A method, apparatus, electronic device, and storage medium for associating image files.

Abstract

This application provides a method, apparatus, electronic device, and storage medium for associating image files, relating to the field of data analysis technology. In this application, based on the overlap degree between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information within a specified time range, the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information is obtained. This allows for the selection of target trajectory information that meets preset similarity conditions, and then the identification information of the target object is associated with the target image file corresponding to the target trajectory information. By using this application, and based on the trajectory similarity between the candidate trajectory information and the actual trajectory information, the identification information of the target object is associated with the target image file corresponding to the target trajectory information, accurately linking the collected trajectory information of the target object to the corresponding image file.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method, apparatus, electronic device and storage medium for associating image files. Background Technology

[0002] With the continuous development of social security construction and Internet of Things technology, the deployment of image acquisition equipment is becoming increasingly sophisticated, and the amount of trajectory information that can be collected is gradually increasing. Therefore, image acquisition equipment can realize the collection of trajectory information of target objects.

[0003] For example, to obtain the trajectory information of a target object, image clustering is used to sort the collected image data containing the same target object by time to generate a corresponding image dataset. Then, each image data in the image dataset is traversed, and the time interval between adjacent image data is compared to whether it meets a preset time threshold condition, and the distance interval between adjacent image data meets a preset distance threshold condition. Finally, when it is detected that adjacent image data meets both the preset time threshold condition and the preset distance threshold condition, the adjacent image data is used as the trajectory information of the target object.

[0004] Furthermore, based on the spatiotemporal characteristics of each image acquisition data containing the same target object, after obtaining the trajectory information of the target object, the trajectory information of the target object acquired by the image acquisition device can be attributed to the image acquisition archive of the target object according to the feature information of the target object.

[0005] However, when using the above image aggregation method, the light intensity may be low when the image acquisition device is collecting the trajectory information of the target image, resulting in blurry feature information of the target object. Therefore, it is impossible to accurately classify the collected trajectory information of the target object into the target object's image file, and thus it is impossible to obtain other trajectory information of the target object in the image file.

[0006] Therefore, the above method cannot accurately associate the collected trajectory information of the target object with the corresponding image file. Summary of the Invention

[0007] This application provides a method, apparatus, electronic device, and storage medium for associating image files, so as to accurately associate the trajectory information of the acquired target object with the corresponding image file.

[0008] In a first aspect, embodiments of this application provide a method for associating image files, the method comprising:

[0009] Within a specified time range, obtain the actual trajectory information of the target object and the candidate trajectory information of each candidate object; wherein, the actual trajectory information includes: at least one monitoring point and its respective monitoring point identifier; each candidate trajectory information includes: at least one monitoring point and its respective monitoring point identifier.

[0010] Based on the overlap between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information, the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information is obtained.

[0011] Based on the obtained similarity of each trajectory, target trajectory information that meets the preset similarity conditions is selected from each candidate trajectory information.

[0012] Identify the target image file corresponding to the target trajectory information and associate the target object's identification information with the target image file.

[0013] Secondly, embodiments of this application also provide an image file association device, the device comprising:

[0014] The acquisition module is used to acquire the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range. The actual trajectory information includes at least one monitoring point and its respective monitoring point identifier. Each candidate trajectory information includes at least one monitoring point and its respective monitoring point identifier.

[0015] The processing module is used to obtain the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information.

[0016] The selection module is used to select target trajectory information that meets the preset similarity conditions from the candidate trajectory information based on the obtained trajectory similarity.

[0017] The association module is used to determine the target image file corresponding to the target trajectory information and associate the identification information of the target object with the target image file.

[0018] In an optional embodiment, before acquiring the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range, the acquisition module is further configured to:

[0019] Obtain the location information corresponding to each monitoring point.

[0020] The location information of each monitoring point is geo-hash encoded to obtain the corresponding encoding results.

[0021] Each of the obtained coding results will be used as the monitoring point identifier for the corresponding monitoring point.

[0022] In an optional embodiment, when obtaining the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information, the processing module is specifically used for:

[0023] For at least one candidate trajectory information, perform the following operations respectively:

[0024] Obtain the number of target road segments with the same monitoring point identifiers corresponding to each candidate trajectory segment in the candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information.

[0025] Based on the number of at least one target road segment obtained, and the number of candidate road segments corresponding to a candidate trajectory information, the overlap degree of monitoring point identification between a candidate trajectory information and the actual trajectory information is determined.

[0026] Based on the overlap of monitoring point identifiers, the trajectory similarity between a candidate trajectory and the actual trajectory is obtained.

[0027] In an optional embodiment, when obtaining the number of target road segments with the same monitoring point identifier corresponding to each candidate trajectory segment included in a candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information, the processing module is specifically used for:

[0028] Based on the respective monitoring point identifiers of each monitoring point, at least one actual trajectory segment is obtained from the actual trajectory information, and at least one candidate trajectory segment is obtained from one candidate trajectory information, and the number of candidate segments of one candidate trajectory information is recorded.

[0029] For at least one target trajectory segment, perform the following operations respectively:

[0030] Obtain the monitoring point identifier corresponding to a target trajectory segment, and the monitoring point identifier corresponding to at least one candidate trajectory segment.

[0031] Determine the number of target road segments in each candidate trajectory segment that correspond to the same monitoring point identifier as an actual trajectory segment.

[0032] In one optional embodiment, when obtaining at least one actual trajectory segment from the actual trajectory information based on the monitoring point identifiers of each monitoring point, the processing module is specifically used for:

[0033] In acquiring actual trajectory information, target monitoring information is obtained by each monitoring point; each target monitoring information includes at least the target monitoring time when the corresponding monitoring point detected the target object.

[0034] For each pair of target monitoring information obtained from adjacent monitoring points, perform the following operations:

[0035] Determine the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points.

[0036] Based on the time interval to which the monitoring time interval belongs, for the original trajectory road segments corresponding to the monitoring information of two targets, the target road segment division rule is selected from the preset candidate road segment division rule set.

[0037] Based on the target road segment division rules, the original trajectory road segments are divided to obtain at least one actual trajectory road segment.

[0038] In one optional embodiment, when dividing the original trajectory segment based on the target road segment division rule to obtain at least one actual trajectory segment, the processing module is specifically used for:

[0039] If the monitoring time interval is greater than the preset time interval threshold, the original trajectory segment is divided according to the set first time interval to obtain the corresponding two actual trajectory segments.

[0040] If the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are different, the original trajectory segment is divided according to the set second time interval to obtain two corresponding actual trajectory segments; wherein, the first time interval is greater than the second time interval.

[0041] If the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are the same, then the original trajectory segment is directly regarded as an actual trajectory segment.

[0042] In an optional embodiment, during the process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment, the processing module is further configured to:

[0043] If the original trajectory segment is divided based on the target segment division rules to obtain two actual trajectory segments, then according to the time order in which the target object appears in the two actual trajectory segments, the monitoring point identifiers corresponding to the two adjacent monitoring points are assigned to the corresponding actual trajectory segments in the two actual trajectory segments.

[0044] Thirdly, this application provides an electronic device, the electronic device comprising:

[0045] Memory, used to store computer programs;

[0046] When the processor executes the computer program stored in the memory, it implements the steps of the image file association method described above.

[0047] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the image file association method described above.

[0048] Fifthly, a computer program product is provided, which, when invoked by a computer, causes the computer to perform the image file association method steps as described in the first aspect.

[0049] The image file association method provided in this application, based on the overlap degree between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information within a specified time range, obtains the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information, thereby selecting the target trajectory information that meets the preset similarity condition, and then associating the identifier information of the target object with the target image file corresponding to the target trajectory information. This method, by associating the identifier information of the target object with the target image file corresponding to the target trajectory information based on the trajectory similarity between the candidate trajectory information and the actual trajectory information, avoids the technical defect that leads to blurred feature information of the target object due to weak light during image acquisition, thus preventing the accurate attribution of the acquired target object's trajectory information to the target object's image file. It can accurately associate the acquired target object's trajectory information with the corresponding image file. Attached Figure Description

[0050] Figure 1 An exemplary diagram illustrates an application scenario to which the embodiments of this application are applicable;

[0051] Figure 2 An exemplary illustration shows a flowchart of a method for obtaining monitoring point identifiers provided in an embodiment of this application;

[0052] Figure 3 An exemplary illustration shows a schematic diagram of an encoding principle provided in an embodiment of this application;

[0053] Figure 4 An exemplary embodiment of this application provides a method based on... Figure 2 A logical diagram;

[0054] Figure 5 An exemplary flowchart of an image file association method provided in an embodiment of this application is shown.

[0055] Figure 6 An exemplary illustration shows a logical diagram of obtaining actual trajectory information and various candidate trajectory information provided in an embodiment of this application;

[0056] Figure 7 An exemplary schematic diagram illustrates a method for obtaining trajectory similarity according to an embodiment of this application;

[0057] Figure 8 An exemplary illustration shows a flowchart of a method for obtaining actual trajectory road segments provided in an embodiment of this application;

[0058] Figure 9 An exemplary illustration shows a logical diagram of a target road segment division rule provided in an embodiment of this application;

[0059] Figure 10 An exemplary embodiment of this application provides a method based on... Figure 5 A logical diagram;

[0060] Figure 11 A schematic diagram illustrating the structure of an image file association device provided in an embodiment of this application is shown.

[0061] Figure 12 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0062] In order to accurately associate the collected trajectory information of the target object with the corresponding image file, in this embodiment of the application, based on the overlap degree of each candidate trajectory information with the monitoring point identifier of the actual trajectory information within a specified time range, the trajectory similarity between the candidate trajectory information and the actual trajectory information is obtained respectively, thereby selecting the target trajectory information that meets the preset similarity condition, and then associating the identifier information of the target object with the target image file corresponding to the target trajectory information.

[0063] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application will be explained below.

[0064] (1) Media Access Control Address: Also known as MAC address, it is an address used to identify the location of a network device. It is used to uniquely identify a network card in the network. If a device has one or more network cards, each network card needs and will have a unique MAC address.

[0065] (2) Geohash Encoding: Geohash encoding refers to converting latitude and longitude coordinates into a sortable and comparable string encoding. The Geohash encoding rules are as follows: Longitude [-180, 180] and latitude [-90, 90] are used as the ranges, divided by the equator and the Prime Meridian. The latitude range [-90, 0) is represented by binary 0, and (0, 90] by binary 1; the longitude range [-180, 0) is represented by binary 0, and (0, 180] by binary 1; and this division is recursively performed in half.

[0066] Furthermore, according to the above Geohash encoding rules, longitude and latitude are converted into binary, and then the binary codes of longitude and latitude are merged according to the rule that longitude is in even positions and latitude is in odd positions. Finally, the merged binary codes are encoded according to the Base32 encoding table to form a Geohash code.

[0067] For example, taking the latitude and longitude coordinates of monitoring point 1 [116.390705, 39.923201] as an example, the latitude 39.923201 belongs to (0, 90], so it is coded as 1; then (0, 90] is divided into two intervals: (0, 45) and (45, 90], and 39.923201 is located in (0, 45), so it is coded as 0; then (0, 45) is divided into two intervals: (0, 22.5) and (22.5, 45), and 39... .923201 is located at (22.5, 45), so its encoding is 1; and so on. Using the above encoding method, the binary encoding of the latitude of monitoring point 1 is: 101110001100011111. Similarly, the binary encoding of the longitude of monitoring point 1 is: 11010010110001000100. Further, by merging the binary encodings of latitude and longitude, with longitude occupying even-numbered positions and latitude occupying odd-numbered positions, the mixed binary encoding is: 11100 11101 00100 01111 00000 01101 01011 00001. If the Base32 encoding table uses the 32 characters 0-9 and BZ (excluding A, I, L, O) for encoding, then the Base32 encoding corresponding to the mixed binary encoding is: WX4G0EC1.

[0068] (3) Base32 encoding: refers to encoding binary data into a visible string. The encoding rule is: given any binary data, it is divided into groups of 5 bits, and each group is encoded to obtain a visible character. For ease of understanding, in this paper, the Base32 encoding table uses 32 characters: 0-9 and BZ (excluding A, I, L, O).

[0069] (4) Radio Frequency Identification (RFID) is an automatic identification technology that uses wireless radio frequency to conduct non-contact two-way data communication and uses wireless radio frequency to read and write recording media (electronic tags or RFID cards) to achieve the purpose of identifying targets and exchanging data.

[0070] It should be noted that the above-mentioned naming method for technical terms is only an example, and the embodiments of this application do not limit the naming method of the above-mentioned technical terms.

[0071] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this invention.

[0072] It should be noted that in the description of this application, "multiple" is understood as "at least two". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A connected to B can represent: A and B directly connected, or A and B connected through C. Furthermore, in the description of this application, terms such as "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or order.

[0073] Figure 1 An exemplary diagram illustrates the application scenario to which the embodiments of this application are applicable, such as... Figure 1 As shown in the diagram, this application scenario includes: a server 101, a terminal device 102, image acquisition devices (103a, 103b, 103c), and a public road 104. The image acquisition devices (103a, 103b, 103c) are positioned at regular intervals on the public road 104 and can transmit their acquired monitoring information to the terminal device 102. Furthermore, the server 101 and the terminal device 102 can exchange information via wireless or wired communication.

[0074] For example, server 101 can access the network via cellular mobile communication technology to communicate with terminal device 102, such as 5th generation mobile networks (5G) technology.

[0075] Optionally, server 101 can access the network via short-range wireless communication to communicate with terminal device 102. The short-range wireless communication method may include, for example, Wireless Fidelity (Wi-Fi) technology.

[0076] This application embodiment does not limit the number of servers and other devices mentioned above. Figure 1 This description uses only one server as an example.

[0077] Server 101 is used to acquire the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range; then, based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information, the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information is obtained; further, based on the obtained trajectory similarity, the target trajectory information that meets the preset similarity conditions is selected from each candidate trajectory information; finally, the target image file corresponding to the target trajectory information is determined, and the identification information of the target object is associated with the target image file.

[0078] Terminal device 102 is a device that can provide voice and / or data connectivity to users, including handheld terminal devices with wireless connectivity, vehicle-mounted terminal devices, etc.

[0079] For example, terminal devices can be: mobile phones, tablets, laptops, handheld computers, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminal devices in industrial control, wireless terminal devices in autonomous driving, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, or wireless terminal devices in smart homes, etc.

[0080] It should be noted that the terminal device 102 can summarize the monitoring information obtained by each image acquisition device (103a, 103b, 103c) to obtain the actual trajectory information of the target object.

[0081] Image acquisition devices (103a, 103b, 103c) are devices used to acquire images or record videos, including handheld image acquisition devices with wireless connectivity, head-mounted image acquisition devices, and fixed image acquisition devices.

[0082] For example, image acquisition devices can be: cameras, video cameras, digital still cameras (DSC), single-lens reflex cameras (SLRC), other image acquisition devices with photo-taking capabilities (mobile phones, tablets, etc.), video capture cards, etc. It should be noted that in this embodiment, the image acquisition device at the monitoring point is described using a checkpoint acquisition device as an example. The checkpoint acquisition device is used to acquire trajectory information sources of multiple traffic objects (including target objects) forming trajectories from the departure area to the arrival area, including but not limited to: MAC acquisition, RFID, vehicle information, etc.

[0083] For ease of description, this article takes MAC acquisition as an example. The checkpoint acquisition device can use devices such as base stations or local area network gateways that communicate with the mobile communication device to obtain the MAC address of the mobile communication device, and then use the MAC address to locate the position of the mobile communication device, thereby obtaining the target trajectory information of the target object corresponding to the mobile terminal device.

[0084] Furthermore, based on the above application scenario diagram, obtain the monitoring point identifier corresponding to each monitoring point, as shown in the reference. Figure 2 As shown in the embodiment of this application, the method flow for obtaining monitoring point identifiers includes the following specific steps:

[0085] S201: Obtain the location information corresponding to each monitoring point.

[0086] Specifically, when executing step S201, the server can use the location information data feature extraction algorithm to obtain the location information corresponding to each monitoring point from the feature datasets of each monitoring point contained in the original database.

[0087] For example, the original database contains feature datasets for each checkpoint acquisition device. Each feature dataset includes at least the location information of the checkpoint acquisition device. The server can use a feature extraction algorithm based on the location information to obtain the location information of the corresponding checkpoint acquisition device from each feature dataset and use the location information of the checkpoint acquisition device as the location information of the corresponding monitoring point.

[0088] S202: Perform geohashing encoding on the location information corresponding to each monitoring point to obtain the corresponding encoding results.

[0089] Specifically, in step S202, after obtaining the location information corresponding to each monitoring point, the server determines the latitude and longitude coordinates of the corresponding monitoring point according to the data type of latitude and longitude, and then obtains the encoding result of the corresponding monitoring point according to the Geohash encoding.

[0090] For example, the server can perform Geohash encoding on the location information of the checkpoint data acquisition device, encoding the two-dimensional spatial latitude and longitude data into a string of a specified number of bits. See [reference needed]. Figure 3 As shown, the basic principle of Geohash is: The Earth is understood as a two-dimensional plane, which is recursively decomposed into smaller sub-blocks. Each sub-block has the same encoded value within a certain latitude and longitude range. Here, similar encoded strings indicate that the corresponding data acquisition devices are close in distance; in most cases, the more prefixes match, the closer the distance.

[0091] It is worth noting that since the location information of the checkpoint acquisition device is fixed, the server can accelerate the calculation process of subsequent trajectory similarity and other related parameters by encoding the location information of the checkpoint acquisition device.

[0092] S203: Use the obtained coding results as the monitoring point identifiers for the corresponding monitoring points.

[0093] Specifically, when executing step S203, after obtaining the encoding results corresponding to each monitoring point, the server can directly use each encoding result as the monitoring point identifier corresponding to each monitoring point.

[0094] For example, see Figure 4 As shown, the server uses a feature extraction algorithm based on location information to obtain the location information corresponding to each monitoring point from the feature datasets of each monitoring point contained in the original database. Then, based on the latitude and longitude data type, the server obtains the latitude and longitude coordinates of the corresponding monitoring point from the obtained location information. Furthermore, the server performs Geohash encoding on each latitude and longitude coordinate to obtain the encoding result corresponding to each monitoring point. Finally, the obtained encoding results are used as the monitoring point identifiers of the corresponding monitoring points.

[0095] Furthermore, based on the aforementioned pre-processing, after the server obtains the monitoring point identifier corresponding to each monitoring point, refer to... Figure 5 As shown in the embodiment of this application, the method flow for associating image files with the actual trajectory information of the target object is as follows:

[0096] S501: Obtain the actual trajectory information of the target object and the candidate trajectory information of each candidate object within the specified time range.

[0097] Specifically, during step S501, the server, based on a specified time range, filters from the original database the candidate trajectory information of each candidate object that meets the specified time range and is obtained from each monitoring point, as well as the actual trajectory information of the target object. The actual trajectory information includes: at least one monitoring point and its respective monitoring point identifier; each candidate trajectory information includes: at least one monitoring point and its respective monitoring point identifier.

[0098] For example, assuming the specified time range is: 2022.01.07-2022.01.10 12:00-14:00, see [reference] Figure 6 As shown, the server can select candidate trajectory information that meets the specified time range requirements from the original trajectory information, based on the time information of each original trajectory information contained in the original database, and obtain the actual trajectory information of the target object at that time, for example, 12:02-13:58 on January 10, 2022. It should be noted that the specified time range is set according to the time range corresponding to the actual trajectory information of the target object.

[0099] S502: Based on the overlap of each candidate trajectory information with the monitoring point identifier of the actual trajectory information, obtain the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information.

[0100] In one possible implementation, during step S502, after obtaining the candidate trajectory information and the actual trajectory information, the server, for a candidate trajectory information, determines the similarity of monitoring point identifiers between the candidate trajectory information and the actual trajectory information based on the number of target road segments with the same monitoring point identifiers corresponding to the corresponding actual trajectory road segments in the actual trajectory information. This process yields the trajectory similarity between the candidate trajectory information and the actual trajectory information. (See [reference]). Figure 7 As shown, the specific steps are as follows:

[0101] S701: Obtain the number of target road segments with the same monitoring point identifiers corresponding to each candidate trajectory segment contained in the candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information.

[0102] Specifically, when executing step S701, the server obtains at least one actual trajectory segment from the actual trajectory information and at least one candidate trajectory segment from the candidate trajectory information based on the monitoring point identifier of each monitoring point, and records the number of candidate segments of a candidate trajectory information.

[0103] Furthermore, for at least one target trajectory segment, the following operations are performed respectively: obtain the monitoring point identifier corresponding to a target trajectory segment and the monitoring point identifier corresponding to at least one candidate trajectory segment, and then determine the number of target segments in each candidate trajectory segment that have the same monitoring point identifier as an actual trajectory segment.

[0104] For example, suppose the monitoring point identifier corresponding to the current actual trajectory segment is Geohash.A, and there are 6 candidate trajectory segments. The monitoring point identifiers corresponding to each candidate trajectory segment are, in order: Geohash.C, Geohash.A, Geohash.B, Geohash.A, Geohash.E, and Geohash.D. After comparing the monitoring point identifier corresponding to the current trajectory segment with the monitoring point identifiers corresponding to the 6 candidate trajectory segments in the candidate trajectory information, the server can determine that there are 2 target segments with the same monitoring point identifier among the current actual trajectory segment and the 6 candidate trajectory segments in the candidate trajectory information.

[0105] Optionally, after obtaining each actual trajectory segment and each candidate trajectory segment, the server can use the following method to obtain the total number of target segments with the same monitoring point identifier in the actual trajectory information and each candidate trajectory information within the set statistical period. Assuming the time threshold of the set statistical period is T2, the actual trajectory information Tra.1 and the candidate trajectory information Tra.2, within the set statistical period, are compared one by one in a traversal manner.

[0106] Specifically, assuming that within the set statistical period, the set of actual trajectory segments corresponding to the actual trajectory information Tra.1 is {A} k1 A k2 The set of candidate trajectory segments corresponding to candidate trajectory information Tra.2 is {B}. k3 B k4 The calculation method for the total number of target road segments with the same monitoring point identifier in the actual trajectory information Tra.1 and candidate trajectory information Tra.2 obtained through MAC acquisition is as follows:

[0107] a1+=1if geohash(A i ) = geohash(B j ), k1<=i<=k2, k3<=j<=k4

[0108] Where a1 represents the total number of target road segments with the same monitoring point identifier in the actual trajectory information Tra.1 and the candidate trajectory information Tra.2; geohash(A i) represents the monitoring point identifier corresponding to the i-th actual trajectory segment; geohash(B j ) is the identifier of the monitoring point corresponding to the j-th actual trajectory segment.

[0109] In one possible implementation, see [reference] Figure 8 As shown in the embodiment of this application, based on the monitoring point identifier of each monitoring point, at least one actual trajectory segment is obtained from the actual trajectory information. The specific steps are as follows:

[0110] S801: In acquiring actual trajectory information, the target monitoring information obtained by each monitoring point.

[0111] Specifically, when executing step S801, the server can extract the target monitoring information of each monitoring point from the actual trajectory information, and then, based on the data type of monitoring time, obtain the target monitoring time of the corresponding monitoring point monitoring the target object from each target monitoring information.

[0112] Furthermore, after obtaining the monitoring time of the target object from the actual trajectory information, the server performs the following operations for each pair of target monitoring information obtained from adjacent monitoring points:

[0113] S802: Determine the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points.

[0114] Specifically, the formula for calculating the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points during step S802 is as follows:

[0115] ΔT=T2-T1

[0116] Where ΔT is the monitoring time interval, and T1 and T2 are both target monitoring times, with target monitoring time T1 being earlier than target monitoring time T2.

[0117] S803: Based on the time interval to which the monitoring time interval belongs, for the original trajectory road segments corresponding to the two target monitoring information, select the target road segment division rule from the preset candidate road segment division rule set.

[0118] For details, please refer to Figure 9As shown, during step S803, after obtaining the monitoring time interval, the server selects the target road segment division rule from the preset set of candidate road segment division rules based on the time interval range to which the monitoring time interval belongs and the correspondence between the time interval range and the candidate road segment division rules. The time interval range can be divided into a first interval range, a second interval range, and a third interval range according to a first time threshold and a second time threshold. The first time threshold is less than the second time threshold, and the first time threshold indicates whether the monitoring point identifiers corresponding to two adjacent monitoring points are the same.

[0119] For example, assuming the first time threshold is 5 minutes and the second time threshold is 30 minutes, if the monitoring time interval is less than 5 minutes, the monitoring time interval belongs to the first interval, and it can be known that the monitoring point identifiers of two adjacent monitoring points are the same; if the monitoring time interval is greater than or equal to 5 minutes and less than 30 minutes, the monitoring time interval belongs to the second interval, and it can be known that the monitoring point identifiers of two adjacent monitoring points are different; if the monitoring time interval is greater than 30 minutes, the monitoring time interval belongs to the third interval, and it can be known that the monitoring point identifiers of two adjacent monitoring points are different.

[0120] S804: Based on the target road segment division rules, the original trajectory road segment is divided to obtain at least one actual trajectory road segment.

[0121] Specifically, during step S804, after the server selects the target road segment division rule corresponding to the monitoring time interval, it divides the original trajectory road segments corresponding to the two target monitoring information based on the target division rule to obtain one or two actual trajectory road segments. If the monitoring time interval is greater than a preset time interval threshold, the original trajectory road segment is divided according to the set first time interval to obtain the corresponding two actual trajectory road segments; if the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are different, the original trajectory road segment is divided according to the set second time interval to obtain the corresponding two actual trajectory road segments; wherein, the first time interval is greater than the second time interval; if the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are the same, the original trajectory road segment is directly taken as one actual trajectory road segment.

[0122] For example, taking a first time threshold of 5 minutes and a second time threshold of 30 minutes as an example, if the monitoring time interval is 52 minutes, it is easy to know that the monitoring time interval belongs to the third interval. Then, according to the first time interval, i.e., 26 minutes, the original trajectory segment is divided to obtain two corresponding actual trajectory segments. If the monitoring time interval is 28 minutes, it is easy to know that the monitoring time interval belongs to the second interval. Then, according to the second time interval, i.e., 14 minutes, the original trajectory segment is divided to obtain two corresponding actual trajectory segments. If the monitoring time interval is 3 minutes, it is easy to know that the monitoring time interval belongs to the first interval. Then, the original trajectory segment is directly taken as one actual trajectory segment.

[0123] Optionally, in the process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment, if the original trajectory segment is divided based on the target road segment division rule to obtain two actual trajectory segments, then according to the time order of the appearance of the target object in the two actual trajectory segments, the monitoring point identifiers corresponding to the two adjacent monitoring points are assigned to the corresponding actual trajectory segments in the two actual trajectory segments.

[0124] For example, suppose that the monitoring point identifiers corresponding to two adjacent monitoring points are Geohash.A and Geohash.B, and the monitoring point corresponding to Geohash.A detects the target object before the monitoring point corresponding to Geohash.B. If the monitoring time interval between these two adjacent monitoring points is 28 minutes, then according to the second time interval, i.e., 14 minutes, the original trajectory segment is divided to obtain two corresponding actual trajectory segments: SG1 and SG2. The target monitoring time corresponding to actual trajectory segment SG1 is earlier than the target monitoring time corresponding to actual trajectory segment SG2. Further, the monitoring point identifier Geohash.A is assigned to actual trajectory segment SG1, and the monitoring point identifier Geohash.B is assigned to actual trajectory segment SG2.

[0125] Optionally, in the process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment, if the original trajectory segment is divided based on the target road segment division rule to obtain an actual trajectory segment, then the same monitoring point identifier corresponding to two adjacent monitoring points is directly assigned to the actual trajectory segment.

[0126] For example, assuming that the monitoring point identifiers corresponding to two adjacent monitoring points are both Geohash.C, if the monitoring time interval is 3 minutes, the original trajectory segment can be directly used as an actual trajectory segment SG3. Furthermore, the monitoring point identifier Geohash.C is assigned to the actual trajectory segment SG3.

[0127] Based on similar method steps in S801 to S804, the server can obtain at least one candidate trajectory segment from a candidate trajectory information based on the monitoring point identifier of each monitoring point, and record the number of candidate segments of a candidate trajectory information, so it will not be described in detail here.

[0128] S702: Based on the number of at least one target road segment obtained and the number of candidate road segments corresponding to a candidate trajectory information, determine the overlap degree of monitoring point identification between a candidate trajectory information and the actual trajectory information.

[0129] Specifically, during step S702, after the server obtains the number of at least one target road segment, it summarizes the number of each target road segment to obtain the total number of target road segments. Then, it combines this with the number of candidate road segments corresponding to the candidate trajectory information to determine the overlap degree between the monitoring point identifiers of the candidate trajectory information and the actual trajectory information. The calculation formula is as follows:

[0130]

[0131] Where α is the overlap of monitoring point identifiers, which can be used as a reference indicator for subsequent determination of the association between the identifier information of the target object and the corresponding target image file; a1 is the total number of target road segments with the same monitoring point identifier in the actual trajectory information and candidate trajectory information; and m is the number of candidate road segments corresponding to the candidate trajectory information.

[0132] S703: Based on the overlap of monitoring point identifiers, obtain the trajectory similarity between a candidate trajectory information and the actual trajectory information.

[0133] For example, when executing step S703, after obtaining the overlap degree of monitoring point identifiers, the server can obtain the corresponding trajectory similarity based on the monitoring point identifier overlap degree conversion formula, which is as follows:

[0134] β=γ×α

[0135] Where β is the trajectory similarity; α is the overlap of monitoring point identifiers; and γ is the trajectory similarity conversion factor, which can be set according to the actual situation.

[0136] S503: Based on the obtained similarity of each trajectory, select the target trajectory information that meets the preset similarity conditions from each candidate trajectory information.

[0137] Specifically, in step S503, after obtaining the similarity of each trajectory, the server filters out at least one candidate similarity based on the obtained similarity of each trajectory and the preset similarity threshold, sorts the candidate similarities, filters out the target trajectory similarity that meets the similarity conditions, thereby determining the candidate trajectory information corresponding to the target trajectory similarity and using it as the target trajectory information.

[0138] For example, assuming the preset similarity threshold is t, when α is greater than t, the server can initially consider the corresponding candidate trajectory information to be similar to the actual trajectory information, where t is the similarity threshold set according to the actual business scenario; then, at least one candidate similarity greater than the similarity threshold is sorted in descending order of similarity from largest to smallest, and the maximum trajectory similarity is selected to determine the candidate trajectory information corresponding to the maximum trajectory similarity, and it is used as the target trajectory information.

[0139] S504: Determine the target image file corresponding to the target trajectory information, and associate the identification information of the target object with the target image file.

[0140] Specifically, when executing step S504, after determining the target trajectory information, the server determines the target image file corresponding to the target trajectory information from the preset image file set, and associates the identification information of the target object with the target image file. Each image file includes the feature information of the corresponding candidate object and all trajectory information.

[0141] For example, after determining the target image file corresponding to the target trajectory information, the server will collect the MAC address of the mobile communication device carried by the target object, and associate the MAC ID associated with the actual trajectory information with the feature information of the target image file. Then, the server can obtain the feature information of the target object and all trajectory information in the target image file associated with it through the MAC ID.

[0142] Based on the above methods and steps, please refer to Figure 10 As shown, the server obtains the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the actual trajectory information, each candidate trajectory information, and the overlap degree between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information within a specified time range. In this way, the server selects the candidate trajectory information that meets the preset similarity conditions and uses it as the target trajectory information. Then, the server associates the identifier information of the target object with the target image file corresponding to the target trajectory information.

[0143] The image file association method provided in this application, based on the overlap degree between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information within a specified time range, obtains the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information, thereby selecting the target trajectory information that meets the preset similarity condition, and then associating the identifier information of the target object with the target image file corresponding to the target trajectory information. This method, by associating the identifier information of the target object with the target image file corresponding to the target trajectory information based on the trajectory similarity between the candidate trajectory information and the actual trajectory information, avoids the technical defect that leads to blurred feature information of the target object due to weak light during image acquisition, thus preventing the accurate attribution of the acquired target object's trajectory information to the target object's image file. It can accurately associate the acquired target object's trajectory information with the corresponding image file.

[0144] Based on the same technical concept, embodiments of this application also provide an image file association device, which can implement the above-described method flow of embodiments of this application. For example... Figure 11 As shown, the image file association device includes: an acquisition module 1101, a processing module 1102, a selection module 1103, and an association module 1104, wherein:

[0145] The acquisition module 1101 is used to acquire the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range; wherein, the actual trajectory information includes: at least one monitoring point and its respective monitoring point identifier; each candidate trajectory information includes: at least one monitoring point and its respective monitoring point identifier.

[0146] The processing module 1102 is used to obtain the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information.

[0147] The selection module 1103 is used to select target trajectory information that meets the preset similarity conditions from each candidate trajectory information based on the obtained trajectory similarity.

[0148] The association module 1104 is used to determine the target image file corresponding to the target trajectory information and associate the identification information of the target object with the target image file.

[0149] In an optional embodiment, before acquiring the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range, the acquisition module 1101 is further configured to:

[0150] Obtain the location information corresponding to each monitoring point.

[0151] The location information of each monitoring point is geo-hash encoded to obtain the corresponding encoding results.

[0152] Each of the obtained coding results will be used as the monitoring point identifier for the corresponding monitoring point.

[0153] In an optional embodiment, when obtaining the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information, the processing module 1102 is specifically used for:

[0154] For at least one candidate trajectory information, perform the following operations respectively:

[0155] Obtain the number of target road segments with the same monitoring point identifiers corresponding to each candidate trajectory segment in the candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information.

[0156] Based on the number of at least one target road segment obtained, and the number of candidate road segments corresponding to a candidate trajectory information, the overlap degree of monitoring point identification between a candidate trajectory information and the actual trajectory information is determined.

[0157] Based on the overlap of monitoring point identifiers, the trajectory similarity between a candidate trajectory and the actual trajectory is obtained.

[0158] In an optional embodiment, when obtaining the number of target road segments with the same monitoring point identifier corresponding to each candidate trajectory segment included in a candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information, the processing module 1102 is specifically used for:

[0159] Based on the respective monitoring point identifiers of each monitoring point, at least one actual trajectory segment is obtained from the actual trajectory information, and at least one candidate trajectory segment is obtained from one candidate trajectory information, and the number of candidate segments of one candidate trajectory information is recorded.

[0160] For at least one target trajectory segment, perform the following operations respectively:

[0161] Obtain the monitoring point identifier corresponding to a target trajectory segment, and the monitoring point identifier corresponding to at least one candidate trajectory segment.

[0162] Determine the number of target road segments in each candidate trajectory segment that correspond to the same monitoring point identifier as an actual trajectory segment.

[0163] In an optional embodiment, when obtaining at least one actual trajectory segment from the actual trajectory information based on the monitoring point identifier of each monitoring point, the processing module 1102 is specifically used for:

[0164] In acquiring actual trajectory information, target monitoring information is obtained by each monitoring point; each target monitoring information includes at least the target monitoring time when the corresponding monitoring point detected the target object.

[0165] For each pair of target monitoring information obtained from adjacent monitoring points, perform the following operations:

[0166] Determine the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points.

[0167] Based on the time interval to which the monitoring time interval belongs, for the original trajectory road segments corresponding to the monitoring information of two targets, the target road segment division rule is selected from the preset candidate road segment division rule set.

[0168] Based on the target road segment division rules, the original trajectory road segments are divided to obtain at least one actual trajectory road segment.

[0169] In an optional embodiment, when dividing the original trajectory segment based on the target road segment division rule to obtain at least one actual trajectory segment, the processing module 1102 is specifically used for:

[0170] If the monitoring time interval is greater than the preset time interval threshold, the original trajectory segment is divided according to the set first time interval to obtain the corresponding two actual trajectory segments.

[0171] If the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are different, the original trajectory segment is divided according to the set second time interval to obtain two corresponding actual trajectory segments; wherein, the first time interval is greater than the second time interval.

[0172] If the monitoring time interval is not greater than the time interval threshold and the monitoring point identifiers of two adjacent monitoring points are the same, then the original trajectory segment is directly regarded as an actual trajectory segment.

[0173] In an optional embodiment, during the process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment, the processing module 1102 is further configured to:

[0174] If the original trajectory segment is divided based on the target segment division rules to obtain two actual trajectory segments, then according to the time order in which the target object appears in the two actual trajectory segments, the monitoring point identifiers corresponding to the two adjacent monitoring points are assigned to the corresponding actual trajectory segments in the two actual trajectory segments.

[0175] Based on the same technical concept, embodiments of this application also provide an electronic device that can implement the method flow provided in the above embodiments of this application. In one embodiment, the electronic device may be a server, a terminal device, or other electronic equipment. Figure 12 As shown, the electronic device may include:

[0176] At least one processor 1201 and a memory 1202 connected to at least one processor 1201. In this embodiment, the specific connection medium between the processor 1201 and the memory 1202 is not limited. Figure 12 The example shown is the connection between processor 1201 and memory 1202 via bus 1200. Bus 1200 is... Figure 12 The connections between other components are shown in thick lines only and are not intended to be limiting. The Bus 1200 can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 12 The term is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, the processor 1201 can also be called a controller; there is no restriction on the name.

[0177] In this embodiment, the memory 1202 stores instructions executable by at least one processor 1201. By executing the instructions stored in the memory 1202, the at least one processor 1201 can execute the image file association method described above. The processor 1201 can implement... Figure 11 The functions of each module in the device shown.

[0178] The processor 1201 is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 1202 and calling data stored in memory 1202, the processor can perform various functions and process data, thereby monitoring the device as a whole.

[0179] In one possible design, processor 1201 may include one or more processing units. Processor 1201 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 1201. In some embodiments, processor 1201 and memory 1202 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0180] The processor 1201 can be a general-purpose processor, such as a CPU, digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the image file association method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0181] Memory 1202, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 1202 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory 1202 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 1202 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0182] By designing and programming the processor 1201, the code corresponding to the image file association method described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute the code during operation. Figure 5 The steps of an image file association method according to the illustrated embodiment are described below. How to design and program the processor 1201 is a technique well-known to those skilled in the art and will not be elaborated upon here.

[0183] Based on the same inventive concept, embodiments of this application also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform an image file association method described above.

[0184] In some possible implementations, various aspects of the image file association method provided by this application can also be implemented in the form of a program product, which includes program code that, when the program product is run on a device, causes the control device to perform the steps in the image file association method according to various exemplary embodiments of this application described above.

[0185] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0186] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0187] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0188] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A method for associating image archives, characterized in that, include: Within a specified time range, obtain the actual trajectory information of the target object and the candidate trajectory information of each candidate object; wherein, the actual trajectory information includes: at least one monitoring point and its respective monitoring point identifier; each candidate trajectory information includes: at least one monitoring point and its respective monitoring point identifier; Based on the overlap degree between each candidate trajectory information and the monitoring point identifier of the actual trajectory information, the trajectory similarity between the corresponding candidate trajectory information and the actual trajectory information is obtained respectively. Based on the obtained trajectory similarity, target trajectory information that meets the preset similarity condition is selected from the candidate trajectory information; Determine the target image file corresponding to the target trajectory information, and associate the identification information of the target object with the target image file; The step of obtaining the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information includes: For each of the at least one candidate trajectory information, the following operations are performed: Each candidate trajectory segment contained in a candidate trajectory information is obtained, and the number of target segments with the same monitoring point identifier corresponding to the actual trajectory segment in the actual trajectory information is obtained. Based on the number of at least one target road segment obtained, and the number of candidate road segments corresponding to the candidate trajectory information, the overlap degree of the monitoring point identifier between the candidate trajectory information and the actual trajectory information is determined; Based on the overlap of the monitoring point identifiers, the trajectory similarity between the candidate trajectory information and the actual trajectory information is obtained.

2. The method as described in claim 1, characterized in that, Before obtaining the actual trajectory information of the target object and the candidate trajectory information of each candidate object within the specified time range, the process further includes: Obtain the location information corresponding to each monitoring point; Geographic hashing is performed on the location information of each monitoring point to obtain the corresponding encoding results; Each of the obtained coding results will be used as the monitoring point identifier for the corresponding monitoring point.

3. The method as described in claim 1, characterized in that, The step of obtaining the number of target road segments with the same monitoring point identifier corresponding to each candidate trajectory segment in the candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information includes: Based on the monitoring point identifier of each monitoring point, at least one actual trajectory segment is obtained from the actual trajectory information, and at least one candidate trajectory segment is obtained from the candidate trajectory information, and the number of candidate segments of the candidate trajectory information is recorded. For each of the at least one target trajectory segment, perform the following operations: Obtain the monitoring point identifier corresponding to a target trajectory segment, and the monitoring point identifier corresponding to each of the at least one candidate trajectory segment; Determine the number of target road segments in each candidate trajectory segment that have the same monitoring point identifier as the actual trajectory segment.

4. The method as described in claim 3, characterized in that, The step of obtaining at least one actual trajectory segment from the actual trajectory information based on the monitoring point identifiers of each monitoring point includes: The actual trajectory information is obtained from the target monitoring information obtained by each monitoring point; wherein each target monitoring information includes at least: the target monitoring time when the corresponding monitoring point detected the target object; For each pair of target monitoring information obtained from adjacent monitoring points, perform the following operations: Determine the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points; Based on the time interval to which the monitoring time interval belongs, for the original trajectory road segments corresponding to the two target monitoring information, target road segment division rules are selected from the preset candidate road segment division rule set; Based on the target road segment division rules, the original trajectory road segment is divided to obtain at least one actual trajectory road segment.

5. The method as described in claim 4, characterized in that, The step of dividing the original trajectory segment based on the target road segment division rule to obtain at least one actual trajectory segment includes: If the monitoring time interval is greater than the preset time interval threshold, the original trajectory segment is divided according to the set first time interval to obtain two corresponding actual trajectory segments. If the monitoring time interval is not greater than the time interval threshold, and the monitoring point identifiers of the two adjacent monitoring points are different, then the original trajectory segment is divided according to the set second time interval to obtain two corresponding actual trajectory segments; wherein, the first time interval is greater than the second time interval; If the monitoring time interval is not greater than the time interval threshold, and the monitoring point identifiers of the two adjacent monitoring points are the same, then the original trajectory segment is directly regarded as an actual trajectory segment.

6. The method as described in claim 4 or 5, characterized in that, The process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment further includes: If the original trajectory segment is divided based on the target segment division rule to obtain two actual trajectory segments, then according to the time order of the appearance of the target object in the two actual trajectory segments, the monitoring point identifiers corresponding to the two adjacent monitoring points are assigned to the corresponding actual trajectory segments in the two actual trajectory segments.

7. An image archive association device, characterized in that, include The acquisition module is used to acquire the actual trajectory information of the target object and the candidate trajectory information of each candidate object within a specified time range; wherein, the actual trajectory information includes: at least one monitoring point and its respective monitoring point identifier; each candidate trajectory information includes: at least one monitoring point and its respective monitoring point identifier; The processing module is used to obtain the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the overlap degree between the monitoring point identifiers of each candidate trajectory information and the actual trajectory information. The selection module is used to select target trajectory information that meets the preset similarity conditions from the candidate trajectory information based on the obtained trajectory similarity. The association module is used to determine the target image file corresponding to the target trajectory information and associate the identification information of the target object with the target image file; Specifically, when obtaining the trajectory similarity between the candidate trajectory information and the actual trajectory information based on the overlap degree of the monitoring point identifiers between each candidate trajectory information and the actual trajectory information, the processing module is used to: For each of the at least one candidate trajectory information, the following operations are performed: Each candidate trajectory segment contained in a candidate trajectory information is obtained, and the number of target segments with the same monitoring point identifier corresponding to the actual trajectory segment in the actual trajectory information is obtained. Based on the number of at least one target road segment obtained, and the number of candidate road segments corresponding to the candidate trajectory information, the overlap degree of the monitoring point identifier between the candidate trajectory information and the actual trajectory information is determined; Based on the overlap of the monitoring point identifiers, the trajectory similarity between the candidate trajectory information and the actual trajectory information is obtained.

8. The apparatus as claimed in claim 7, characterized in that, Before acquiring the actual trajectory information of the target object and the candidate trajectory information of each candidate object within the specified time range, the acquisition module is further configured to: Obtain the location information corresponding to each monitoring point; Geographic hashing is performed on the location information of each monitoring point to obtain the corresponding encoding results; Each of the obtained coding results will be used as the monitoring point identifier for the corresponding monitoring point.

9. The apparatus as claimed in claim 7, characterized in that, When obtaining the number of target road segments with the same monitoring point identifier corresponding to each candidate trajectory segment in the candidate trajectory information and the corresponding actual trajectory segment in the actual trajectory information, the processing module is specifically used for: Based on the monitoring point identifier of each monitoring point, at least one actual trajectory segment is obtained from the actual trajectory information, and at least one candidate trajectory segment is obtained from the candidate trajectory information, and the number of candidate segments of the candidate trajectory information is recorded. For each of the at least one target trajectory segment, perform the following operations: Obtain the monitoring point identifier corresponding to a target trajectory segment, and the monitoring point identifier corresponding to each of the at least one candidate trajectory segment; Determine the number of target road segments in each candidate trajectory segment that have the same monitoring point identifier as the actual trajectory segment.

10. The apparatus as claimed in claim 9, characterized in that, When obtaining at least one actual trajectory segment from the actual trajectory information based on the respective monitoring point identifiers of each monitoring point, the processing module is specifically used for: The actual trajectory information is obtained from the target monitoring information obtained by each monitoring point; wherein each target monitoring information includes at least: the target monitoring time when the corresponding monitoring point detected the target object; For each pair of target monitoring information obtained from adjacent monitoring points, perform the following operations: Determine the monitoring time interval between two target monitoring information obtained from two adjacent monitoring points; Based on the time interval to which the monitoring time interval belongs, for the original trajectory road segments corresponding to the two target monitoring information, target road segment division rules are selected from the preset candidate road segment division rule set; Based on the target road segment division rules, the original trajectory road segment is divided to obtain at least one actual trajectory road segment.

11. The apparatus as claimed in claim 10, characterized in that, When dividing the original trajectory segment based on the target road segment division rule to obtain at least one actual trajectory segment, the processing module is specifically used for: If the monitoring time interval is greater than the preset time interval threshold, the original trajectory segment is divided according to the set first time interval to obtain two corresponding actual trajectory segments. If the monitoring time interval is not greater than the time interval threshold, and the monitoring point identifiers of the two adjacent monitoring points are different, then the original trajectory segment is divided according to the set second time interval to obtain two corresponding actual trajectory segments; wherein, the first time interval is greater than the second time interval; If the monitoring time interval is not greater than the time interval threshold, and the monitoring point identifiers of the two adjacent monitoring points are the same, then the original trajectory segment is directly regarded as an actual trajectory segment.

12. The apparatus as claimed in claim 10 or 11, characterized in that, In the process of dividing the original trajectory segment based on the target road segment division rule to obtain at least one corresponding actual trajectory segment, the processing module is further configured to: If the original trajectory segment is divided based on the target segment division rule to obtain two actual trajectory segments, then according to the time order of the appearance of the target object in the two actual trajectory segments, the monitoring point identifiers corresponding to the two adjacent monitoring points are assigned to the corresponding actual trajectory segments in the two actual trajectory segments.

13. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-6.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

15. A computer program product, characterized in that, When the computer program product is invoked by a computer, it causes the computer to perform the method as described in any one of claims 1-6.

Images