Target tracking photographing method, indexing method, device, medium and electronic equipment

Abstract

Embodiments of the present application disclose a target tracking and shooting method, an indexing method, a device, a medium and an electronic device. The target tracking and shooting method comprises: if it is detected that a tracking target enters a shooting range, obtaining candidate identification information of a wireless device collected by a wireless network module, and collecting image feature information of the tracking target; if candidate identification information and image feature information transmitted by a previous front-end collection device are received, determining a tracking result of the tracking target in a monitoring range of a current front-end collection device according to candidate identification information collected within a preset time and the received candidate identification information, and / or according to image feature information collected within the preset time and the received image feature information. The technical solution can regard multiple cameras as a whole, dynamically call associated camera video analysis for target tracking when analyzing a task, and improve the accuracy and efficiency of target tracking.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of video shooting, and in particular to a target tracking shooting method, an indexing method, a device, a medium and an electronic device. BACKGROUND

[0002] With the rapid development of science and technology, video monitoring is increasingly applied in the field of security. In some cases, it may be necessary to continuously watch the passing process of a tracking object from videos captured by multiple cameras. Therefore, tracking shooting and identification of the tracking object are particularly important. Since the tracking object may have certain body changes during the passing process, such as walking upright in the shooting area of one camera, squatting to pick up an object in the shooting area of another camera, and possibly changing another piece of clothing in the shooting area of another camera. Changes in such body posture or other features make it difficult to complete accurate tracking shooting without the identification of staff. Therefore, the existing tracking shooting method is often based on the identification and labeling of staff to determine the passing process of a tracking object and obtain a tracking route, such as the passing processes of camera 01, camera 03, camera 04 and camera 07. Such an identification method obviously requires a large amount of human resources, and the staff must also have knowledge of the deployment of cameras in the entire area, resulting in the problem of low efficiency in determining the tracking shooting process of the tracking target. SUMMARY

[0003] Embodiments of the present application provide a target tracking shooting method, an indexing method, a device, a medium and an electronic device, which can realize autonomous tracking by simultaneous operation of multiple front-end collection devices and using the same label for the same target in videos collected by different front-end collection devices.

[0004] In a first aspect, embodiments of the present application provide a target tracking shooting method, which is executed by a front-end collection device, the front-end collection device is configured with a wireless network module, the wireless network module is set to a wireless access point enabled mode, the front-end collection device is associated with at least one front-end collection device, and the method comprises:

[0005] If it is detected that a tracking target enters the shooting range, candidate identification information of a wireless device collected by the wireless network module is obtained, and image feature information of the tracking target is collected;

[0006] If the candidate identification information and the image feature information transmitted by the previous front-end acquisition device are received, the tracking result of the tracking target in the monitoring range of the current front-end acquisition device is determined according to the candidate identification information collected in the preset time and the received candidate identification information, and / or according to the image feature information collected in the preset time and the received image feature information.

[0007] In a second aspect, the embodiments of the present application provide a tracking index method of a target, which is executed by a server, the server being executed with a front-end acquisition device, the front-end acquisition device being configured with a wireless network module, the tracking index method of the target comprising:

[0008] receiving and storing the tracking result of the tracking target in the monitoring range of each front-end acquisition device; wherein the tracking result of the tracking target comprises candidate identification information of a wireless device collected by each front-end acquisition device, and image feature information of the tracking target;

[0009] determining a front-end acquisition device associated with the trajectory of the tracking target based on the candidate identification information of the wireless device collected by each front-end acquisition device, and the image feature information of the tracking target.

[0010] In a third aspect, the embodiments of the present application provide a tracking shooting device of a target, the device being configured in a front-end acquisition device, the front-end acquisition device being configured with a wireless network module, the wireless network module being set to a wireless access point start mode, the front-end acquisition device being associated with at least one front-end acquisition device, the device comprising:

[0011] a tracking target information acquisition module, if it is detected that a tracking target enters the shooting range, the candidate identification information of a wireless device collected by the wireless network module is acquired, and the image feature information of the tracking target is acquired;

[0012] a tracking result determination module, if the candidate identification information and the image feature information transmitted by the previous front-end acquisition device are received, the tracking result of the tracking target in the monitoring range of the current front-end acquisition device is determined according to the candidate identification information collected in the preset time and the received candidate identification information, and / or according to the image feature information collected in the preset time and the received image feature information.

[0013] In a fourth aspect, the embodiments of the present application provide a tracking index device of a target, the device being configured in a server, the server being executed with a front-end acquisition device, the front-end acquisition device being configured with a wireless network module, the tracking index device of the target comprising:

[0014] The tracking result receiving module receives and stores the tracking result of the tracking target in the monitoring range of each front-end collection device; wherein the tracking result of the tracking target comprises candidate identification information of the wireless device collected by each front-end collection device and image feature information of the tracking target;

[0015] The trajectory-associated front-end collection device determining module determines the trajectory-associated front-end collection device of the tracking target based on the candidate identification information of the wireless device collected by each front-end collection device and the image feature information of the tracking target.

[0016] In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the target tracking shooting method according to the embodiments of the present application, or implement the target tracking indexing method according to the embodiments of the present application.

[0017] In a sixth aspect, an embodiment of the present application provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable by the processor, and the processor implements the target tracking shooting method according to the embodiments of the present application or implements the target tracking indexing method according to the embodiments of the present application when executing the computer program.

[0018] The technical solution provided by the embodiments of the present application can realize the effect of autonomous tracking by the joint of multiple front-end collection devices and using the same mark for the same target in the videos collected by different front-end collection devices, thereby improving the efficiency and accuracy of target tracking. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of the target tracking shooting method provided for the first embodiment of the present application;

[0020] Figure 2 A flowchart of the target tracking shooting method provided for the second embodiment of the present application;

[0021] Figure 3 A flowchart of the target tracking indexing method provided for the third embodiment of the present application;

[0022] Figure 4A structure schematic diagram of a target tracking photographing device provided by the embodiment four of the present application;

[0023] Figure 5 A structure schematic diagram of a target tracking index device provided by the embodiment five of the present application;

[0024] Figure 6 A structure schematic diagram of an electronic device provided by the embodiment seven of the present application. DETAILED DESCRIPTION

[0025] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.

[0026] Before discussing the example embodiments in more detail, it is noted that some example embodiments are described as processes or methods depicted as flow diagrams. Although the processes are described in a particular sequential order, many of the steps can be performed in parallel, concurrently or in any order. In addition, the order of the steps can be re-arranged. The processes can be terminated when their operations are completed, but can also have additional steps not included in the figure, which can also be performed after the operations of the processes are completed. The processes can correspond in part to method steps for implementing the described functionality.

[0027] Embodiment one

[0028] Figure 1 A flow chart of a target tracking photographing method provided by the embodiment one of the present application, the embodiment can be applied to any scene needing target tracking, and applied to a front-end acquisition device. The method can be executed by a target tracking photographing device provided by the embodiment of the present application, the device can be realized by software and / or hardware, and can be integrated in an electronic device.

[0029] As shown in Figure 1 the target tracking photographing method comprises:

[0030] S110, if it is detected that a tracking target enters the photographing range, candidate identification information of a wireless device collected by a wireless network module is acquired, and image feature information of the tracking target is collected.

[0031] The scheme is executed by a front-end acquisition device, which can be a visible light imaging device, a thermal infrared imaging device, or a dual-sensor imaging device integrating the above devices. The front-end acquisition device should have a shooting function and can collect images, such as a security camera, an infrared thermal imager, or a dual-sensor imaging device with a synchronous imaging function. The front-end acquisition device can identify and track targets and detect whether a tracking target appears in the field of view. The tracking target can be a vehicle, a person, or a part of a person's body, such as a face, a hand, or a leg. In response to the needs of different scenarios, the tracking target can also be an animal, a vehicle, and other objects that can move. In addition, the tracking target can be one or more, and any moving target appearing in the field of view of the front-end acquisition device can be considered a tracking target.

[0032] The front-end acquisition device is configured with a wireless network module, which is set to a wireless access point start mode, so that the wireless network module can easily collect information from wireless devices. The wireless device is an electronic device with communication function with the wireless network module, such as a mobile phone, a tablet computer, a smart watch, etc. The wireless device has candidate identification information, which can include time, wireless device number, received signal strength indication (RSSI), and MAC address (physical address) of the wireless device, etc.

[0033] The front-end acquisition device can collect image feature information of the tracking target, which is information obtained directly or indirectly from the image. Taking a pedestrian as an example, the image feature information can include the pedestrian's appearance characteristics, such as clothing color, height, posture, hairstyle, and whether or not to have accessories, etc., and can also include the pedestrian's actions, such as walking, raising hands, jumping, and running, etc.

[0034] In the scheme, optionally, after detecting that a tracking target enters the shooting range, the method further comprises:

[0035] If the candidate identification information and image feature information transmitted by the previous front-end acquisition device are received, the coding information of the tracking target transmitted by the previous front-end acquisition device is used;

[0036] Or,

[0037] If the candidate identification information and image feature information transmitted by the previous front-end acquisition device are not received, the coding information of the tracking target is generated.

[0038] The front-end acquisition device mentioned in the embodiment is associated with at least one front-end acquisition device. If there is one or more front-end acquisition devices before the current front-end acquisition device, the candidate identification information and the image feature information have been acquired by the previous front-end acquisition devices. In this case, the current front-end acquisition device can use the coding information of the tracking target transmitted by the previous front-end acquisition device. If there is no front-end acquisition device before the current front-end acquisition device, the coding information of the tracking target cannot be inherited from the previous front-end acquisition device. The coding information can be the number of the tracking target, and the number of each tracking target is unique. For example, two people pass by, one of whom is numbered P1 and the other is numbered P2, and such numbers are used regardless of how many front-end acquisition devices the two people pass through. Through such a setting, the same tracking target can have the same coding information in different front-end acquisition devices, which facilitates the application and query of tracking target information by subsequent front-end acquisition devices and servers. Through comparative analysis, the embodiment only needs to retrieve one information record of the tracking target, and can find all personnel trajectory information associated with the personnel coding information of the record, compared with the prior art, greatly reducing the number of comparisons and improving the retrieval efficiency.

[0039] In S120, if the candidate identification information and the image feature information transmitted by the previous front-end acquisition device are received, the tracking result of the tracking target in the monitoring range of the current front-end acquisition device is determined according to the candidate identification information acquired within a preset time and the received candidate identification information, and / or according to the image feature information acquired within a preset time and the received image feature information.

[0040] The acquired candidate identification information is the candidate identification information acquired by the current front-end acquisition device, and the received candidate identification information is the candidate identification information acquired by the previous front-end acquisition device. Assuming that the shooting range of the previous front-end acquisition device is C1 and the shooting range of the current front-end acquisition device is C2. Taking candidate identification information including time, wireless device number, received signal strength indication and MAC address of the wireless device as an example, Table 1 is the received candidate identification information, and Table 2 is the acquired candidate identification information.

[0041] Table 1:

[0042] Time STA device RSSI value MAC address T1 STA1 RSSI1_1 MAC1 T1 STA2 RSSI2_1 MAC2

[0043] Table 2:

[0044] Time STA device RSSI value MAC address T2 STA1 RSSI1_2 MAC1 T2 STA3 RSSI3_1 MAC3

[0045] Still taking the example that the tracking target is a pedestrian, it can be analyzed from Table 1 and Table 2 that the STA2 device does not appear in the shooting range of the current front-end collection device at T2 time, which indicates that the pedestrian carrying the STA2 device has left before entering the shooting range of the current front-end collection device. The STA1 device appears in the shooting range of the current front-end collection device at T2 time, which indicates that the pedestrian carrying the STA1 device has moved from C1 to C2.

[0046] The collected image feature information is the image feature information acquired by the current front-end collection device, and the received image feature information is the image feature information acquired by the previous front-end collection device. According to the collected image feature information and the received image feature information, the tracking result of the tracking target in the monitoring range of the current front-end collection device can be further determined, such as the relationship between the wireless device and the pedestrian. Based on the above example of tracking a pedestrian, it is assumed that two pedestrians P1 and P2 appear in the image captured by the previous front-end collection device, and two pedestrians P1 and P3 appear in the image captured by the current front-end collection device. The image feature information includes time, pedestrian number, clothing color, and hairstyle. Table 3 below is the received image feature information, and Table 4 is the collected image feature information.

[0047] Table 3:

[0048] Time Pedestrian number Clothing color Hairstyle T1 P1 Red Long straight hair T1 P2 Green Short curly hair

[0049] Table 4:

[0050] Time Pedestrian number Clothing color Hairstyle T2 P1 Red Long straight hair T2 P3 Blue Long curly hair

[0051] Based on the conclusion obtained from Table 1 and Table 2, it can be analyzed that the pedestrian carrying the STA1 device is P1, and P1 has moved from C1 to C2, thus realizing the tracking of the pedestrian.

[0052] Whether it is candidate identification information or image feature information, the embodiment limits the time range of the collected information and the received information. Because the appearance of the tracking target in the monitoring range of the front-end collection device has a certain time range, if the preset time is not limited, the front-end collection device will analyze and operate a large amount of irrelevant information, increasing the workload and being not conducive to realizing real-time target tracking. The preset time can be determined according to the actual distance between the current front-end collection device and the previous front-end collection device, or according to the speed of the tracking target movement, or according to the number of front-end collection devices within a certain range. The candidate identification information and image feature information within the preset time range are more referential and targeted, which can realize efficient and accurate target tracking while saving costs.

[0053] The technical scheme provided in the embodiment of the application, if it is detected that a tracking target enters the shooting range, candidate identification information of a wireless device collected by a wireless network module is acquired, and image feature information of the tracking target is collected; if candidate identification information and image feature information transmitted by a previous front-end collection device are received, a tracking result of the tracking target in a monitoring range of a current front-end collection device is determined according to candidate identification information collected in a preset time and the received candidate identification information, and / or according to image feature information collected in the preset time and the received image feature information. The technical scheme can realize the effect of autonomous tracking by the joint of multiple front-end collection devices and using the same mark for the same target in images collected by different front-end collection devices, thereby improving the efficiency and accuracy of target tracking.

[0054] Embodiment Two

[0055] The embodiment is a preferred embodiment provided on the basis of the above-described embodiment. Figure 2 The flowchart of the target tracking and shooting method provided for the embodiment two of the application is optimized on the basis of the above-described embodiment.

[0056] As shown in Figure 2 , the method of the embodiment specifically includes the following steps:

[0057] S210, if it is detected that a tracking target enters the shooting range, candidate identification information of a wireless device collected by a wireless network module is acquired, and image feature information of the tracking target is collected.

[0058] The candidate identification information of the wireless device collected by the wireless network module can be collected after it is detected that the tracking target enters the shooting range, or can be collected in a period of time before the tracking target enters the shooting range, for example, candidate identification information of a wireless device collected by the wireless network module in a period of 20 seconds before the appearance of the tracked personnel.

[0059] Taking a pedestrian as the tracking target, the scheme can be executed by a camera, assuming that the candidate identification information includes time, wireless device number, RSSI and MAC address of the wireless device, camera B is the current camera, camera A is the previous camera of camera B, Table 5 is candidate identification information acquired by camera A, and Table 6 is candidate identification information acquired by camera B.

[0060] Table 5:

[0061]

[0062]

[0063] Table 6:

[0064] Time Wireless device number RSSI value MAC address T2 STA1 RSSI1_2 MAC1 T2 STA3 RSSI3_2 MAC3 T2 STA4 RSSI4_2 MAC4 T2 STA5 RSSI5_2 MAC5 … … … …

[0065] S220, determining the intersection of the candidate identification information according to the candidate identification information collected within the preset time and the candidate identification information received; and determining the image feature information similarity according to the image feature information collected and the image feature information received.

[0066] The determination of the intersection of the candidate identification information can be an intersection operation on a certain item of content included in the candidate identification information, for example, only the MAC address of the wireless device is selected as a basis to filter the candidate identification information of camera B, or some items of content included in the candidate identification information are selected for intersection operation, for example, the wireless device number and the MAC address of the wireless device are selected as comparison standards to filter the candidate identification information of camera B. Table 7 below is the intersection of the candidate identification information determined by camera B. The purpose of determining the intersection of the candidate identification information is to filter the candidate identification information irrelevant to the tracking target, and gradually narrow down the determination range of the tracking target.

[0067] Table 7:

[0068]

[0069]

[0070] In general, camera B is at a certain distance from camera A, and there are certain differences in the physical environment when taking pictures, which can include lighting conditions, temperature, etc. At the same time, due to maintenance and replacement, camera B and camera A may have different structures and devices, which also affect the imaging quality of the two cameras. In addition, since the tracking target is moving, there will be certain differences in the imaging on the two cameras. Therefore, the image collected by camera B and the received image cannot be directly compared in pixel level similarity, and the image collected by camera B and the received image can be preprocessed, image enhanced, etc. to improve the image quality, or the image collected by camera B and the received image can be feature extracted using a feature extraction algorithm to convert the image information into digital information. This further comparison of the collected image feature information and the received image feature information is simpler and more convenient, and the determination of the image feature information similarity is more targeted, improving the accuracy of image recognition.

[0071] 230, if there is at least one candidate identification information in the intersection of the candidate identification information, and the image feature information similarity exceeds the set threshold, the tracking result of the tracking target in the monitoring range of the current front-end collection device is obtained.

[0072] In the scheme, it can be understood that the two operation processes can not be distinguished in sequence, and one of the operation processes can be performed first, or they can be performed simultaneously, for the identification of the intersection of the candidate identification information, and for the determination that the image feature information similarity exceeds the set threshold. In the scheme, preferably, the identification of the intersection of the candidate identification information is performed first, and if there is no intersection, that is, there is no candidate identification information existing in both front-end collection devices, then the subsequent identification can be omitted. The advantage of such setting is that the identification calculation process of the intersection of the candidate identification information is relatively simple, the calculation cost is relatively low, and the priority setting is beneficial to improve the operation speed and reduce the operation burden. The image feature information similarity refers to the similarity of the image feature information collected by the current front-end collection device and the received image feature information. The similarity can be obtained by comparing the differences between the collected image feature information and the received image feature information, calculating the proportion of the number of image feature information without differences in the total number of image feature information, or by digitizing the collected image feature information and the received image feature information, calculating the distance between the two digitized image feature information as the similarity, where the distance can be Euclidean distance or Mahalanobis distance, etc. The collected image feature information and the received image feature information can also be clustered to obtain the similarity. The embodiment of the application does not limit the way the image feature information similarity is obtained. In actual application, the image feature information similarity needs to be compared with the set threshold to determine whether the collected image feature information and the received image feature information can be considered the same.

[0073] At the same time, there should be at least one candidate identification information in the intersection of the candidate identification information calculated in S220, which indicates that there is a candidate tracking target in the monitoring range of the current front-end collection device. Through the determination of the image feature information similarity and the candidate identification information, the tracking result of the tracking target in the monitoring range of the current front-end collection device can be further determined.

[0074] In the scheme, if there is no intersection of the candidate identification information, the tracking result of the tracking target in the monitoring range of the current front-end collection device is that there is no tracking target. It can be understood that if there is no intersection of the candidate identification information collected by the two front-end collection devices, it indicates that the tracking target does not appear in the two front-end collection devices, and it can be determined that there is no tracking target in the current monitoring range. Through such identification, the tracking result in the case where there is no tracking target can be quickly determined.

[0075] S240, when the tracking target leaves the shooting range, the next front-end collection device entered by the tracking target is determined according to the path analysis result.

[0076] When the tracking target leaves the shooting range of the current front-end acquisition device, the next front-end acquisition device that the tracking target will enter can be determined according to the path analysis result of the tracking target. The path analysis result can be determined by the candidate identification information of the wireless device collected by the wireless network module, such as the size of the received signal strength indication value of the wireless device, the direction, and the like; or can be determined by the image feature information collected, such as the turning action of the pedestrian in the image, which can determine which camera the pedestrian will enter; or can be that all the neighboring front-end acquisition devices around the current front-end acquisition device are considered as the next front-end acquisition device that the tracking target will enter.

[0077] Correspondingly, when the tracking target leaves the shooting range, the wireless network module configured by the current front-end acquisition device stops collecting the candidate identification information of the wireless device.

[0078] It can be understood that when the tracking target leaves the shooting range, the current front-end acquisition device collecting the candidate identification information of the wireless device also does not have application significance, and therefore, from the perspective of saving resources, the server or the controller of the front-end acquisition device can control the wireless network module of the current front-end acquisition device to stop collecting the candidate identification information of the wireless device.

[0079] In the present scheme, optionally, if there are at least two front-end acquisition devices receiving the candidate identification information and the image feature information transmitted by the previous front-end acquisition device, and one of them detects that the tracking target enters the shooting range, the front-end acquisition devices other than the one that detects that the tracking target enters the shooting range stop collecting the candidate identification information and stop identifying the tracking result.

