WO2023112214A1 - Dispositif, procédé, et programme de détection de vidéo d'intérêt - Google Patents

Dispositif, procédé, et programme de détection de vidéo d'intérêt Download PDF

Info

Publication number
WO2023112214A1
WO2023112214A1 PCT/JP2021/046299 JP2021046299W WO2023112214A1 WO 2023112214 A1 WO2023112214 A1 WO 2023112214A1 JP 2021046299 W JP2021046299 W JP 2021046299W WO 2023112214 A1 WO2023112214 A1 WO 2023112214A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
detection
distance
processing unit
information
Prior art date
Application number
PCT/JP2021/046299
Other languages
English (en)
Japanese (ja)
Inventor
基宏 高木
重邦 近藤
裕司 青野
Original Assignee
日本電信電話株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Priority to PCT/JP2021/046299 priority Critical patent/WO2023112214A1/fr
Priority to JP2023567396A priority patent/JPWO2023112214A1/ja
Publication of WO2023112214A1 publication Critical patent/WO2023112214A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • One aspect of the present invention relates to a target video detection device, method, and program for detecting a target video including an object of interest from video data.
  • Non-Patent Document 1 In order to accurately detect human behavior, it is generally necessary to observe a large amount of images. In that case, manual observation is time-consuming and labor-intensive, so techniques using algorithms that automatically detect specific behaviors are being researched. In addition, in order to individually detect movements of a plurality of persons, studies related to the robustness of person tracking technology and face recognition technology are actively being conducted (see, for example, Non-Patent Document 1).
  • Non-Patent Document 1 detects the movement of a specific person or object to be monitored by itself. For this reason, it may not be possible to accurately detect a person's behavior.
  • the present invention has been made with a focus on the above circumstances, and aims to provide a technique that enables accurate detection of a target image necessary for estimating the motion of an object of interest.
  • one aspect of the attention video detection apparatus or method includes a first processing unit or process for acquiring video data captured by a camera; and a second processing unit or process for detecting object detection information including information representing the position of the object in the video frame; a third processing unit or process for detecting distance detection information representing a distance distribution from a camera; a fourth processing unit or process for detecting a specific image area in which a second object to be worked on exists within a predetermined distance; and a fifth processing unit or process for detecting the video of interest.
  • a first object designated as an object of interest and a surrounding second object to be worked on by the first object are included, and the first object and the A video in which the distance to the second object is within the threshold is detected as the video of interest.
  • FIG. 1 is a block diagram showing an example of the hardware configuration of a target video detection apparatus according to an embodiment of the present invention together with the configuration of peripheral parts.
  • FIG. 2 is a block diagram showing an example of the software configuration of the attention video detection device according to one embodiment of the present invention.
  • FIG. 3 is a flowchart showing an example of processing procedures and processing contents of attention video detection processing executed by a control unit of the attention video detection apparatus shown in FIG.
  • FIG. 4 is a flowchart showing an example of the processing procedure and processing contents of object detection processing in the attention video detection processing shown in FIG.
  • FIG. 5 is a flow chart showing an example of a processing procedure and processing contents of a distance information detection process in the attention video detection process shown in FIG.
  • FIG. 1 is a block diagram showing an example of the hardware configuration of a target video detection apparatus according to an embodiment of the present invention together with the configuration of peripheral parts.
  • FIG. 2 is a block diagram showing an example of the software configuration of the attention video detection device according to one embodiment of the present
  • FIG. 6A is a flowchart showing the processing procedure of the specific section determination processing in the attention video detection processing shown in FIG. 3 and the processing of the first half of the processing contents.
  • FIG. 6B is a flowchart showing the processing procedure of the specific section determination processing in the attention video detection processing shown in FIG. 3 and the latter half of the processing contents.
  • FIG. 7 is a flowchart showing an example of the processing procedure and processing contents of the attention video detection processing of the attention video detection processing shown in FIG. 8 is a diagram showing an example of a target video detection rule stored in the target video detection related information storage unit shown in FIG. 3.
  • FIG. 3 is a flowchart showing the processing procedure of the specific section determination processing in the attention video detection processing shown in FIG. 3 and the processing of the first half of the processing contents.
  • FIG. 6B is a flowchart showing the processing procedure of the specific section determination processing in the attention video detection processing shown in FIG. 3 and the latter half of the processing contents.
  • FIG. 7 is a flowchart showing an example of the
  • FIG. 1 is a block diagram showing an example of the hardware configuration of a target video detection device according to an embodiment of the present invention together with its peripheral devices
  • FIG. 2 is a block diagram showing an example of the software configuration of the target video detection device. .
  • the target video detection device BD is made up of an information processing device such as a server computer or a personal computer, for example.
  • a camera CM and a terminal MT are connected to this target video detection device BD via a signal cable or a network (not shown).
  • a camera CM is installed, for example, on a ceiling or a wall surface capable of photographing an area to be monitored, and photographs the whole body of a person to be monitored who is present in the area to be monitored along with its surrounding area, and converts time-series video data into a video of interest. Send to detector BD.
  • the video data captured by the camera CM may be directly transmitted from the camera CM to the target video detection device BD, but it should be temporarily stored in a video database (not shown) and then sent to the target video detection device BD. good too.
  • the number of camera CMs is not limited to one, and may be plural.
  • a terminal MT is used by, for example, a system administrator or a supervisor who monitors the behavior of a person to be monitored, and is composed of an information processing terminal such as a personal computer.
  • the terminal MT for example, has a function of receiving attention video information detected by the attention video detection device BD and analyzing the behavior of a person to be monitored based on the received attention video information.
  • the attention video detection device BD may have the function of analyzing the behavior of the person to be monitored based on the attention video.
  • the terminal MT may have a function of inputting learning data necessary for learning the machine learning model to the target video detection device BD when the target video detection device BD has a machine learning model.
  • the video detection device of interest BD includes a control unit 1 using hardware processors such as a central processing unit (CPU) and an image processing unit (graphics processing unit: GPU).
  • a storage unit having a program storage section 2 and a data storage section 3 is connected to an input/output interface (hereinafter the interface is abbreviated as I/F) section 4 via.
  • I/F input/output interface
  • the control unit 1 may be configured using a PLD (Programmable Logic Device), an FPGA (Field Programmable Gate Array), or the like.
  • the input/output I/F unit 4 has a communication interface function, and transmits/receives video data and each input/output data to/from the camera CM and the terminal MT via a signal cable or network.
  • the program storage unit 2 is composed of, for example, a non-volatile memory such as an SSD (Solid State Drive) that can be written and read at any time as a storage medium, and a non-volatile memory such as a ROM (Read Only Memory). , OS (Operating System) and other middleware, as well as application programs necessary for executing various control processes according to one embodiment.
  • OS Operating System
  • application programs necessary for executing various control processes according to one embodiment.
  • the OS and each application program will be collectively referred to as programs.
  • the data storage unit 3 is, for example, a combination of a non-volatile memory such as SSD that can be written and read at any time and a volatile memory such as RAM (Random Access Memory) as a storage medium, and implements one embodiment.
  • a video data storage unit 31, a specific section video determination related information storage unit 32, and a target video detection related information storage unit 33 are provided as main storage units necessary for this purpose.
  • the video data storage unit 31 is used to temporarily store the time-series video data transmitted from the camera CM for subsequent target video detection processing.
  • the specific section video determination related information storage unit 32 stores specific section video determination related information including the names of specified areas and specified objects previously specified as monitoring targets.
  • the designated area is automatically determined using a method such as semantic segmentation based on the image of the camera CM by the terminal MT or the target image detection device BD. is set Note that the specified area may be set manually from the terminal MT by an administrator or a supervisor.
  • the specified area is represented by a shape such as a rectangle, polygon, or circle, for example.
  • the designated area is not limited to one, and a plurality of designated areas can be designated.
  • the shape is a rectangle
  • a plurality of rectangles are specified as detection target areas within a video frame captured by one fixed camera CM.
  • the specified area does not necessarily have to be set. In this case, the entire area of the video frame is regarded as the specified area.
  • the specified object the name of the object to be detected, such as a person, ladder, hammer, safety belt, etc., is specified. Note that the specified object does not necessarily have to be specified. In this case, all objects are considered to be detected.
  • the attention video detection related information storage unit 33 stores detection rules necessary for detecting the attention video.
  • the detection rule is a rule for determining whether or not the video of the specific section detected by the specific section determination processing unit 14, which will be described later, is the video of interest in which there is a high possibility that an interaction will occur between a person and an object. , and multiple are stored in advance.
  • the control unit 1 includes a video data acquisition processing unit 11, an object detection processing unit 12, a distance information detection processing unit 13, a specific section determination processing unit 14, and and a target video detection processing unit 15 .
  • Each of the processing units 11 to 15 is realized by causing the hardware processor of the control unit 1 to execute an application program stored in the program storage unit 2 .
  • the video data acquisition processing unit 11 acquires time-series video data output from the camera CM via the input/output I/F unit 4, and temporarily stores each of the acquired video data in the video data storage unit 31. process.
  • the object detection processing unit 12 has a machine learning model for object detection constructed using a neural network. Then, the object detection processing unit 12 reads the image data frame by frame from the image data storage unit 31, and inputs the read image frame to the machine learning model for object detection, so that the image captured in the image frame is Object class and position are detected as object detection information. An example of this object detection processing will be described in the operation example.
  • the distance information detection processing unit 13 has a machine learning model for distance information detection constructed using a neural network. Then, the distance information detection processing unit 13 reads video data frame by frame from the video data storage unit 31, and inputs the read video frames to the machine learning model for detecting distance information so that the distance information is captured in the video frames. The distance from the camera CM of the captured image is detected in units of pixels. An example of this distance information detection process will also be described with an operation example.
  • the specific section determination processing unit 14 receives object detection information and distance detection information from the object detection processing unit 12 and the distance information detection processing unit 13, respectively. Then, by collating this detection information with the specific section video determination related information stored in the specific section video determination related information storage unit 32, the video of the specific section in which the designated object appears in the designated area is detected. process. An example of the specific section detection process will be described in more detail in the operation example.
  • the target video detection processing unit 15 receives the specific section video information detected by the specific section determination processing unit 14 . Then, by comparing the received specific section video information with the detection rule stored in the target video detection related information storage unit 33, it is determined whether or not the specific section video information is the target video. If it is a video, the process of outputting the video of interest from the input/output I/F unit 4 to the terminal MT is performed. An example of the target video determination process will also be described in more detail in the operation example.
  • the machine learning model for object detection and the machine learning model for distance information detection are configured by, for example, convolutional neural networks, but the type of neural network can be appropriately selected and used. Further, in the specific section determination processing unit 14 and the target video detection processing unit 15, the specific section determination processing and the target video detection processing may be executed using machine learning models, respectively.
  • FIG. 3 is a flowchart showing an example of the overall processing procedure and processing contents of the target video detection process executed by the control unit 1 of the target video detection device BD.
  • the control unit 1 of the target video detection device BD receives time-series video data obtained by photographing the area to be monitored by the camera CM. Acquired via the output I/F unit 4 . Then, the acquired video data is sequentially stored in the video data storage unit 31 frame by frame.
  • the control unit 1 of the target image detection device BD under the control of the object detection processing unit 12, detects an object from the image data for each frame in step S1.
  • the processing for detecting information representing the class and position of is performed as follows.
  • FIG. 4 is a flowchart showing an example of the processing procedure and processing contents of the object detection processing executed by the object detection processing unit 12.
  • FIG. 4 is a flowchart showing an example of the processing procedure and processing contents of the object detection processing executed by the object detection processing unit 12.
  • the object detection processing unit 12 reads video data frame by frame from the video data storage unit 31 in step S11. Then, the read video frame is input to a machine learning model for object detection, and information representing the class and position of the object shown in the video frame is detected by this learning model.
  • the learning model for object detection of the object detection processing unit 12 in step S12, the video frame , detection processing of each object is performed, and class information represented by a binary vector in which detected objects are "1" and undetected objects are "0" is output. For example, if “person” and “ladder” are detected in the current video frame, class information (1, 1, 0) is output. Note that the vector length depends on the number of object classes.
  • Bounding box information is represented by (x_min, y_min, x_max, y_max). This indicates the coordinates of the upper left corner point (x_min, y_min) and the lower right corner point (x_max, y_max) of the rectangle when the coordinates of the upper left corner of the video frame are (0, 0).
  • the object detection learning model of the object detection processing unit 12 outputs bounding box information for each object included in the class information in step S13.
  • the object detection processing unit 12 outputs object detection information consisting of the class information and bounding box information output from the learning model for object detection to the specific section determination processing unit 14 in step S14.
  • a person ID that identifies the person may be generated using a well-known person tracking technology, and this person ID may be included in the object detection information.
  • Person tracking technology is described in detail, for example, in K. Zhou et al. “Omni-Scale Feature Learning for Person Re-Identification.” ICCV2019.
  • a well-known method can also be used for the method of detecting an object from a video frame.
  • control unit 1 of the target video detection device BD extracts the image shown in the video frame in step S2 under the control of the distance information detection processing unit 13. from the camera CM in units of pixels (pixels).
  • FIG. 5 is a flowchart showing an example of the processing procedure and processing contents of the distance information detection processing executed by the distance information detection processing unit 13.
  • FIG. 5 is a flowchart showing an example of the processing procedure and processing contents of the distance information detection processing executed by the distance information detection processing unit 13.
  • the distance information detection processing unit 13 first reads video data frame by frame from the video data storage unit 31 in step S21. Then, the read video frame is input to a machine learning model for detecting distance information, and the learning model detects and outputs information representing the distance distribution for each pixel from the camera CM of the image captured in the video frame. do.
  • the distance distribution is represented by the depth frame D.
  • the depth frame D contains corresponding depth information d(u, v) for each pixel p(u, v) of the video frame I.
  • p and d are functions that return pixel values and depth values corresponding to each pixel position on the video frame, and u and v represent pixel positions on the video frame.
  • the machine learning model for distance information detection extracts the depth frame D corresponding to the input video data in step S22, and uses the extracted depth frame D as distance detection information in step S23 to determine the specific section determination processing unit 14. Output to
  • the depth frame may be obtained from the depth camera.
  • the depth frames obtained from the depth camera must be temporally and spatially aligned with the video frames.
  • step S3 under the control of the specific section determination processing section 14, the control section 1 of the target video detection device BD determines the image frame based on the object detection information and the distance detection information.
  • a process of determining a specific section in which a specified object appears in a specified area inside is executed as follows.
  • FIG. 6A and 6B are flowcharts showing an example of the processing procedure and processing contents of the specific section determination processing executed by the specific section determination processing unit 14.
  • FIG. 6A and 6B are flowcharts showing an example of the processing procedure and processing contents of the specific section determination processing executed by the specific section determination processing unit 14.
  • the specific section determination processing unit 14 first receives the object detection information and the distance from the object detection processing unit 12 and the distance information detection processing unit 13 in step S311 of FIG. 6A. Receive detection information. Further, in step S312, the specific section video determination related information is read from the specific section video determination related information storage unit 32.
  • FIG. 1 illustrates the specific section video determination related information storage unit 32.
  • step S313 the specific section determination processing unit 14 collates the object detection information with the specific section video determination related information, and detects that there is some object in the detection target designated area defined in the specific section video determination related information. Determine whether or not the image is captured. Then, if any object appears in the designated area, the entire designated area is extracted as object area information.
  • step S314 the specific section determination processing unit 14 determines whether or not there is object area information including a person in the plurality of pieces of detected object area information. If not, terminate the process. On the other hand, if object area information including a person is found, the specific section determination processing unit 14 next proceeds to step S315 to determine if an object other than a person is included in the object area information including a person. It is determined whether or not there is any object area information, and if the corresponding object area information does not exist, the process is terminated.
  • step S316 the specific section determination processing unit 14 extracts specified object area information including an object that matches the object specified as a detection target by the specific section video determination related information.
  • At least one human region in which a person is shown exists in the specified region, and an object region in which a specified object that can be a work target of the person is shown. is detected.
  • the specific section determination processing unit 14 detects the specified object region information from the distance detection information previously received in step S311. Extract distance detection information. That is, it extracts distance detection information corresponding to each of a human region in which a person is shown and an object region in which a designated object is shown in the specified region.
  • the distance detection information corresponding to the person area and the object area is included as depth information in the depth frame corresponding to the bounding box of each area.
  • the distance detection information corresponding to each of the human region and the object region is a set of depth information d(u, v) included in the depth frame corresponding to the bounding box (x_min, y_min, x_max, y_max).
  • step S322 the specific section determination processing unit 14 calculates the average distance for each of the person area and the object area. This average distance is calculated as the average of the set of depth information d(u,v) included in the depth frame corresponding to the bounding box (x_min, y_min, x_max, y_max).
  • step S327 the specific section determination processing unit 14 compares the calculated difference E of the average distances with the threshold value T to determine whether the difference E of the average distances is equal to or less than the threshold value T. As a result of this determination, if the average distance difference E is equal to or less than the threshold value T, the combination of the person area h_0 and the object area o_0 and its average distance difference E are added to the specific section video information in step S328. If the average distance difference E exceeds the threshold value T, the process proceeds to step S329 without performing the above addition.
  • step S329 the specific section determination processing unit 14 increments j of the object region information o_j (j+1) to select the next object region information o_1, returns to step S326, and A difference E between the average distance and the average distance of the person area h_0 is calculated. Then, in step S327, it is determined whether or not the calculated difference E is equal to or less than the threshold T. If the difference E is equal to or less than the threshold T, the combination of the human region information h_0 and the object region information o_1 and its The average distance difference E is added to the specific section video information, and if the difference E exceeds the threshold T, the addition is not performed.
  • the specific section determination processing unit 14 increments (i+1) the value of i of the person area h_i in step S331 to select the next person area h_1. Then, after returning to step S325 and initializing j of the object region o_j, the difference E between the average distance of the human region h_1 and the average distance of the object region o_0 is calculated in step S326, and the difference E is equal to or less than the threshold value T. Then, if the difference E is equal to or less than the threshold value T, the combination of the person area h_1 and the object area o_0 and the difference E of the average distance between them are added to the specific section video information.
  • step S333 the specific section determination processing unit 14 outputs the specific section video information obtained by the above series of processes to the target video detection processing unit 15.
  • step S4 the control unit 1 of the video of interest detection device BD performs processing for detecting a video of interest from the specific section video information under the control of the video-of-interest detection processing unit 15 as follows. run to
  • FIG. 7 is a flowchart showing an example of the processing procedure and processing contents of the attention video detection processing executed by the attention video detection processing unit 15.
  • FIG. 7 is a flowchart showing an example of the processing procedure and processing contents of the attention video detection processing executed by the attention video detection processing unit 15.
  • the target video detection processing unit 15 first receives specific section video information from the specific section determination processing unit 14 in step S41.
  • step S42 attention image detection related information is read from the attention image detection related information storage unit 33.
  • step S43 the attention video detection processing unit 15 collates the specific section video information with the detection rule defined by the attention video detection related information, and determines whether there is specific section video information corresponding to the detection rule. determine whether or not
  • the attention video detection processing unit 15 determines whether the combination of the person region and the object region and the difference in the average distance correspond to any of the above detection rules for each specific section video included in the specific section video information. determine whether or not In making this determination, the distance on the video frame between the person area and the object area is also considered.
  • the distance on the image frame between the human region and the object region is expressed by the Euclidean distance between the center point of the bounding box of the human region and the center point of the bounding box of the object region.
  • the target video detection processing unit 15 detects the specific section video as a target video in step S44, and outputs the target video from the input/output I/F unit 4 to the terminal. Output to MT.
  • a specific segment video that does not meet any of the above detection rules is discarded.
  • the class and position of an object captured in the video frame are detected as object detection information, and the object captured in the video frame is detected as object detection information.
  • the distance distribution of the image from the camera CM is detected as distance detection information.
  • all the object area information including the person and the object to be worked on are detected from the specified area defined as the detection target by the specific section video related information, and further the distance detection information.
  • all the specific section videos including pairs of persons and objects whose difference in average distance between the person and the object is equal to or less than the threshold are detected from the object area information.
  • the specific section video corresponding to the detection rule predefined by the target video detection related information is detected, and the detected specific section video is output as the target video. ing.
  • a video including a person designated as a detection target and a surrounding object that the person is working on, and in which the distance between the person and the object is within a threshold value. is detected as the video of interest.
  • a video region in which the difference in distance between the person and the surrounding object is equal to or less than a threshold is set as the target video.
  • detection targets are not limited to the combination of a person and an object. An image including a combination with surrounding objects may be detected as the target image.
  • an example is described in which an image in which the difference in distance between a person and surrounding objects is equal to or less than a threshold is set as an image of interest. If the video continues for more than a period of time, the video may be set as the video of interest.
  • the function of the target video detection device BD is provided in an information processing device such as a server computer or a personal computer provided independently of the camera CM and the terminal MT has been described as an example.
  • the present invention is not limited to this, and all or part of the functions of the target video detection device BD may be provided in the camera CM and the terminal MT.
  • the types and functions of the target video detection device BD, its processing procedures, processing contents, etc. can be modified in various ways without departing from the gist of the present invention.
  • the present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the gist of the invention at the implementation stage.
  • various inventions can be formed by appropriate combinations of the plurality of constituent elements disclosed in the above embodiments. For example, some components may be omitted from all components shown in the embodiments.
  • constituent elements of different embodiments may be combined as appropriate.
  • BD attention video detection device CM... camera MT... terminal 1... control unit 2... program storage unit 3... data storage unit 4... input/output I/F unit 5... bus 11... video data acquisition processing unit 12... object detection processing unit REFERENCE SIGNS LIST 13: Distance information detection processing unit 14: Specific section determination processing unit 15: Target video detection processing unit 31: Video data storage unit 32: Specific section video determination related information storage unit 33: Target video detection related information storage unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)

Abstract

Selon un aspect de la présente invention, des informations de détection d'objet comprenant des informations représentant un objet et la position de l'objet dans une trame vidéo de données vidéo capturées par une caméra sont détectées à partir de la trame vidéo, et des informations de détection de distance représentant la distribution de distance de la caméra à l'image dessinée dans la trame vidéo sont détectées à partir de la trame vidéo. Puis, une région vidéo spécifique, dans laquelle un premier objet qui est une cible d'intérêt et un second objet qui est une cible de travail du premier objet existent dans une plage de distance prédéterminée, est détectée sur la base des informations de détection d'objet et des informations de détection de distance, et dans la région vidéo spécifique détectée, une région vidéo spécifique qui satisfait une condition de détection prédéfinie est détectée en tant que vidéo d'intérêt.
PCT/JP2021/046299 2021-12-15 2021-12-15 Dispositif, procédé, et programme de détection de vidéo d'intérêt WO2023112214A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2021/046299 WO2023112214A1 (fr) 2021-12-15 2021-12-15 Dispositif, procédé, et programme de détection de vidéo d'intérêt
JP2023567396A JPWO2023112214A1 (fr) 2021-12-15 2021-12-15

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/046299 WO2023112214A1 (fr) 2021-12-15 2021-12-15 Dispositif, procédé, et programme de détection de vidéo d'intérêt

Publications (1)

Publication Number Publication Date
WO2023112214A1 true WO2023112214A1 (fr) 2023-06-22

Family

ID=86773846

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/046299 WO2023112214A1 (fr) 2021-12-15 2021-12-15 Dispositif, procédé, et programme de détection de vidéo d'intérêt

Country Status (2)

Country Link
JP (1) JPWO2023112214A1 (fr)
WO (1) WO2023112214A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013232181A (ja) * 2012-04-06 2013-11-14 Canon Inc 画像処理装置、画像処理方法
JP2017147689A (ja) * 2016-02-19 2017-08-24 富士通株式会社 映像編集装置、映像編集方法及び映像編集用コンピュータプログラム
JP2020010154A (ja) * 2018-07-06 2020-01-16 エヌ・ティ・ティ・コムウェア株式会社 危険作業検出システム、解析装置、表示装置、危険作業検出方法、および、危険作業検出プログラム
JP2020093890A (ja) * 2018-12-12 2020-06-18 株式会社神鋼エンジニアリング＆メンテナンス クレーン作業監視システム、クレーン作業監視方法、危険状態判定装置、及びプログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013232181A (ja) * 2012-04-06 2013-11-14 Canon Inc 画像処理装置、画像処理方法
JP2017147689A (ja) * 2016-02-19 2017-08-24 富士通株式会社 映像編集装置、映像編集方法及び映像編集用コンピュータプログラム
JP2020010154A (ja) * 2018-07-06 2020-01-16 エヌ・ティ・ティ・コムウェア株式会社 危険作業検出システム、解析装置、表示装置、危険作業検出方法、および、危険作業検出プログラム
JP2020093890A (ja) * 2018-12-12 2020-06-18 株式会社神鋼エンジニアリング＆メンテナンス クレーン作業監視システム、クレーン作業監視方法、危険状態判定装置、及びプログラム

Also Published As

Publication number Publication date
JPWO2023112214A1 (fr) 2023-06-22

Similar Documents

Publication Publication Date Title
US20220301300A1 (en) Processing method for augmented reality scene, terminal device, system, and computer storage medium
US10810438B2 (en) Setting apparatus, output method, and non-transitory computer-readable storage medium
CN108875708A (zh) 基于视频的行为分析方法、装置、设备、系统及存储介质
JP2006079272A (ja) 異常動作検出装置および異常動作検出方法
JP2019003299A (ja) 画像認識装置および画像認識方法
US11887331B2 (en) Information processing apparatus, control method, and non-transitory storage medium
CN112528825A (zh) 一种基于图像识别的车站乘客招援服务方法
US20200084416A1 (en) Information processing apparatus, control method, and program
CN110909691B (zh) 动作检测方法、装置、计算机可读存储介质和计算机设备
CN115861915A (zh) 消防通道监控方法、消防通道监控装置以及存储介质
US20220076005A1 (en) Person authentication apparatus, control method, and non-transitory storage medium
CN110390226B (zh) 人群事件识别方法、装置、电子设备及系统
CN114764895A (zh) 异常行为检测装置和方法
WO2023112214A1 (fr) Dispositif, procédé, et programme de détection de vidéo d'intérêt
JP7214437B2 (ja) 情報処理装置、情報処理方法及びプログラム
KR20220019377A (ko) 딥러닝을 이용한 드론 검출 장치 및 방법
JP7372391B2 (ja) 入力データにおける異常を検知するための概念
JP2015187769A (ja) 物体検出装置、物体検出方法及びプログラム
JP2020201674A (ja) 映像解析装置及びその制御方法及びプログラム
CN117671594B (zh) 安全监控方法、装置、电子设备和存储介质
WO2023112213A1 (fr) Dispositif, procédé et programme de détection de comportement spécifique
US20230401894A1 (en) Behavior estimation device, behavior estimation method, and recording medium
CN111062337B (zh) 人流方向检测方法及装置、存储介质和电子设备
KR102369151B1 (ko) 동작 인식을 위한 메타 데이터 생성 시스템 및 생성 방법
WO2022018902A1 (fr) Appareil, système et procédé de détection d'objet

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21968129

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023567396

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE