, if the image B to be compared is a portrait picture captured by the capturing device C2 at the time t2, and the first similarity between the image B to be compared and the portrait archive M is greater than the first threshold, the image B to be compared will be incorporated into the portrait archive M. If the portrait file M is the concerned portrait file, based on this, in the reminding step S103, in addition to the prompt information, the update information of the portrait file M is generated, for example, the portrait file M appears at the place where C2 exists at time t2, and the portrait file M is updated at time t 2; and portrait picture update information, such as portrait picture B incorporated into portrait archive M at time t 2.
Further, if the portrait archive update information and the portrait picture update information are already checked by the user, the portrait archive update information and the portrait picture update information at this time will not appear again when the prompt information is sent next time.
It should be noted that a special mark may be added to the updated portrait picture, so that the user can clearly distinguish the updated portrait picture from the numerous portrait pictures in the corresponding portrait file when viewing the portrait picture.
Based on the same inventive concept, the embodiment of the present disclosure further provides a personnel state tracking apparatus 200. As shown in fig. 5, the apparatus includes an obtaining module 201, configured to obtain an image to be compared and a portrait archive, where the portrait archive has archive level information; the comparison module 202 is configured to obtain a first similarity according to the feature value of the image to be compared and the feature value of the portrait file, and if the first similarity is greater than a first threshold, perform a prompt; and the reminding module 203 is used for executing reminding, including generating the reminding information and determining the time for sending the reminding information according to the file level information of the portrait file.
In one example, the personnel state tracking apparatus 200 further includes a ranking module for obtaining a personnel static library, where the personnel static library includes personnel images, and the personnel images have attention level information; and obtaining a second similarity according to the characteristic value of the personnel image and the characteristic value of the personnel image file, and if the second similarity is greater than a second threshold value, determining the file level information of the personnel image file according to the attention level information of the personnel image.
In one example, the personnel state tracking apparatus 200 further includes a profile generation module, configured to obtain a plurality of portrait pictures and generate a portrait profile according to similarities between feature values of the plurality of portrait pictures; generating a portrait archive characteristic value according to all portrait pictures in the portrait archive; or, one portrait picture in the portrait archive is taken as a main picture, and the characteristic value of the main picture is taken as the characteristic value of the portrait archive.
In one example, the grading module is further configured to, if the second similarity is greater than a second threshold, use the person image as a main image of the portrait archive, and use a feature value of the person image as a feature value of the portrait archive.
In one example, the grading module is further configured to determine, according to the user instruction, the file hierarchy information of the portrait file if the second similarity is less than or equal to a second threshold.
In one example, the archive tier information includes a first tier, a second tier, or a third tier; the reminding step comprises that if the file level information of the portrait file is a first level, the prompt information is sent immediately; if the file level information of the portrait file is a second level, the prompt message is sent when the user logs in; and if the file level information of the portrait file is the third level, the prompt message is sent at a timing.
In one example, the instant sending of the prompt message is performed at the time, and if the prompt message is generated in the reminding step, the prompt message is synchronized to the message list in real time; sending the prompt information when the user logs in, if the prompt information is generated in the prompting step, pushing the prompt information to a message list when the user logs in the system; the timing of sending the prompt information comprises that if the prompt information is generated in the reminding step, the prompt information is pushed to a message list when the preset time for sending the prompt information is reached.
In one example, the reminding module 203 is further configured to determine a display order of the prompt information in the message list according to the file hierarchy information and/or the prompt time of the portrait file corresponding to the prompt information, where the prompt time is a time for generating the prompt information.
In one example, the prompt message is used to prompt the user that the person corresponding to the portrait file has a new trend; the prompt message at least comprises one of the following items: a person corresponding to the portrait file presents a new trend portrait picture, the portrait file generates prompt time of prompt information, and a portrait file aggregation list; the portrait archive aggregation list is a summary list of all the portrait archives with archive level information, in the portrait archive aggregation list, portrait pictures of people corresponding to the portrait archives, in which the new trend appears, are displayed in the portrait archives in a marked manner, and the portrait archives are displayed in the portrait archive clustering list in a marked manner.
In one example, after the user views the reminder, the reminder will no longer appear in the message list.
In one example, after the user checks the portrait picture with the new trend of the person corresponding to the portrait file, the portrait picture with the new trend of the person corresponding to the portrait file is displayed in the portrait file in an unmarked form, and the portrait file is displayed in the portrait file clustering list in an unmarked form.