[0080] In order to further save resources, if there are two or more front-end acquisition devices receiving the candidate identification information and the image feature information transmitted by the previous front-end acquisition device, and at least one of them detects that the tracking target appears in the shooting range, the server or the controller of the front-end acquisition device can control the other undetected front-end acquisition devices to stop collecting the candidate identification information of the wireless device.

[0081] The present scheme can avoid the interference of other information by selectively reducing the number of front-end acquisition devices, maximize the tracking efficiency of the target; on the other hand, it can save energy and prolong the service life of the front-end acquisition device.

[0082] S250, transmitting the tracking result of the tracking target to the next front-end acquisition device, so that the next front-end acquisition device determines the tracking result of the tracking target in the monitoring range of the next front-end acquisition device based on the collected identification information and image feature information.

[0083] Similarly, the current front-end acquisition device can pass the tracking result of the tracking target to the next front-end acquisition device, so that the next front-end acquisition device can also determine the tracking result of the tracking target in the monitoring range of the next front-end acquisition device according to the collected identification information and image feature information.

[0084] With the continuous information transmission between the associated front-end acquisition devices, the candidate identification information and the image feature information will be filtered layer by layer, and the one-to-one correspondence relationship between the wireless device and the tracking target can be finally determined, so as to realize effective tracking of the tracking target. According to the step-by-step filtering of information, the present scheme can achieve good target tracking effect in the scene of multiple tracking targets, such as pedestrian tracking in crowded places such as shopping malls.

[0085] The embodiment introduces a specific implementation of determining the tracking result of the tracking target in the monitoring range of the current front-end acquisition device on the basis of the above-mentioned embodiment. The intersection of the candidate identification information and the image feature information similarity can improve the accuracy and resource utilization of target tracking. Passing the tracking result of the tracking target to the next front-end acquisition device can achieve more efficient target tracking effect.

[0086] Embodiment Three

[0087] Figure 3 is a flowchart of the target tracking index method provided by Embodiment Three of the present application. The present embodiment can be applied to any scene that needs target tracking and is applied to a back-end server. The method can be executed by the target tracking index device provided by the present application. The device can be realized by software and / or hardware and can be integrated in an electronic device.

[0088] As shown in Figure 3 , the target tracking index method comprises:

[0089] S310, receiving and storing the tracking result of the tracking target in the monitoring range of each front-end acquisition device; wherein the tracking result of the tracking target comprises the candidate identification information of the wireless device collected by each front-end acquisition device, and the image feature information of the tracking target.

[0090] In an actual target tracking scenario, usually multiple front-end acquisition devices are included, and these front-end acquisition devices are widely distributed and cover a certain area range. At the same time, information exchange is needed between these front-end acquisition devices, such as the current front-end acquisition device needs to receive the candidate identification information and image feature information transmitted by the previous front-end acquisition device. Therefore, multiple front-end acquisition devices need to be managed by a unified back-end server. The server can receive and store the tracking results of the tracking target in the monitoring range of the front-end acquisition device. At the same time, it can be understood that the tracking result of the tracking target can include the candidate identification information of the wireless device collected by each front-end acquisition device, and the image feature information of the tracking target. The server can also analyze and process these candidate identification information and image feature information to obtain a processing result and return it to each front-end acquisition device.

[0091] S320, determining the track associated front-end acquisition device of the tracking target based on the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracking target.

[0092] Among them, the server can determine the track associated front-end acquisition device of the tracking target according to the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracking target. That is, the server obtains the path analysis result according to the candidate identification information and the image feature information. Generally, due to resource limitations, each front-end acquisition device can only obtain limited candidate identification information and image feature information, and the server can obtain all candidate identification information and image feature information collected by the front-end acquisition device. Through comprehensive analysis of the information of multiple front-end acquisition devices, the track information of the tracking target can be obtained, and then analyzed. The server can apply the associated front-end acquisition device information on the track to timely notify the associated front-end acquisition device to receive the candidate identification information and image feature information from the previous front-end acquisition device. In addition, during the time when the tracking target is active in the shooting range of the front-end acquisition device, the candidate identification information and image feature information collected by the front-end acquisition device can be a large amount, and the server can also filter and arrange a large amount of information, thereby benefiting the effective use of resources.

[0093] S330, in response to the index request of the tracking target, obtaining index feature information of the tracking target; wherein the index feature information includes identification information and / or image feature information of the wireless device of the tracking target.

[0094] When the index of the tracking target is needed, the operator or the front-end acquisition device initiates an index request of the tracking target to the server, and the server can respond to the index request of the tracking target to obtain the index feature information of the tracking target from the stored data. It can be understood that the index feature information can include the identification information of the wireless device of the tracking target and / or the image feature information, and can also include analysis information obtained according to the candidate identification information and / or the image feature information.

[0095] In S340, based on the index feature information, the trajectory associated front-end acquisition device of the tracking target is called, and the index result video of the tracking target is generated according to the collection time of each trajectory associated front-end acquisition device.

[0096] It is easy to understand that according to the index feature information, the server can also call the trajectory associated front-end acquisition device of the tracking target, and the image or video data of the tracking target can be obtained through the calling operation of the server. The image or video data obtained is arranged according to the collection time of the trajectory associated front-end acquisition device, and the index result video of the tracking target is generated, which presents the motion process of the tracking target and provides a good visual effect for the user.

[0097] The technical scheme provided by the embodiment of the application can receive and store the candidate identification information and image feature information collected by each front-end acquisition device, and through analysis and processing of the information, the trajectory associated front-end acquisition device of the tracking target can be determined, the index feature information of the tracking target can be obtained, and the index result video of the tracking target can be generated. The information resources collected by the front-end acquisition device are fully utilized, the index and visualization requirements of the user are met, and a good user experience is provided.

[0098] Embodiment four

[0099] Figure 4 A structure block diagram of a target tracking and shooting device is provided for the fourth embodiment of the application. The device can execute the target tracking and shooting method provided by any embodiment of the application, has a function module and beneficial effect corresponding to the execution method. The target tracking and shooting device is configured in a front-end acquisition device, the front-end acquisition device is configured with a wireless network module, the wireless network module is set to a wireless access point start mode, and the front-end acquisition device is associated with at least one front-end acquisition device, as shown in the figure, the device can include: Figure 4

[0100] The tracking target information acquisition module 410 is used to acquire the candidate identification information of the wireless device collected by the wireless network module and acquire the image feature information of the tracking target if it is detected that the tracking target enters the shooting range.

[0101] ​The tracking result determination module 420 is configured to, if candidate identification information and image feature information transmitted by a previous front-end acquisition device are received, determine a tracking result of the tracking target in a monitoring range of the current front-end acquisition device according to candidate identification information acquired within a preset time and the received candidate identification information, and / or according to image feature information acquired within the preset time and the received image feature information.

[0102] In the present solution, the apparatus further includes, optionally:

[0103] The next front-end acquisition device determination module 430 is configured to, when the tracking target leaves the shooting range, determine a next front-end acquisition device entered by the tracking target according to the path analysis result.

[0104] The tracking result transmission module 440 is configured to transmit the tracking result of the tracking target to the next front-end acquisition device, so that the next front-end acquisition device determines a tracking result of the tracking target in a monitoring range of the next front-end acquisition device based on acquired identification information and image feature information.

[0105] In the embodiment of the present application, the apparatus further includes, optionally:

[0106] The encoding information generation module 450 is configured to, if candidate identification information and image feature information transmitted by a previous front-end acquisition device are received, use encoding information of the tracking target transmitted by the previous front-end acquisition device.

[0107] The encoding information generation module is further configured to:

[0108] If candidate identification information and image feature information transmitted by a previous front-end acquisition device are not received, the encoding information generation module generates encoding information of the tracking target.

[0109] In the present solution, the tracking result determination module 420 is further configured to:

[0110] determine a candidate identification information intersection according to candidate identification information acquired within a preset time and the received candidate identification information, and determine an image feature information similarity according to the acquired image feature information and the received image feature information.

[0111] If there is at least one candidate identification information in the candidate identification information intersection, and the image feature information similarity exceeds a set threshold, a tracking result of the tracking target in a monitoring range of the current front-end acquisition device is obtained.

[0112] In the embodiment of the present application, the apparatus further includes, optionally:

[0113] The current front-end acquisition device acquisition stop control module 460 is configured to control the wireless network module of the current front-end acquisition device to stop collecting the candidate identification information of the wireless device when the tracked target leaves the shooting range.

[0114] The product can execute the target tracking and shooting method provided in the embodiments of the application, has the function modules corresponding to the execution method and the beneficial effects.

[0115] Embodiment five

[0116] Figure 5 A structural block diagram of a target tracking and indexing device provided for the fifth embodiment of the application is shown in the figure. The device can execute the target tracking and indexing method provided in any embodiment of the application. The device is configured in a server, and the server is executed with a front-end acquisition device. The front-end acquisition device is configured with a wireless network module. The execution of the target tracking and shooting method provided in any embodiment of the application has the function modules corresponding to the execution method and the beneficial effects. Figure 5 As shown in the figure, the device can include:

[0117] The tracking result receiving module 510 is configured to receive and store the tracking results of the tracked target in the monitoring range of each front-end acquisition device. The tracking results of the tracked target include the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracked target.

[0118] The trajectory-associated front-end acquisition device determining module 520 is configured to determine the trajectory-associated front-end acquisition device of the tracked target based on the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracked target.

[0119] In the embodiment of the application, the device can further include:

[0120] The indexing feature information obtaining module 530 is configured to obtain the indexing feature information of the tracked target in response to the indexing request of the tracked target. The indexing feature information includes the identification information and / or the image feature information of the wireless device of the tracked target.

[0121] The indexing result video generating module 540 is configured to call the trajectory-associated front-end acquisition device of the tracked target based on the indexing feature information, and generate the indexing result video of the tracked target according to the collection time of each trajectory-associated front-end acquisition device.

[0122] The product can execute the target tracking and indexing method provided in the third embodiment of the application, has the function modules corresponding to the execution method and the beneficial effects.

[0123] Embodiment six

[0124] The embodiment six of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the tracking shooting method provided by all the embodiments of the present application.

[0125] If it is detected that the tracking target enters the shooting range, candidate identification information of the wireless device collected by the wireless network module is acquired, and image feature information of the tracking target is collected;

[0126] If the candidate identification information and the image feature information transmitted by the previous front-end collection device are received, the tracking result of the tracking target in the monitoring range of the current front-end collection device is determined according to the candidate identification information collected in the preset time and the received candidate identification information, and / or according to the image feature information collected in the preset time and the received image feature information.

