Method and system for tracking movement path of object by using multiple cameras
The system efficiently tracks object movement paths across multiple cameras by associating path information with event occurrences and using object identification, addressing the computational challenges of existing technologies and aiding in offline space operation planning.
Patent Information
- Application Number
- PCT/KR2024/015950
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-10-27
- Filing Date
- 2024-10-21
- Publication Date
- 2025-05-01
AI Technical Summary
Existing technologies, such as SORT, face challenges in efficiently tracking the movement paths of objects in large environments like malls or department stores using multiple cameras, due to the excessive computational resources required for analyzing large amounts of data.
A method and system that utilize multiple cameras to track the movement path of objects by determining if an event occurs based on photographic images, associating the movement path information with event occurrences, and using object identification information to link path information across different camera viewpoints.
This approach provides efficient tracking of object movement paths across multiple cameras, reducing computational resource needs and enabling the creation of useful information for offline space operation planning.
Smart Images

Figure KR2024015950_01052025_PF_FP_ABST
Abstract
Description
Method and system for tracking the movement path of an object using multiple cameras
[0001] The present invention relates to a method and system for tracking the movement path of an object using multiple cameras.
[0002] Recently, with the advancement of artificial intelligence technology, technologies for detecting and tracking objects in images captured by cameras have been introduced.
[0003] As an example of a prior art in this regard, the Simple Online and Realtime Tracking (SORT) technology can be cited, according to which an object to be tracked is detected at a specific point in time, the location of the object at the next point in time is predicted using a Kalman filter, and based on the predicted value, an object identical to the object to be tracked is found among the objects detected at the next point in time, thereby enabling tracking of the object.
[0004] However, when tracking objects using images taken over a relatively long period of time in multiple locations with many objects to track, for example, when tracking the movement path of visitors using images taken by multiple CCTVs installed in a large mart or department store, there was a problem that excessive computing resources were required when analyzing all data using the above-mentioned conventional technology and the technologies introduced so far.
[0005] <Prior Art Literature>
[0006] <Non-patent literature>
[0007] (Non-patent Document 1) Simple Online and Realtime Tracking, Bewley et al. (2017. 7. 7)
[0008] The purpose of the present invention is to solve all of the problems of the above-mentioned prior art.
[0009] In addition, the present invention has another purpose of determining whether an event has occurred by a target object using a captured image of the target object captured by a first camera, and, in response to determining that the event has occurred, specifying information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information, and associating information about a movement path of the target object at a second point in time different from the first point in time with the first information based on object identification information about the target object.
[0010] In addition, another object of the present invention is to provide useful information that can be helpful in establishing a plan for operating an offline space by tracking the movement path of a target object using a plurality of cameras installed in a specific location.
[0011] In addition, another object of the present invention is to provide useful information that can be helpful in planning the operation of an offline space by generating information about the journey of a target object in a specific location.
[0012] A representative configuration of the present invention to achieve the above purpose is as follows.
[0013] According to one aspect of the present invention, a method is provided, including a step of determining whether an event has occurred by a target object using a captured image of the target object captured by a first camera; a step of specifying, in response to determining that the event has occurred, information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information; and a step of associating information about a movement path of the target object at a second point in time different from the first point in time with the first information based on object identification information about the target object.
[0014] According to another aspect of the present invention, a system is provided, including an event management unit that determines whether an event has occurred by a target object using a captured image of the target object captured by a first camera, and, in response to determining that the event has occurred, specifies information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information, and a movement path management unit that associates information about a movement path of the target object at a second point in time different from the first point in time with the first information based on object identification information about the target object.
[0015] In addition, a non-transitory computer-readable recording medium recording another method for implementing the present invention, another system, and a computer program for executing the method are further provided.
[0016] According to the present invention, it is possible to determine whether an event has occurred by a target object using a captured image of the target object captured by a first camera, and in response to determining that the event has occurred, to specify information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information, and to associate information about a movement path of the target object at a second point in time different from the first point in time with the first information based on object identification information about the target object.
[0017] In addition, according to the present invention, by tracking the movement path of a target object using multiple cameras installed in a specific location, it is possible to provide useful information that can be helpful in establishing a plan for operating an offline space.
[0018] In addition, according to the present invention, by generating information about the journey of a target object in a specific location, it is possible to provide useful information that can be helpful in establishing a plan for operating an offline space.
[0019] FIG. 1 is a diagram schematically illustrating the configuration of an entire system for tracking the movement path of an object using multiple cameras according to one embodiment of the present invention.
[0020] FIG. 2 is a drawing showing in detail the internal configuration of a movement path tracking system according to one embodiment of the present invention.
[0021] FIG. 3 is a drawing exemplarily showing a tracklet according to one embodiment of the present invention.
[0022] <Explanation of symbols>
[0023] 100: Communications network
[0024] 200: Movement path tracking system
[0025] 210: Event Management Department
[0026] 220: Movement Route Management Department
[0027] 230: Movement Path Analysis Department
[0028] 240: Communications Department
[0029] 250: Control Unit
[0030] 300: Shooting System
[0031] The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified and implemented from one embodiment to another without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each embodiment may also be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is to be construed to encompass the scope of the claims and all equivalents thereof. Like reference numerals in the drawings represent the same or similar elements throughout the several aspects.
[0032] Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.
[0033] Meanwhile, in this specification, the term "captured image" should be understood as a broad concept meaning an image having one or more frames created by being captured by a camera, i.e. a photograph or video.
[0034] In addition, although the present specification focuses primarily on an embodiment in which the object of movement path tracking, i.e. the target object, is a person, it should be understood that the target object in the present invention need not necessarily be a person, and any object that can move can be a target object.
[0035] Composition of the entire system
[0036] FIG. 1 is a diagram schematically illustrating the configuration of an entire system for tracking the movement path of an object using multiple cameras according to one embodiment of the present invention.
[0037] As illustrated in FIG. 1, the entire system according to one embodiment of the present invention may include a communication network (100), a movement path tracking system (200), and a photographing system (300).
[0038] First, the communication network (100) according to one embodiment of the present invention can be configured regardless of the communication mode such as wired communication or wireless communication, and can be configured with various communication networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). Preferably, the communication network (100) referred to herein may be the well-known Internet or the World Wide Web (WWW). However, the communication network (100) is not necessarily limited thereto, and may include at least a portion of a well-known wired or wireless data communication network, a well-known telephone network, or a well-known wired or wireless television communication network.
[0039] For example, the communication network (100) may be a wireless data communication network that implements conventional communication methods such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc., at least in part. As another example, the communication network (100) may be an optical communication network that implements conventional communication methods such as LiFi (Light Fidelity), etc., at least in part.
[0040] Next, the movement path tracking system (200) according to one embodiment of the present invention can perform a function of determining whether an event has occurred by a target object using a captured image of the target object captured by a first camera, and, in response to determining that the event has occurred, specifying information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information, and associating information about a movement path of the target object at a second point in time different from the first point in time with the first information based on object identification information about the target object.
[0041] The configuration and function of the movement path tracking system (200) according to the present invention will be described in detail below.
[0042] Next, the shooting system (300) according to one embodiment of the present invention is a device that includes a function for communicating after connecting to the movement path tracking system (200) and a function for shooting images, and may include a plurality of cameras (301 and 302). Here, the camera according to one embodiment of the present invention may mean, but is not limited to, a CCTV, an IP camera, etc. Furthermore, the shooting system (300) according to one embodiment of the present invention may be a concept that includes a recording medium that stores a shooting image shot by a CCTV, an IP camera, etc., for example, a DVR (Digital Video Recorder), an NVR (Network Video Recorder), etc.
[0043] In addition, the shooting system (300) according to one embodiment of the present invention may include a single camera image analysis module (not shown) that generates various information using a captured image of a target object captured by a single camera (301 or 302). For example, such information may include at least one of information regarding a movement path of the target object within the captured image captured by the single camera (301 or 302), object identification information regarding the target object, and demographic information (e.g., gender, age group, etc.) regarding the target object. To this end, the single camera image analysis module according to one embodiment of the present invention may use an object recognition model that appropriately utilizes an algorithm such as R-CNN (Regions with Convolutional Neural Network), YOLO (You Only Look Once), etc. Meanwhile, a detailed description of the information regarding the movement path of the target object and the object identification information regarding the target object will be described later.
[0044] Meanwhile, it is obvious to those skilled in the art that at least a part of the components or functions of the single camera image analysis module (not shown) according to one embodiment of the present invention may be realized within the movement path tracking system (200) according to one embodiment of the present invention or included within the movement path tracking system (200) as needed.
[0045] The shooting system (300) according to one embodiment of the present invention may include an application (not shown) that supports a user to receive services such as movement path analysis from the movement path tracking system (200). Such an application may be downloaded from the movement path tracking system (200) or an external application distribution server (not shown). Meanwhile, the characteristics of such an application may be generally similar to the event management unit (210), movement path management unit (220), movement path analysis unit (230), communication unit (240), and control unit (250) of the movement path tracking system (200), which will be described later. Here, at least a part of the application may be replaced with a hardware device or firmware device that can perform functions substantially the same as or equivalent to the application, as necessary.
[0046] Configuration of the movement path tracking system
[0047] Below, the internal configuration and functions of each component of the movement path tracking system (200) that performs important functions for implementing the present invention will be examined.
[0048] FIG. 2 is a drawing showing in detail the internal configuration of a movement path tracking system (200) according to one embodiment of the present invention.
[0049] As illustrated in FIG. 2, a movement path tracking system (200) according to one embodiment of the present invention may be configured to include an event management unit (210), a movement path management unit (220), a movement path analysis unit (230), a communication unit (240), and a control unit (250). According to one embodiment of the present invention, at least some of the event management unit (210), the movement path management unit (220), the movement path analysis unit (230), the communication unit (240), and the control unit (250) may be program modules that communicate with an external system (not shown). These program modules may be included in the movement path tracking system (200) in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known memory devices. In addition, these program modules may also be stored in a remote memory device that can communicate with the movement path tracking system (200). Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types, as described below, according to the present invention.
[0050] Meanwhile, although the movement path tracking system (200) has been described as above, this description is exemplary, and it is obvious to those skilled in the art that at least some of the components or functions of the movement path tracking system (200) may be realized within the shooting system (300) or server (not shown) or included within an external system (not shown) as needed.
[0051] First, the event management unit (210) according to one embodiment of the present invention can perform a function of determining whether an event has occurred by a target object using a captured image of the target object captured by the first camera.
[0052] Specifically, the event management unit (210) according to one embodiment of the present invention can determine whether to specifically track the movement path of the target object depending on whether an event has occurred by the target object. That is, the event management unit (210) according to one embodiment of the present invention can start specifically tracking the movement path of the target object if it is determined that an event has occurred by the target object. According to one embodiment of the present invention, the occurrence of such an event may be when the target object enters a store or purchases (pays for) an item in the store. However, the occurrence of an event according to one embodiment of the present invention is not limited to the contents described above, and may be variously changed within the scope that can achieve the purpose of the present invention.
[0053] More specifically, the event management unit (210) according to one embodiment of the present invention can determine whether an event has occurred based on the location information of the target object. According to one embodiment of the present invention, the location information of the target object can be generated by recognizing the target object using a captured image captured by the first camera, or additionally, by detecting an action that can determine the location of the target object, for example, the target object scanning a QR code displayed at a specific location, the target object purchasing (paying for) an item at a store, etc. The event management unit (210) according to one embodiment of the present invention can appropriately utilize a single camera image analysis module (not shown) to recognize the target object using the captured image.
[0054] For example, the event management unit (210) according to one embodiment of the present invention may determine that an event has occurred in response to determining that a target object has crossed a predetermined line (which may mean a virtual line) or visited a predetermined area.
[0055] More specifically, for example, the event management unit (210) according to one embodiment of the present invention may determine that an event has occurred when a target object is recognized at a specific location within a captured image captured by the first camera. In this case, the event management unit (210) according to one embodiment of the present invention may also determine that an event has occurred when the target object is continuously recognized (i.e., remains) at the specific location for a predetermined period of time.
[0056] As another example, the event management unit (210) according to one embodiment of the present invention may determine that an event has occurred when a target object recognized in a captured image captured by the first camera passes through a specific location. In this case, the event management unit (210) according to one embodiment of the present invention may also consider the path or direction in which the target object passes through the specific location. For example, assuming that there are areas A and B that are distinguished by a virtual line (i.e., a specific location), when a target object passes through a specific location by moving from area A to area B, it may be determined that an event has occurred, and when it passes through a specific location by moving from area B to area A, it may be determined that an event has not occurred (in some cases, an event that has occurred has ended or disappeared).
[0057] Meanwhile, the event management unit (210) according to one embodiment of the present invention can determine whether an event has occurred due to a target object by using a captured image of the target object captured by the first camera and a captured image of the target object captured by another camera that is installed in a different location from the first camera but captures a location that at least partially overlaps with the location captured by the first camera, thereby increasing the accuracy of the determination.
[0058] Continuing, the event management unit (210) according to one embodiment of the present invention, in response to determining that an event has occurred by a target object, may specify information about a movement path of the target object at a first point in time associated with the occurrence of the event as first information.
[0059] Specifically, according to one embodiment of the present invention, information about the movement path of the target object at the first point in time associated with the occurrence of an event by the target object may mean information about the movement path of the target object at the first point in time (in one frame) or during the first point in time (in multiple frames) when the frame(s) that serve as the basis for the event management unit (210) according to one embodiment of the present invention determining that an event has occurred by the target object are captured. In other words, in this specification, the point in time (which may include not only the first point in time above but also the second point in time and the third point in time described below) may be a concept meaning the time at which a captured image composed of one or more frames is captured.
[0060] According to an embodiment of the present invention, information about the movement path of a target object may be managed in the form of a tracklet, but is not limited thereto. FIG. 3 is a diagram exemplarily showing tracklets (410, 420, and 430) according to an embodiment of the present invention. Referring to FIG. 3, tracklets (410, 420, and 430) according to an embodiment of the present invention may mean a set (or array) of information about detection results for the same object (e.g., information about a bounding box) collected in chronological order. As illustrated in FIG. 3, a plurality of tracklets (410, 420, and 430) may exist for the same object (objects indicated by shapes of the same shape mean the same object). Of course, according to an embodiment of the present invention, there may be only one tracklet. Also, although FIG. 3 shows that one tracklet contains information about multiple bounding boxes, in some cases it may be possible for one tracklet to contain information about only one bounding box.
[0061] Meanwhile, the movement path management unit (220) according to one embodiment of the present invention can obtain information about the movement path of a target object at a specific point in time (including the first point in time to the third point in time), which will be described in detail below.
[0062] Next, the movement path management unit (220) according to one embodiment of the present invention can perform a function of associating information about the movement path of the target object at a second time point different from the first time point associated with the occurrence of the event, based on object identification information about the target object, with first information specified by the event management unit (210) according to one embodiment of the present invention.
[0063] Specifically, the movement path management unit (220) according to one embodiment of the present invention can obtain information about the movement path of the target object at a second time point that is different from the first time point by using a captured image of the target object captured by a second camera that is different from the first camera. The event management unit (210) according to one embodiment of the present invention can appropriately use a single camera image analysis module (not shown) to recognize the target object and obtain information about the movement path by using a captured image of the target object captured by the second camera.
[0064] Here, according to one embodiment of the present invention, the second point in time may refer to at least a portion of a time period from immediately after the first point in time associated with the occurrence of the event to the point in time associated with the termination or disappearance of the event. For example, the first point in time associated with the occurrence of the event may be the point in time when the target object is determined to have entered the store, and the point in time associated with the termination or disappearance of the event may be the point in time when the target object is determined to have exited the store.
[0065] Continuing, the movement path management unit (220) according to one embodiment of the present invention may perform a function of associating information about the movement path of the target object at a second point in time with first information specified by the event management unit (210) according to one embodiment of the present invention based on object identification information about the target object.
[0066] Specifically, according to one embodiment of the present invention, object identification information regarding a target object may be information regarding external features of the target object stored in the form of an image tensor. The movement path management unit (220) according to one embodiment of the present invention may appropriately utilize a single camera image analysis module (not shown) to obtain such object identification information regarding the target object.
[0067] A movement path management unit (220) according to one embodiment of the present invention can determine, based on object identification information about a target object, whether a movement path of a target object at a first time point associated with the occurrence of an event and a movement path of a target object at a second time point correspond to movement paths of the same object. In addition, if the movement path management unit (220) according to one embodiment of the present invention determines that the movement paths correspond to the same object, the movement path management unit (220) can generate information about the entire movement path of the target object by associating information about the movement path of the target object at the second time point with the first information, for example, by making it into one tracklet.
[0068] For example, the movement path management unit (220) according to one embodiment of the present invention can calculate the similarity between the first object identification information obtained based on the captured image of the target object at the first time point and the second object identification information obtained based on the captured image of the target object at the second time point. According to one embodiment of the present invention, a similarity calculation method such as Cosine Distance or Euclidean Distance may be used to calculate the similarity, but is not limited thereto. In addition, the movement path management unit (220) according to one embodiment of the present invention can associate information about the movement path of the target object at the second time point with the first information in response to the similarity calculated in this way being equal to or greater than a threshold value (i.e., in response to the target object at the first time point and the target object at the second time point being determined to be the same object).
[0069] Meanwhile, the movement path management unit (220) according to one embodiment of the present invention can determine whether information about the movement path of a specific object at a third time point that is different from the first and second time points is about the reoccurrence of an event by the target object.
[0070] Specifically, according to one embodiment of the present invention, it can be assumed that a visit by a target object to a certain area is determined to be an event occurrence. In this case, if the target object visits the area more than once, each visit may be determined to be an event occurrence. This may result in a situation where information regarding the movement path of the same object is managed as information regarding the movement paths of different objects. For example, information that should be managed as a single tracklet may be managed as multiple tracklets. In this case, the movement path management unit (220) according to one embodiment of the present invention may associate information regarding the movement path of a specific object at a third point in time with the first information in response to determining that the information regarding the movement path of the specific object is related to the reoccurrence of an event by the target object. This can prevent information regarding the movement path of a single target object from being managed in multiple separate pieces.
[0071] Meanwhile, the movement path management unit (220) according to one embodiment of the present invention may calculate the similarity between the first object identification information obtained based on the captured image of the target object at the first time point and the third object identification information obtained based on the captured image of the target object at the third time point in order to determine whether the information regarding the movement path of the specific object at the third time point is regarding the reoccurrence of an event by the target object. According to one embodiment of the present invention, a similarity calculation method such as Cosine Distance or Euclidean Distance may be used to calculate the similarity, but is not limited thereto. In addition, the movement path management unit (220) according to one embodiment of the present invention may associate the information regarding the movement path of the specific object at the third time point with the first information in response to the similarity calculated in this way being equal to or greater than a threshold value (i.e., in response to the target object at the first time point and the specific object at the third time point being determined to be the same object).
[0072] Next, the movement path analysis unit (230) according to one embodiment of the present invention can calculate the accuracy of information about the entire movement path of the target object generated by associating the information about the movement path of the target object at the second time point with the first information as described above.
[0073] Specifically, the movement path analysis unit (230) according to one embodiment of the present invention can calculate an accuracy indicating the likelihood that the information regarding the entire movement path of the target object generated as described above is actually regarding the movement path of a single object. In addition, the movement path analysis unit (230) according to one embodiment of the present invention can perform a function of determining the information regarding the entire movement path of the target object as the analysis target information in response to the accuracy thus calculated being greater than or equal to a threshold.
[0074] Here, according to one embodiment of the present invention, the entire movement path of the target object may refer to the movement path from immediately after the first point in time associated with the occurrence of an event to the point in time associated with the termination or disappearance of the event. For example, the first point in time associated with the occurrence of an event may be the point in time when the target object is determined to have entered the store, and the point in time associated with the termination or disappearance of the event may be the point in time when the target object is determined to have exited the store.
[0075] In addition, the movement path analysis unit (230) according to one embodiment of the present invention can generate information regarding the target object's journey within a store based on the analysis target information determined as described above and the target object's purchase information within the store. Here, according to one embodiment of the present invention, the "store" may refer to a single large space, such as a department store or large supermarket, or it may refer to any one of several individual stores within such a large space.
[0076] According to one embodiment of the present invention, information regarding the target object's journey may refer to information combining information regarding the target object's movement path within a store with information regarding products or services purchased or shown interest while moving along that path. The movement path analysis unit (230) according to one embodiment of the present invention may visualize and provide to a user information regarding the target object's journey. Of course, since there may be multiple target objects, information regarding the journeys of all target objects determined to have triggered an event may be comprehensively visualized and provided.
[0077] Next, the communication unit (240) according to one embodiment of the present invention can perform a function that enables data transmission and reception from / to the event management unit (210), the movement path management unit (220), and the movement path analysis unit (230).
[0078] Finally, the control unit (250) according to one embodiment of the present invention can perform a function of controlling the flow of data between the event management unit (210), the movement path management unit (220), the movement path analysis unit (230), and the communication unit (240). That is, the control unit (250) according to one embodiment of the present invention can control the flow of data from / to the outside of the movement path tracking system (200) or the flow of data between each component of the movement path tracking system (200), thereby controlling the event management unit (210), the movement path management unit (220), the movement path analysis unit (230), and the communication unit (240) to perform their own functions.
[0079] The embodiments of the present invention described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. Hardware devices may be changed into one or more software modules to perform processing according to the present invention, and vice versa.
[0080] Although the present invention has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present invention, and the present invention is not limited to the above examples, and those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and changes based on this description.
[0081] Therefore, the idea of the present invention should not be limited to the embodiments described above, and not only the scope of the patent claims described below but also all scopes equivalent to or equivalently modified from the scope of the patent claims are considered to fall within the scope of the idea of the present invention.
Claims
1. A method for tracking the movement path of an object using multiple cameras, A step of determining whether an event has occurred by a target object using a captured image of the target object captured by the first camera, In response to determining that the above event has occurred, a step of specifying information about the movement path of the target object at a first point in time associated with the occurrence of the above event as first information, and A step of associating information about a movement path of the target object at a second time point different from the first time point with the first information based on object identification information about the target object. method.
2. In paragraph 1, In the above judgment step, whether the event has occurred is judged based on the location information of the target object. method.
3. In paragraph 2, In the above judgment step, in response to determining that the target object has crossed a predetermined line or visited a predetermined area, the event is determined to have occurred. method.
4. In paragraph 1, Information about the movement path of the target object at the second point in time is obtained by using a captured image of the target object captured by a second camera different from the first camera. method.
5. In paragraph 1, The above-mentioned association step is a step of calculating a similarity between first object identification information obtained based on a photographed image of the target object at the first time point and second object identification information obtained based on a photographed image of the target object at the second time point, and In response to the similarity calculated above being greater than a threshold, a step of associating information about the movement path of the target object at the second time point with the first information is included. method.
6. In paragraph 1, A step of determining whether information about the movement path of a specific object at a third time point different from the first time point and the second time point is related to the reoccurrence of the event by the target object, and In response to determining that the information about the movement path of the specific object relates to the reoccurrence of the event by the target object, the method further comprises associating the information about the movement path of the specific object with the first information. method.
7. In paragraph 1, A step of calculating the accuracy of information about the entire movement path of the target object generated by associating the information about the movement path of the target object at the second time point with the first information, and In response to the accuracy being greater than or equal to a threshold, the step of determining information about the entire movement path as analysis target information is further included. method.
8. In paragraph 7, The above analysis target information is about the movement path in the store, A method further comprising: generating information about the journey of the target object in the store based on the analysis target information and the purchase information of the target object in the store. method.
9. A non-transitory computer-readable recording medium recording a computer program for executing the method according to paragraph 1.
10. A system for tracking the movement path of an object using multiple cameras, An event management unit that determines whether an event has occurred by a target object using a captured image of the target object captured by the first camera, and, in response to determining that the event has occurred, specifies information about the movement path of the target object at a first point in time associated with the occurrence of the event as first information; and A movement path management unit that associates information about a movement path of the target object at a second time point different from the first time point with the first information based on object identification information about the target object. System.
11. In paragraph 10, The above event management unit determines whether the event has occurred based on the location information of the target object. System.
12. In paragraph 11, The above event management unit determines that the event has occurred in response to the target object being judged to have crossed a predetermined line or visited a predetermined area. System.
13. In paragraph 10, The above movement path management unit obtains information about the movement path of the target object at the second point in time by using a captured image of the target object captured by a second camera different from the first camera. System.
14. In paragraph 10, The movement path management unit calculates a similarity between first object identification information obtained based on a photographed image of the target object at the first time point and second object identification information obtained based on a photographed image of the target object at the second time point, and in response to the calculated similarity being greater than or equal to a threshold, associates information about the movement path of the target object at the second time point with the first information. System.
15. In paragraph 10, The above movement path management unit determines whether information about the movement path of a specific object at a third time point different from the first time point and the second time point is related to the reoccurrence of the event by the target object, and in response to determining that the information about the movement path of the specific object is related to the reoccurrence of the event by the target object, associates the information about the movement path of the specific object with the first information. System.
16. In paragraph 10, A movement path analysis unit is further included, which calculates the accuracy of information about the entire movement path of the target object generated by associating the first information with the information about the movement path of the target object at the second time point, and determines the information about the entire movement path as analysis target information in response to the accuracy being greater than or equal to a threshold. System.
17. In paragraph 16, The above analysis target information is about the movement path in the store, The above movement path analysis unit generates information about the target object's journey in the store based on the analysis target information and the target object's purchase information in the store. System.
Citation Information
Patent Citations
Movement analyzing device
JP2003263641A
Person tracking device and person tracking program
JP5230793B2
Vison monitoring method of dvr
KR101256107B1
System and method for interworking with target interest through handover between multiple cameras in cloud
KR101840167B1
Tracking system of target using fixed camera and tracking method of target thereof
KR1020120095579A