KR20140106883A - Apparatus and method for detecting a risk situation by analyzing a relation of object - Google Patents

Apparatus and method for detecting a risk situation by analyzing a relation of object Download PDF

Info

Publication number
KR20140106883A
KR20140106883A KR1020130021112A KR20130021112A KR20140106883A KR 20140106883 A KR20140106883 A KR 20140106883A KR 1020130021112 A KR1020130021112 A KR 1020130021112A KR 20130021112 A KR20130021112 A KR 20130021112A KR 20140106883 A KR20140106883 A KR 20140106883A
Authority
KR
South Korea
Prior art keywords
risk
situation
information
scenario
state
Prior art date
Application number
KR1020130021112A
Other languages
Korean (ko)
Inventor
김건우
Original Assignee
한국전자통신연구원
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 한국전자통신연구원 filed Critical 한국전자통신연구원
Priority to KR1020130021112A priority Critical patent/KR20140106883A/en
Publication of KR20140106883A publication Critical patent/KR20140106883A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B23/00—Alarms responsive to unspecified undesired or abnormal conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons

Landscapes

  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Emergency Management (AREA)
  • Alarm Systems (AREA)
  • Image Analysis (AREA)

Abstract

The present invention relates to a method to detect a risk situation of an object in an image. According to the present invention, a device to detect a risk situation by analyzing a correlation between objects comprises: an object database to manage state information of at least one object in an input image as a profile; a risk situation scenario database to manage at least one risk situation scenario generated for a predetermined risk situation; and a risk determination unit to determine whether it is a risk situation by analyzing a correlation between the state information of the objects based on the risk situation scenario. According to the device and the method of the present invention, damage can be minimized by checking the state of a plurality of objects in an image in real time, detect a risk situation based on the state of the objects, cope with the risk situation in real time, and security service companies and image equipment companies can create profits through a new business model.

Description

 TECHNICAL FIELD The present invention relates to an apparatus and method for analyzing a risk situation by analyzing associations among objects,

 The present invention relates to a method for detecting a dangerous situation of an object in an image.

The conventional risk detection method is a method of generating an event by analyzing the state of a single object. However, this method has difficulties in detecting various risk scenarios.

The present invention has been conceived to solve the above problems of the prior art, and it is an object of the present invention to automatically analyze images collected through CCTV, etc. to grasp the state of an object such as a person or a vehicle in the image, It is intended to provide a method for detecting and predicting situations.

According to an aspect of the present invention, there is provided an apparatus for analyzing a risk through an association between objects, the apparatus comprising: an object database for managing status information of at least one object in a received image as a profile; A risk situation scenario database for managing at least one risk situation scenario generated for a predetermined risk situation; And a risk judgment unit for analyzing a correlation between each state information of the object based on the risk situation scenario to determine whether or not the risk situation exists.

Preferably, the risk-situation analyzing apparatus further includes an object detecting unit that detects an object from the input image, and the database manages state information of the detected object by the object-specific profile.

The risk scenario is preferably generated for a risk situation determined according to environmental information including the current or past and present time-space situations of a single object.

It is preferable that the dangerous situation scenario is generated for a plurality of objects in a dangerous situation in which state information of other objects expected to be generated in association with the state information of an object is not generated.

It is preferable that the dangerous situation scenario is generated for a dangerous situation in which, in a plurality of images related to a space, an object included in one image does not appear in another image of a space associated with the image after disappearing from the space of the image.

Preferably, the object includes a dynamic object including a person or a vehicle and a static object including a building or facility.

And the state information of the object may include external shape information of the dynamic object and speed information according to motion of the object.

The risk-situation analyzing apparatus further includes a risk-situation notifying unit for notifying occurrence of the dangerous situation to a predetermined corresponding server according to the type of the dangerous situation when the danger determining unit determines the dangerous situation.

According to an aspect of the present invention, there is provided a risk analysis method for analyzing an association between objects according to an embodiment of the present invention includes: receiving object profile information about status information of at least one object in an input image; Receiving at least one risk scenario generated for a predetermined risk situation; And analyzing a relation between each state information of the object through the input object profile information based on the risk scenario, and determining whether the object is in a dangerous state.

According to another aspect of the present invention, there is provided a risk analysis method for analyzing a correlation between objects, comprising: detecting an object from an input image; Managing status information of the detected object by the per-object profile information; Receiving profile information for each object of at least one object in the input image; Receiving at least one risk scenario generated for a predetermined risk situation; And analyzing a relation between each state information of the object through the input object profile information based on the risk scenario, and determining whether the object is in a dangerous state.

 According to the present invention, it is possible to minimize the damage by coping with a dangerous situation in real time by detecting the state of multiple objects in real time in real time and detecting a dangerous situation based on the status, To generate revenue.

FIG. 1 is a diagram illustrating a configuration of an analysis system to which an apparatus for analyzing a risk according to an inter-object association analysis according to an embodiment of the present invention is applied.
2 is a block diagram illustrating a risk situation analyzing apparatus according to an embodiment of the present invention.
FIG. 3 is a flowchart illustrating a method for analyzing a risk situation through an inter-object association analysis according to an embodiment of the present invention.
FIG. 4 is a detailed flowchart illustrating a method for analyzing a risk through an inter-object association analysis according to an embodiment of the present invention.

The following merely illustrates the principles of the invention. Therefore, those skilled in the art will be able to devise various apparatuses which, although not explicitly described or shown herein, embody the principles of the invention and are included in the concept and scope of the invention. It is also to be understood that all conditional terms and examples recited in this specification are, in principle, expressly intended for the purpose of enabling the inventive concept to be understood, and are not intended to be limiting as to such specifically recited embodiments and conditions .

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: . In the following description, a detailed description of known technologies related to the present invention will be omitted when it is determined that the gist of the present invention may be unnecessarily blurred. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a diagram illustrating a configuration of an analysis system to which an apparatus for analyzing a risk according to an inter-object association analysis according to an embodiment of the present invention is applied.

 Referring to FIG. 1, the analysis system includes a camera 10 for capturing the state of an object, a risk situation analyzing apparatus 100, and a risk response server 1000.

The camera 10 is a photographing means such as a CCTV capable of photographing a specific area, and provides a photographed image as data for determining whether or not a dangerous situation has occurred, according to the present invention.

The risk situation analyzing apparatus 100 is a device for real time grasping the state of multiple objects in an image and detecting a dangerous situation based on the state of the multiple objects, which will be described later.

Furthermore, the risk countermeasure server 1000 is a network server of a service provider that provides a corresponding service when the risk situation analyzing apparatus determines that the risk situation analyzing apparatus is a dangerous situation. In the present embodiment, A private receiving server of the providing company.

In the present embodiment, when a dangerous situation occurs, the dangerous situation analysis apparatus 100 notifies the corresponding server determined according to the type of occurrence of the dangerous situation. For example, when a crime situation occurs, it notifies the reception server of the police case reporting center and notifies the reception server of the fire department when a fire or an emergency occurs. Further, the patient can be notified of the emergency medical information center when it occurs.

Hereinafter, with reference to FIG. 2, the risk event analysis apparatus 100 according to an embodiment of the present invention will be described in more detail.

In the present embodiment, the risk situation analyzing apparatus includes an object detecting unit 110, an object database 120, a risk situation scenario database 130, and a risk judging unit 140.

The object detection unit 110 detects an object from the input image. Detection of an object can be performed by extracting features such as points, boundaries, edges, textures, colors, etc., which are distinguished from other parts and detecting the object.

Further, in the present embodiment, since the object includes a dynamic object including a person or a vehicle and a static object including a building or a facility, the detection of the object may be performed by separately extracting a background object and a foreground object (or a motion object) Therefore, an extraction technique using a background image and an extraction technique using a continuous frame can be used.

In order to extract a desired object from an image, region segmentation, in which similar regions (regions) are grouped, is considered as a unit based on features representing regions, and region-based segmentation A boundary - based zoning method can also be used to extract meaningful regions using the zoning information obtained after extracting the edges from the zoning method and the image.

As described above, the present invention is not focused on the object detection method, but rather, it is determined whether the object is a dangerous situation by using the detected object information, and thus a detailed description of the object detection method is omitted.

Referring to FIG. 2, the object database 120 manages the state information of the object detected by the object detection unit according to the per-object profile. In the present embodiment, the profile by object refers to information obtained by summarizing the detected state information of each object according to the time order. The state information includes information on the time at which the object is photographed, the characteristic information of the object, Information, spatial location information, and the like.

Specifically, state information includes, for example, all states that can represent the current situation of a person, such as a current position, a standing position, a sitting state, a walking state, a running state, a lying state, And may include all states that can represent the current state of the vehicle, such as the current position, the ignition off state, the parking state, the stop state, and the running state when the object is a vehicle.

In this embodiment, the object database 120 provides status information of an object to be managed to a risk determination unit, which will be described later, and determines whether or not a risk situation exists by grasping the association of the objects.

Next, in this embodiment, the risk situation scenario database 130 manages at least one risk situation scenario generated for a predetermined risk situation.

In the present embodiment, a dangerous situation refers to a case where a safety problem arises in an object, or a case where an urgent action is required due to the occurrence of an abnormal situation although it is not a safety problem. The dangerous situation may include accidents, incidents, assaults, Includes all risk factors such as local access, suspicious situations, and risk prediction situations.

The risk situation scenario is a comparison data for generalizing such a risk situation and judging whether the correlation between objects recognized as state information of each of the objects in various environments can correspond to a risk situation.

That is, in this embodiment, the dangerous situation scenario may be generated for a dangerous situation determined according to environmental information including the current or past and present temporal and spatial conditions of a single object.

In addition, the risk situation scenario may be generated for a plurality of objects, for a dangerous situation in which state information of another object expected to be generated in association with the state information of one object is not generated.

In addition, the risk scenario may be generated for a plurality of images of an associated space, and for a dangerous situation in which an object included in one image does not appear in another image of a space associated with the image after disappearing from the space of the image .

As described above, in the present embodiment, the risk situation scenario database 130 stores and manages the risk situation scenarios generated for the above-described risk situations, and provides them to the risk judgment unit to determine whether or not the risk situation exists.

The risk judging unit 140 according to the present embodiment analyzes the association between each state information of the object based on the risk situation scenario to determine whether or not the risk situation exists.

For example, based on a scenario for a risk situation determined according to environmental information including a current or past and present time-and-space situation of a single object, for example, through the association analysis between respective object state information, It is possible to determine the occurrence of a dangerous situation by identifying a case where a person identified through the image is located on a train track, on a railway bridge, or in the middle of a road.

In addition, for example, through association analysis between object state information, it is considered that the direction of movement according to the speed of the person, which is grasped through the past image and the current image, is directed to dangerous places such as a train line, a building rail, Or when the vehicle is reversing the road, it is possible to judge the occurrence of a dangerous situation

Also, based on the risk scenarios that are set for the dangerous situation where the status information of other objects expected to be generated in association with the status information of an object is not generated in a plurality of objects, The object state information indicating that the start of the vehicle identified as the object is turned off is recognized and the driver is expected to get off, such as when the person does not get off the vehicle for a certain period of time after the vehicle is parked in the underground parking lot, It is possible to determine the occurrence of a dangerous situation by grasping the case where the object state information for the driver is not recognized in the image.

Further, based on scenarios generated for a dangerous situation in which a plurality of images of an associated space are not displayed in another image of an associated space after the objects included in one image disappear from the space of the image, For example, if a person who disappeared in the elevator direction from the underground parking lot does not appear in the image installed at the entrance of the elevator, the accident occurred in the CCTV blind spot. And predicts the occurrence of a dangerous situation.

Referring to FIG. 2 again, when the risk judging unit 140 judges a dangerous situation, the apparatus 100 for dangerous situation analysis according to the present embodiment detects the occurrence of the dangerous situation in a corresponding server predetermined according to the type of the dangerous situation (Not shown) for notifying the user of the risk. When the dangerous situation is determined as described above, the occurrence of the dangerous situation is notified to the predetermined corresponding server according to the type of the dangerous situation. For example, when a crime situation occurs, it notifies the reception server of the police case reporting center and notifies the reception server of the fire department when a fire or an emergency occurs. Further, the patient can be notified of the emergency medical information center when it occurs.

According to the present invention, it is possible to minimize the damage by coping with a dangerous situation in real time by detecting real-time status of multiple objects in a video and detecting a dangerous situation based on the status, You can generate revenue through models. 3 to 4, a method for analyzing a risk situation through analysis of inter-object association performed in the apparatus 100 for analyzing a risk situation according to the embodiment described above will be described.

Referring to FIG. 3, the method for analyzing risk through analysis of inter-object association according to an exemplary embodiment of the present invention includes an object profile input step S100, a risk situation scenario input step S200, .

The object profile input step S100 receives the object profile information about the state information of at least one object in the input image.

Further, the risk state scenario inputting step (S200) receives at least one risk situation scenario generated for a predetermined risk situation.

In the risk state determination step S300, based on the risk situation scenario, the association of each state information of the object is analyzed through the input object profile information to determine whether or not the risk state exists.

4, the dangerous situation analysis method receives an image photographed by a camera (S10), and detects an object from an image input by the object detection unit rk (S20).

The object database generates and manages state information of the object detected by the object detector as the per-object profile information (S30). Then, the object profile information is provided to the risk judging unit for judging the risk situation, and the risk judging unit is inputted (S100). Further, the risk situation scenario database stores and manages the risk situation scenarios generated for the above-described risk situations, provides them to the risk judgment unit, and the risk judgment unit receives the input (S200) to determine whether or not the risk situation exists.

The risk judging unit analyzes the association of each state information of the object based on the input risk profile scenario information (S210).

In the case of a dangerous situation, the dangerous situation notification unit notifies the corresponding server determined in advance according to the type of the dangerous situation, and notifies the occurrence of the dangerous situation and responds thereto.

If it is not a dangerous situation, it executes the risk situation analysis method by analyzing the correlation between objects through the input of images.

Meanwhile, the risk analysis method through the inter-object correlation analysis of the present invention can be implemented by a computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. Computer-readable code in a distributed fashion can be stored and executed. In addition, functional programs, codes, and code segments for implementing the present invention can be easily deduced by programmers skilled in the art to which the present invention belongs.

It will be apparent to those skilled in the art that various modifications, substitutions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. will be.

Therefore, the embodiments disclosed in the present invention and the accompanying drawings are intended to illustrate and not to limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings . The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

Claims (18)

An object database for managing status information of at least one object in the input image as a profile;
A risk situation scenario database for managing at least one risk situation scenario generated for a predetermined risk situation; And
And a risk determination unit for analyzing a correlation between each state information of the object based on the risk state scenario to determine whether or not the state is a dangerous state. The risk analysis apparatus according to claim 1,
Further comprising an object detecting unit for detecting an object from the input image,
Wherein the database manages the state information of the detected object as the object-by-object profile. The method according to claim 1,
Wherein the dangerous situation scenario is generated for a dangerous situation determined according to environmental information including a current or past and current temporal and spatial conditions of a single object. The method according to claim 1,
Wherein the dangerous situation scenario is generated for a plurality of objects in a dangerous situation in which state information of other objects expected to be generated in association with the state information of an object is not generated, Hazardous situation analysis device. The method according to claim 1,
The dangerous situation scenario is generated for a dangerous situation in which a plurality of images for a space to be associated do not appear in another image for a space after an object included in one image disappears in the space of the image An apparatus for analyzing a risk situation by analyzing associations among objects. The method according to claim 1,
Wherein the object includes a dynamic object including a person or a vehicle and a static object including a building or a facility. The method according to claim 6,
Wherein the state information of the object includes the external shape information of the dynamic object and the velocity information according to the motion of the object. The risk analysis apparatus according to claim 1,
And a risk status notification unit for notifying occurrence of the dangerous situation to a predetermined corresponding server according to the type of the dangerous situation when the risk determination unit determines the dangerous situation. . Receiving object profile information for state information of at least one object in an input image;
Receiving at least one risk scenario generated for a predetermined risk situation; And
Analyzing the association between each state information of the object through the input object profile information based on the risk state scenario to determine whether or not the object is in a dangerous state; . The risk analysis method according to claim 9,
Detecting an object from an input image; And
And managing status information of the detected object with the per-object profile information,
Wherein the step of receiving the object profile information includes receiving the profile information of each object. 10. The method of claim 9,
Wherein the risk scenario is generated for a risk situation determined according to environmental information including a current or past and a current time-and-space situation of a single object. 10. The method of claim 9,
Wherein the dangerous situation scenario is generated for a plurality of objects in a dangerous situation in which state information of other objects expected to be generated in association with the state information of an object is not generated, Risk analysis method. 10. The method of claim 9,
The dangerous situation scenario is generated for a dangerous situation in which a plurality of images for a space to be associated do not appear in another image for a space after an object included in one image disappears in the space of the image A risk analysis method through correlation between objects. 10. The method of claim 9,
Wherein the object includes a dynamic object including a person or a vehicle and a static object including a building or a facility. 15. The method of claim 14,
And the state information of the object includes the external shape information of the dynamic object and the speed information according to the motion of the object. The risk analysis method according to claim 9,
And a risk status notification unit for notifying occurrence of the dangerous situation to a predetermined correspondence server according to the type of the dangerous situation when the risk determination unit determines the dangerous situation. . Detecting an object from an input image;
Managing status information of the detected object by the per-object profile information;
Receiving profile information for each object of at least one object in the input image;
Receiving at least one risk scenario generated for a predetermined risk situation; And
Analyzing the association between each state information of the object through the input object profile information based on the risk state scenario to determine whether or not the object is in a dangerous state; . Detecting an object from an input image;
Managing status information of the detected object by the per-object profile information;
Receiving profile information for each object of at least one object in the input image;
Receiving at least one risk scenario generated for a predetermined risk situation; And
Analyzing the association between each state information of the object through the input object profile information based on the risk state scenario to determine whether or not the object is in a dangerous state; On a computer-readable recording medium
KR1020130021112A 2013-02-27 2013-02-27 Apparatus and method for detecting a risk situation by analyzing a relation of object KR20140106883A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020130021112A KR20140106883A (en) 2013-02-27 2013-02-27 Apparatus and method for detecting a risk situation by analyzing a relation of object

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020130021112A KR20140106883A (en) 2013-02-27 2013-02-27 Apparatus and method for detecting a risk situation by analyzing a relation of object

Publications (1)

Publication Number Publication Date
KR20140106883A true KR20140106883A (en) 2014-09-04

Family

ID=51754994

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020130021112A KR20140106883A (en) 2013-02-27 2013-02-27 Apparatus and method for detecting a risk situation by analyzing a relation of object

Country Status (1)

Country Link
KR (1) KR20140106883A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160104940A (en) * 2015-02-27 2016-09-06 광운대학교 산학협력단 A Method for Providing Event Occurrence Information Using Big Data and A System for the Same
KR101889282B1 (en) * 2017-05-11 2018-08-20 곽종우 Method and apparatus for safety management for playing facilities
WO2019066502A1 (en) * 2017-09-27 2019-04-04 Samsung Electronics Co., Ltd. Method and device for detecting dangerous situation
KR20190059723A (en) * 2017-11-23 2019-05-31 (주)에이텍티앤 Artificial intelligence based traffic accident prediction system and method
KR101979375B1 (en) * 2018-02-23 2019-08-28 주식회사 삼알글로벌 Method of predicting object behavior of surveillance video
CN111931746A (en) * 2020-10-09 2020-11-13 深圳壹账通智能科技有限公司 Vehicle loss judgment method and device, computer equipment and readable storage medium
CN113610167A (en) * 2021-08-10 2021-11-05 宿迁旺春机械制造有限公司 Equipment risk detection method based on metric learning and visual perception

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160104940A (en) * 2015-02-27 2016-09-06 광운대학교 산학협력단 A Method for Providing Event Occurrence Information Using Big Data and A System for the Same
KR101889282B1 (en) * 2017-05-11 2018-08-20 곽종우 Method and apparatus for safety management for playing facilities
WO2019066502A1 (en) * 2017-09-27 2019-04-04 Samsung Electronics Co., Ltd. Method and device for detecting dangerous situation
KR20190036315A (en) * 2017-09-27 2019-04-04 삼성전자주식회사 Method and apparatus for detecting a dangerous situation
US11298049B2 (en) 2017-09-27 2022-04-12 Samsung Electronics Co., Ltd. Method and device for detecting dangerous situation
KR20190059723A (en) * 2017-11-23 2019-05-31 (주)에이텍티앤 Artificial intelligence based traffic accident prediction system and method
WO2019103197A1 (en) * 2017-11-23 2019-05-31 (주)에이텍티앤 System for predicting traffic accident on basis of artificial intelligence and method therefor
KR101979375B1 (en) * 2018-02-23 2019-08-28 주식회사 삼알글로벌 Method of predicting object behavior of surveillance video
CN111931746A (en) * 2020-10-09 2020-11-13 深圳壹账通智能科技有限公司 Vehicle loss judgment method and device, computer equipment and readable storage medium
CN111931746B (en) * 2020-10-09 2021-02-12 深圳壹账通智能科技有限公司 Vehicle loss judgment method and device, computer equipment and readable storage medium
CN113610167A (en) * 2021-08-10 2021-11-05 宿迁旺春机械制造有限公司 Equipment risk detection method based on metric learning and visual perception

Similar Documents

Publication Publication Date Title
KR20140106883A (en) Apparatus and method for detecting a risk situation by analyzing a relation of object
US11276256B2 (en) Traffic event recording and recreation
US10552687B2 (en) Visual monitoring of queues using auxillary devices
AU2016203571A1 (en) Predicting external events from digital video content
JP2013218679A (en) Video-based detection device and notification device for catching short-time parking violation
KR101036947B1 (en) The automatic guard system to prevent the crime and accident using computer video image analysis technology
US9830823B1 (en) Detection of vehicle operation characteristics
CN103150899B (en) The monitoring method of Traffic Information, Apparatus and system
KR20160074208A (en) System and method for providing safety service using beacon signals
CN110992628B (en) Cable tunnel anti-intrusion system based on intelligent video
US11727580B2 (en) Method and system for gathering information of an object moving in an area of interest
CN102254401A (en) Intelligent analyzing method for passenger flow motion
CN115410354A (en) Safety early warning method, device and system for industrial plant
WO2018037392A1 (en) System and method for access control in open restricted areas
CN113647097A (en) Carry-over detection device and carry-over detection method
CN112580470A (en) City visual perception method and device, electronic equipment and storage medium
CN116246416A (en) Intelligent analysis early warning platform and method for security protection
US11470285B2 (en) Method and system for monitoring portal to detect entry and exit
KR20180066688A (en) Digital Social Shield System using Deep Active Semi-Supervised Learning
CN114582118A (en) Public security inspection station vehicle intelligent distribution method and system based on passing strategy
KR102614856B1 (en) System and method for predicting risk of crowd turbulence
CN114694339A (en) Fire prevention and control method and system for rail transit
KR20140056674A (en) Commnication service system, method and apparatus for supporting process of accident in the system
KR102389521B1 (en) Convergence Monitoring System and Method for Industry Safety
US11847904B2 (en) Integrated security management system and method

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination