CN115620228B - Subway shielding door close-door passenger door-opening early warning method based on video analysis - Google Patents

Subway shielding door close-door passenger door-opening early warning method based on video analysis Download PDF

Info

Publication number
CN115620228B
CN115620228B CN202211251732.9A CN202211251732A CN115620228B CN 115620228 B CN115620228 B CN 115620228B CN 202211251732 A CN202211251732 A CN 202211251732A CN 115620228 B CN115620228 B CN 115620228B
Authority
CN
China
Prior art keywords
door
passenger
target
risk
early warning
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202211251732.9A
Other languages
Chinese (zh)
Other versions
CN115620228A (en
Inventor
王曦明
刘光杰
孙同庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Information Science and Technology
Original Assignee
Nanjing University of Information Science and Technology
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 Nanjing University of Information Science and Technology filed Critical Nanjing University of Information Science and Technology
Priority to CN202211251732.9A priority Critical patent/CN115620228B/en
Publication of CN115620228A publication Critical patent/CN115620228A/en
Application granted granted Critical
Publication of CN115620228B publication Critical patent/CN115620228B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
    • B61K13/00—Other auxiliaries or accessories for railways
    • B61K13/04—Passenger-warning devices attached to vehicles; Safety devices for preventing accidents to passengers when entering or leaving vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/23—Recognition of whole body movements, e.g. for sport training
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Mechanical Engineering (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

The invention discloses a subway shielding door close-door passenger door-opening early warning method based on video analysis, which comprises the following steps: starting a passenger door-break early warning terminal system installed at the door head of the shielding door at the moment of closing the door, and continuously acquiring video frames according to a given frame rate by a video acquisition module; the video analysis module continuously calculates the motion trail of the pedestrian target in the front area based on the YOLOv5 and the deep; the gate running risk assessment module calculates the gate running risk of the total passengers facing the gate based on the motion trail of all the pedestrian targets; and carrying out secondary gate running early warning treatment comprising audible and visual alarm and gate control linkage on the condition that the estimated risk exceeds a given threshold. The invention provides an effective scheme for reducing adverse effects of passenger door-breaking behaviors on driving and passenger safety.

Description

Subway shielding door close-door passenger door-opening early warning method based on video analysis
Technical Field
The invention relates to an intelligent station for urban rail transit, in particular to a method for early warning that passengers close to a door break the door based on video analysis.
Background
The subway has become a main tool and a field of great development of public transportation in many cities due to the advantages of safety, quasi points, rapidness, comfort, environmental protection and the like. The intelligent subway essentially achieves the aims of improving the operation efficiency, reducing the operation risk, improving the passenger service satisfaction and the like by intelligently enabling various systems such as train vehicles, wire network stations, dispatching management, operation and maintenance guarantee and the like. Development of intelligent subway technology and application based on cloud computing, internet of things, artificial intelligence and other technologies is well-developed. In recent years, face recognition non-inductive payment gate passing, voice recognition intelligent customer service, station operation based on intelligent video analysis and other systems have been applied to major cities in China in demonstration and have achieved practical results.
In the intelligent station scene, the CCTV connected with the signal system can detect abnormal scenes such as the escalator retrograde, stair crowding, barrier delivery, passenger falling, article omission and the like by performing intelligent video analysis, so that the initiative and timeliness of abnormal event discovery are improved. During the whole process of taking a passenger, the door-breaking behavior of the passenger close to the door-closing period is a high-risk behavior endangering the safety of the passenger and the driving safety. Generally, both the shielding door and the train door are provided with anti-holding functions, but these functions only have feedback on objects with rigidity and large size, so that a large number of passengers break the door to cause the door to be unable to be normally closed, the vehicle to be unable to normally run, and serious accidents caused by the passengers being held between the shielding door and the door to cause death. In recent years, some cities have explored the benefits of new equipment based on sensors such as visible light vision and laser radar in the aspect of foreign matter detection between a shielding door and a door gap of a train door, but still can only solve the problems of post emergency and linkage treatment of a clamped object, and the lack of active door-rushing early warning means is always lacking. CCTV monitoring conventionally configured on a platform layer usually adopts several groups of cameras parallel to a track, and cannot cope with early warning under the condition of rapid door running of each door passenger due to unfavorable view field and medium-high delay video analysis at the stage of the station.
The invention provides a subway shielding door-closing passenger door-opening early warning method based on the on-site computing capability of cameras with oblique downward visual angles and passenger door-opening early warning terminal systems, which are arranged at the door heads of each shielding door, so as to reduce adverse effects of passenger door-opening behaviors on driving and passenger safety.
Disclosure of Invention
The invention aims to: the invention aims to provide a subway shielding door close-door passenger door-opening early warning method based on video analysis, so that adverse influence of passenger door-opening behaviors on driving and passenger safety is reduced through active door-opening early warning.
The technical scheme is as follows: in order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, a method for early warning a door break of a passenger close to a door of a subway shielding door based on video analysis is provided, which comprises the following steps:
step S1: the time for closing the door is still T seconds, and the video frames I of the field of view F are continuously acquired according to the preset frame rate R 1 、I 2 、....I i 、....；
Step S2: for the current video frame I i Pedestrian targets are detected based on the Yolov5 neural network and are associated with the detected targets in the preamble video frames based on Deepsort to achieve target O 1 、O 2 、...、O n Where n is the number of all pedestrian targets, converting the motion trajectory of the target in the field of view F into a continuous motion trajectory Tr of the target in the corresponding front-door region H by perspective transformation 1 (t)、Tr 2 (t)、...Tr n (t)；
Step S3: by means of pedestrian targets O 1 、O 2 、...、O n Motion trajectory Tr in front door region H i (t) carrying out single-target gate-running risk assessment on the data, and calculating a continuous risk assessment value R of each target 1 (t)、R 2 (t)、...、R n (t) and generating a total passenger running door risk RH (t) of the door facing by integrating the single target risk;