[0127] The program is executed by the processor to realize the tracking index method provided by all the embodiments of the present application:

[0128] The tracking result of the tracking target in the monitoring range of each front-end collection device is received and stored, wherein the tracking result of the tracking target includes the candidate identification information of the wireless device collected by each front-end collection device and the image feature information of the tracking target;

[0129] Based on the candidate identification information of the wireless device collected by each front-end collection device and the image feature information of the tracking target, the front-end collection device associated with the trajectory of the tracking target is determined.

[0130] Any combination of one or more computer readable medium can be employed. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.

[0131] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0132] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0133] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] Example 7

[0135] Embodiment 7 of this application provides an electronic device. Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment Seven of this application. Figure 6 As shown, this embodiment provides an electronic device 600, which includes: one or more processors 620; and a storage device 610 for storing one or more programs. When the one or more programs are executed by the one or more processors 620, the one or more processors 620 implement the target tracking and shooting method (the electronic device is a front-end acquisition device) provided in this application embodiment. The method includes:

[0136] If a target is detected entering the shooting range, the candidate identification information of the wireless device collected by the wireless network module is obtained, and the image feature information of the target is collected.

[0137] If the candidate identification information and the image feature information transmitted by the previous front-end acquisition device are received, the tracking result of the tracking target in the monitoring range of the current front-end acquisition device is determined according to the candidate identification information collected in the preset time and the received candidate identification information, and / or according to the image feature information collected in the preset time and the received image feature information.

[0138] Alternatively, a tracking index method (the electronic device is a server) for achieving the object provided by all the embodiments of the present application is implemented, and the method comprises the following steps:

[0139] receiving and storing the tracking result of the tracking target in the monitoring range of each front-end acquisition device; wherein the tracking result of the tracking target comprises the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracking target;

[0140] determining the track-associated front-end acquisition device of the tracking target based on the candidate identification information of the wireless device collected by each front-end acquisition device and the image feature information of the tracking target.

[0141] Of course, those skilled in the art can understand that the processor 620 also implements the technical solutions of the tracking shooting method of the target or the tracking index method of the target provided by any embodiment of the present application.

[0142] Figure 6 The electronic device 600 shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0143] As shown in Figure 6 the electronic device 600 comprises a processor 620, a storage device 610, an input device 630 and an output device 640; the number of processors 620 in the electronic device can be one or more, Figure 6 and the processor 620 in the electronic device is taken as an example; the processor 620, the storage device 610, the input device 630 and the output device 640 in the electronic device can be connected through a bus or other means, Figure 6 and the connection through the bus 650 is taken as an example.

[0144] The storage device 610, as a kind of computer readable storage medium, can be used to store software programs, computer executable programs and module units, such as the program instructions corresponding to the tracking shooting method of the target or the tracking index method of the target in the embodiments of the present application.

[0145] The storage 610 can include a program storage area that can store an operating system, at least one application program required for a function, and a data storage area that can store data created according to use of the terminal, etc. In addition, the storage 610 can include a high-speed random access memory, and can further include a non-volatile memory such as at least one of a magnetic disk storage device, a flash memory device, or other non-volatile solid state memory device. In some examples, the storage 610 can further include a memory disposed remotely with respect to the processor 620, and these remote memories can be connected through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The input device 630 can be used to receive inputted numbers, character information, or voice information, and to generate key signal input related to user settings and function control of the electronic device. The output device 640 can include a display screen, a speaker, etc. of the electronic device.

[0147] The electronic device provided by the embodiments of the present application can realize the effect of autonomous tracking by simultaneously using multiple front-end collection devices and using the same mark for the same target in videos collected by different front-end collection devices.

[0148] The target tracking and photographing device, the target tracking and indexing device, the medium, and the electronic device provided in the above embodiments can execute the target tracking and photographing method or the target tracking and indexing method provided by any of the embodiments of the present application, and have the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the above embodiments can be referred to the target tracking and photographing method or the target tracking and indexing device provided by any of the embodiments of the present application.

[0149] Note that the above merely provides preferred embodiments of the present application and the technical principles applied. It is understood by those skilled in the art that the present application is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A tracking photographing method of an object, characterized by, The method is executed by a front-end collection device, the front-end collection device is configured with a wireless network module, the wireless network module is set to a wireless access point opening mode, the front-end collection device is associated with at least one front-end collection device, and the method comprises: If it is detected that a tracking target enters the shooting range, candidate identification information of a wireless device collected by the wireless network module is acquired, and image feature information of the tracking target is collected; If candidate identification information and image feature information transmitted by a previous front-end collection device are received, tracking results of the tracking target in a monitoring range of the current front-end collection device are determined according to candidate identification information collected within a preset time and the received candidate identification information, and image feature information collected within the preset time and the received image feature information; The tracking results of the tracking target in the monitoring range of the current front-end collection device are determined according to candidate identification information collected within a preset time and the received candidate identification information, and image feature information collected within the preset time and the received image feature information, and comprise: The candidate identification information intersection is determined according to candidate identification information collected within a preset time and the received candidate identification information, and the image feature information similarity is determined according to the collected image feature information and the received image feature information; If there is at least one candidate identification information in the candidate identification information intersection, and the image feature information similarity exceeds a set threshold, tracking results of the tracking target in the monitoring range of the current front-end collection device are obtained; If there is no intersection of the candidate identification information, tracking results of the tracking target in the monitoring range of the current front-end collection device are obtained as no tracking target; The candidate identification information comprises time, a wireless device number, a received signal strength indication, and a MAC address of the wireless device; and the candidate identification information intersection is obtained by performing an intersection operation on at least one item of content included in the candidate identification information; After it is detected that a tracking target enters the shooting range, the method further comprises: If candidate identification information and image feature information transmitted by a previous front-end collection device are received, tracking target coding information transmitted by the previous front-end collection device is used.

2. The method of claim 1, wherein, After tracking results of the tracking target in the monitoring range of the current front-end collection device are determined, the method further comprises: When the tracking target leaves the shooting range, a next front-end collection device through which the tracking target enters is determined according to a path analysis result; The tracking results of the tracking target are transmitted to the next front-end collection device, so that the next front-end collection device determines tracking results of the tracking target in a monitoring range of the next front-end collection device based on collected identification information and image feature information.

3. The method of claim 1, wherein, After it is detected that a tracking target enters the shooting range, the method further comprises: If candidate identification information and image feature information transmitted by a previous front-end collection device are not received, tracking target coding information is generated.

4. The method of claim 1, wherein, The method further comprises: When the tracking target leaves the shooting range, the wireless network module configured in the current front-end collection device is controlled to stop collecting candidate identification information of a wireless device.

5. The method of claim 1, wherein, The method further comprises: If at least two front-end collection devices receive candidate identification information and image feature information transmitted by a previous front-end collection device, and one of them detects that a tracking target enters the shooting range, the front-end collection device other than the one that detects the tracking target entering the shooting range stops collecting candidate identification information and stops identifying tracking results.

6. A target tracking indexing method, the method is executed by a server, the server is in communication connection with a front-end acquisition device, the front-end acquisition device is configured with a wireless network module, the front-end acquisition device executes the target tracking shooting method as claimed in any one of claims 1-5, characterized in that, The tracking index method of the target comprises: receiving and storing tracking results of the tracking target in the monitoring range of each front-end collection device; wherein the tracking results of the tracking target include candidate identification information of wireless devices collected by each front-end collection device, and image feature information of the tracking target; based on the candidate identification information of wireless devices collected by each front-end collection device, and the image feature information of the tracking target, determining the trajectory associated front-end collection device of the tracking target.

7. The method of claim 6, wherein, After determining the trajectory associated front-end collection device of the tracking target, the method further comprises: in response to an index request of the tracking target, obtaining index feature information of the tracking target; wherein the index feature information includes identification information and / or image feature information of the wireless device of the tracking target; based on the index feature information, calling the trajectory associated front-end collection device of the tracking target, and generating an index result video of the tracking target according to the collection time of each trajectory associated front-end collection device.

8. A tracking camera device for a target, characterized by, The device is configured in a front-end collection device, the front-end collection device is configured with a wireless network module, the wireless network module is set to a wireless access point start mode, the front-end collection device is associated with at least one front-end collection device, and the device comprises: a tracking target information collection module, configured to obtain candidate identification information of wireless devices collected by the wireless network module and collect image feature information of the tracking target if it is detected that a tracking target enters the shooting range; a tracking result determination module, configured to determine the tracking results of the tracking target in the monitoring range of the current front-end collection device according to candidate identification information collected within a preset time and received candidate identification information, and image feature information collected within a preset time and received image feature information, if candidate identification information and image feature information transmitted by a previous front-end collection device are received. The tracking result determination module is further configured to: determine the intersection of candidate identification information according to candidate identification information collected within a preset time and received candidate identification information, and determine the image feature information similarity according to collected image feature information and received image feature information; if there is at least one candidate identification information in the intersection of candidate identification information, and the image feature information similarity exceeds a set threshold, the tracking results of the tracking target in the monitoring range of the current front-end collection device are obtained; if there is no intersection of candidate identification information, the tracking results of the tracking target in the monitoring range of the current front-end collection device are obtained as no tracking target; wherein the candidate identification information includes time, wireless device number, received signal strength indication and MAC address of the wireless device; the intersection of candidate identification information is the intersection operation on at least one content included in the candidate identification information. Wherein, after detecting that the tracking target enters the shooting range, the method further comprises: If candidate identification information and image feature information transmitted by the previous front-end acquisition device are received, the encoding information of the tracking target transmitted by the previous front-end acquisition device is used.

9. A tracking index device of a target, the device is configured in a server, the server is in communication connection with a front-end acquisition device, the front-end acquisition device is configured with a wireless network module, the front-end acquisition device is also configured as the tracking shooting device of the target according to claim 8, characterized in that, The tracking index device of the target comprises: A tracking result receiving module, configured to receive and store tracking results of the tracking target in the monitoring range of each front-end acquisition device; wherein, the tracking results of the tracking target comprise candidate identification information of the wireless device collected by each front-end acquisition device, and image feature information of the tracking target; A trajectory-associated front-end acquisition device determining module, configured to determine the trajectory-associated front-end acquisition device of the tracking target based on the candidate identification information of the wireless device collected by each front-end acquisition device, and the image feature information of the tracking target.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the target tracking shooting method of any one of claims 1-5, or the target tracking index method of any one of claims 6-7.

11. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the target tracking shooting method of any one of claims 1-5, or the target tracking index method of any one of claims 6-7.

Images