Door positioning method and monitoring equipment

Abstract

The invention discloses a door positioning method and monitoring equipment. The door positioning method comprises the following steps: acquiring video data of a monitoring area in a preset time period; acquiring a behavior track of the target object in the monitoring area from the video data; and determining a target area corresponding to the position of the door in the monitoring area according to the behavior track. According to the technical scheme, a user does not need to draw a door, the method is friendly to the user, and the target area corresponding to the position of the door can be determined relatively accurately.

Description

Technical Field

[0001] This application relates to the technical field of video surveillance, and particularly relates to a door positioning method and a surveillance device. Background Art

[0002] In the field of video surveillance, the position of a door is important information and an important part of functions such as determining whether a family member is home / away and detecting the approach of a stranger.

[0003] In related technologies, a simple door positioning method is to invite users to participate and draw the position of the door in the surveillance area. This method usually has the problem of inaccurate drawing of the door position and is not user-friendly. For the elderly user group, they may not be able to complete this operation. Summary of the Invention

[0004] On the one hand, this application provides a door positioning method applied to a surveillance device. The method includes: obtaining video data of a surveillance area within a preset time period; obtaining the behavior trajectory of a target object within the surveillance area from the video data; and determining a target area corresponding to the position of the door within the surveillance area according to the behavior trajectory.

[0005] In some embodiments, determining a target area corresponding to the position of the door within the surveillance area according to the behavior trajectory includes: determining the target area according to the endpoints of the behavior trajectory, where the endpoints include the start point and / or the end point.

[0006] In some embodiments, the surveillance area includes multiple sub-areas; determining the target area according to the endpoints of the behavior trajectory includes: counting the number of endpoints of the behavior trajectory within the sub-area as the heat value of the sub-area; and determining the target area according to the heat value of the sub-area.

[0007] In some embodiments, determining the target area according to the heat value of the sub-area includes: taking the sub-area with the largest heat value as the target area.

[0008] In some embodiments, the target object includes a valid object and an interfering object; determining the target area according to the endpoints of the behavior trajectory includes: screening out the behavior trajectories of the valid objects from the behavior trajectories; and determining the target area according to the endpoints of the behavior trajectories of the valid objects.

[0009] In some embodiments, the behavior trajectory includes invalid trajectories; determining the target area according to the endpoints of the behavior trajectory includes: excluding the invalid trajectories from the behavior trajectories; and determining the target area according to the endpoints of the remaining behavior trajectories.

[0010] In some embodiments, determining a target area according to the heat value of a sub-area includes: sequentially sending the information of the sub-areas to a display device for display in descending order of the heat value, so that a user can select the sub-area where the target area is located until an indication message is received. The indication message is generated and sent by the display device based on the user's interaction operation and is used to indicate the sub-area selected by the user.

[0011] In some embodiments, each behavior track corresponds to a video segment in video data; the information of the sub-area includes a video segment corresponding to a behavior track whose starting point or ending point is within the sub-area, so that a user can select a video segment involving entering or leaving the door; the indication message is used to indicate the video segment selected by the user.

[0012] In the step of sequentially sending the information of the sub-areas to the display device for display in descending order of the heat value, the information of multiple sub-areas is sent to the display device each time, so that the display device can display the information of multiple sub-areas simultaneously; determining the target area according to the heat value of the sub-area further includes: determining whether the number of sub-areas indicated by the indication message is greater than one; in response to the number of indicated sub-areas being greater than one, taking the sub-area with the largest heat value as the target area.

[0013] In some embodiments, sequentially sending the information of the sub-areas to the display device for display in descending order of the heat value includes: sequentially sending the information of non-adjacent sub-areas to the display device for display in descending order of the heat value, and the number of sub-areas between non-adjacent sub-areas is greater than a preset value.

[0014] In some embodiments, determining the target area according to the endpoints of the behavior track includes: performing clustering analysis on the endpoints of the behavior track to obtain a clustering center, and taking the clustering center as the target area.

[0015] In some embodiments, determining the target area corresponding to the position of a door in a monitoring area according to the behavior track includes: inputting the behavior track into a trained model so that the model can output the target area.

[0016] In some embodiments, determining the target area corresponding to the position of a door in a monitoring area according to the behavior track includes: inputting the behavior track into a trained model so that the model can output the behavior track involving entering or leaving the door; determining the target area according to the starting point or ending point of the behavior track involving entering or leaving the door.

[0017] In some embodiments, after determining a target area corresponding to the position of the door within the monitoring area according to the behavior trajectory, the method further includes: determining whether the number of target areas is greater than one; in response to the number of target areas being greater than one, sequentially sending the information of the target areas to a display device for display according to a preset rule, so that the user can select the real target area until an indication message is received, where the indication message is generated and sent by the display device based on the user's interaction operation and is used to indicate the target area selected by the user.

[0018] In some embodiments, each behavior trajectory corresponds to a video segment in the video data; the information of the target area includes a video segment corresponding to a behavior trajectory whose starting point or ending point is within the target area, so that the user can select a video segment involving entering or exiting the door; the indication message is used to indicate the video segment selected by the user.

[0019] On the other hand, the present application provides a monitoring device. The monitoring device includes a processor and a memory, where a computer program is stored in the memory, and the processor is configured to execute the computer program to implement the door positioning method as described above.

[0020] In the solution of the present application, the target area corresponding to the position of the door is determined from the monitoring area according to multiple behavior trajectories of the target object, without the need for the user to draw the door, which is user-friendly and can relatively accurately determine the target area corresponding to the position of the door. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts, where:

[0022] Figure 1 is a flowchart of an embodiment of the door positioning method of the present application;

[0023] Figure 2 is a flowchart of another embodiment of the door positioning method of the present application;

[0024] Figure 3 is a flowchart of another embodiment of the door positioning method of the present application;

[0025] Figure 4 is a flowchart of another embodiment of the door positioning method of the present application;

[0026] Figure 5 is a schematic diagram of an embodiment of adjacent sub-areas of the present application;

[0027] Figure 6 It is a schematic diagram of another embodiment of adjacent sub-regions of the present application;

[0028] Figure 7 It is a schematic flowchart of another embodiment of the door positioning method of the present application;

[0029] Figure 8 It is a schematic flowchart of another embodiment of the door positioning method of the present application;

[0030] Figure 9 It is a schematic flowchart of another embodiment of the door positioning method of the present application;

[0031] Figure 10 It is a schematic structural diagram of an embodiment of the monitoring device of the present application. Specific embodiments

[0032] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be specifically noted that the following embodiments are only used to illustrate the present application, but do not limit the scope of the present application. Similarly, the following embodiments are only partial embodiments of the present application rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0033] Referring to "embodiments" in the present application means that the specific features, structures or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase appears at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0034] The terms "first", "second", and "third" in this application are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. In the embodiments of this application, all directional indications (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will change accordingly. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0035] On the one hand, this application provides a door positioning method, which is applied to a monitoring device. In this embodiment, the monitoring system may include a camera and a control center platform. The control center platform is used to receive and process the video data acquired by the camera. At this time, the monitoring device may refer to the control center platform, that is, the control center platform executes the door positioning method described in this application.

[0036] In some embodiments, the monitoring system may include a camera and a cloud server. The cloud server is used to receive and process the video data acquired by the camera. At this time, the monitoring device may refer to the cloud server, that is, the cloud server executes the door positioning method described in this application.

[0037] In some embodiments, the camera itself may have a certain data processing ability and be able to process video data. At this time, the monitoring device may refer to the camera, that is, the camera executes the door positioning method described in this application. It should be noted that the above are only several examples of the monitoring device and do not constitute a limitation to this application.

[0038] As Figure 1 shown, Figure 1 is a schematic flowchart of an embodiment of the door positioning method of this application. The door positioning method may include the following steps:

[0039] S110: Obtain video data of the monitoring area within a preset time period.

[0040] Each camera can correspond to a three-dimensional monitoring area. For a movable camera, its monitoring area can refer to the maximum area that the camera can cover. For example, each azimuth of the movable camera corresponds to an area, and the monitoring area of the camera can refer to the sum of the areas corresponding to the camera in each azimuth.

[0041] For example, the preset time period can be one week, and this application does not limit this. Those skilled in the art can select according to actual needs. The camera can obtain the video data of the monitoring area within one week and send the video data to the monitoring device.

[0042] S120: Obtain the behavior trajectory of the target object in the monitoring area from the video data.

[0043] In this embodiment, the target object can be a person. In some embodiments, the target object can also be other moving objects, and this application does not limit this. Those skilled in the art can select according to actual needs.

[0044] The monitoring device can identify multiple video segments of the target object's behavior activities in the monitoring area from the video data. Among them, each video segment corresponds to a behavior trajectory of the target object in the monitoring area. Thus, the monitoring device can obtain multiple behavior trajectories of the target object in the monitoring area from the video data.

[0045] S130: Determine the target area corresponding to the position of the door in the monitoring area according to the behavior trajectory.

[0046] Among them, the target area can be the area where the physical door is located, or it can refer to the necessary area for the user to enter or exit the door. This application does not limit this. Those skilled in the art can select according to actual needs.

[0047] In the solution of this embodiment, the target area corresponding to the position of the door is determined from the monitoring area according to the multiple behavior trajectories of the target object, without the need for the user to draw the door, which is user-friendly and can relatively accurately determine the target area corresponding to the position of the door.

[0048] In the related art, the position of the door can also be detected through image recognition technology. However, this method requires a large amount of computing power and can only be used to detect physical doors. When the camera is installed outdoors, there are often no physical doors in the monitoring area, making the image recognition technology ineffective. In the solution of this embodiment, the target area corresponding to the position of the door is determined from the monitoring area according to multiple behavior trajectories of the target object. This can not only be used to determine the position of the physical door, but when there is no physical door in the monitoring area, the target area can refer to the necessary area for the user to enter or exit the door. Therefore, the method described in this embodiment can also be used to determine the necessary area for the user to enter or exit the door, and the required computing power is relatively small.

[0049] When the user adjusts the installation position of the camera, the monitoring area of the camera may change. At this time, by executing the above steps S110 - S130 again, the target area corresponding to the position of the door can be determined relatively accurately, without the user having to draw the door, which is user-friendly.

[0050] When the camera is installed outside the door, the end point of the behavior trajectory has a relatively high possibility of being related to entering the door, and the starting point of the behavior trajectory has a relatively high possibility of being related to going out; when the camera is installed inside the door, the starting point of the behavior trajectory has a relatively high possibility of being related to entering the door, and the end point of the behavior trajectory has a relatively high possibility of being related to going out.

[0051] Considering that the starting point or end point of the behavior trajectory of the target object has a relatively high possibility of being related to entering or going out the door, therefore, the target area can be determined according to the end points of the behavior trajectory. The end points of the behavior trajectory include the starting point and / or the end point. That is to say, the end point of the behavior trajectory can refer to the end point of the behavior trajectory, can refer to the starting point of the behavior trajectory, or can refer to the starting point and the end point of the behavior trajectory.

[0052] As Figure 2 shown, Figure 2 is a schematic flowchart of an embodiment of the door positioning method of this application. The door positioning method may include the following steps:

[0053] S210: Obtain the video data of the monitoring area within a preset time period. The monitoring area includes multiple sub - areas.