step S4: and carrying out classified door-rushing early warning treatment based on the door-rushing risk RH (t) of the main passenger facing the door and a preset secondary threshold value.
In some embodiments, in the step S1, the method for acquiring the video frame of the field of view F includes:
and according to the time plan of the train driving dispatching signal system, a passenger mounted at the door head of the shielding door breaks a door early warning terminal system, and when the time for closing the door is still T seconds, the passenger close to the door is started to break the door early warning function, and a video acquisition module of the system acquires video frames by using a camera mounted at an oblique downward visual angle right above the shielding door.
In some embodiments, the step S2 includes:
s201: for the current video frame I acquired in the step S1 i Pedestrian target detection based on YOLOv5 neural network and detection output O 1 、O 2 、...、O n N pedestrian targets in total, and if no pedestrian target is detected, outputting NULL;
s202: if S201 output is NULL, the step S201 is circularly executed for the next frame I output by S1 i+1 Performing pedestrian target detection operation until the current time t=t;
if a pedestrian object is detected in step S201, then the previous frame I is used i-1 Performing Deepsort target association tracking operation on the recorded target detection result to form O 1 、O 2 、...、O n Motion trail K of each target in field of view F 1 (t)、K 2 (t)、...K n (t)；
S203: k is transformed by a perspective transformation matrix calibrated in advance 1 (t)、K 2 (t)、...K n (t) conversion to the trajectory Tr in the plan view coordinates corresponding to the door front region H 1 (t)、Tr 2 (t)、...Tr n (t)。
In some embodiments, the step S3 includes:
s301: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the included angle u between the motion direction and the Y axis i The coordinate system of the front door region H is defined as taking the downward direction of the central line as the Y axis and taking the right direction of the upper edge line of the H region as the X axis;
s302: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the Y-axis component v of its motion velocity i The coordinate system of the front door region H is defined as taking the downward direction of the central line as the Y axis and taking the right direction of the upper edge line of the H region as the X axis;
s303: for all detected and generated motion trails Tr i Target O of (t) i Record target O i The distance from the bottom line of the H area in the Y direction is D i ；
According to R i (t)＝max(cos(u i ),0)×max(1.5-v i ×(T-t)/D i 0) calculating the target O at the current time t i Running a door to risk;
s304: the total risk of running the door by the passengers facing the door is calculated as follows: RH (t) =max (R 1 (t),R 2 (t),...,R n (t))。
In some embodiments, the step S4 includes:
running a door risk RH (t) for a total passenger exceeding a first threshold Th 1 The first-level response of the shielding door is that the passenger is reminded through an audible and visual alarm device arranged above the shielding door;
running the door risk RH (t) for the total passenger exceeding the second threshold Th 2 The shielding door and the door control system are linked to keep the shielding door and the door open while keeping the audible and visual alarm until the door main passenger runs the door risk RH (t) to return to zero, and then the shielding door and the door control system are linked to close the shielding door and the door, wherein the second threshold Th 2 Greater than a first threshold Th 1 。
The step S4 further includes:
and recording and generating and storing a video record of the passenger running the door while performing the primary response or the secondary response.
In some embodiments, the first threshold Th 1 Is 0.25, the second threshold Th 2 0.5.
In a second aspect, the invention provides a subway shield door-closing passenger door-opening early warning device based on video analysis, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to the first aspect.
In a third aspect, the present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of the first aspect.
The beneficial effects are that: compared with the prior art, the invention has the following advantages:
1. the invention solves the problem that the current stations and trains lack a passenger door-break early warning mechanism, and provides an effective scheme for reducing the occurrence rate of passenger door-break and the risk of clamping people and objects in extreme cases;
2. compared with the detection of abnormal behaviors of passengers based on the existing video monitoring in the hall, the method and the system can provide early warning of the running of passengers facing each single door based on the favorable view field of the intelligent computing unit arranged on the door head of the shielding door and the real-time computing capability of the terminal, and have higher real-time performance and reliability.
Drawings
Fig. 1 is a flowchart of a method for early warning a passenger running a door when a subway shielded door is close based on video analysis in an embodiment of the invention;
fig. 2 is a schematic diagram of the moving direction and speed of a pedestrian object in a front area of a door in an embodiment.
Detailed Description
In order that the manner in which the invention is accomplished, as well as the manner in which it is characterized and attained and its efficacy, a better understanding of the invention is obtained, a further description of the invention will be obtained when reference is made to the following detailed description.
In the description of the present invention, the meaning of a number is one or more, the meaning of a number is two or more, and greater than, less than, exceeding, etc. are understood to exclude the present number, and the meaning of a number is understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, the descriptions of the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Example 1
A subway shielding door-closing passenger door-running early warning method based on video analysis comprises the following steps:
step S1: the time for closing the door is still T seconds, and the video frames I of the field of view F are continuously acquired according to the preset frame rate R 1 、I 2 、....I i 、....；
Step S2: for the current video frame I i Pedestrian targets are detected based on the Yolov5 neural network and are associated with the detected targets in the preamble video frames based on Deepsort to achieve target O 1 、O 2 、...、O n Where n is the number of all pedestrian targets, converting the motion trajectory of the target in the field of view F into a continuous motion trajectory Tr of the target in the corresponding front-door region H by perspective transformation 1 (t)、Tr 2 (t)、...Tr n (t)；
Step S3: by means of pedestrian targets O 1 、O 2 、...、O n Motion trajectory Tr in front door region H i (t) carrying out single-target gate-running risk assessment on the data, and calculating a continuous risk assessment value R of each target 1 (t)、R 2 (t)、...、R n (t) and generating a total passenger running door risk RH (t) of the door facing by integrating the single target risk;
step S4: and carrying out classified door-rushing early warning treatment based on the door-rushing risk RH (t) of the main passenger facing the door and a preset secondary threshold value.
In some embodiments, as shown in fig. 1, a method for early warning a passenger approaching a door of a subway shielding door to break the door based on video analysis comprises the following steps: starting a passenger door-break early warning terminal system installed at the door head of the shielding door at the moment of closing the door, and continuously acquiring video frames according to a given frame rate by a video acquisition module; the video analysis module continuously calculates the motion trail of the pedestrian target in the front area based on the YOLOv5 and the deep; the gate running risk assessment module calculates the gate running risk of the total passengers facing the gate based on the motion trail of all the pedestrian targets; and carrying out gate running early warning treatment comprising audible and visual alarm and gate control linkage on the condition that the estimated risk exceeds a given threshold.
The specific steps in this embodiment are as follows:
s1: passenger door-break early-warning terminal installed at door head of shielding door according to time plan of train driving dispatching signal systemThe system starts the door-break early warning function of passengers approaching to the door when T seconds (according to the specific configuration of the door-break opening and early warning of a station, the T value proposal is set to 10S) remain in the door-break time, and a video acquisition module of the system continuously acquires video frames I of a view field F according to a frame rate R (in order to ensure the real-time performance of motion detection, the proposal frame rate is not lower than 720@60 fps) by using a camera arranged at an oblique downward visual angle right above a shielding door 1 、I 2 、....；
S2: for the current frame I i Detecting pedestrian targets based on the YOLOv5 neural network and correlating with detected targets in the preamble frames based on Deepsort to achieve target O 1 、O 2 、...、O n Where n is the number of all pedestrian targets, converting the motion trajectory of the targets in the field of view F into continuous motion trajectories Tr of the targets in the corresponding door front region H by perspective transformation (perspective transformation matrix is calculated in advance based on parameters such as camera lens parameters and mounting position, and the unified perspective transformation matrix is shared by all lines with the mounting accuracy ensured) 1 (t)、Tr 2 (t)、...Tr n (t)；
S3: by means of pedestrian targets O 1 、O 2 、...、O n Motion trajectory Tr in front door region H i (t) carrying out single-target gate-running risk assessment on the data, and calculating a continuous risk assessment value R of each target 1 (t)、R 2 (t)、...、R n (t) and generating a total passenger running door risk RH (t) of the door facing by integrating the single target risk;
s4: and carrying out hierarchical gate running early warning treatment comprising audible and visual alarm and gate control linkage based on the gate running risk RH (t) of the gate master passenger and a set secondary threshold.
In this embodiment, the step S2 specifically includes the following steps:
s201: for the current frame I acquired in the step S1 i Pedestrian target detection based on YOLOv5 neural network and detection output O 1 、O 2 、...、O n N pedestrian targets in total, and if no pedestrian target is detected, outputting NULL;
s202: if S201 output is NULL, loop executionS201 step is to output the next frame I of S1 i+1 Performing a pedestrian target detection operation until t=t; if the pedestrian target is detected in the step S201, the method is based on the previous frame I i-1 Performing Deepsort target association tracking operation on the recorded target detection result to form O 1 、O 2 、...、O n Motion trail K of each target in field of view F 1 (t)、K 2 (t)、...K n (t)；
S203: k is transformed by a perspective transformation matrix calibrated in advance 1 (t)、K 2 (t)、...K n (t) conversion to trajectory Tr in plan view coordinates corresponding to door front region H 1 (t)、Tr 2 (t)、...Tr n (t)；
In this embodiment, the step S2 specifically includes the following steps:
s301: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the included angle u between the motion direction and the Y axis i As shown in fig. 2, the coordinate system of the front door region H is defined as the Y-axis in the downward direction of the center line, and the right direction of the upper edge line of the H region is the X-axis;
s302: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the Y-axis component v of its motion velocity i As shown in fig. 2, the coordinate system of the front door region H is defined as the Y-axis in the downward direction of the center line, and the right direction of the upper edge line of the H region is the X-axis;
s303: for all detected and generated motion trails Tr i Target O of (t) i Record target O i The distance from the bottom line of the H area in the Y direction is D i According to R i (t)＝max(cos(u i ),0)×max(1.5-v i ×(T-t)/D i 0) calculating the target O at the current time t i And (5) risk of running the door.
S304: calculating the total passenger running risk of the door position as RH (t) =max (R 1 (t),R 2 (t),...,R n (t))。
In this embodiment, the step S4 specifically includes the following steps:
s401: running a door risk RH (t) for a total passenger exceeding a thresholdValue Th 1 Is based on the sensitivity requirement of the risk assessment of running a gate, th 1 Suggested to be 0.25), reminding is carried out through an acousto-optic alarm device arranged above the shielding door;
s402: risk of running the door RH (t) for the total passenger exceeding the threshold Th 1 Higher threshold Th 2 Is based on the sensitivity requirement of the risk assessment of running a gate, th 2 0.5), the sound and light alarm is kept, and the shielding door and the door control system are connected in parallel to keep the door open until the total door running risk RH (t) of the passengers is reset to zero, and then the shielding door and the door control system are connected to close the shielding door and the door;
s403: and recording and generating and saving video records of the passengers running the doors while performing primary and secondary responses.
Example 2
In a second aspect, the embodiment provides a subway shielding door-closing passenger door-opening early warning device based on video analysis, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is operative according to the instructions to perform the steps of the method according to embodiment 1.
Example 3
In a third aspect, the present embodiment provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method described in embodiment 1.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be appreciated by those skilled in the art that the present invention can be carried out in other embodiments without departing from the spirit or essential characteristics thereof. Accordingly, the above disclosed embodiments are illustrative in all respects, and not exclusive. All changes that come within the scope of the invention or equivalents thereto are intended to be embraced therein.

