Method, device, electronic device and storage medium for monitoring fellow passengers

Abstract

An embodiment of the present invention provides a method for monitoring companions, the method comprising: when a target person has companions in a target area, obtaining a first file of the target person and a second file of the companions; performing trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and performing trajectory analysis on the second file to obtain a second trajectory of the companions in the target area; and determining whether the target person and the companions are lost based on the first trajectory and the second trajectory. By performing trajectory analysis on the first file of the target person and the second file of the companions, the spatiotemporal position of the target person in the target area and the spatiotemporal position of the companions in the target area are obtained, and the first trajectory of the target person and the second trajectory of the companions are used to promptly detect the loss of the target person and the companions, and the first trajectory and the second trajectory can be used to determine the position of the target person and the position of the companions, thereby improving the efficiency of finding people.

Description

Technical Field

[0001] The present invention relates to the field of file processing, and in particular to a method, device, electronic equipment and storage medium for monitoring fellow personnel. Background Art

[0002] Generally speaking, in areas with large flow of people, there is a risk of companions getting lost. For example, in crowded scenic spots or shopping malls, people's attention will be distracted by the scenery or goods, and they will ignore whether their companions are still with them. Because their attention is distracted, most people are usually unaware of the loss when it just happens. It will take some time before they realize that their companions are missing. At this time, they will report it to the relevant departments, and the relevant departments and the companions will have to inquire and search for them through manpower, which is not efficient. Summary of the Invention

[0003] An embodiment of the present invention provides a companion monitoring method, which aims to solve the problem in the prior art that when a companion is found to be missing, inquiries and searches are conducted by manpower, resulting in low efficiency in finding the companion. By performing trajectory analysis on the first file of the target person and the second file of the companion, the spatiotemporal position of the target person in the target area and the spatiotemporal position of the companion in the target area are obtained respectively. The first trajectory of the target person and the second trajectory of the companion are used to promptly detect the loss of the target person and the companion, and the first trajectory and the second trajectory can be used to determine the position of the target person and the companion, thereby improving the efficiency of finding the companion.

[0004] In a first aspect, an embodiment of the present invention provides a method for monitoring a companion, the method comprising:

[0005] When the target person has a companion in the target area, obtaining a first file of the target person and a second file of the companion;

[0006] Performing trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and performing trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area;

[0007] Based on the first trajectory and the second trajectory, determine whether the target person and the traveling companions are lost.

[0008] Optionally, when the target person has a companion in the target area, before obtaining the first file of the target person and the second file of the companion, the method further includes:

[0009] Acquire snapshot images of each monitored person in the target area;

[0010] Files are created for the monitoring personnel based on the captured images to obtain files of each monitored person.

[0011] Optionally, when the target person has a companion in the target area, before obtaining the first file of the target person and the second file of the companion, the method further includes:

[0012] When it is detected for the first time in the target area that the distance between at least two persons to be confirmed is less than a preset value, the traveling relationship between the at least two persons to be confirmed is confirmed within a first preset time;

[0013] If it is confirmed that at least two of the persons to be confirmed have a traveling companion relationship, the target person and the traveling companion are determined from the at least two persons to be confirmed.

[0014] Optionally, when it is detected for the first time in the target area that the distance between at least two persons to be confirmed is less than a preset value, confirming the traveling relationship between the at least two persons to be confirmed within a first preset time includes:

[0015] In the target area, performing human body detection on at least two persons to be confirmed to obtain human body detection results of the at least two persons to be confirmed;

[0016] Calculating the distance between the at least two persons to be confirmed based on the human body detection results of the at least two persons to be confirmed;

[0017] When it is detected for the first time that the distance between at least two persons to be confirmed is less than a preset value, body tracking is performed on the at least two persons to be confirmed within the first preset time to obtain body tracking results of the at least two persons to be confirmed;

[0018] Calculating the distance between the at least two persons to be confirmed within the first preset time based on the body tracking results of the at least two persons to be confirmed;

[0019] The traveling relationship between the at least two persons to be confirmed is confirmed based on the distance between the at least two persons to be confirmed within the first preset time.

[0020] Optionally, if it is confirmed that at least two of the persons to be confirmed have a traveling companion relationship, determining the target person and the traveling companion from the at least two persons to be confirmed includes:

[0021] If it is confirmed that at least two of the persons to be confirmed have a peer relationship, obtaining the person attributes corresponding to the at least two persons to be confirmed respectively;

[0022] The target person and the accompanying person are determined from the at least two persons to be confirmed according to the person attributes corresponding to the at least two persons to be confirmed.

[0023] Optionally, determining whether the target person and the traveling companions are lost based on the first trajectory and the second trajectory includes:

[0024] Calculating the degree of overlap between the first trajectory and the second trajectory within a second preset time;

[0025] Whether the target person and the traveling companion are lost is determined based on the degree of overlap between the first trajectory and the second trajectory.

[0026] Optionally, determining whether the target person and the traveling companion are lost based on the degree of overlap between the first trajectory and the second trajectory includes:

[0027] When the degree of overlap between the first trajectory and the second trajectory is greater than or equal to a threshold value of overlap, it is determined that the target person and the traveling companion are not lost;

[0028] When the degree of overlap between the first track and the second track is less than a threshold value of overlap, calculating the degree of disorder of the first track and the second track after separation;

[0029] If the disorder degree of the first trajectory or the second trajectory after separation is greater than the disorder degree threshold, it is determined that the target person and the traveling companion are lost.

[0030] In a second aspect, an embodiment of the present invention provides a companion monitoring device, the device comprising:

[0031] A first acquisition module is used to acquire a first file of the target person and a second file of the companion when the target person has a companion in the target area;

[0032] an analysis module, configured to perform trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and to perform trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area;

[0033] A processing module is used to determine whether the target person and the accompanying person are lost based on the first trajectory and the second trajectory.

[0034] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the method for monitoring companions provided in an embodiment of the present invention are implemented.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the companion monitoring method provided in the embodiment of the invention are implemented.

[0036] In an embodiment of the present invention, when a target person has a companion in a target area, a first file of the target person and a second file of the companion are obtained; a trajectory analysis is performed on the first file to obtain a first trajectory of the target person in the target area, and a trajectory analysis is performed on the second file to obtain a second trajectory of the companion in the target area; based on the first trajectory and the second trajectory, it is determined whether the target person and the companion are lost. By performing trajectory analysis on the first file of the target person and the second file of the companion, the spatiotemporal position of the target person in the target area and the spatiotemporal position of the companion in the target area are obtained respectively. The first trajectory of the target person and the second trajectory of the companion can be used to promptly discover the situation in which the target person and the companion are lost, and the first trajectory and the second trajectory can be used to determine the position of the target person and the position of the companion, thereby improving the efficiency of finding people. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is a flow chart of a method for monitoring fellow passengers provided by an embodiment of the present invention;

[0039] Figure 2 1 is a schematic structural diagram of a companion monitoring device provided by an embodiment of the present invention;

[0040] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] See Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for monitoring fellow passengers provided by an embodiment of the present invention. Figure 1 As shown, the peer monitoring method includes the following steps:

[0043] 101. When the target person has a companion in the target area, obtain the first file of the target person and the second file of the companion.

[0044] In an embodiment of the present invention, the above-mentioned first file and the above-mentioned second file can be constructed based on the captured images in the target area. For each monitored person entering the target area, a corresponding file is established, which may include a captured face image and a captured body image.

[0045] When the target person has companions in the target area, it can be said that at least two people appear together in the target area. The target area can be a scene area with a large flow of people, such as a scenic spot, amusement park, supermarket, etc. The target person can be a person with specific attributes among the at least two people who appear together, such as a mother and child pair, where the target person is the mother and the companions are the children; for example, among three or more people, the target person is the leader and the companions are the people behind the target person, or the target person is in the middle and the companions are the people on both sides of the target person.

[0046] When a monitored person appears in the target area, an image capture device installed in the target area can capture the monitored person in real time to obtain a captured image of the monitored person. A file is created based on the captured image of the monitored person to obtain the monitored person's profile. The cover of the file of the monitored person can be a captured image of the monitored person's face. The monitored person's profile is stored in a temporary database for that day.

[0047] When the target person has a companion in the target area, the first file of the target person and the second file of the companion can be found in the temporary database of the day based on the facial capture image of the target person and the facial capture image of the companion.

[0048] 102. Perform trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and perform trajectory analysis on the second file to obtain a second trajectory of the companion in the target area.

[0049] In an embodiment of the present invention, the above-mentioned first file includes a captured image of the target person in the target area. The appearance time and location of the target person can be determined based on the capture time and capture location of the captured image, thereby generating the time-space location of the target person based on the appearance time and location of the target person, and connecting the time-space locations to obtain the first trajectory of the target person in the target area.

[0050] The above-mentioned second file includes captured images of the companions in the target area. The appearance time and location of the companions can be determined based on the capture time and capture location of the captured images, thereby generating the time-space position of the companions based on the appearance time and location of the companions. The time-space positions are connected to obtain the first trajectory of the companions in the target area.

[0051] In a possible embodiment, the distance from the target person and the accompanying persons in the captured image to the image capture device can be calculated, and the real positions of the target person and the accompanying persons can be calculated by using the mapping relationship between the internal coordinate system of the image capture device and the real-world coordinate system. The real position of the target person is used as the appearance position of the target person, so that the spatiotemporal position of the target person can be generated based on the appearance time and appearance position of the target person; the real position of the accompanying persons is used as the appearance position of the accompanying persons, so that the spatiotemporal position of the accompanying persons can be generated based on the appearance time and appearance position of the accompanying persons.

[0052] 103. Based on the first trajectory and the second trajectory, determine whether the target person and the accompanying persons are lost.

[0053] In an embodiment of the present invention, the above-mentioned first trajectory is the movement trajectory of the target person in the target area, and the first trajectory indicates the movement of the target person in the target area. The above-mentioned second trajectory is the movement trajectory of the companions in the target area, and the second trajectory indicates the movement of the companions in the target area. It can be determined whether the target person and the companions are lost based on the movement of the target person in the target area and the movement of the companions in the target area. For example, if the movement of the target person in the target area is similar to the movement of the companions in the target area, it can be determined that the target person and the companions are not lost. If the movement of the target person in the target area is significantly different from the movement of the companions in the target area, it can be determined that the target person and the companions are lost.

[0054] Furthermore, if it is determined that the target person and their companions are lost, relevant personnel can be notified. The relevant personnel can be the target person, the companions, and the staff in the target area. The staff in the target area can determine the current location of the target person based on the first trajectory and the current location of the companions based on the second trajectory, and then search for the target person based on the current location of the target person and the current location of the companions, or notify the target person of the current location of the companions, and notify the companions of the current location of the target person.

[0055] In one possible embodiment, if it is determined that the target person and the companion are lost, whether the target person or the companion has the intention to leave the target area is determined based on the first trajectory or the second trajectory. If it is determined that the target person or the companion has the intention to leave the target area, the current location of the target person or the other party with the intention to leave the target area can be prompted. When the latest position of the first trajectory is the exit area of ​​the target area, it can be determined that the target person has the intention to leave the target area. When the latest position of the second trajectory is the exit area of ​​the target area, it can be determined that the companion has the intention to leave the target area.

[0056] In an embodiment of the present invention, when a target person has a companion in a target area, a first file of the target person and a second file of the companion are obtained; a trajectory analysis is performed on the first file to obtain a first trajectory of the target person in the target area, and a trajectory analysis is performed on the second file to obtain a second trajectory of the companion in the target area; based on the first trajectory and the second trajectory, it is determined whether the target person and the companion are lost. By performing trajectory analysis on the first file of the target person and the second file of the companion, the spatiotemporal position of the target person in the target area and the spatiotemporal position of the companion in the target area are obtained respectively. The first trajectory of the target person and the second trajectory of the companion can be used to promptly discover the situation in which the target person and the companion are lost, and the first trajectory and the second trajectory can be used to determine the position of the target person and the position of the companion, thereby improving the efficiency of finding people.

[0057] Optionally, when the target person has companions in the target area, before obtaining the first file of the target person and the second file of the companions, you can also obtain snapshot images of each monitored person in the target area; create files for the monitored persons based on the snapshot images, and obtain files of each monitored person.

[0058] In the embodiment of the present invention, the person entering the target area is the monitored person, and the monitored person in the target area can be captured by an image capture device arranged in the target area to obtain a captured image.

[0059] Specifically, when a monitored person is first captured in the target area, their captured image can be captured for file creation, and their facial image can be extracted as the cover of the profile. After the profile is created, the profile is stored in a temporary database for that day. As more captured images are taken of the monitored person, subsequent images are added to the profile in chronological order.

[0060] At the end of the day, the monitored person files in the temporary database can be transferred to the archive database for storage, and the monitored person files can be merged in the archive database. The temporary database only stores the files of monitored persons who appeared in the target area on that day. This can speed up the acquisition of the first and second files, and the archive database can store the monitored person files for a longer period of time.

[0061] Optionally, when the target person has a companion in the target area, before the step of obtaining the first file of the target person and the second file of the companion, when it is detected for the first time in the target area that the distance between at least two persons to be confirmed is less than a preset value, the companion relationship between the at least two persons to be confirmed is confirmed within a first preset time; if it is confirmed that there is a companion relationship between the at least two persons to be confirmed, the target person and the companion are determined among the at least two persons to be confirmed.

[0062] In an embodiment of the present invention, the at least two persons to be confirmed are at least two monitored persons whose relationship is to be confirmed. Specifically, when at least two monitored persons appear in the same captured image, the at least two monitored persons can be determined as at least two persons to be confirmed. The distance between the at least two persons to be confirmed in the captured image is detected to obtain the distance between the at least two persons to be confirmed, and it is determined whether the distance between the at least two persons to be confirmed is less than a preset value for the first time. If the distance between the at least two persons to be confirmed is less than the preset value for the first time, it indicates that the two persons to be confirmed have met for the first time in the target area. Then, the encounter situation between the at least two persons to be confirmed can be analyzed within a first preset time, thereby confirming the relationship between the at least two persons to be confirmed. The more times the at least two persons to be confirmed meet within the first preset time, the greater the probability that the at least two persons to be confirmed are in a relationship. The fewer times the at least two persons to be confirmed meet within the first preset time, the smaller the probability that the at least two persons to be confirmed are in a relationship.

[0063] The first preset time can be determined based on the attributes of the at least two persons to be confirmed and the average time it takes for the at least two persons to be confirmed to enter the target area when the distance between the at least two persons to be confirmed is first detected to be less than a preset value. The attributes of the at least two persons to be confirmed can be facial expressions. Specifically, the captured image can be input into a trained attribute recognition model to identify the facial expressions of the at least two persons to be confirmed in the captured image. After obtaining the facial expressions of the at least two persons to be confirmed, the first preset time is determined based on the facial expressions of the at least two persons to be confirmed. For example, when the facial expressions of the two persons to be confirmed are both happy, the first preset time can be set to 1 / 2 of the average time it takes for the at least two persons to be confirmed to enter the target area; when the facial expressions of the at least two persons to be confirmed are both indifferent, the first preset time can be set to the average time it takes for the at least two persons to be confirmed to enter the target area; and when the facial expressions of the at least two persons to be confirmed are both disgusted, the first preset time can be set to 3 / 2 of the average time it takes for the at least two persons to be confirmed to enter the target area. The emotional relationship between at least two persons to be determined is determined by using different facial expression attributes. For the determination of the traveling relationship between persons with a good emotional relationship, the first preset time can be set shorter. For the determination of the traveling relationship between persons with a bad emotional relationship, the first preset time can be set longer. In this way, it is considered that the probability of traveling together between persons with a good emotional relationship is greater than the probability of traveling together between persons with a bad emotional relationship.

[0064] In an embodiment of the present invention, considering that the target person and the accompanying persons may not enter the target area at the same time, the starting time of the accompanying detection is when the distance between at least two persons to be confirmed is first detected to be less than a preset value, which can more accurately determine the target person and the accompanying persons.

[0065] Optionally, in the target area, when it is detected for the first time that the distance between at least two persons to be confirmed is less than a preset value, in the step of confirming the traveling relationship between at least two persons to be confirmed within the first preset time, human body detection can be performed on the at least two persons to be confirmed in the target area to obtain human body detection results of the at least two persons to be confirmed; based on the human body detection results of the at least two persons to be confirmed, the distance between the at least two persons to be confirmed is calculated; when it is detected for the first time that the distance between at least two persons to be confirmed is less than a preset value, human body tracking is performed on the at least two persons to be confirmed within the first preset time to obtain human body tracking results of the at least two persons to be confirmed; based on the human body tracking results of the at least two persons to be confirmed, the distance between the at least two persons to be confirmed within the first preset time is calculated; and the traveling relationship between the at least two persons to be confirmed is confirmed based on the distance between the at least two persons to be confirmed within the first preset time.

[0066] In an embodiment of the present invention, when at least two monitored persons appear in the same captured image, the at least two monitored persons can be identified as at least two persons to be confirmed. Human body detection is performed on the captured image to obtain human body detection frames of the at least two persons to be confirmed. The human body detection frames can be represented by (x, y, w, h, u), where (x, y) represents the center point coordinates of the human body detection frame, w represents the width of the human body detection frame, h represents the height of the human body detection frame, and u represents the confidence level of the human body detection frame. The distance between the at least two persons to be confirmed can be calculated based on the center point coordinates of the human body detection frame.

[0067] In a possible embodiment, the ratio between the intersection area of ​​two human detection frames and the area corresponding to the human detection frame with the smaller area among the two human detection frames can be calculated. The closer the ratio is to 1, the smaller the distance between the two persons to be confirmed.

[0068] After first detecting that the distance between at least two persons to be confirmed is less than a preset value, the at least two persons to be confirmed can be tracked and captured by an image capture device set in the target area to obtain tracking images of the at least two persons to be confirmed. Based on the tracking images of the at least two persons to be confirmed within the first preset time, human bodies are tracked in the tracking images using an image tracking algorithm to obtain human body tracking results of the at least two persons to be confirmed. Based on the human body tracking results of the at least two persons to be confirmed, the number of times the distance between the at least two persons to be confirmed is less than a preset value within the first preset time is calculated. When the number of times the distance between the at least two persons to be confirmed is less than the preset value within the first preset time is greater than or equal to the preset number, it can be determined that there is a traveling relationship between the at least two persons to be confirmed; when the number of times the distance between the at least two persons to be confirmed is less than the preset value within the first preset time is less than the preset number, it can be determined that there is no traveling relationship between the at least two persons to be confirmed.

[0069] Optionally, in the step of determining the target person and the traveling person among the at least two persons to be confirmed, if it is confirmed that at least two persons to be confirmed have a traveling relationship, the person attributes corresponding to the at least two persons to be confirmed can be obtained respectively; based on the person attributes corresponding to the at least two persons to be confirmed, the target person and the traveling person can be determined among the at least two persons to be confirmed.

[0070] In an embodiment of the present invention, the personnel attributes corresponding to the at least two persons to be confirmed may be age group attributes, gender attributes, or position attributes. Specifically, the age group attributes may be divided into three age groups: the first age group, the second age group, and the third age group. The maximum age in the first age group is less than the minimum age in the second age group, and the maximum age in the second age group is less than the minimum age in the third age group. When the age group attributes corresponding to the at least two persons to be confirmed include multiple age group attributes, and the multiple age group attributes include the second age group attribute, the persons to be confirmed with the second age group attribute are confirmed as target persons, and the remaining persons to be confirmed are companions. When the age group attributes corresponding to the at least two persons to be confirmed include only one age group attribute, or the multiple age group attributes do not include the second age group attribute, the target person and companions may be determined based on the position attributes. For example, when determining the leading person based on the position attributes, the leading person is determined as the target person, and the companions are the persons behind the target person, or when determining the person in the middle position based on the position attributes, the person in the middle position is determined as the target person, and the companions are the persons on both sides of the target person. After it is determined that at least two persons to be confirmed have a traveling relationship, the captured images corresponding to the at least two persons to be confirmed may be input into a trained person attribute recognition model to obtain person attributes corresponding to the at least two persons to be confirmed.

[0071] Optionally, in the step of determining whether the target person and the accompanying person are lost based on the first trajectory and the second trajectory, the degree of overlap between the first trajectory and the second trajectory within the second preset time can be calculated; and based on the degree of overlap between the first trajectory and the second trajectory, it is determined whether the target person and the accompanying person are lost.

[0072] In an embodiment of the present invention, the starting time of the second preset time is the time when the distance between the target person and the traveling companions was last detected to be less than the preset value, and the ending time of the second preset time is the current time.

[0073] Specifically, a feature vector of the first trajectory and a feature vector of the second trajectory may be extracted, and the similarity between the feature vector of the first trajectory and the feature vector of the second trajectory is calculated as the overlap degree between the first trajectory and the second trajectory.

[0074] When the degree of overlap between the first and second trajectories is greater than or equal to the overlap threshold, it can be determined that the target person and the accompanying person are not lost. When the degree of overlap between the first and second trajectories is less than the overlap threshold, it can be determined that the target person and the accompanying person are lost.

[0075] Optionally, in the step of determining whether the target person and the accompanying persons are lost based on the degree of overlap between the first trajectory and the second trajectory, when the degree of overlap between the first trajectory and the second trajectory is greater than or equal to the overlap threshold, it can be determined that the target person and the accompanying persons are not lost; when the degree of overlap between the first trajectory and the second trajectory is less than the overlap threshold, the degree of disorder of the first trajectory and the second trajectory after separation is calculated; if the degree of disorder of the first trajectory or the second trajectory after separation is greater than the disorder threshold, it is determined that the target person and the accompanying persons are lost.

[0076] In this embodiment of the present invention, when the degree of overlap between the first and second trajectories is less than the overlap threshold, it indicates that the first and second trajectories have been separated for a long time. In this case, the degree of disorder of the first and second trajectories after separation can be used to determine whether the target person and the accompanying person separated consciously or unconsciously.

[0077] Specifically, after determining that the overlap between the first and second trajectories is less than the overlap threshold, the time and place of separation can be determined based on the first and second trajectories, the trajectory of the first trajectory after separation can be intercepted to obtain the third trajectory, and the trajectory of the second trajectory after separation can be intercepted to obtain the fourth trajectory. The degree of clutter of the third and fourth trajectories can be determined based on the number of stops and returns in the third and fourth trajectories. The greater the number of stops and returns, the greater the degree of clutter. When the degree of clutter of the third trajectory is greater than the clutter threshold, it can be said that the target person frequently stops to observe and frequently returns to search. Similarly, when the degree of clutter of the fourth trajectory is greater than the clutter threshold, it can be said that the companions frequently stop to observe and frequently return to confirm.

[0078] It should be noted that the companion monitoring method provided in the embodiment of the present invention can be applied to devices such as smart cameras, smart phones, computers, servers, etc. that can perform the companion monitoring method.

[0079] Optional, see Figure 2 , Figure 2 FIG. 1 is a schematic structural diagram of a companion monitoring device provided by an embodiment of the present invention. Figure 2 As shown, the device includes:

[0080] A first acquisition module 201 is configured to acquire a first file of the target person and a second file of the companion when the target person has a companion in the target area;

[0081] An analysis module 202 is configured to perform trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and to perform trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area;

[0082] The processing module 203 is used to determine whether the target person and the traveling companions are lost based on the first trajectory and the second trajectory.

[0083] Optionally, the device further includes:

[0084] A second acquisition module is used to acquire snapshot images of each monitored person in the target area;

[0085] The filing module is used to file the monitored personnel according to the captured images to obtain the files of each monitored person.

[0086] Optionally, the device further includes:

[0087] A first confirmation module is configured to confirm the traveling relationship between the at least two persons to be confirmed within a first preset time when the distance between the at least two persons to be confirmed is detected to be less than a preset value for the first time in the target area;

[0088] The second confirmation module is used to determine the target person and the traveling person from the at least two persons to be confirmed if it is confirmed that there is a traveling relationship between the at least two persons to be confirmed.

[0089] Optionally, the first confirmation module is also used to perform human body detection on at least two of the persons to be confirmed in the target area to obtain human body detection results of the at least two persons to be confirmed; calculate the distance between the at least two persons to be confirmed based on the human body detection results of the at least two persons to be confirmed; when it is first detected that the distance between the at least two persons to be confirmed is less than a preset value, perform human body tracking on the at least two persons to be confirmed within the first preset time to obtain human body tracking results of the at least two persons to be confirmed; calculate the distance between the at least two persons to be confirmed within the first preset time based on the human body tracking results of the at least two persons to be confirmed; and confirm the traveling relationship between the at least two persons to be confirmed based on the distance between the at least two persons to be confirmed within the first preset time.

[0090] Optionally, the second confirmation module is also used to obtain the personnel attributes corresponding to at least two persons to be confirmed respectively if it is confirmed that at least two persons to be confirmed have a peer relationship; and determine the target person and the peer person among at least two persons to be confirmed based on the personnel attributes corresponding to at least two persons to be confirmed.

[0091] Optionally, the processing module 203 is further configured to calculate a degree of overlap between the first trajectory and the second trajectory within a second preset time; and determine whether the target person and the accompanying person are lost based on the degree of overlap between the first trajectory and the second trajectory.

[0092] Optionally, the processing module 203 is further used to determine that the target person and the accompanying person are not lost when the degree of overlap between the first trajectory and the second trajectory is greater than or equal to a degree of overlap threshold; when the degree of overlap between the first trajectory and the second trajectory is less than a degree of overlap threshold, calculate the degree of disorder of the first trajectory and the second trajectory after separation; if the degree of disorder of the first trajectory or the second trajectory after separation is greater than a degree of disorder threshold, determine that the target person and the accompanying person are lost.

[0093] It should be noted that the companion monitoring device provided in the embodiment of the present invention can be applied to devices such as smart cameras, smart phones, computers, servers, etc. that can perform the companion monitoring method.

[0094] The companion monitoring device provided in the embodiment of the present invention can implement each process implemented by the companion monitoring method in the above method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0095] See also Figure 3 , Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a companion monitoring method stored in the memory 302 and executable on the processor 301, wherein:

[0096] The processor 301 is configured to call the computer program stored in the memory 302 and execute the following steps:

[0097] When the target person has a companion in the target area, obtaining a first file of the target person and a second file of the companion;

[0098] Performing trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and performing trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area;

[0099] Based on the first trajectory and the second trajectory, determine whether the target person and the traveling companions are lost.

[0100] Optionally, when the target person has a companion in the target area, before obtaining the first profile of the target person and the second profile of the companion, the method executed by the processor 301 further includes:

[0101] Acquire snapshot images of each monitored person in the target area;

[0102] Files are created for the monitoring personnel based on the captured images to obtain files of each monitored person.

[0103] Optionally, when the target person has a companion in the target area, before obtaining the first profile of the target person and the second profile of the companion, the method executed by the processor 301 further includes:

[0104] When it is detected for the first time in the target area that the distance between at least two persons to be confirmed is less than a preset value, the traveling relationship between the at least two persons to be confirmed is confirmed within a first preset time;

[0105] If it is confirmed that at least two of the persons to be confirmed have a traveling companion relationship, the target person and the traveling companion are determined from the at least two persons to be confirmed.

[0106] Optionally, the processor 301 executes the step of confirming the traveling relationship between the at least two persons to be confirmed within a first preset time when it is first detected in the target area that the distance between the at least two persons to be confirmed is less than a preset value, including:

[0107] In the target area, performing human body detection on at least two persons to be confirmed to obtain human body detection results of the at least two persons to be confirmed;

[0108] Calculating the distance between the at least two persons to be confirmed based on the human body detection results of the at least two persons to be confirmed;

[0109] When it is detected for the first time that the distance between at least two persons to be confirmed is less than a preset value, body tracking is performed on the at least two persons to be confirmed within the first preset time to obtain body tracking results of the at least two persons to be confirmed;

[0110] Calculating the distance between the at least two persons to be confirmed within the first preset time based on the body tracking results of the at least two persons to be confirmed;

[0111] The traveling relationship between the at least two persons to be confirmed is confirmed based on the distance between the at least two persons to be confirmed within the first preset time.

[0112] Optionally, if it is confirmed that at least two persons to be confirmed have a traveling relationship, the processor 301 determines the target person and the traveling person from the at least two persons to be confirmed, including:

[0113] If it is confirmed that at least two of the persons to be confirmed have a peer relationship, obtaining the person attributes corresponding to the at least two persons to be confirmed respectively;

[0114] The target person and the accompanying person are determined from the at least two persons to be confirmed according to the person attributes corresponding to the at least two persons to be confirmed.

[0115] Optionally, the processor 301 determines whether the target person and the traveling companion are lost based on the first trajectory and the second trajectory, including:

[0116] Calculating the degree of overlap between the first trajectory and the second trajectory within a second preset time;

[0117] Whether the target person and the traveling companion are lost is determined based on the degree of overlap between the first trajectory and the second trajectory.

[0118] Optionally, the determining, by the processor 301, of whether the target person and the traveling companion are lost based on the degree of overlap between the first trajectory and the second trajectory includes:

[0119] When the degree of overlap between the first trajectory and the second trajectory is greater than or equal to a threshold value of overlap, it is determined that the target person and the traveling companion are not lost;

[0120] When the overlap between the first track and the second track is less than an overlap threshold, calculating the degree of disorder of the first track and the second track after separation;

[0121] If the disorder degree of the first trajectory or the second trajectory after separation is greater than the disorder degree threshold, it is determined that the target person and the traveling companion are lost.

[0122] The electronic device provided in the embodiment of the present invention can implement each process of the companion monitoring method in the above method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0123] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the peer monitoring method provided by the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0124] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (RON), or a random access memory (RAN).

[0125] The above disclosure is merely a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for monitoring fellow passengers, characterized in that: Used for the missing companion monitoring, including the following steps: When it is detected for the first time in a target area that the distance between at least two persons to be confirmed is less than a preset value, the traveling relationship between the at least two persons to be confirmed is confirmed within a first preset time; specifically, human body detection is performed on the at least two persons to be confirmed in the target area to obtain human body detection results of the at least two persons to be confirmed; based on the human body detection results of the at least two persons to be confirmed, the distance between the at least two persons to be confirmed is calculated; when it is detected for the first time that the distance between at least two persons to be confirmed is less than a preset value, human body tracking is performed on the at least two persons to be confirmed within the first preset time to obtain human body tracking results of the at least two persons to be confirmed; based on the human body tracking results of the at least two persons to be confirmed, the distance between the at least two persons to be confirmed within the first preset time is calculated; and the traveling relationship between the at least two persons to be confirmed is confirmed based on the distance between the at least two persons to be confirmed within the first preset time; If it is confirmed that at least two of the persons to be confirmed have a traveling relationship, then the target person and the traveling relationship are determined from the at least two persons to be confirmed; When the target person has a companion in the target area, obtaining a first file of the target person and a second file of the companion; Performing trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and performing trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area; Based on the first trajectory and the second trajectory, determine whether the target person and the traveling companions are lost.

2. The method for monitoring fellow passengers according to claim 1, wherein: When the target person has a companion in the target area, before obtaining the first file of the target person and the second file of the companion, the method further includes: Acquire snapshot images of each monitored person in the target area; Files are created for the monitoring personnel based on the captured images to obtain files of each monitored person.

3. The method for monitoring fellow passengers according to claim 1, wherein: If it is confirmed that at least two of the persons to be confirmed have a traveling relationship, determining the target person and the traveling person from the at least two persons to be confirmed includes: If it is confirmed that at least two of the persons to be confirmed have a peer relationship, obtaining the person attributes corresponding to the at least two persons to be confirmed respectively; The target person and the accompanying person are determined from the at least two persons to be confirmed according to the person attributes corresponding to the at least two persons to be confirmed.

4. The method for monitoring fellow passengers according to claim 3, wherein: The determining, based on the first trajectory and the second trajectory, whether the target person and the traveling companion are lost includes: Calculating the degree of overlap between the first trajectory and the second trajectory within a second preset time; Whether the target person and the traveling companion are lost is determined based on the degree of overlap between the first trajectory and the second trajectory.

5. The method for monitoring fellow passengers according to claim 4, wherein: The determining, based on the degree of overlap between the first trajectory and the second trajectory, whether the target person and the traveling companion are lost includes: When the degree of overlap between the first trajectory and the second trajectory is greater than or equal to a threshold value of overlap, it is determined that the target person and the traveling companion are not lost; When the overlap between the first track and the second track is less than an overlap threshold, calculating the degree of disorder of the first track and the second track after separation; If the disorder degree of the first trajectory or the second trajectory after separation is greater than the disorder degree threshold, it is determined that the target person and the traveling companion are lost.

6. A companion monitoring device, characterized in that: The device comprises: A first confirmation module is configured to, when it is first detected in a target area that the distance between at least two persons to be confirmed is less than a preset value, confirm the traveling relationship between the at least two persons to be confirmed within a first preset time; specifically, perform body detection on the at least two persons to be confirmed in the target area to obtain body detection results of the at least two persons to be confirmed; calculate the distance between the at least two persons to be confirmed based on the body detection results of the at least two persons to be confirmed; when it is first detected that the distance between at least two persons to be confirmed is less than a preset value, perform body tracking on the at least two persons to be confirmed within the first preset time to obtain body tracking results of the at least two persons to be confirmed; calculate the distance between the at least two persons to be confirmed within the first preset time based on the body tracking results of the at least two persons to be confirmed; and confirm the traveling relationship between the at least two persons to be confirmed based on the distance between the at least two persons to be confirmed within the first preset time; A second confirmation module is configured to determine a target person and the traveling person from among the at least two persons to be confirmed if it is confirmed that the at least two persons to be confirmed have a traveling relationship; A first acquisition module is used to acquire a first file of the target person and a second file of the companion when the target person has a companion in the target area; an analysis module, configured to perform trajectory analysis on the first file to obtain a first trajectory of the target person in the target area, and to perform trajectory analysis on the second file to obtain a second trajectory of the traveling companion in the target area; A processing module is used to determine whether the target person and the accompanying person are lost based on the first trajectory and the second trajectory.

7. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the companion monitoring method as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the companion monitoring method according to any one of claims 1 to 5.

Images