Method and device for adding global parameter for synchronizing intelligent CCTV analysis server data

Abstract

Provided are a method and a device for adding a global parameter for synchronizing intelligent CCTV analysis server data. The method may comprise the steps of: receiving image data from a camera device; extracting a first image hash value for each frame of the image data; storing the extracted first image hash values in a sequential queue; receiving analysis server data from an analysis server; extracting, from among the first image hash values stored in the sequential queue, a specific first image hash value that matches a second image hash value included in the analysis server data; extracting a specific frame corresponding to the specific first image hash value; and mapping metadata included in the analysis server data to the specific frame.

Description

Method and device for adding global parameters for intelligent CCTV analysis server data synchronization

[0001] The present disclosure relates to a method and apparatus for adding global parameters for synchronizing intelligent CCTV analysis server data.

[0002] CCTV surveillance systems are being applied in various fields for purposes such as facility management, disaster response, security, and traffic management.

[0003] Existing CCTVs utilized a method that only provided recorded video to the client in real time, but this approach had the problem of being inefficient for control center operators to monitor.

[0004] Accordingly, an intelligent CCTV system based on video understanding and recognition technology was introduced.

[0005] Intelligent CCTV systems utilize complex image processing technologies such as object detection, tracking, and event detection. With the recent rise in the use of intelligent CCTVs, there is an increasing demand to utilize additional metadata for real-time video.

[0006] The embodiments disclosed in this disclosure aim to provide a method and apparatus for adding global parameters for intelligent CCTV analysis server data synchronization.

[0007] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0008] A method for adding global parameters for intelligent CCTV analysis server data synchronization according to one aspect of the present disclosure for achieving the aforementioned technical problem may include: receiving video data from a camera device; extracting a first image hash value for each frame of the video data; storing the extracted first image hash value in a sequential queue; receiving analysis server data from an analysis server; extracting a specific first image hash value that matches a second image hash value included in the analysis server data among the first image hash values ​​stored in the sequential queue; extracting a specific frame corresponding to the specific first image hash value; and mapping metadata included in the analysis server data to the specific frame.

[0009] In addition, the above metadata can be generated through object recognition for each frame.

[0010] Additionally, the above method may further include the step of parsing and storing the received analysis server data into the second image hash value and the metadata.

[0011] In addition, the first image hash value and the second image hash value are each generated by the device and the analysis server, respectively, for the same frame, and can be utilized as global parameters for synchronization between the image data and the analysis server data.

[0012] Additionally, the above method may further include the step of excluding the specific first image hash value from the sequential queue.

[0013] Additionally, in the step of excluding from the sequential queue, if there is at least one first image hash value placed before the specific first image hash value in the sequential queue, the at least one first image hash value may also be excluded from the sequential queue along with the specific first image hash value.

[0014] In addition, the above method may further include a step of outputting the image data based on the mapped result.

[0015] Additionally, the outputting step may apply the metadata to only at least one frame to which the metadata is mapped among a plurality of consecutive frames containing the same object.

[0016] Additionally, a device for adding global parameters for synchronizing intelligent CCTV analysis server data according to another aspect of the present disclosure for achieving the aforementioned technical problem comprises a communication unit, a memory storing at least one process for synchronizing intelligent CCTV analysis server data using global parameters, and a processor that performs operations based on said process. The processor receives image data from a camera device through the communication unit, extracts a first image hash value for each frame of the image data, stores the extracted first image hash value in a sequential queue, receives analysis server data from an analysis server through the communication unit, extracts a specific first image hash value that matches a second image hash value included in the analysis server data among the first image hash values ​​stored in the sequential queue, extracts a specific frame corresponding to the specific first image hash value, and maps metadata included in the analysis server data to the specific frame.

[0017] In addition, a computer program stored on a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0018] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0019] According to the aforementioned means for solving the problem of the present disclosure, synchronization with metadata sent from an analysis server can be ensured when a client receives real-time CCTV camera footage while maintaining the existing CCTV system configuration.

[0020] In other words, by utilizing image hash values ​​as global parameters, it is possible to synchronize video data received directly from the CCTV with metadata generated through analysis on the analysis server.

[0021] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0022] FIGS. 1a and FIGS. 1b are drawings for explaining a conventional CCTV video analysis system.

[0023] FIG. 2 is a diagram schematically illustrating a system for synchronizing intelligent CCTV analysis server data using global parameters according to one embodiment of the present disclosure.

[0024] FIG. 3 is a block diagram of a global parameter addition device for intelligent CCTV analysis server data synchronization according to one embodiment of the present disclosure.

[0025] FIG. 4 is a flowchart of a method for adding global parameters for intelligent CCTV analysis server data synchronization according to one embodiment of the present disclosure.

[0026] FIG. 5 is a diagram illustrating synchronization using an image hash value according to one embodiment of the present disclosure.

[0027] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0028] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0029] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0030] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0031] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0032] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0033] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0034] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0035] Prior to the explanation, the meanings of the terms used in this specification are briefly explained. However, since the explanation of terms is intended to aid in understanding this specification, it should be noted that they are not used to limit the technical scope of this disclosure unless explicitly stated to be a limiting factor.

[0036] In this specification, the term "device" includes all various devices capable of performing computational processing and providing results to a user. For example, a device may include a computer, a server device, and a portable terminal, or may take the form of any one of these.

[0037] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0038] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0039] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0040] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0041] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform a desired characteristic (or objective) are created by a basic artificial intelligence model being trained using a number of training data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0042] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), such as a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, but is not limited to the examples mentioned above.

[0043] The processor can create a neural network, train (or learn) the neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network.

[0044] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo It will be understood by a person skilled in the art that any neural network may be included, but is not limited to, State Network, Deep Residual Network, Differential Neural Computer, Neural Turning Machine, Capsule Network, Kohonen Network, and Attention Network.

[0045] According to an exemplary embodiment of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as recommendation and data creation, may be used, but are not limited thereto.

[0046] FIGS. 1a and FIGS. 1b are drawings for explaining a conventional CCTV video analysis system.

[0047] The conventional CCTV video analysis system illustrated in FIG. 1a is a method in which the client (2) does not receive video through a separate storage but directly connects to the CCTV camera (1) to receive video data (RTP), and in the same way, the storage (4) and the analysis server (3) each receive and process streams directly from the CCTV camera (1). In the case of the analysis server (3), it directly receives RTP stream data from the camera (1), decodes it, and then transmits metadata, which is the result of analysis through an AI model, to the client (GUI).

[0048] In this case, a sync problem may occur because the sequence of the stream video received by the client (2) and the sequence of the stream video received by the analysis server (3) are different. If there is a reference time of the camera (1) to synchronize the two, the sync can be achieved based on this, but most cameras (1) currently on the market do not include a global sequence in the RTP header. The absence of such a global sequence causes the sync problem.

[0049] A method proposed to solve this synchronization problem is the conventional CCTV video analysis system illustrated in FIG. 1b, in which physically separated relay servers (5) are deployed so that the relay servers (5) receive all multi-channel camera streams and re-transmit them after taking a global timestamp. That is, the client (2), storage (4), and analysis server (3) all connect to the relay servers (5) to receive camera video, and visualize the received video streams by matching the result values ​​of the analysis server (3) with the global timestamps.

[0050] However, this method requires physically separated relay servers (5), which increases costs, and there is a problem that it is impossible to process it with an integrated server due to bandwidth issues.

[0051] Accordingly, the present disclosure proposes a method that maintains the configuration of the existing system shown in FIG. 1a, while ensuring synchronization with metadata sent from the analysis server (3) even when the client (2) receives real-time CCTV camera footage as is.

[0052] Hereinafter, embodiments of the present disclosure will be described in detail with reference to FIGS. 2 to 5.

[0053] FIG. 2 is a diagram schematically illustrating a system for synchronizing intelligent CCTV analysis server data using global parameters according to one embodiment of the present disclosure.

[0054] FIG. 3 is a block diagram of a global parameter addition device for intelligent CCTV analysis server data synchronization according to one embodiment of the present disclosure.

[0055] FIG. 4 is a flowchart of a method for adding global parameters for intelligent CCTV analysis server data synchronization according to one embodiment of the present disclosure.

[0056] FIG. 5 is a diagram illustrating synchronization using an image hash value according to one embodiment of the present disclosure.

[0057] Referring to FIG. 2, a system for synchronizing intelligent CCTV analysis server data using global parameters according to one embodiment may include a camera device (10), a global parameter adding device (20), and an analysis server (30). However, in some embodiments, the system according to the present disclosure may include fewer or more components than the components shown in FIG. 2.

[0058] The camera device (10) may refer to a CCTV camera, but is not limited thereto and any device that captures images may be applied.

[0059] The global parameter addition device (20) may be a device for providing a data synchronization service using global parameters according to the present disclosure.

[0060] According to an embodiment, the global parameter adding device (20) may be a server device of a provider of the service. In this case, the global parameter adding device (20) may provide output images, analysis data, etc. to a user terminal (control center, controller, individual user, or corporate user, etc.).

[0061] According to an embodiment, when the service is provided in an on-device format, the global parameter adding device (20) may be a server device of a control center monitoring CCTV, a terminal device of a controller monitoring CCTV, or a server device or terminal device of an individual user or corporate user monitoring CCTV. However, it is not limited thereto, and any device for monitoring CCTV can be applied as the global parameter adding device (20).

[0062] The analysis server (30) can generate metadata by analyzing CCTV footage based on AI.

[0063] Referring to FIG. 2, the camera device (10) can provide an image of a specific space captured by the camera device (10) to the global parameter adding device (20) and the analysis server (30), respectively. At this time, the image data may include multiple frames. For example, the image data may be provided at 60 frames per second (60fps).

[0064] The analysis server (30) can generate analysis server data by analyzing multiple frames included in the video data one by one and provide it to the global parameter addition device (20). At this time, the analysis server data may not be provided in the order of the frames, but in the order in which processing is completed. That is, the global parameter addition device (20) receives the analysis server data for each frame randomly.

[0065] The global parameter adding device (20) utilizes frame-by-frame image hash values ​​to map analysis server data, which is received randomly frame by frame from the analysis server (30), to multiple frames of video data received from the camera device (10) in a one-to-one manner. That is, the global parameter adding device (20) can synchronize video data and analysis server data by utilizing frame-by-frame image hash values ​​as global parameters.

[0066] Referring to FIG. 3, the global parameter adding device (20) may include a communication unit (21), a memory (22), and a processor (23). The processor (23) may include an image data analysis module (231) and an analysis server data analysis module (232). However, in some embodiments, the global parameter adding device (20) and the processor (23) may include fewer or more components than the components shown in FIG. 3.

[0067] The communication unit (21) may include one or more modules that enable wireless or wired communication between the global parameter adding device (20) and the camera device (10), between the global parameter adding device (20) and the analysis server (30), between the global parameter adding device (20) and an external server (not shown), and between the global parameter adding device (20) and a communication network. For example, it may include at least one of a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0068] Various types of communication networks may be used, for example, wireless communication methods such as WLAN (Wireless LAN), Wi-Fi, Wibro, Wimax, and HSDPA (High Speed ​​Downlink Packet Access), or wired communication methods such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coax), FTTC (Fiber to The Curb), and FTTH (Fiber to The Home).

[0069] Meanwhile, the communication network is not limited to the communication method presented above, and may include all forms of communication methods that are widely known or will be developed in the future, in addition to the communication method described above.

[0070] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0071] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0072] A short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0073] The memory (22) may store at least one process for synchronizing intelligent CCTV analysis server data using global parameters.

[0074] The memory (22) can store data supporting various functions of the global parameter adding device (20) and programs for the operation of the processor (23), and can store input / output data (e.g., music files, still images, videos, etc.), and can store a number of application programs (or applications) running on the global parameter adding device (20), data for the operation of the global parameter adding device (20), and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0075] Such memory (22) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, memory (22) may be a database that is separated from the global parameter adding device (20) but connected via wired or wireless connection. Alternatively, the database may be included in the global parameter adding device (20) as an individual component with memory (22).

[0076] The processor (23) may perform the aforementioned operation using a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the global parameter addition device (20), and the data stored in the memory. In this case, the memory (22) and the processor (23) may each be implemented as separate chips. Alternatively, the memory (22) and the processor (23) may be implemented as a single chip.

[0077] Additionally, the processor (23) can control one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in FIG. 4 and FIG. 5 below on the global parameter adding device (20).

[0078] The image data analysis module (231) of the processor (23) can extract a first image hash value for each frame from the image data received from the camera device (10) and store the extracted first image hash value for each frame in a sequential queue.

[0079] The analysis server data analysis module (232) of the processor (23) can parse the frame-by-frame analysis server data received from the analysis server (30) into metadata and a second image hash value.

[0080] The processor (23) can compare the second image hash value with the first image hash values ​​stored in the sequential queue to extract the first image hash value that matches the second image hash value, and map metadata to the frame corresponding to the extracted first image hash value. Accordingly, when image data is output, the image data and metadata are synchronized and output.

[0081] Hereinafter, with reference to FIGS. 4 and FIGS. 5, a method for adding global parameters for synchronizing intelligent CCTV analysis server data according to the present disclosure will be described in detail. For convenience of explanation, each step is described as being performed by the processor (23), but each step can be understood as being performed by any one of the image data analysis module (231), the analysis server data analysis module (232), and a module not shown in FIG. 3 included in the processor (23).

[0082] Referring to FIG. 4, the processor (23) of the global parameter addition device (20) can receive image data from the camera device (10) (S410).

[0083] Here, the video data is an RTP video of a specific space, and the processor (23) can receive a preset number of frames per second. For example, if set to 60fps (frames per second), the processor (23) can receive video data containing 60 frames per second.

[0084] In this way, the camera device (10) can provide video data to the processor (23) by transmitting multiple frames per second, and can provide video data to the analysis server (30) in the same way.

[0085] The analysis server (30) analyzes multiple received frames one by one to generate analysis server data, and provides the analysis server data generated for each frame to the processor (23) one by one.

[0086] The processor (23) of the global parameter addition device (20) can extract a first image hash value for each frame of the image data (S420).

[0087] The processor (23) of the global parameter addition device (20) can store the extracted first image hash value in a sequential queue (S430).

[0088] Here, the first image hash value is generated based on the characteristics of each image frame and is a unique value for each frame.

[0089] A sequential queue is a queue in which the first image hash value of a corresponding frame is stored in frame order.

[0090] According to an embodiment, when the processor (23) receives image data from the camera device (10), it receives the data in the order of a plurality of frames, extracts each first image hash value, and stores them sequentially in a sequential queue.

[0091] According to an embodiment, when the processor (23) receives image data from the camera device (10), it may receive a plurality of frames randomly, extract a first image hash value for each of the randomly received frames, and store them in a sequential queue in the order of the frames rather than the order in which they were received randomly. That is, a plurality of frames may be received randomly, but each first image hash value may be stored in the sequential queue in the order of the frames.

[0092] The processor (23) of the global parameter addition device (20) can receive the analysis server data from the analysis server (30) (S440).

[0093] As described above, the analysis server (30) can generate analysis server data by analyzing a plurality of frames included in the video data one by one and provide it to the processor (23). That is, the analysis server (30) can perform analysis on a frame-by-frame basis to extract the second image hash value and metadata of each frame, and provide the analysis server data including the second image hash value and metadata to the processor (23).

[0094] At this time, the analysis server data is not provided in the order of frames, but can be provided in the order in which processing is completed. That is, the processor (23) receives the analysis server data for each frame randomly.

[0095] The processor (23) can parse and store frame-by-frame analysis server data received from the analysis server (30) into metadata and a second image hash value.

[0096] Here, the second image hash value is generated based on the characteristics of each image frame and is a unique value for each frame.

[0097] That is, the first image hash value and the second image hash value are generated by different entities (generated by the processor (23) and the analysis server (30), respectively), but are generated with the same value for the same frame. For example, the first image hash value and the second image hash value can be generated with the same value for frame 1.

[0098] The present disclosure synchronizes image data and analysis server data by utilizing a unique image hash value for each frame as a global parameter.

[0099] Metadata can be generated through object recognition for each frame. The metadata may include at least one of the number of bounding boxes, the location information of each bounding box, and the size information of each bounding box. However, it is not limited thereto, and the metadata may include all descriptive information for describing the image generated through image analysis.

[0100] The processor (23) can extract a specific first image hash value that matches a second image hash value included in the analysis server data among the first image hash values ​​stored in the sequential queue (S450).

[0101] As described above, the first image hash value and the second image hash value are each generated by the processor (23) and the analysis server (30) for the same frame, respectively, and can be used as global parameters for synchronization between image data and analysis server data.

[0102] Referring to FIG. 5, when the processor (23) extracts a first image hash value for each of the four frames (#0, #1, #2, #3), the hash value (00, 01, 02, 03) for each frame can be stored in a sequence queue.

[0103] When the processor (23) receives analysis server data for a specific frame and obtains a second image hash value through parsing, it can compare this with values ​​in the sequence queue.

[0104] Referring to FIG. 5, if the second image hash value is “01”, the first image hash value “01” in the second queue of the sequence queue can be extracted.

[0105] The processor (23) of the global parameter addition device (20) can extract a specific frame corresponding to a specific first image hash value (S460).

[0106] The processor (23) of the global parameter addition device (20) can map metadata included in the analysis server data to a specific frame (S470).

[0107] The processor (23) can map metadata associated with the second image hash value (i.e., metadata that was included in one analysis server data along with the second image hash value) to a specific extracted frame.

[0108] Referring to FIG. 4, a frame #1 with a first hash value of “01” can be extracted, and metadata that is parsed and stored together with a second image hash value can be mapped to frame #1.

[0109] When the mapping is completed in this way, the processor (23) can exclude the specific first image hash value for which the mapping is completed from the sequential queue.

[0110] Referring to Fig. 4, excluding “01” for which mapping is complete, the frame with the hash value “01” can be visualized by designating it as the current frame.

[0111] At this time, the processor (23) may not only exclude the specific first image hash value for which mapping is completed, but also exclude at least one first image hash value placed before the specific first image hash value in the sequential queue, along with the specific first image hash value, from the sequential queue.

[0112] When values ​​are excluded from the sequential queue in this way, the values ​​placed at the back can move forward to fill the empty space.

[0113] The processor (23) can output the image data based on the mapped result.

[0114] That is, through the mapping operation described above, the image data received from the camera device (10) is processed so that metadata is mapped on a frame-by-frame basis, thereby allowing the mapping data to be output together with the image data output. At this time, instead of mapping metadata to the entire frame, the hash value can be used as a global parameter so that metadata is mapped only to the frame where the hash value matches. This enables synchronization between the image data and the analysis server data.

[0115] According to an embodiment, the processor (23) may apply the metadata to only at least one frame to which the metadata is mapped among a plurality of consecutive frames containing the same object and output it.

[0116] Even if consecutive frames contain the same object, their respective hash values ​​may differ because the image characteristics vary from frame to frame. Therefore, the metadata is mapped only to the frames extracted through hash value comparison.

[0117] For example, if four frames (#0, #1, #2, #3) are consecutive frames containing the same object, and one analysis server data is received from the analysis server (30), the processor (23) can confirm that the frame with matching first and second image hash values ​​is #0 through hash value comparison, and map the metadata of the corresponding frame to frame #0 to exclude the first image hash value of frame #0 from the sequence queue.

[0118] After that, when another analysis server data is received from the analysis server (30), the processor (23) can confirm that the frame with matching first and second image hash values ​​is #3 by comparing hash values, and can exclude the first image hash value of frame #3 from the sequence queue by mapping the metadata of the corresponding frame to frame #3, and at this time, the first image hash values ​​of frames #1 and #2, which are earlier than frame #3, can also be excluded from the sequence queue together.

[0119] Accordingly, when 4 frames (#0, #1, #2, #3) are output, metadata can be mapped and output only to frames #0 and #3.

[0120] Although FIG. 4 describes the steps being executed sequentially, this is merely an illustrative explanation of the technical concept of the present embodiment. A person skilled in the art to which the present embodiment belongs can modify and adapt the steps described in FIG. 4 in various ways, such as changing the order or executing them in parallel, without departing from the essential characteristics of the present embodiment. Therefore, FIG. 4 is not limited to a chronological order.

[0121] Meanwhile, in the above description, the steps described in FIG. 4 may be further divided into additional steps or combined into fewer steps according to an embodiment of the present disclosure. Also, some steps may be omitted as necessary, and the order between steps may be changed.

[0122] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0123] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0124] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively.

[0125] 10: Camera device

[0126] 20: Global Parameter Addition Device

[0127] 21: Communications Department

[0128] 22: Memory

[0129] 23: Processor

[0130] 231: Image Data Analysis Module

[0131] 232: Analysis Server Data Analysis Module

[0132] 30: Analysis Server

[0133] -

Claims

1. A method for adding global parameters for intelligent CCTV analysis server data synchronization performed by a device, A step of receiving image data from a camera device; A step of extracting a first image hash value for each frame of the above image data; A step of storing the extracted first image hash value in a sequential queue; A step of receiving the analysis server data from the analysis server; A step of extracting a specific first image hash value that matches a second image hash value included in the analysis server data among the first image hash values ​​stored in the sequential queue; A step of extracting a specific frame corresponding to the above-mentioned specific first image hash value; and A step of mapping metadata included in the analysis server data to the specific frame; comprising Method for adding global parameters for intelligent CCTV analysis server data synchronization.

2. In Paragraph 1, The above metadata is generated through object recognition for each frame, Method for adding global parameters for intelligent CCTV analysis server data synchronization.

3. In Paragraph 1, The method further comprises the step of parsing the received analysis server data into the second image hash value and the metadata and storing them. Method for adding global parameters for intelligent CCTV analysis server data synchronization.

4. In Paragraph 1, The first image hash value and the second image hash value are each generated by the device and the analysis server, respectively, for the same frame and are utilized as global parameters for synchronization between the image data and the analysis server data. Method for adding global parameters for intelligent CCTV analysis server data synchronization.

5. In Paragraph 1, The method further comprises the step of excluding the specific first image hash value from the sequential queue. Method for adding global parameters for intelligent CCTV analysis server data synchronization.

6. In Paragraph 5, The step of excluding from the above sequential queue is, If there is at least one first image hash value placed before the specific first image hash value in the sequential queue, the at least one first image hash value is also excluded from the sequential queue along with the specific first image hash value. Method for adding global parameters for intelligent CCTV analysis server data synchronization.

7. In Paragraph 5, A step of outputting the image data based on the mapped result; further comprising Method for adding global parameters for intelligent CCTV analysis server data synchronization.

8. In Paragraph 7, The above outputting step is, Outputting by applying the metadata only to at least one frame to which the metadata is mapped among a plurality of consecutive frames containing the same object. Method for adding global parameters for intelligent CCTV analysis server data synchronization.

9. A computer-readable recording medium combined with a computer that is hardware, and storing a computer program that executes the method of any one of claims 1 through 8.

10. Communications Department; A memory storing at least one process for synchronizing intelligent CCTV analysis server data using global parameters; and A processor that performs operations based on the above process; including The above processor is, Receiving image data from a camera device through the above communication unit, and A first image hash value is extracted for each frame of the above image data, and The extracted first image hash value is stored in a sequential queue, and Receives the analysis server data from the analysis server through the communication unit above, and Extract a specific first image hash value that matches a second image hash value included in the analysis server data among the first image hash values ​​stored in the sequential queue, and Extract a specific frame corresponding to the above specific first image hash value, and Mapping metadata included in the analysis server data to the specific frame mentioned above, Global parameter addition device for intelligent CCTV analysis server data synchronization.

Images