In one example, the personnel state tracking device further comprises a collection module for collecting the portrait file according to the user instruction; the comparison module 202 is further configured to obtain a third similarity according to the feature value of the image to be compared and the feature value of the collected portrait file, and execute the reminding step if the third similarity is greater than a third threshold.
In one example, the comparison module is further configured to, if the first similarity is greater than a first threshold, classify the image to be compared into the portrait archive.
Fig. 6 shows an electronic device 30 provided in one embodiment of the present disclosure. As shown in fig. 6, an embodiment of the present disclosure provides an electronic device 30, where the electronic device 30 includes a memory 310, a processor 320, and an Input/Output (I/O) interface 330. The memory 310 is used for storing instructions. A processor 320 for calling the instructions stored in the memory 310 to execute the disclosed person state tracking method. The processor 320 is connected to the memory 310 and the I/O interface 330, respectively, for example, via a bus system and/or other connection mechanism (not shown). The memory 310 may be used to store programs and data, including programs related to the tracking of the status of the person in the embodiments of the present disclosure, and the processor 320 executes various functional applications and data processing of the electronic device 30 by executing the programs stored in the memory 310.
In the embodiment of the present disclosure, the processor 320 may be implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), and the processor 320 may be one or a combination of several Central Processing Units (CPUs) or other forms of Processing units with data Processing capability and/or instruction execution capability.
In the disclosed embodiment, the I/O interface 330 may be used to receive input instructions (e.g., numeric or character information, and generate key signal inputs related to user settings and function control of the electronic device 30, etc.), and may also output various information (e.g., images or sounds, etc.) to the outside. The I/O interface 330 in embodiments of the present disclosure may include one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, a touch panel, and the like.
In some embodiments, the present disclosure provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, perform any of the methods described above.
Although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in serial order, or that all illustrated operations be performed, to achieve desirable results. In certain environments, multitasking and parallel processing may be advantageous.
The methods and apparatus of the present disclosure can be accomplished with standard programming techniques with rule-based logic or other logic to accomplish the various method steps. It should also be noted that the words "means" and "module," as used herein and in the claims, is intended to encompass implementations using one or more lines of software code, and/or hardware implementations, and/or equipment for receiving inputs.
Any of the steps, operations, or procedures described herein may be performed or implemented using one or more hardware or software modules, alone or in combination with other devices. In one embodiment, the software modules are implemented using a computer program product comprising a computer readable medium containing computer program code, which is executable by a computer processor for performing any or all of the described steps, operations, or procedures.
The foregoing description of the implementations of the disclosure has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure to the precise form disclosed, and modifications and variations are possible in light of the above teachings or may be acquired from practice of the disclosure. The embodiments were chosen and described in order to explain the principles of the disclosure and its practical application to enable one skilled in the art to utilize the disclosure in various embodiments and with various modifications as are suited to the particular use contemplated.
Claims (16)
1. A person state tracking method, wherein the method comprises:
the method comprises the steps of obtaining an image to be compared and a portrait archive, wherein the portrait archive has archive level information;
a comparison step, namely obtaining a first similarity according to the characteristic value of the image to be compared and the characteristic value of the portrait file, and if the first similarity is greater than a first threshold value, executing a reminding step;
and the reminding step is to generate prompt information and determine the time for sending the prompt information according to the file level information of the portrait file.
2. The method of claim 1, wherein the comparing step further comprises:
if the first similarity is larger than the first threshold value, the image to be compared is classified into the portrait archive.
3. The method of claim 1 or 2, wherein prior to the obtaining step, the method further comprises:
a step of grading, wherein a personnel static library is obtained, the personnel static library comprises personnel images, and the personnel images have attention level information;
and obtaining a second similarity according to the characteristic value of the personnel image and the characteristic value of the personnel image file, and if the second similarity is greater than a second threshold value, determining the file level information of the personnel image file according to the attention level information of the personnel image.
4. The method of claim 3, wherein the method further comprises:
a step of generating a file, which is to acquire a plurality of portrait pictures and cluster the portrait pictures to generate the portrait file;
generating a characteristic value of the portrait file according to all the portrait pictures in the portrait file; or, one portrait picture in the portrait archive is used as a main picture, and the characteristic value of the main picture is used as the characteristic value of the portrait archive.
5. The method of claim 4, wherein the ranking step further comprises:
and if the second similarity is larger than the second threshold value, taking the personnel image as the main image of the personnel image file, and taking the characteristic value of the personnel image as the characteristic value of the personnel image file.
6. The method of claim 3, wherein the ranking step further comprises:
and if the second similarity is smaller than or equal to the second threshold, determining the file level information of the portrait file according to a user instruction.
7. The method of claim 1 or 2,
the archive tier information comprises a first tier, a second tier, or a third tier;
the reminding step comprises that if the file level information of the portrait file is the first level, the opportunity for sending the prompt information is instant sending; if the file level information of the portrait file is the second level, the opportunity of sending the prompt information is sent when a user logs in; and if the file level information of the portrait file is the third level, the opportunity of sending the prompt information is timing sending.
8. The method of claim 7, wherein,
the time for sending the prompt message is instant sending, and if the prompt message is generated in the reminding step, the prompt message is synchronized to a message list in real time; and/or
The time for sending the prompt message is sent when the user logs in, if the prompt message is generated in the prompting step, the prompt message is pushed to a message list when the user logs in the system; and/or
The timing of sending the prompt message comprises that if the prompt message is generated in the reminding step, the prompt message is pushed to a message list when the preset time of sending the prompt message is reached.
9. The method of claim 8, wherein,
the reminding step also comprises the step of determining the display sequence of the prompt information in a message list according to the file level information and/or the prompt time of the portrait file corresponding to the prompt information; wherein the prompt time is the time for generating the prompt information.
10. The method of any one of claims 1-9,
the prompt information is used for prompting a user that a new trend of personnel corresponding to the portrait file appears;
the prompt message at least comprises one of the following items: a person corresponding to the portrait file presents a new trend portrait picture, and the portrait file generates the prompt time of the prompt information and a portrait file aggregation list;
the portrait archive aggregation list is a summary list of all the portrait archives with the archive level information, in the portrait archive aggregation list, portrait pictures of people corresponding to the portrait archives and having new trends are displayed in the portrait archives in a marked mode, and the portrait archives are displayed in the portrait archive clustering list in a marked mode.
11. The method of claim 10, wherein,
after the user views the prompt message, the prompt message does not appear in the message list.
12. The method of claim 10, wherein,
after the user checks the portrait picture with the new trend of the personnel corresponding to the portrait archive, the portrait picture with the new trend of the personnel corresponding to the portrait archive is displayed in the portrait archive in an unmarked mode, and the portrait archive is displayed in the portrait archive clustering list in an unmarked mode.
13. The method of claim 1, wherein the method further comprises:
a collection step, wherein the portrait file is collected according to a user instruction;
the comparison step further comprises the step of obtaining a third similarity according to the characteristic value of the image to be compared and the characteristic value of the collected portrait file, and if the third similarity is larger than a third threshold value, the reminding step is executed.
14. A person state tracking apparatus, wherein the apparatus comprises:
the system comprises an acquisition module, a comparison module and a comparison module, wherein the acquisition module is used for acquiring an image to be compared and a portrait file, and the portrait file has file level information;
the comparison module is used for obtaining a first similarity according to the characteristic value of the image to be compared and the characteristic value of the portrait file, and if the first similarity is larger than a first threshold value, reminding is executed;
and the reminding module is used for executing the reminding, generating reminding information and determining the time for sending the reminding information according to the file level information of the portrait file.
15. An electronic device, wherein the electronic device comprises:
a memory to store instructions; and
a processor for invoking the memory-stored instructions to perform the person state tracking method of any one of claims 1-13.
16. A computer-readable storage medium, wherein,
the computer-readable storage medium stores computer-executable instructions that, when executed by a processor, perform the person state tracking method of any one of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068995.5A CN112906474B (en) | 2019-08-01 | 2019-08-12 | Prompt message generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910708917 | 2019-08-01 | ||
| CN201910708917X | 2019-08-01 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068995.5A Division CN112906474B (en) | 2019-08-01 | 2019-08-12 | Prompt message generation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112307856A true CN112307856A (en) | 2021-02-02 |
Family
ID=74485547
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910741740.3A Withdrawn CN112307856A (en) | 2019-08-01 | 2019-08-12 | Personnel state tracking method and device |
| CN202110068995.5A Active CN112906474B (en) | 2019-08-01 | 2019-08-12 | Prompt message generation method and device, electronic equipment and storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068995.5A Active CN112906474B (en) | 2019-08-01 | 2019-08-12 | Prompt message generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112307856A (en) |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101042580A (en) * | 2006-03-23 | 2007-09-26 | 上海宝信软件股份有限公司 | Method for real time unconventionality judging and dynamic alarming |
| CN104809732B (en) * | 2015-05-07 | 2017-06-20 | 山东鲁能智能技术有限公司 | A kind of power equipment appearance method for detecting abnormality compared based on image |
| CN107666589A (en) * | 2016-07-29 | 2018-02-06 | 中兴通讯股份有限公司 | A kind of long-distance monitoring method and equipment |
| CN108156205B (en) * | 2016-12-06 | 2021-01-22 | 阿里巴巴（中国）有限公司 | Message pushing method, client, server and programmable device |
| CN108171032A (en) * | 2017-12-01 | 2018-06-15 | 平安科技（深圳）有限公司 | A kind of identity identifying method, electronic device and computer readable storage medium |
| CN108763532A (en) * | 2018-05-31 | 2018-11-06 | 上海掌门科技有限公司 | For pushed information, show the method and apparatus of information |
| CN108989534A (en) * | 2018-06-28 | 2018-12-11 | 努比亚技术有限公司 | Message prompt method, mobile terminal and computer readable storage medium |
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109344271A (en) * | 2018-09-30 | 2019-02-15 | 南京物盟信息技术有限公司 | Video portrait records handling method and its system |
| CN109815349B (en) * | 2018-12-20 | 2022-02-22 | 维沃移动通信有限公司 | Information acquisition method and terminal equipment |
| CN109558861A (en) * | 2018-12-28 | 2019-04-02 | 上海依图网络科技有限公司 | A kind of method and device of determining passerby track |
-
2019
- 2019-08-12 CN CN201910741740.3A patent/CN112307856A/en not_active Withdrawn
- 2019-08-12 CN CN202110068995.5A patent/CN112906474B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112906474A (en) | 2021-06-04 |
| CN112906474B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11210504B2 (en) | Emotion detection enabled video redaction | |
| US9141184B2 (en) | Person detection system | |
| US7978936B1 (en) | Indicating a correspondence between an image and an object | |
| KR101346539B1 (en) | Organizing digital images by correlating faces | |
| US9998598B1 (en) | Methods and systems for automatically recognizing actions in a call center environment using screen capture technology | |
| JP5669082B2 (en) | Verification device | |
| JP2015076687A (en) | Monitoring system, monitoring method, monitoring program, and recording medium having the program recorded therein | |
| JP2022518459A (en) | Information processing methods and devices, storage media | |
| US20180150683A1 (en) | Systems, methods, and devices for information sharing and matching | |
| US10638298B1 (en) | Public event detection platform | |
| JP2018206361A (en) | System and method for user-oriented topic selection and browsing, and method, program, and computing device for displaying multiple content items | |
| US20200210684A1 (en) | System and method of biometric identification and storing and retrieving suspect information | |
| JP2010211485A (en) | Gaze degree measurement device, gaze degree measurement method, gaze degree measurement program and recording medium with the same program recorded | |
| CN110263830B (en) | Image processing method, device and system and storage medium | |
| US8300256B2 (en) | Methods, systems, and computer program products for associating an image with a communication characteristic | |
| CN113568934A (en) | Data query method and device, electronic equipment and storage medium | |
| CN112307856A (en) | Personnel state tracking method and device | |
| CN111739182A (en) | Attendance checking method and device, electronic equipment and storage medium | |
| WO2016151802A1 (en) | Face verification system and face verification method | |
| CN114416500A (en) | Alarm information identification method, device and equipment based on information system | |
| CN114359783A (en) | Abnormal event detection method, device and equipment | |
| US10750346B1 (en) | Emergency incident detection platform | |
| JP2012049774A (en) | Video monitoring device | |
| KR20210031444A (en) | Method and Apparatus for Creating Labeling Model with Data Programming | |
| US11250271B1 (en) | Cross-video object tracking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210202 |
|
| WW01 | Invention patent application withdrawn after publication |