[0054] For example, the monitoring area can be evenly divided into 10×10 sub - areas. This application does not limit this, and those skilled in the art can choose according to actual needs.

[0055] Regarding the remaining details of this step, they can be the same as or similar to S110, and will not be elaborated here.

[0056] S220: Obtain the behavior trajectory of the target object in the monitoring area from the video data.

[0057] For the remaining details of this step, they can be the same as or similar to those in S120, and will not be elaborated here.

[0058] S230: Count the number of endpoints of the behavior trajectories within the sub-region as the heat value of this sub-region.

[0059] In this embodiment, the monitoring device can count the number of endpoints of the behavior trajectories within each sub-region as the heat value of this sub-region.

[0060] In some embodiments, the monitoring device can count the number of starting points of the behavior trajectories within each sub-region as the heat value of this sub-region, or can also count the total number of starting points and endpoints of the behavior trajectories within each sub-region as the heat value of this sub-region. This application does not limit this, and those skilled in the art can make selections according to actual needs.

[0061] S240: Determine the target area according to the heat value of the sub-region.

[0062] For example, the monitoring area can be mapped onto a two-dimensional monitoring screen. The monitoring screen is evenly divided into multiple grids, and each sub-region corresponds to a grid. Count the heat values of the sub-regions corresponding to each grid, and use different colors to represent different magnitudes of heat values, then a heat map can be obtained. This heat map can reflect the activity of the target object within the monitoring area. For instance, the change of color from cold tones (such as blue or green) to warm tones (such as red or yellow) can indicate the increase of the heat value from low to high.

[0063] After the camera has been installed for a period of time, the monitoring device can automatically obtain multiple behavior trajectories of the target object within the monitoring area. For example, after the camera has been installed for one week, the monitoring device can obtain all the behavior trajectories of the target object within one week for drawing a heat map.

[0064] In this embodiment, since the heat value counts the number of endpoints of the behavior trajectories within each sub-region, and the camera is installed inside the door, considering that the endpoints of the behavior trajectories are more likely to be related to the possibility of entering the door, the sub-region with the highest heat value is most likely the target area corresponding to the position of the door. Therefore, the sub-region with the highest heat value can be used as the target area.

[0065] In addition, through a large number of experiments, the inventors of the present application found that when the monitoring device and the door positioning method described in the present application are applied to ordinary household users and the camera is installed outside the door, using the number of endpoints in each sub-region as the heat value of the sub-region is beneficial to improving the accuracy of the door positioning method compared with the solution of using the number of starting points in each sub-region as the heat value of the sub-region and the solution of using the total number of starting points and endpoints in each sub-region as the heat value of the sub-region.

[0066] When the monitoring device and the door positioning method described in the present application are applied to ordinary household users and the camera is installed outside the door, the door of the user's own home may appear in the monitoring area, and the door of the neighbor's home may also appear. The target objects may include the user and the user's family members, and may also include neighbors and strangers. In order to avoid misjudgment of the target area, the present application further provides another door positioning method.

[0067] As Figure 3 shown, Figure 3 FIG. is a schematic flow chart of another embodiment of the door positioning method of the present application. The door positioning method may include the following steps:

[0068] S310: Obtain video data of the monitoring area within a preset time period. The monitoring area includes a plurality of sub-regions.

[0069] Regarding the remaining details of this step, they may be the same as or similar to S210, and will not be elaborated here.

[0070] S320: Obtain the behavior trajectories of the target objects in the monitoring area from the video data. The target objects include valid objects and interfering objects.

[0071] For example, when the monitoring device and the door positioning method described in the present application are applied to ordinary household users, the valid objects may include the user and the user's family members. The interfering objects may refer to neighbors and strangers.

[0072] Regarding the remaining details of this step, they may be the same as or similar to S220, and will not be elaborated here.

[0073] S330: Screen out the behavior trajectories of the valid objects from the behavior trajectories.

[0074] For example, when the valid objects include the user and the user's family members and the interfering objects refer to neighbors and strangers, the behavior trajectories of the valid objects can be screened out from multiple behavior trajectories using a face recognition algorithm or a human form recognition algorithm. Regarding the specific face recognition algorithm or human form recognition algorithm, the present application does not make any restrictions, and those skilled in the art can select according to actual needs.

[0075] S340: Determine a target area corresponding to the position of the door within the monitoring area based on the endpoints of the behavior trajectories of valid objects.

[0076] Specifically, the monitoring device can count the number of endpoints of the behavior trajectories of valid objects within the sub-area as the heat value of the sub-area, and determine the target area based on the heat value of the sub-area. The specific details can be the same as or similar to those of S230 and S240, and will not be elaborated here.

[0077] In the related art, when detecting the position of the door through image recognition technology, if there are multiple doors within the monitoring area of the camera, there is a high probability of misjudging the position of the door. In the solution of this embodiment, the behavior trajectories of valid objects are screened out from multiple behavior trajectories, and the target area corresponding to the position of the door within the monitoring area is determined based on the endpoints of the behavior trajectories of valid objects, so as to avoid the interference of the behavior trajectories of interfering objects and more accurately identify the target area, and to a certain extent avoid misjudgment of the target area.

[0078] It should be noted that the above-described scenario of ordinary household users with the camera installed at a position outside the door is only for descriptive purposes. The solution of this embodiment can also be used in other living or working scenarios. This application does not limit this, and those skilled in the art can choose according to actual needs.

[0079] Among the behavior trajectories of valid objects, some behavior trajectories may be generated by housework or wandering. These trajectories have nothing to do with entering or leaving the door and belong to invalid trajectories. Moreover, the number is relatively large, which may cause certain interference to the determination of the target area and lead to misjudgment of the target area. In order to more accurately determine the target area, in some embodiments, S340 can be implemented through the following steps it includes:

[0080] S341: Exclude invalid trajectories from the behavior trajectories of valid objects.

[0081] Specifically, use a behavior recognition model to identify invalid trajectories from multiple behavior trajectories and exclude them. Regarding the specific behavior recognition model, this application does not limit it, and those skilled in the art can choose according to actual needs.

[0082] S342: Determine the target area based on the endpoints of the remaining behavior trajectories of valid objects.

[0083] Specifically, the remaining behavior trajectories of valid objects can be called valid trajectories. The monitoring device can count the number of endpoints of the valid trajectories within the sub-area as the heat value of the sub-area, and determine the target area based on the heat value of the sub-area. The specific details can be the same as or similar to those of S230 and S240, and will not be elaborated here.

[0084] By excluding invalid trajectories from multiple behavior trajectories of valid objects and determining the target area according to the endpoints of the remaining behavior trajectories of valid objects, the interference of invalid trajectories can be avoided, the target area can be identified more accurately, and the misjudgment of the target area can be avoided to a certain extent.

[0085] like Figure 4 As shown, Figure 4 This is a flow chart of another embodiment of the door positioning method of the present application. In order to avoid misjudgment of the target area and determine the target area more accurately, the present application also provides another door positioning method assisted by user screening. Specifically, the door positioning method may include the following steps:

[0086] S410: Obtain video data of a monitoring area within a preset time period, where the monitoring area includes multiple sub-areas.

[0087] The rest of the details of this step may be the same or similar to those of S210 and will not be described again here.

[0088] S420: Obtaining a behavior trajectory of the target object in the monitoring area from the video data.

[0089] The rest of the details of this step may be the same or similar to those of S220 and will not be described again here.

[0090] S430: Counting the number of endpoints of the behavior trajectory in the sub-region as the thermal value of the sub-region.

[0091] The rest of the details of this step may be the same or similar to those of S230 and will not be described again here.

[0092] S440: Send the sub-area information to the display device for display in order of thermal value from large to small, so that the user can select the sub-area where the target area is located, until the indication information is received. The indication information is generated and sent by the display device based on the user's interactive operation, and is used to indicate the sub-area selected by the user.

[0093] Specifically, the information of non-adjacent sub-regions can be sent to the display device for display in order of thermal value from large to small, and the number of sub-regions between non-adjacent sub-regions is greater than a preset value, so as to screen out the sub-region where the target region is located as soon as possible.

[0094] For example, the preset value may be 0, in which case the number of sub-regions spaced between adjacent sub-regions is 0. Figure 5 As shown, for Figure 5 For sub-region A in the diagram, sub-region B is adjacent to sub-region A, and the number of sub-regions separated from sub-region A by the remaining sub-regions is greater than 0, and they are not adjacent to sub-region A.

[0095] For another example, the preset value can be 1. In this case, the number of sub-regions between adjacent sub-regions is less than or equal to 1. As shown in Figure 6 , for the sub-region A in Figure 6 , sub-region B is adjacent to sub-region A, and the number of sub-regions between the remaining sub-regions and sub-region A is greater than 1, so they are not adjacent to sub-region A.

[0096] In this embodiment, when sending the information of the sub-regions to the display device for display in the order of decreasing heat value, multiple sub-regions' information can be sent to the display device each time, so that the display device can display the information of multiple sub-regions simultaneously, facilitating the user to quickly screen out the sub-region where the target region is located.

[0097] For example, the monitoring device can send the information of four sub-regions to the display device each time. These four sub-regions are not adjacent to each other, so that the display device can display the information of the four sub-regions in the form of a four-grid. In some embodiments, the monitoring device can send the information of nine sub-regions to the display device each time. These nine sub-regions are not adjacent to each other, so that the display device can display the information of the nine sub-regions in the form of a nine-grid.

[0098] As mentioned above, each row of trajectories corresponds to a video segment in the video data. In this embodiment, the monitoring device counts the number of endpoints of the behavior trajectories in each sub-region as the heat value of the sub-region, and the information of the sub-region can refer to a video segment corresponding to a behavior trajectory whose endpoint is in the sub-region.

[0099] For example, the monitoring device can sort the heat values in descending order, first select the four sub-regions with the top four heat values in the sorting, and judge whether there are adjacent sub-regions among them. If not, send the information of these four sub-regions to the display device. The information of each sub-region refers to a video segment corresponding to a behavior trajectory whose endpoint is in the sub-region. That is to say, the monitoring device sends four video segments to the display device.

[0100] Among the four sub-regions with the top four heat values in the sorting, if the second and third sub-regions in the sorting are adjacent to each other, remove the one with the smaller heat value among these two adjacent sub-regions, that is, remove the sub-region ranked third, and add the sub-region ranked fifth. If the four sub-regions ranked first, second, fourth, and fifth are not adjacent to each other, send the information of the four sub-regions ranked first, second, fourth, and fifth to the display device. The information of each sub-region refers to a video segment corresponding to a behavior trajectory whose endpoint is in the sub-region. That is to say, the monitoring device sends four video segments to the display device.

[0101] The display device can receive four video clips from the monitoring device and display these four video clips. For example, the display device can be a mobile phone, which has a display screen and can display the four received video clips in a four-grid format. If there is a video clip related to entering or leaving the door among the four displayed video clips, the user can perform an interactive operation on the display device to select the video frequency band related to entering or leaving the door. The display device can then generate indication information for indicating the video frequency band selected by the user based on the user's interactive operation and send it to the monitoring device.

[0102] In this embodiment, the monitoring device counts the number of endpoints of the behavior trajectories in each sub-region as the heat value of that sub-region. At this time, if the camera is installed outside the door, the endpoints of the behavior trajectories related to entering the door are usually closely related to the target area, and the user can select the video clip related to entering the door through interaction with the display device. If the camera is installed inside the door, the endpoints of the behavior trajectories related to leaving the door are usually closely related to the target area, and the user can select the video clip related to leaving the door through interaction with the display device. This application does not limit this, and those skilled in the art can make selections according to actual needs.

[0103] If there is no video clip related to entering the door among the four displayed video clips, the monitoring device can send information about the next four non-adjacent sub-regions with larger heat values to the display device. The information of each sub-region refers to a video clip corresponding to a behavior trajectory whose endpoint is in that sub-region, until the monitoring device receives the indication information for indicating the video frequency band selected by the user.

[0104] After receiving the indication information, the monitoring device can determine the sub-region selected by the user according to the video clip indicated by the indication information.

[0105] In some embodiments, the monitoring device can also count the number of starting points of the behavior trajectories in each sub-region as the heat value of that sub-region, and the information of the sub-region can refer to a video clip corresponding to a behavior trajectory whose starting point is in that sub-region. At this time, if the camera is installed outside the door, the starting points of the behavior trajectories related to leaving the door are usually closely related to the target area, and the user can select the video clip related to leaving the door through interaction with the display device; if the camera is installed inside the door, the starting points of the behavior trajectories related to entering the door are usually closely related to the target area, and the user can select the video clip related to entering the door through interaction with the display device. This application does not limit this, and those skilled in the art can make selections according to actual needs.

[0106] In some embodiments, the monitoring device may also count the total number of starting points and ending points of the behavior trajectories within each sub-region as the heat value of the sub-region. The information of the sub-region may refer to a video clip corresponding to a behavior trajectory whose starting point or ending point is within the sub-region. This application does not limit this, and those skilled in the art can make selections according to the actual situation.

[0107] As mentioned above, since the monitoring device can send the information of multiple sub-regions to the display device each time, so that the display device can display the information of multiple sub-regions simultaneously, the sub-region where the target region selected by the user is located may be one or more. At this time, in order to accurately identify the target region, this door positioning method may further include the following steps performed after S430:

[0108] S450: Determine whether the number of sub-regions indicated by the indication information is greater than one.

[0109] If the number of sub-regions indicated by the indication information is one, the monitoring device may directly use this sub-region as the target region.

[0110] S460: In response to the number of indicated sub-regions being greater than one, use the sub-region with the largest heat value as the target region.

[0111] If the number of sub-regions indicated by the indication information is multiple, the monitoring device may select the sub-region with the highest heat value from them as the target region.

[0112] In the solution of this embodiment, the information of the sub-regions is sent to the display device for display in order from largest to smallest heat value, so that the user can select the sub-region where the target region is located, thereby being able to accurately identify the target region and avoid misjudgment of the target region.

[0113] Figures 2 to 4 The solutions shown above all divide the monitoring area into multiple sub-regions on average, count the number of endpoints of the behavior trajectories within each sub-region as the heat value of the sub-region, and determine the target region according to the heat value. In addition, it is also possible to perform clustering analysis on the endpoints of the behavior trajectories to obtain the clustering center, and use the clustering center as the target region corresponding to the position of the door.

[0114] As Figure 7 shown, this application also provides another door positioning method, which specifically may include:

[0115] S510: Obtain the video data of the monitoring area within a preset time period.

[0116] Regarding the remaining details of this step, they may be the same as or similar to S110, and will not be elaborated here.

[0117] S520: Obtain the behavior trajectory of the target object within the monitoring area from the video data.

[0118] For the remaining details of this step, they can be the same as or similar to S120, and will not be elaborated here.

[0119] S530: Perform clustering analysis on the endpoints of the behavior trajectory to obtain the clustering centers, and use the clustering centers as the target areas.

[0120] In this embodiment, the monitoring device can perform clustering analysis on the endpoints of the behavior trajectory to obtain the clustering centers, and use the clustering centers as the target areas.

[0121] In some embodiments, the monitoring device can perform clustering analysis on the starting points of the behavior trajectory to obtain the clustering centers, and use the clustering centers as the target areas. It can also perform clustering analysis on the starting points and endpoints of the behavior trajectory to obtain the clustering centers, and use the clustering centers as the target areas. This application does not limit this, and those skilled in the art can make selections according to actual needs.

[0122] This application does not limit the specific algorithm for clustering analysis, and those skilled in the art can make selections according to actual needs.

[0123] The number of clustering centers may be one or multiple. Therefore, in some embodiments, this door positioning method may further include the following steps:

[0124] S540: Determine whether the number of target areas is greater than one.

[0125] When the number of clustering centers is one, that is to say, there is only one possible target area. At this time, this clustering center can be directly used as the real target area. When the number of clustering centers is multiple, that is to say, there are multiple possible target areas. At this time, the user can assist in screening out the real target area.

[0126] S550: In response to the number of target areas being greater than one, sequentially send the information of the target areas to the display device for display according to a preset rule, so that the user can select the target area corresponding to the real target area until an indication message is received. The indication message is generated and sent by the display device based on the user's interaction operation, and is used to indicate the target area selected by the user.

[0127] As described above, in this embodiment, the monitoring device can perform clustering analysis on the endpoints of the behavior trajectory to obtain the clustering centers, and use the clustering centers as the target areas. Therefore, the information of the target areas can be sequentially sent to the display device for display in descending order of the number of endpoints of the behavior trajectories in the target areas, so as to quickly screen out the real target area.

[0128] Among them, information of multiple target areas can be sent to the display device each time, so that the display device can display information of multiple target areas simultaneously, facilitating the user to quickly screen out the real target areas.

[0129] For example, the monitoring device can send information of four target areas to the display device each time, so that the display device can display information of the four target areas in the form of a four-grid. In some embodiments, the monitoring device can send information of nine target areas to the display device each time, so that the display device can display information of the nine target areas in the form of a nine-grid.

[0130] As mentioned above, each behavior track corresponds to a video segment in the video data. In this embodiment, the information of the target area can refer to a video segment corresponding to a behavior track whose end point is within the target area.

[0131] For example, the monitoring device can sort the target areas in descending order according to the number of end points of the behavior tracks in the target areas, first select the top four target areas, and send information of these four target areas to the display device. The information of each target area refers to a video segment corresponding to a behavior track whose end point is within the target area. That is to say, the monitoring device sends four video segments to the display device.

[0132] The display device can receive the four video segments from the monitoring device and display these four video segments. For example, the display device can be a mobile phone with a display screen, and can display the four received video segments in the form of a four-grid. If there is a video segment involving entering or leaving the door among the four displayed video segments, the user can perform an interaction operation on the display device to select the video segment involving entering or leaving the door. The display device can then generate indication information for indicating the selected video segment based on the user's interaction operation and send it to the monitoring device.

[0133] In this embodiment, the monitoring device can perform clustering analysis on the end points of the behavior tracks to obtain a clustering center, and use the clustering center as the target area. At this time, if the camera is installed outside the door, the end points of the behavior tracks involving entering the door are usually closely related to the target area, and the user can select the video segment involving entering the door through interaction with the display device. If the camera is installed inside the door, the end points of the behavior tracks involving leaving the door are usually closely related to the target area, and the user can select the video segment involving leaving the door through interaction with the display device. This application does not limit this, and those skilled in the art can make selections according to actual needs.

[0134] If there is no video clip involving entering or exiting among the four displayed video clips, the monitoring device can send information about the next batch of target areas to the display device. The information for each target area refers to a video clip corresponding to a behavior trajectory whose end point is within that target area, until the monitoring device receives the indication information for indicating the video frequency band selected by the user.

[0135] After receiving the indication information, the monitoring device can determine the target area selected by the user based on the video clip indicated by the indication information.

[0136] As mentioned above, since the monitoring device can send information about multiple target areas to the display device each time, so that the display device can display the information of multiple target areas simultaneously, the target area selected by the user may be one or more. At this time, in order to accurately identify the real target area, this door positioning method may further include the following steps executed after S550:

[0137] S560: Determine whether the number of target areas indicated by the indication information is greater than one.

[0138] If the number of target areas indicated by the indication information is one, the monitoring device can directly use this target area as the real target area.

[0139] S570: In response to the number of indicated target areas being greater than one, use the target area with the largest number of end points of the behavior trajectory as the real target area.

[0140] If the number of target areas indicated by the indication information is multiple, the monitoring device can select the target area with the largest number of end points of the behavior trajectory from them as the real target area.

[0141] In some embodiments, the monitoring device can perform clustering analysis on the starting points of the behavior trajectories to obtain the clustering center, and use the clustering center as the target area. Further, the monitoring device can send the information of the target areas to the display device for display in descending order of the number of starting points of the behavior trajectories in the target areas, so as to quickly screen out the real target area. In such an embodiment, the information of the target area may refer to a video clip corresponding to a behavior trajectory whose starting point is within that target area.

[0142] In some embodiments, the monitoring device may perform clustering analysis on the starting and ending points of the behavior trajectories to obtain the clustering centers, and use the clustering centers as the target areas. Further, the monitoring device may sequentially send the information of the target areas to the display device for display in the order of the total number of starting and ending points of the behavior trajectories in the target areas from largest to smallest, so as to quickly screen out the real target areas. In such an embodiment, the information of the target area may refer to a video segment corresponding to a behavior trajectory whose starting or ending point is within the target area.

[0143] Figures 2 to 4 and Figure 7 The embodiments described above all relate to the solution of determining the target area based on the end points of the behavior trajectories. In addition, the complete behavior trajectory may be input into the trained model, and the target area may be determined based on the output result of the model.

[0144] As Figure 8 shown, the present application also provides another method for door positioning. Specifically, the method for door positioning may include:

[0145] S610: Obtain the video data of the monitoring area within a preset time period.

[0146] For the remaining details of this step, they may be the same as or similar to those of S110, and will not be elaborated here.

[0147] S620: Obtain the behavior trajectories of the target object in the monitoring area from the video data.

[0148] For the remaining details of this step, they may be the same as or similar to those of S120, and will not be elaborated here.

[0149] S630: Input the behavior trajectories into the trained model so that the model can output the target area.

[0150] Specifically, by inputting multiple behavior trajectories into the trained model, the model can directly optimize and output the target area and its probability value. Specifically, each target area may correspond to a probability value, and this probability value reflects the possibility that the target area is the real target area.

[0151] The target area output by the model optimization may be one or multiple. Therefore, in some embodiments, the method for door positioning may further include the following steps:

[0152] S640: Determine whether the number of target areas is greater than one.

[0153] When there is only one target area output by the model, at this time, this target area may be directly used as the real target area. When there are multiple target areas output by the model, the user may assist in screening out the real target area.

[0154] S650: In response to the number of target regions being greater than one, the information of the target regions is sequentially sent to a display device for display according to a preset rule, so that a user can select a true target region until an indication message is received. The indication message is generated and sent by the display device based on the user's interaction operation and is used to indicate the target region selected by the user.

[0155] Specifically, when there are multiple target regions output by the model, the information of the target regions can be sequentially sent to the display device for display in descending order of probability values, so as to quickly screen out the true target region.

[0156] Each time, the information of multiple target regions can be sent to the display device, so that the display device can simultaneously display the information of multiple target regions, facilitating the user to quickly screen out the true target region.

[0157] For example, the monitoring device can send the information of four target regions to the display device each time, so that the display device can simultaneously display the information of the four target regions in a four-grid form. In some embodiments, the monitoring device can send the information of nine target regions to the display device each time, so that the display device can simultaneously display the information of the nine target regions in a nine-grid form.

[0158] As described above, each row of behavior trajectories corresponds to a video segment in the video data. In this embodiment, the information of the target region can refer to a video segment corresponding to a behavior trajectory whose end point is within the target region.

[0159] For example, the monitoring device can perform a descending order sorting on the target regions in descending order of probability values, first select the four target regions ranked in the top four, and send the information of these four target regions to the display device. The information of each target region refers to a video segment corresponding to a behavior trajectory whose end point is within the target region. That is to say, the monitoring device sends four video segments to the display device.

[0160] The display device can receive the four video segments from the monitoring device and display these four video segments. For example, the display device can be a mobile phone with a display screen and can display the four received video segments in a four-grid form. If there is a video segment involving entering or leaving the door among the four displayed video segments, the user can perform an interaction operation on the display device to select the video segment involving entering or leaving the door. The display device can then generate an indication message for indicating the video segment selected by the user based on the user's interaction operation and send it to the monitoring device.

[0161] If there is no video clip involving entering or exiting among the four displayed video clips, the monitoring device may send information about the next batch of target areas to the display device. The information of each target area refers to a video clip corresponding to a behavior trajectory whose end point is within the target area, until the monitoring device receives the indication information for indicating the video frequency band selected by the user.

[0162] After receiving the indication information, the monitoring device may determine the target area selected by the user according to the video clip indicated by the indication information.

[0163] As described above, since the monitoring device can send information about multiple target areas to the display device each time, so that the display device can display the information of multiple target areas simultaneously, the target area selected by the user may be one or more. At this time, in order to accurately identify the real target area, the door positioning method may further include the following steps performed after S550:

[0164] S660: Determine whether the number of target areas indicated by the indication information is greater than one.

[0165] If the number of target areas indicated by the indication information is one, the monitoring device may directly use this target area as the real target area.

[0166] S670: In response to the number of indicated target areas being greater than one, use the target area with the largest probability value as the real target area.

[0167] If the number of target areas indicated by the indication information is multiple, the monitoring device may select the target area with the largest probability value from them as the real target area.

[0168] In some embodiments, the information of each target area may refer to a video clip corresponding to a behavior trajectory whose starting point is within the target area. This application does not limit this, and those skilled in the art can select according to actual needs.

[0169] As Figure 9 shown, this application also provides another door positioning method, which may specifically include:

[0170] S710: Obtain the video data of the monitoring area within a preset time period.

[0171] Regarding the remaining details of this step, they may be the same as or similar to S110, and will not be elaborated here.

[0172] S720: Obtain the behavior trajectory of the target object within the monitoring area from the video data.

[0173] Regarding the remaining details of this step, they may be the same as or similar to S120, and will not be elaborated here.

[0174] S730: Input the behavior trajectory into the trained model so that the model can output the behavior trajectory related to entering or exiting the door.

[0175] In this embodiment, multiple behavior trajectories are input into the trained model, and the model can output the behavior trajectory related to entering the door and its corresponding probability value. Specifically, each behavior trajectory can correspond to a probability value, and this probability value reflects the possibility that the behavior trajectory is related to entering the door.

[0176] S740: Determine the target area according to the starting point or the ending point of the behavior trajectory related to entering or exiting the door.

[0177] In this embodiment, what the model outputs is the behavior trajectory related to entering the door. When the camera is installed outside the door, the area where the ending point of the behavior trajectory related to entering the door is located can be used as the target area; when the camera is installed inside the door, the area where the starting point of the behavior trajectory related to entering the door is located can be used as the target area.

[0178] The number of behavior trajectories related to entering the door output by the model may be one or multiple. Therefore, in the step of S740, the number of target areas determined by the monitoring device can also be one or multiple. Therefore, in some embodiments, this door positioning method may further include the following steps:

[0179] S750: Determine whether the number of target areas is greater than one.

[0180] When there is only one target area, at this time, this target area can be directly used as the real target area. When there are multiple target areas, the user can assist in screening out the real target area.

[0181] S760: In response to the number of target areas being greater than one, sequentially send the information of the target areas to the display device for display according to a preset rule so that the user can select the real target area until an indication message is received. The indication message is generated and sent by the display device based on the user's interaction operation and is used to indicate the target area selected by the user.

[0182] In this embodiment, each target area corresponds to a behavior trajectory related to entering the door. The information of the target areas can be sequentially sent to the display device for display in the order of the probability values of the behavior trajectories corresponding to the target areas from large to small to quickly screen out the real target area.

[0183] Multiple pieces of information about target regions can be sent to a display device each time, enabling the display device to simultaneously display the information of multiple target regions, facilitating the user to quickly screen out the real target regions. As mentioned above, each behavior track corresponds to a video segment in video data. In this embodiment, the information of a target region may refer to the video segment corresponding to the behavior track corresponding to the target region, and the indication information can be used to indicate the video segment selected by the user.

[0184] Regarding other details not covered in this embodiment, they can be the same as or similar to the Figure 8 embodiment shown, and will not be elaborated here.

[0185] In this embodiment, the behavior track output by the model can also be related to going out. When the camera is installed outside the door, the area where the starting point of the behavior track related to going out is located can be used as the target region; when the camera is installed inside the door, the area where the ending point of the behavior track related to going out is located can be used as the target region.

[0186] In addition, the present application also provides a monitoring device 800. Please refer to Figure 10 , Figure 10 which is a schematic structural diagram of an embodiment of the monitoring device of the present application. The monitoring device 800 includes a memory 810, a processor 820, and a computer program stored on the memory 810 and executable on the processor 820. When the processor 820 executes the computer program, it implements the steps of any of the door positioning methods described above.

[0187] Among them, the processor 820 can also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 820 may be an integrated circuit chip with signal processing capabilities. The processor 820 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor 820 can also be any conventional processor, etc.

[0188] The memory 810 may include a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory 810 (EPROM), an electrically erasable programmable read-only memory (EEPROM), registers, a hard disk, a removable disk, a CD-ROM, and so on. The memory 810 may store program data, which may include, for example, a single instruction or many instructions, and may be distributed over several different code segments, across different programs, and across multiple memories. The memory 810 may be coupled to the processor 820 such that the processor 820 can read from / write information to the memory 810. Of course, the memory 810 may be integrated into the processor 820, and this application does not limit this, and those skilled in the art can make a choice according to actual needs.

[0189] In several embodiments provided by this application, it should be understood that the disclosed door positioning method can be implemented in other ways. For example, the monitoring device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

[0190] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0191] In addition, each functional unit in each embodiment of this application may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0192] The above is only a partial embodiment of this application, and thus does not limit the protection scope of this application. Any equivalent device or equivalent process transformation made using the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of this application.

Claims

1. A door positioning method, applied to a monitoring device, characterized in that, The method includes: Obtaining video data of a monitoring area within a preset time period; Obtaining the behavior trajectory of a target object within the monitoring area from the video data; Determining a target area corresponding to the position of a door within the monitoring area according to the behavior trajectory.

2. The method according to claim 1, wherein The determining the target area corresponding to the position of the door within the monitoring area according to the behavior trajectory includes: Determining the target area according to the endpoints of the behavior trajectory, where the endpoints include the starting point and / or the ending point.

3. The method according to claim 2, wherein The monitoring area includes a plurality of sub-areas; The determining the target area according to the endpoints of the behavior trajectory includes: Counting the number of endpoints of the behavior trajectory within the sub-area as the heat value of the sub-area; Determining the target area according to the heat value of the sub-area.

4. The method according to claim 3, wherein The determining the target area according to the heat value of the sub-area includes: Taking the sub-area with the largest heat value as the target area.

5. The method according to claim 4, characterized in that, The target object includes a valid object and an interference object; The determining the target area according to the endpoints of the behavior trajectory includes: Filtering out the behavior trajectories of the valid objects from the behavior trajectories; Determining the target area according to the endpoints of the behavior trajectories of the valid objects.

6. The method according to any one of claims 4-5, characterized in that, The behavior trajectory includes an invalid trajectory; The determining the target area according to the endpoints of the behavior trajectory includes: Excluding the invalid trajectory from the behavior trajectory; Determining the target area according to the endpoints of the remaining behavior trajectories.

7. The method according to claim 3, characterized in that The determining the target area according to the heat value of the sub-area includes: Sequentially sending the information of the sub-areas to a display device for display in descending order of the heat value, so that a user can select the sub-area where the target area is located until an indication information is received. The indication information is generated and sent by the display device based on the user's interaction operation and is used to indicate the sub-area selected by the user.

8. The method according to claim 7, wherein Each behavior trajectory corresponds to a video segment in the video data; The information of the sub-area includes a video segment corresponding to a behavior trajectory whose starting point or ending point is within the sub-area, so that a user can select the video segment related to entering or leaving the door; The indication information is used to indicate the video segment selected by the user.

9. The method according to claim 7, wherein In the sequentially sending the information of the sub-areas to the display device for display in descending order of the heat value, multiple pieces of information of the sub-areas are sent to the display device each time, so that the display device can simultaneously display the information of multiple sub-areas; The determining the target area according to the heat value of the sub-area further includes: Determining whether the number of the sub-areas indicated by the indication information is greater than one; In response to the number of the indicated sub-areas being greater than one, taking the sub-area with the largest heat value among them as the target area.

10. The method according to any one of claims 7-9, characterized in that, The sequentially sending the information of the sub-areas to the display device for display in descending order of the heat value includes: Send the information of the non-adjacent sub-regions to the display device for display in descending order of the heat value, and the number of sub-regions between the non-adjacent sub-regions is greater than a preset value.

11. The method according to claim 2, wherein The determining the target region according to the endpoints of the behavior trajectory includes: Performing clustering analysis on the endpoints of the behavior trajectory to obtain a clustering center, and using the clustering center as the target region.

12. The method according to claim 1, characterized in that, The determining the target region corresponding to the position of the gate in the monitoring region according to the behavior trajectory includes: Inputting the behavior trajectory into a trained model so that the model can output the target region.

13. The method according to claim 1, characterized in that, The determining the target region corresponding to the position of the gate in the monitoring region according to the behavior trajectory includes: Inputting the behavior trajectory into a trained model so that the model can output the behavior trajectory related to entering or leaving the door; Determining the target region according to the starting point or the ending point of the behavior trajectory related to entering or leaving the door.

14. The method according to any one of claims 11-13, characterized in that, After the determining the target region corresponding to the position of the gate in the monitoring region according to the behavior trajectory, the method further includes: Determining whether the number of the target regions is greater than one; In response to the number of the target regions being greater than one, sending the information of the target regions to the display device for display in sequence according to a preset rule so that the user can select the real target region until an indication information is received, where the indication information is generated and sent by the display device based on the user's interaction operation and is used to indicate the target region selected by the user.

15. The method according to claim 14, wherein Each behavior trajectory corresponds to a video segment in the video data; The information of the target region includes a video segment corresponding to a behavior trajectory whose starting point or ending point is within the target region, so that the user can select the video segment related to entering or leaving the door; The indication information is used to indicate the video segment selected by the user.

16. A monitoring device, characterized in that, Including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to execute the computer program to implement the door positioning method according to any one of claims 1-15.

Images