Claims (8)

1. A subway shielding door close-door passenger door-running early warning method based on video analysis is characterized by comprising the following steps:
step S1: at a distance ofThe gate time is left for T seconds, and video frames I of the field of view F are continuously acquired according to a preset frame rate R 1 、I 2 、....I i 、....；
Step S2: for the current video frame I i Pedestrian targets are detected based on the Yolov5 neural network and are associated with the detected targets in the preamble video frames based on Deepsort to achieve target O 1 、O 2 、...、O n Where n is the number of all pedestrian targets, converting the motion trajectory of the target in the field of view F into a continuous motion trajectory Tr of the target in the corresponding front-door region H by perspective transformation 1 (t)、Tr 2 (t)、...Tr n (t)；
Step S3: by means of pedestrian targets O 1 、O 2 、...、O n Motion trajectory Tr in front door region H i (t) carrying out single-target gate-running risk assessment on the data, and calculating a continuous risk assessment value R of each target 1 (t)、R 2 (t)、...、R n (t) and generating a total passenger running door risk RH (t) for the door facing by combining the single target risks, comprising:
s301: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the included angle u between the motion direction and the Y axis i The coordinate system of the front door region H is defined as taking the downward direction of the central line as the Y axis and taking the right direction of the upper edge line of the H region as the X axis;
s302: for all detected and generated motion trails Tr i Target O of (t) i Continuously estimating the Y-axis component v of its motion velocity i The coordinate system of the front door region H is defined as taking the downward direction of the central line as the Y axis and taking the right direction of the upper edge line of the H region as the X axis;
s303: for all detected and generated motion trails Tr i Target O of (t) i Record target O i The distance from the bottom line of the H area in the Y direction is D i The method comprises the steps of carrying out a first treatment on the surface of the According to R i (t)＝max(cos(u i ),0)×max(1.5-v i ×(T-t)/D i 0) calculating the target O at the current time t i Running a door to risk;
s304: calculating the risk of running the door of the main passenger facing the door as：RH(t)＝max(R 1 (t),R 2 (t),...,R n (t))；
Step S4: and carrying out classified door-rushing early warning treatment based on the door-rushing risk RH (t) of the main passenger facing the door and a preset secondary threshold value.
2. The method for pre-warning the door break of the passengers close to the subway shield door based on the video analysis according to claim 1, wherein in the step S1, the method for collecting the video frames of the field of view F comprises the following steps:
and according to the time plan of the train driving dispatching signal system, a passenger mounted at the door head of the shielding door breaks a door early warning terminal system, and when the time for closing the door is still T seconds, the passenger close to the door is started to break the door early warning function, and a video acquisition module of the system acquires video frames by using a camera mounted at an oblique downward visual angle right above the shielding door.
3. The method for pre-warning the passengers approaching the door of the subway shield door to break based on video analysis according to claim 1, wherein the step S2 comprises:
s201: for the current video frame I acquired in the step S1 i Pedestrian target detection based on YOLOv5 neural network and detection output O 1 、O 2 、...、O n N pedestrian targets in total, and if no pedestrian target is detected, outputting NULL;
s202: if S201 output is NULL, the step S201 is circularly executed for the next frame I output by S1 i+1 Performing pedestrian target detection operation until the current time t=t;
if a pedestrian object is detected in step S201, then the previous frame I is used i-1 Performing Deepsort target association tracking operation on the recorded target detection result to form O 1 、O 2 、...、O n Motion trail K of each target in field of view F 1 (t)、K 2 (t)、...K n (t)；
S203: k is transformed by a perspective transformation matrix calibrated in advance 1 (t)、K 2 (t)、...K n (t) conversion into plan view coordinates corresponding to the door front region HTrack Tr of (2) 1 (t)、Tr 2 (t)、...Tr n (t)。
4. The method for pre-warning the passengers approaching the door of the subway shield door to break based on video analysis according to claim 1, wherein the step S4 comprises:
running a door risk RH (t) for a total passenger exceeding a first threshold Th 1 The first-level response of the shielding door is that the passenger is reminded through an audible and visual alarm device arranged above the shielding door;
running the door risk RH (t) for the total passenger exceeding the second threshold Th 2 The shielding door and the door control system are linked to keep the shielding door and the door open while keeping the audible and visual alarm until the door main passenger runs the door risk RH (t) to return to zero, and then the shielding door and the door control system are linked to close the shielding door and the door, wherein the second threshold Th 2 Greater than a first threshold Th 1 。
5. The method for pre-warning the passengers of the subway shield door approaching the door based on the video analysis according to claim 4, wherein the step S4 further comprises:
and recording and generating and storing a video record of the passenger running the door while performing the primary response or the secondary response.
6. The method for pre-warning passengers of subway shield door approaching door based on video analysis as set forth in claim 4, wherein the first threshold Th 1 Is 0.25, the second threshold Th 2 0.5.
7. The subway shielding door-closing passenger door-opening early warning device based on video analysis is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor being operative according to the instructions to perform the steps of the method according to any one of claims 1 to 6.
8. A storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the method according to any of claims 1 to 6.
CN202211251732.9A 2022-10-13 2022-10-13 Subway shielding door close-door passenger door-opening early warning method based on video analysis Active CN115620228B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211251732.9A CN115620228B (en) 2022-10-13 2022-10-13 Subway shielding door close-door passenger door-opening early warning method based on video analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211251732.9A CN115620228B (en) 2022-10-13 2022-10-13 Subway shielding door close-door passenger door-opening early warning method based on video analysis

Publications (2)

Publication Number Publication Date
CN115620228A CN115620228A (en) 2023-01-17
CN115620228B true CN115620228B (en) 2023-05-23

Family

ID=84863445

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211251732.9A Active CN115620228B (en) 2022-10-13 2022-10-13 Subway shielding door close-door passenger door-opening early warning method based on video analysis

Country Status (1)

Country Link
CN (1) CN115620228B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106219367A (en) * 2016-08-05 2016-12-14 沈阳聚德视频技术有限公司 A kind of elevator O&M based on intelligent vision light curtain monitoring method
CN110008867A (en) * 2019-03-25 2019-07-12 五邑大学 A kind of method for early warning based on personage's abnormal behaviour, device and storage medium
CN110895861A (en) * 2018-09-13 2020-03-20 杭州海康威视数字技术股份有限公司 Abnormal behavior early warning method and device, monitoring equipment and storage medium
CN114663390A (en) * 2022-03-22 2022-06-24 平安普惠企业管理有限公司 Intelligent anti-pinch method, device, equipment and storage medium for automatic door

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103198605A (en) * 2013-03-11 2013-07-10 成都百威讯科技有限责任公司 Indoor emergent abnormal event alarm system
CN206298233U (en) * 2016-11-07 2017-07-04 何桂尧 A kind of Elevator Monitoring is saved oneself disposal device
CN108001460B (en) * 2017-12-12 2019-06-14 徐薇 Subway shield door limit area's intelligent anti-clip detects warning device and method
CN209765074U (en) * 2018-12-27 2019-12-10 上海仁童电子科技有限公司 Platform shield door foreign matter detection device
CN112509190B (en) * 2021-02-08 2021-05-11 南京信息工程大学 Subway vehicle section passenger flow statistical method based on shielded gate passenger flow counting
CN113658192B (en) * 2021-07-08 2023-10-17 华南理工大学 Multi-target pedestrian track acquisition method, system, device and medium
CN113343960A (en) * 2021-08-06 2021-09-03 南京信息工程大学 Method for estimating and early warning passenger flow retained in subway station in real time
CN115131821A (en) * 2022-06-29 2022-09-30 大连理工大学 Improved YOLOv5+ Deepsort-based campus personnel crossing warning line detection method
CN115063730A (en) * 2022-07-13 2022-09-16 山东建筑大学 Video track analysis-based method and system for early warning of intrusion of workers into borderline area

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106219367A (en) * 2016-08-05 2016-12-14 沈阳聚德视频技术有限公司 A kind of elevator O&M based on intelligent vision light curtain monitoring method
CN110895861A (en) * 2018-09-13 2020-03-20 杭州海康威视数字技术股份有限公司 Abnormal behavior early warning method and device, monitoring equipment and storage medium
CN110008867A (en) * 2019-03-25 2019-07-12 五邑大学 A kind of method for early warning based on personage's abnormal behaviour, device and storage medium
CN114663390A (en) * 2022-03-22 2022-06-24 平安普惠企业管理有限公司 Intelligent anti-pinch method, device, equipment and storage medium for automatic door

Also Published As

Publication number Publication date
CN115620228A (en) 2023-01-17

Similar Documents

Publication Publication Date Title
CN104809887B (en) A kind of retrograde detection method of vehicle on expressway and autoalarm
CN112885144B (en) Early warning method and system for vehicle crash event in construction operation area
CN110473402A (en) A kind of accident detection early warning system based on target abnormal behaviour trajectory analysis
CN102945603B (en) Method for detecting traffic event and electronic police device
WO2021077766A1 (en) Large-area multi-target traffic event detection system and method
WO2018096371A1 (en) Passenger transport monitoring system
KR101101860B1 (en) Monitoring system for traffic condition
CN111126171A (en) Vehicle reverse running detection method and system
CN110288738B (en) Intelligent comprehensive management and control system and method for bicycle lane
CN110796862B (en) Highway traffic condition detection system and method based on artificial intelligence
CN104637071A (en) People tracking method based on intelligent video analysis
CN104134350A (en) Intelligent dome camera system for traffic violation behavior recognition
CN115909223A (en) Method and system for matching WIM system information with monitoring video data
CN114494998B (en) Intelligent analysis method and system for vehicle data
CN206961331U (en) A kind of high threat vehicle monitoring early warning system
CN111062238A (en) Escalator flow monitoring method and system based on human skeleton information and multi-target tracking
CN115620228B (en) Subway shielding door close-door passenger door-opening early warning method based on video analysis
Zheng Developing a traffic safety diagnostics system for unmanned aerial vehicles usingdeep learning algorithms
CN113487873A (en) Intelligent detection system for road traffic safety
CN112422672A (en) Electronic escorting system and escorting method
KR102540794B1 (en) Accident detection system
Zheng et al. Toward real-time congestion measurement of passenger flow on platform screen doors based on surveillance videos analysis
CN113538968B (en) Method and apparatus for outputting information
Zhao et al. A Video Analytic System for Rail Crossing Point Protection
CN113919571A (en) Dangerous chemical transportation premium estimation method based on edge calculation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant