Object determination method and system

By setting time threshold and similarity matching in the monitoring system, combining trajectory data and position information, we can automatically judge strange objects in the video, solving the problem of low manual screening efficiency in the existing technology, and achieving rapid identification and accurate monitoring of strange objects .

CN114495009BActive Publication Date: 2024-11-19CHONGQING UNISINSIGHT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210135082.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-14
Publication Date
2024-11-19
Estimated Expiration
2042-02-14

AI Technical Summary

Technical Problem

The existing technology lacks automated methods to screen new unfamiliar objects in surveillance videos in real time, and usually rely on manual screening, resulting in inefficiency.

Method used

By obtaining all the data of online devices, filtering the data of the target device, setting time thresholds for repeated data filtering, performing similarity matching, combining trajectory data and position information to determine whether the object is a strange object, and adjusting it through real-time archive gathering and data verification Thresholds to improve accuracy.

Benefits of technology

It realizes the rapid identification of unfamiliar objects in massive data, reduces the difficulty of user observation, avoids frequent image search load, and improves monitoring efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114495009B_ABST
    Figure CN114495009B_ABST
Patent Text Reader

Abstract

The present invention provides an object determination method and system, the method comprising: obtaining data of all devices on the network, filtering the data once according to the device attribution of the data according to the target device, and obtaining target image data; determining repeated data in the target image data by comparing the acquisition time and the first time threshold, and performing secondary filtering; determining objects less than the similarity threshold as unfamiliar objects through similarity matching; if greater than or equal to, obtaining trajectory data; if there is trajectory data, determining it as a non-strange object; if there is no trajectory data, judging the data validity according to the spatiotemporal accessibility of the trajectory data; the present invention eliminates the situation of repeated capture of devices through the time threshold, avoids frequent image-based file searches causing excessive load on real-time file aggregation services, and reduces the difficulty of user observation, preventing old data from affecting the generation of unfamiliar object data in the current environment, without the need to observe global massive data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the fields of security and computer application, and in particular to an object determination method and system. Background Art

[0002] As modern society places increasingly higher demands on security precautions, the security field has developed rapidly in recent years. More and more front-end cameras have been created by users, and massive amounts of structured data and images have been stored, which are relatively convenient for users to troubleshoot subsequent problems.

[0003] As user demands continue to increase, in practical applications, it is sometimes necessary to screen out new unfamiliar objects in a specific area that is monitored by the customer in real time. However, in the prior art, the screening method by establishing a database is not applicable, and usually only manual screening can be used. There is currently no automated solution for this. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides an object determination method and system to solve the above-mentioned technical problems.

[0005] The object determination method provided by the present invention comprises:

[0006] Acquire the data of all devices on the network, filter the data once according to the device ownership of the pre-selected target device, remove the data of non-target devices, and acquire the target image data including the target object;

[0007] Presetting a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, wherein the first time threshold is smaller than the second time threshold, and the second time threshold is smaller than the third time threshold;

[0008] Acquire the last piece of data transmitted by the target device where the target image data is located, as well as the acquisition time, determine duplicate data in the target image data by comparing the acquisition time with the first time threshold, and perform secondary filtering to remove the duplicate data;

[0009] Performing similarity matching between a target object in the target image data and an archive object in a pre-established image database;

[0010] If the matching result is less than the preset similarity threshold, the target object is determined to be a stranger;

[0011] If the matching result is greater than or equal to the similarity threshold, then obtaining the trajectory data of the archive object between the second time threshold and the third time threshold;

[0012] If the trajectory data exists, determining that the target object is a non-strange object;

[0013] If the trajectory data does not exist, it is determined whether the target object is a strange object based on the position information of the trajectory data.

[0014] In one embodiment of the present invention,

[0015] If the server has the last piece of data transmitted by the target device, and the acquisition time difference between the target data and the last piece of data is less than or equal to the first time threshold, the target image data is determined to be duplicate data, and the data is discarded;

[0016] If the server has the last piece of data transmitted by the target device, and the acquisition time difference between the target data and the last piece of data is greater than the first time threshold, the target image data is determined to be non-duplicate data, and the capture data time of the target device in the server is updated;

[0017] If the previous data transmitted by the target device does not exist in the server, or the acquisition time difference between the target data and the previous data is greater than the first time threshold, the acquisition time of the target image data is used as the captured data time of the target device in the server.

[0018] In one embodiment of the present invention, judging whether the target object is a strange object according to the location information of the trajectory data includes:

[0019] Acquire the collection device of the archive object, the location information of the collection device and the location information of the target device, wherein the location information includes the latitude and longitude of the device;

[0020] According to the location information, it is determined whether the target object is reachable in time and space. If it is reachable in time and space, the target object is determined to be a strange object. If it is not reachable in time and space, the target object is determined to be a non-strange object.

[0021] In one embodiment of the present invention, determining whether the target object is reachable in time and space includes:

[0022] According to the location information of the acquisition device and the location information of the target device, the speed of the target object is calculated.

[0023] If the speed is within a preset speed threshold range, it is determined to be reachable in time and space;

[0024] If the speed exceeds the speed threshold range, it is determined that the time and space are unreachable.

[0025] In one embodiment of the present invention, filtering data according to target devices includes:

[0026] Pre-set device list;

[0027] According to the target image data corresponding to the target device, a target device list is obtained;

[0028] Filter the data of all devices on the network whose devices are not in the target device list, and save the data consumption progress in the server after filtering.

[0029] In one embodiment of the present invention, it further includes performing real-time aggregation according to the target device list, and providing data services through real-time aggregation, wherein the data services include:

[0030] Perform similarity matching and archive aggregation on image data;

[0031] Based on the input image data, archive retrieval is performed and the retrieval results are fed back.

[0032] In one embodiment of the present invention, the data is periodically checked:

[0033] Periodically obtain the false positive rate and missed positive rate of determining that the target object is a strange object;

[0034] When the false positive rate and the missed positive rate exceed the preset verification threshold, the first time threshold, the second time threshold and the third time threshold are adjusted in the next cycle, and the adjusted false positive rate and the missed positive rate are obtained;

[0035] The optimal time threshold is obtained by comparing data from multiple cycles.

[0036] The present invention also includes an object determination system, characterized in that it includes a server side, and the server side is provided with:

[0037] Data acquisition module, used to obtain data from all devices on the network;

[0038] A filtering module, for filtering the data once according to the device belonging to the data according to the pre-selected target device, obtaining the target image data including the target object, and performing a secondary filtering on the data determined to be duplicate;

[0039] a configuration module, configured to preset a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, wherein the first time threshold is smaller than the second time threshold, and the second time threshold is smaller than the third time threshold;

[0040] A judgment module, used to judge whether the target object is a strange object;

[0041] Acquire the last piece of data transmitted by the target device where the target image data is located, as well as the acquisition time, and determine duplicate data in the target image data by comparing the acquisition time with the first time threshold;

[0042] Performing similarity matching between a target object in the target image data and an archive object in a pre-established image database;

[0043] If the matching result is less than the preset similarity threshold, the target object is determined to be a stranger;

[0044] If the matching result is greater than or equal to the similarity threshold, then obtaining the trajectory data of the archive object between the second time threshold and the third time threshold;

[0045] If the trajectory data exists, determining that the target object is a non-strange object;

[0046] If the trajectory data does not exist, whether the target object is a strange object is determined based on the location information of the trajectory data. The present invention also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements any of the above methods when executed by a processor.

[0047] The present invention also provides an electronic terminal, comprising: a processor and a memory;

[0048] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods described above.

[0049] Beneficial effects of the present invention: The object determination method and system in the present invention can find the most concerned data in massive data and realize early warning of unfamiliar objects. The time threshold can eliminate the situation where the device repeatedly captures the image, avoid frequent image searches that cause excessive load on the real-time archiving business, and at the same time reduce the user's observation difficulty and prevent previous old data from affecting the generation of unfamiliar object data in the current environment, so that users do not need to observe the global massive data, and can directly view the data through specific areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of a specific embodiment of the object determination method in the embodiment of the present invention.

[0051] Figure 2 It is a schematic diagram of the overall flow of the object determination method in an embodiment of the present invention.

[0052] Figure 3 A schematic diagram of the hardware structure of a terminal device provided in an embodiment.

[0053] Figure 4 A schematic diagram of the hardware structure of a terminal device provided in another embodiment.

[0054] Description of Reference Numerals

[0055] 1100 Input Devices

[0056] 1101 First Processor

[0057] 1102 Output devices

[0058] 1103 First Memory

[0059] 1104 Communication Bus

[0060] 1200 Processing Components

[0061] 1201 Second processor

[0062] 1202 Second Memory

[0063] 1203 Communication Components

[0064] 1204 Power Supply Components

[0065] 1205 Multimedia Components

[0066] 1206 Voice Component

[0067] 1207 Input / Output Interface

[0068] 1208 Sensor Components DETAILED DESCRIPTION

[0069] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0070] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0071] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0072] like Figure 1 As shown, the object determination method in this embodiment includes:

[0073] S101 obtains data from all devices on the network, filters the data once according to the device attribution of the data according to the pre-selected target device, and obtains target image data including the target object;

[0074] S102. Preset a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, respectively, the first time threshold is less than the second time threshold, and the second time threshold is less than the third time threshold;

[0075] S103. Obtain the last data transmitted by the target device where the target image data is located, as well as the acquisition time,

[0076] S104. Determine and filter duplicate data in the target image data by comparing the acquisition time and the first time threshold;

[0077] S105. Perform similarity matching between the target object in the target image data and the file object in the pre-established image database,

[0078] S106. If the matching result is less than the preset similarity threshold, the target object is determined to be a strange object;

[0079] S107. If the matching result is greater than or equal to the similarity threshold, then obtaining the trajectory data of the archive object between the second time threshold and the third time threshold;

[0080] S108. If there is trajectory data, it is determined that the target object is a non-strange object;

[0081] S109. If the trajectory data does not exist, determine whether the target object is a strange object based on the location information of the trajectory data.

[0082] In step S101 of this embodiment, firstly, the data of all devices on the network are obtained, and the data is filtered once according to the target device to obtain the target image data including the target object. Since there may be a large number of devices in the entire environment, and each device is pushing corresponding data to the system, the data consumption scheme in this embodiment is to consume all data, independently record the data consumption progress, that is, the consumption offset, and independently manage the progress of data consumption. First, determine whether the data is in the device list specified by the user. If it is not in the user list, the data is filtered out, the data is not processed, and the offset record is added to the database and server. The server in this embodiment can be a data structure server redis. If the data is in the device list set by the user, that is, the target device list, the subsequent process processing is performed.

[0083] In step S102 of the present embodiment, a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening are preset, the first time threshold is less than the second time threshold, and the second time threshold is less than the third time threshold. In the present embodiment, the first time threshold, the second time threshold and the third time threshold can be set to 5 seconds, within 5 minutes, and 30 minutes, respectively. Among them, the main function of the first time threshold is the deduplication time of the same device, and the main function of the second time threshold and the third time threshold is the repeated alarm time of strange objects and the invalid trajectory time, that is, the valid trajectory time is outside 5 minutes and within 30 minutes. After the configuration is completed, the data is accessed. After the data is accessed, the data is filtered and the business logic is judged. If the conditions are met, the data is considered to be strange object data, and the alarm information is returned.

[0084] In steps S103 and S104 of this embodiment, the last data transmitted by the target device where the target image data is located, as well as the acquisition time, are obtained. By comparing the acquisition time with the first time threshold, the duplicate data in the target image data is determined and filtered. In this embodiment, if the data is in the device list, it is determined whether the acquisition data time of the device exists in the data structure server. If the acquisition time of the last data of the device exists, it is determined whether the time of the last data of the device is within 5 seconds. If so, it is considered that the data is reported repeatedly, the data is discarded, and the corresponding time of the device in the data structure server is not updated. If the time difference between the time of the last data and the current time is greater than 5S, it is considered that the data is not reported repeatedly, and subsequent process processing is performed, and the corresponding device capture time in the data structure server is updated; if there is no data of the device in the data structure server or the last data of the device is 5S ago, the corresponding device capture data time is added in redis and the subsequent process continues.

[0085] In steps S105-S108 of the present embodiment, the target object in the target image data is matched with the file object in the pre-established image database for similarity. If the matching result is less than the preset similarity threshold, the target object is determined to be a strange object; if the matching result is greater than or equal to the similarity threshold, the trajectory data of the file object between the second time threshold and the third time threshold is obtained; if the trajectory data exists, the target object is determined to be a non-strange object; if the trajectory data does not exist, the target object is determined to be a strange object according to the position information of the trajectory data. In the present embodiment, after the judgment is completed that the snapshot data that is not repeated within 5S is completed, the file search is performed to search the file trajectory of the snapshot image. If there is no file with a similarity reaching the threshold, the alarm of the strange object is directly performed. If there is a file with a similarity reaching the threshold, the trajectory point data within 5 minutes and beyond 30 minutes in the file trajectory is first excluded. If there is no other file trajectory after exclusion, it is considered to be a strange object of the file, and the next step of data confirmation is performed; if there is still a similar file trajectory after exclusion, it is considered that the data is not a strange object data, and no strange alarm is performed.

[0086] In this embodiment, after the result of searching for files by image shows that the file is a strange object, in order to prevent errors in the real-time data of the archive, the search for images will be checked again to confirm whether there is highly similar automatically collected picture data. If there is no highly similar picture, it is considered to be a strange object and strange object warning data is generated. If there is a highly similar picture, for example, the similarity threshold can be set to 88%. When it is higher than the similarity threshold, the spatiotemporal accessibility of the highly similar pictures is calculated.

[0087] In this embodiment, the calculation of spatiotemporal accessibility is performed through the location information of the trajectory data. First, the collection device of the archive object, the location information of the collection device and the location information of the target device are obtained, wherein the location information in this embodiment includes the longitude and latitude of the device; according to the location information, it is determined whether the target object is spatiotemporally accessible. If it is spatiotemporally accessible, the target object is determined to be a strange object. If it is not spatiotemporally accessible, the target object is determined to be a non-strange object. When making a judgment, first exclude all data within 5S (excluding its own pictures) and outside half an hour (too long data). If there is still data, find the longitude and latitude of the corresponding device based on highly similar pictures, and calculate the spatiotemporal accessibility. The spatiotemporal accessibility is calculated by the camera position of the similar picture and the position of the collected archive strange object. If the spatiotemporal accessibility of the search image is not reachable, it is considered that the similar data is invalid, and the archive strange object data is valid, and a strange object alarm is issued; if the spatiotemporal accessibility is reachable, the similar data is considered to be valid.

[0088] In this embodiment, the example calculation formula for calculating two points A and B on the earth according to longitude and latitude is:

[0089]

[0090] Among them, Lng1 and Lat1 represent the longitude and latitude of point A respectively, Lng2 and Lat2 represent the longitude and latitude of point B respectively, a=Lat1-Lat2 is the difference between the latitudes of the two points, b=Lng1-Lng2 is the difference between the longitudes of the two points, and 6378.137 is the equatorial radius of the earth in kilometers.

[0091] According to the formula:

[0092] V=S / (T1-T2)

[0093] Determine whether it is within the speed range of the object. If it is within the speed range, it is considered to be reachable in time and space. If it is not within the speed range, it is considered to be unreachable in time and space. The speed range V in this embodiment can be set in advance.

[0094] In this embodiment, it also includes real-time archiving according to the target device list, and providing data services through real-time archiving. The data services include: similarity matching of image data and aggregation of archives; archive retrieval and feedback of retrieval results based on the input image data. In this embodiment, real-time archiving tasks can be configured when collating a specific device list. The purpose is to improve technical data assurance for subsequent business. The system automatically adds real-time archiving tasks in sequence according to the user's newly added list. The specific method of real-time archiving can be implemented in the technology. Real-time archiving mainly provides two services. One is to perform data similarity analysis and archive aggregation on the collected pictures, and the other is to provide the ability to search archives by image, retrieve archives based on the incoming pictures, and return matching archive data.

[0095] In this embodiment, it also includes periodic data verification, and the judgment mechanism can be dynamically and adaptively adjusted based on the actual judgment accuracy. The false positive rate and missed positive rate of judging that the target object is a strange object are periodically obtained; when the false positive rate and missed positive rate exceed the preset verification threshold, the first time threshold, the second time threshold and the third time threshold are adjusted in the next cycle, and the adjusted false positive rate and missed positive rate are obtained; the optimal time threshold is obtained by comparing data from multiple cycles. Specifically, the alarm information can be checked to determine whether it is a misjudgment or omission, and the data screening method can be adjusted according to the misjudgment or omission rate until the best data screening method is selected, such as excluding data within X seconds, excluding repeated device capture, excluding trajectory points within Y minutes, avoiding multiple alarms within Y minutes for unfamiliar objects in the control circle, excluding data beyond Z minutes, and preventing previous old data from affecting the generation of unfamiliar object data in the current environment, that is, selecting the best X, Y, and Z values. For example, in one cycle, data within 5 seconds is excluded to exclude repeated device capture, but this method has a high misjudgment rate. In the next cycle, data within 4 seconds can be excluded to exclude repeated device capture. By comparing data from multiple cycles, the best exclusion time is obtained and applied to the judgment of unfamiliar objects in subsequent cycles to improve the accuracy of unfamiliar object judgment.

[0096] Accordingly, this embodiment further provides an object determination system, including a server side, wherein the server side is provided with:

[0097] Data acquisition module, used to obtain data from all devices on the network.

[0098] A filtering module, used to filter data according to a target device to obtain target image data including a target object;

[0099] a configuration module, configured to preset a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, wherein the first time threshold is smaller than the second time threshold, and the second time threshold is smaller than the third time threshold;

[0100] A judgment module, used to judge whether the target object is a strange object;

[0101] Get the last data transmitted by the target device where the target image data is located, as well as the acquisition time.

[0102] Determine and filter duplicate data in the target image data by comparing the acquisition time and the first time threshold;

[0103] The target object in the target image data is matched with the archive object in the pre-established image database by similarity.

[0104] If the matching result is less than the preset similarity threshold, the target object is determined to be a stranger;

[0105] If the matching result is greater than or equal to the similarity threshold, then obtaining the trajectory data of the archive object between the second time threshold and the third time threshold;

[0106] If the trajectory data exists, determining that the target object is a non-strange object;

[0107] If the trajectory data does not exist, it is determined whether the target object is a strange object based on the position information of the trajectory data.

[0108] In this embodiment, the server uses the data structure server Redis, and the value can be a string, hash, list, set, or sorted set. In the entire environment, there may be a large number of devices, and each device is pushing corresponding data to the system. The consumption data solution of this embodiment consumes all data, independently records the consumption offset, and independently manages the progress of data consumption. For example, if a stranger is a person, Figure 1 As shown, first determine whether the data is in the device list specified by the user. If it is not in the user list, the data is filtered out, the data is not processed, and the offset record is added to the database and redis. If the data is in the device list set by the user, the subsequent process processing is carried out. If the data is in the device list, determine whether the data collection time of the device exists in redis. If there is the collection time of the previous data of the device, determine whether the time of the previous data of the device is within 5s. If so: the data is considered to be reported repeatedly, the data is discarded, and the corresponding time of the device in redis is not updated. If the time difference between the time of the previous data and the current time is greater than 5S, it is considered to be non-duplicate reporting of data, and the subsequent process processing is carried out, and the corresponding device capture time in redis is updated; if there is no data of the device in redis or the previous data of the device is 5S ago, the corresponding device capture data time is added in redis and the subsequent process continues.

[0109] In this embodiment, after judging that the captured data is not repeated within 5S, the image search is performed to search the archive track of the captured image. If there is no archive with a similarity reaching the threshold, the alarm of the strange object is directly performed. If there is an archive with a similarity reaching the threshold, the track point data within 5 minutes and beyond 30 minutes in the archive track is first excluded. If there is no other archive track after exclusion, it is considered to be an archive strange object, and the next step of data confirmation is performed; if there is still a similar archive track after exclusion, it is considered that the data is not a strange object data, and no strange alarm is performed. When it is displayed as an archive strange object according to the result of the image search, in order to prevent errors in the real-time aggregated data, the image search function will be performed again to confirm whether there is highly similar automatically collected picture data. If there is no highly similar picture, it is considered to be a strange object, and strange object alarm data is generated. If there is a highly similar picture (the threshold can be set to 88%), the highly similar pictures are calculated in time and space. First, exclude all data within 5S (excluding its own pictures) and outside half an hour (data that is too old). If there is still data, find the longitude and latitude of the corresponding device based on highly similar pictures and calculate the spatiotemporal accessibility. The spatiotemporal accessibility is calculated based on the camera position of similar pictures and the position of the collected archived unfamiliar objects. If the spatiotemporal accessibility of the image search is not reachable, it is considered that the similar data is invalid, the archived unfamiliar object data is valid, and an unfamiliar object alarm is issued; if the spatiotemporal accessibility is reachable, the similar data is considered valid.

[0110] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented.

[0111] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0112] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0113] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0114] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0115] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0116] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0117] Figure 3 This is a schematic diagram of the hardware structure of a terminal device provided in one embodiment of the present application. Figure 3 As shown, the terminal device may include: an input device 1100, a first processor 1101, an output device 1102, a first memory 1103 and at least one communication bus 1104. The communication bus 1104 is used to realize the communication connection between the components. The first memory 1103 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage. Various programs may be stored in the first memory 1103 to complete various processing functions and implement the method steps of this embodiment.

[0118] Optionally, the first processor 1101 may be implemented, for example, as a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and the first processor 1101 is coupled to the input device 1100 and the output device 1102 via a wired or wireless connection.

[0119] Optionally, the input device 1100 may include multiple input devices, for example, at least one of a user interface for users, a device interface for devices, a software programmable interface, a camera, and a sensor. Optionally, the device interface for devices may be a wired interface for data transmission between devices, or a hardware insertion interface for data transmission between devices (such as a USB interface, a serial port, etc.); Optionally, the user interface for users may be, for example, a control button for users, a voice input device for receiving voice input, and a touch sensing device for users to receive user touch input (such as a touch screen with a touch sensing function, a touchpad, etc.); Optionally, the software programmable interface may be, for example, an entry for users to edit or modify programs, such as an input pin interface or an input interface of a chip; the output device 1102 may include output devices such as a display and a speaker.

[0120] In this embodiment, the processor of the terminal device includes functions for executing each module of the voice recognition device in each device. The specific functions and technical effects can be referred to the above embodiments and will not be repeated here.

[0121] Figure 4 A schematic diagram of the hardware structure of a terminal device provided for one embodiment of the present application. Figure 4 Yes Figure 3 A specific embodiment in the implementation process. Figure 4 As shown, the terminal device of this embodiment may include a second processor 1201 and a second memory 1202 .

[0122] The second processor 1201 executes the computer program code stored in the second memory 1202 to implement the above embodiment. Figure 4 The method.

[0123] The second memory 1202 is configured to store various types of data to support operations on the terminal device. Examples of such data include instructions for any application or method used to operate on the terminal device, such as messages, pictures, videos, etc. The second memory 1202 may include a random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage.

[0124] Optionally, the second processor 1201 is arranged in the processing component 1200. The terminal device may further include: a communication component 1203, a power component 1204, a multimedia component 1205, a voice component 1206, an input / output interface 1207 and / or a sensor component 1208. The specific components included in the terminal device are set according to actual needs, and this embodiment does not limit this.

[0125] The processing component 1200 generally controls the overall operation of the terminal device. The processing component 1200 may include one or more second processors 1201 to execute instructions to complete all or part of the steps in the above-mentioned data processing method. In addition, the processing component 1200 may include one or more modules to facilitate the interaction between the processing component 1200 and other components. For example, the processing component 1200 may include a multimedia module to facilitate the interaction between the multimedia component 1205 and the processing component 1200.

[0126] The power supply component 1204 provides power to various components of the terminal device. The power supply component 1204 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal device.

[0127] The multimedia component 1205 includes a display screen that provides an output interface between the terminal device and the user. In some embodiments, the display screen may include a liquid crystal display (LCD) and a touch panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0128] The voice component 1206 is configured to output and / or input voice signals. For example, the voice component 1206 includes a microphone (MIC), and when the terminal device is in an operating mode, such as a voice recognition mode, the microphone is configured to receive an external voice signal. The received voice signal can be further stored in the second memory 1202 or sent via the communication component 1203. In some embodiments, the voice component 1206 also includes a speaker for outputting voice signals.

[0129] The input / output interface 1207 provides an interface between the processing component 1200 and the peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include but are not limited to: volume buttons, start buttons, and lock buttons.

[0130] The sensor component 1208 includes one or more sensors for providing various aspects of status assessment for the terminal device. For example, the sensor component 1208 can detect the open / closed state of the terminal device, the relative positioning of the components, and the presence or absence of contact between the user and the terminal device. The sensor component 1208 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact, including detecting the distance between the user and the terminal device. In some embodiments, the sensor component 1208 may also include a camera, etc.

[0131] The communication component 1203 is configured to facilitate wired or wireless communication between the terminal device and other devices. The terminal device can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In one embodiment, the terminal device may include a SIM card slot for inserting a SIM card, so that the terminal device can log in to a GPRS network and establish communication with a server via the Internet.

[0132] From the above, we can see that Figure 4 The communication component 1203, the voice component 1206, the input / output interface 1207, and the sensor component 1208 involved in the embodiment can all be used as Figure 3 Implementation method of the input device in the embodiment.

[0133] In the above embodiments, unless otherwise specified, the use of serial numbers such as "first" and "second" to describe common objects only indicates that they refer to different instances of the same object, rather than indicating that the objects being described must adopt a given order, whether in time, space, sorting or any other way.

[0134] In the above embodiments, the description refers to "this embodiment", "an embodiment", "another embodiment", or "other embodiments" to indicate that the specific features, structures, or characteristics described in conjunction with the embodiments are included in at least some embodiments, but not necessarily all embodiments. Multiple occurrences of "this embodiment", "an embodiment", or "another embodiment" do not necessarily all refer to the same embodiment.

[0135] In the above-described embodiments, although the invention has been described in conjunction with specific embodiments of the invention, many substitutions, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other storage structures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed. Embodiments of the invention are intended to encompass all such substitutions, modifications, and variations that fall within the broad scope of the appended claims.

[0136] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0137] The present invention can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like.

[0138] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0139] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An object determination method, characterized in that: include: Acquire the data of all devices on the network, filter the data once according to the device ownership of the pre-selected target device, remove the data of non-target devices, and acquire the target image data including the target object; Presetting a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, wherein the first time threshold is smaller than the second time threshold, and the second time threshold is smaller than the third time threshold; Obtain the last piece of data transmitted by the target device where the target image data is located, and the acquisition time, and determine the duplicate data in the target image data by comparing the acquisition time with the first time threshold, and perform secondary filtering to eliminate the duplicate data, wherein obtaining the last piece of data transmitted by the target device where the target image data is located, and the acquisition time, and determining the duplicate data in the target image data by comparing the acquisition time with the first time threshold, and performing secondary filtering to eliminate the duplicate data includes: if the last piece of data transmitted by the target device exists in the server, and the acquisition time difference between the target image data and the last piece of data is less than or equal to the first time threshold, determining that the target image data is duplicate data, and discarding the data; if the last piece of data transmitted by the target device exists in the server, and the acquisition time difference between the target image data and the last piece of data is greater than the first time threshold, determining that the target image data is non-duplicate data, and updating the captured data time of the target device in the server; if the last piece of data transmitted by the target device does not exist in the server, or the acquisition time difference between the target image data and the last piece of data is greater than the first time threshold, using the acquisition time of the target image data as the captured data time of the target device in the server; Performing similarity matching between a target object in the target image data and an archive object in a pre-established image database; If the matching result is less than the preset similarity threshold, the target object is determined to be a stranger; If the matching result is greater than or equal to the similarity threshold, then obtaining the trajectory data of the archive object between the second time threshold and the third time threshold; If the trajectory data exists, determining that the target object is a non-strange object; If the trajectory data does not exist, it is determined whether the target object is a strange object based on the position information of the trajectory data.

2. The object determination method according to claim 1, characterized in that: The determining whether the target object is a strange object according to the location information of the trajectory data includes: Acquire the collection device of the archive object, the location information of the collection device and the location information of the target device, wherein the location information includes the latitude and longitude of the device; According to the location information, it is determined whether the target object is reachable in time and space. If it is reachable in time and space, the target object is determined to be a strange object. If it is not reachable in time and space, the target object is determined to be a non-strange object.

3. The object determination method according to claim 2, characterized in that: Determining whether the target object is reachable in time and space includes: Calculate the speed of the target object according to the location information of the acquisition device and the location information of the target device; If the speed is within a preset speed threshold range, it is determined to be reachable in time and space; If the speed exceeds the speed threshold range, it is determined that the time and space are unreachable.

4. The object determination method according to claim 1, characterized in that: The filtering of the data according to the device belonging to the data according to the pre-selected target device includes: Pre-set device list; According to the target image data corresponding to the target device, a target device list is obtained; Filter the data of all devices on the network whose devices are not in the target device list, and save the data consumption progress in the server after filtering.

5. The object determination method according to claim 4, characterized in that: It also includes performing real-time aggregation according to the target device list, and providing data services through real-time aggregation, wherein the data services include: Perform similarity matching and archive aggregation on image data; Based on the input image data, archive retrieval is performed and the retrieval results are fed back.

6. The object determination method according to claim 1, characterized in that: It also includes periodic data verification, and the periodic data verification includes: Periodically obtain the false positive rate and missed positive rate of determining that the target object is a strange object; When the false positive rate and the missed positive rate exceed the preset verification threshold, the first time threshold, the second time threshold and the third time threshold are adjusted in the next cycle, and the adjusted false positive rate and the missed positive rate are obtained; The optimal time threshold is obtained by comparing data from multiple cycles.

7. An object determination system, characterized in that: The server comprises: Data acquisition module, used to obtain data from all devices on the network; A filtering module is used to filter the data once according to the device belonging to the data according to the pre-selected target device, remove the data of non-target devices, obtain the target image data including the target object, and perform a secondary filtering on the data determined to be duplicate; a configuration module, configured to preset a first time threshold for determining data duplication, and a second time threshold and a third time threshold for trajectory screening, wherein the first time threshold is smaller than the second time threshold, and the second time threshold is smaller than the third time threshold; A judgment module is used to judge whether the target object is a strange object, obtain the last data transmitted by the target device where the target image data is located, and the acquisition time, and judge the repeated data in the target image data by comparing the acquisition time and the first time threshold; perform similarity matching on the target object in the target image data and the archive object in the pre-established image database; if the matching result is less than the preset similarity threshold, the target object is judged to be a strange object; if the matching result is greater than or equal to the similarity threshold, the trajectory data of the archive object between the second time threshold and the third time threshold is obtained; if the trajectory data exists, the target object is judged to be a non-strange object; if the trajectory data does not exist, whether the target object is a strange object is judged according to the position information of the trajectory data; wherein, the last data transmitted by the target device where the target image data is located is obtained, and the acquisition time and the first time threshold are compared; the target object in the target image data is matched with the archive object in the pre-established image database; if the matching result is less than the preset similarity threshold, the target object is judged to be a strange object; if the matching result is greater than or equal to the similarity threshold, the trajectory data of the archive object between the second time threshold and the third time threshold are obtained; if the trajectory data exists, the target object is judged to be a non-strange object; if the trajectory data does not exist, whether the target object is a strange object is judged according to the position information of the trajectory data; Collection time, by comparing the collection time with the first time threshold, determining the duplicate data in the target image data, and performing secondary filtering to eliminate the duplicate data includes: if the server has the last data transmitted by the target device, and the collection time difference between the target image data and the last data is less than or equal to the first time threshold, determining that the target image data is duplicate data, and discarding the data; if the server has the last data transmitted by the target device, and the collection time difference between the target image data and the last data is greater than the first time threshold, determining that the target image data is non-duplicate data, and updating the captured data time of the target device in the server; if the server does not have the last data transmitted by the target device, or the collection time difference between the target image data and the last data is greater than the first time threshold, using the collection time of the target image data as the captured data time of the target device in the server.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic terminal, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic terminal executes the method according to any one of claims 1 to 6.