A subway operation safety inspection system based on intelligence and image analysis

Abstract

The present invention discloses a subway operation safety inspection system based on intelligence and image analysis, comprising: a target area division module, a waiting area safety analysis module, a subway tunnel safety analysis module, a subway internal air quality analysis module, a database and an early warning terminal. The present invention not only comprehensively monitors and analyzes the air quality in subway tunnels and subway cars, but also monitors and analyzes the behavior of waiting passengers in the subway waiting area. The analysis dimensions are relatively diversified, thereby ensuring the accuracy of the analysis of subway tunnel safety, waiting passenger behavior in the waiting area and air quality in the subway, ensuring that the humidity in each car meets the comfortable humidity for the human body, improving the driver's comfort, thereby reducing the impact of unsuitable humidity on the driver's driving behavior, monitoring and analyzing the humidity in the subway tunnel, and thus ensuring the safe and effective operation of the subway.

Description

Technical Field

[0001] The present invention relates to the technical field of subway operation, and in particular to a subway operation safety inspection system based on intelligence and image analysis. Background Art

[0002] The rapid development of science and technology in recent years has promoted the rapid development of subways. As a daily means of transportation, subways can bring people convenient and fast rail transit services. Subways have the advantages of saving time, reducing waste pollution, alleviating ground traffic pressure, accurate time and helping employment. When the safety of subway operation cannot be guaranteed, it will threaten the personal safety of people in the station. Therefore, it is extremely important to conduct safety monitoring and analysis of subway operation.

[0003] The existing subway operation safety monitoring and analysis has the following shortcomings:

[0004] (1) Existing subway operation safety monitoring and analysis mainly focuses on the operation parameters of the subway itself, such as the subway's operating speed, subway arrival time, and the accuracy of subway door opening. The monitoring and analysis of subway tunnel safety and subway car air quality are not comprehensive, and the analysis dimension is relatively single. There is a lack of monitoring and analysis of the behavior of waiting passengers in the subway waiting area, which leads to inaccurate analysis of the behavior of waiting passengers in the subway tunnel and waiting area and the air quality in the subway, resulting in risks in subway operation and the inability to ensure the safe and effective operation of the subway.

[0005] (2) The existing subway operation safety monitoring and analysis of air quality in subway cars mostly installs temperature sensors and smoke sensors in each car to sense the temperature and smoke concentration of each car, and then further analyzes them, ignoring the impact of humidity on air quality. As a result, the humidity in the subway car may not meet the human comfort level, making the driver feel uncomfortable, thereby affecting the driver's driving behavior. In turn, there may be a phenomenon that improper driving behavior leads to unsafe subway operation, which increases the incidence of driving accidents caused by improper driving behavior.

[0006] (3) The existing subway operation safety monitoring and analysis in the tunnel mostly monitors and analyzes the noise in the subway tunnel, ignoring the impact of humidity in the subway tunnel on the safety in the tunnel. The analysis is not comprehensive, and there may be water seepage and leakage in the subway tunnel but the staff do not repair it. When the water accumulation reaches a certain level, it will affect the safe operation of the subway, and the normal operation of the subway cannot be guaranteed. Summary of the Invention

[0007] In order to overcome the shortcomings of the background technology, an embodiment of the present invention provides a subway operation safety inspection system based on intelligence and image analysis, which can effectively solve the problems involved in the above background technology.

[0008] The purpose of the present invention can be achieved by the following technical solutions:

[0009] A subway operation safety inspection system based on intelligence and image analysis, including: a target area division module, a waiting area safety analysis module, a subway tunnel safety analysis module, a subway internal air quality analysis module, a database and an early warning terminal;

[0010] The target area division module is used to divide the target area into a waiting area and an inner area of ​​the tunnel, divide the waiting area into waiting sub-areas, and obtain monitoring videos of the waiting area;

[0011] The waiting area safety analysis module is used to analyze the safety factor corresponding to each waiting sub-area based on the waiting area surveillance video;

[0012] The subway tunnel safety analysis module is used to analyze the subway tunnel safety, and the subway tunnel safety analysis module includes a subway tunnel safety monitoring unit and a subway tunnel safety analysis unit;

[0013] The subway internal air quality analysis module is used to analyze the internal air quality of the subway, and the subway internal air quality analysis module includes an air quality monitoring unit and an air quality analysis unit;

[0014] The database is used to store back features corresponding to leaning behaviors, risk coefficients corresponding to various leaning angles, hand features corresponding to throwing behaviors, weight factors corresponding to unit volumes of various types of thrown objects, normal images of the passenger drop-off area, risk factors corresponding to various abnormal conditions, allowable noise decibels in the tunnel, safe humidity in the tunnel, and safe temperature, safe humidity, and allowable smoke concentration in the carriage;

[0015] The early warning terminal is used to issue corresponding early warnings based on the safety factors corresponding to each waiting sub-area, the analysis results of the subway tunnel safety analysis unit and the air quality analysis unit.

[0016] Furthermore, the target area is a subway riding area.

[0017] Furthermore, the specific analysis method for analyzing the safety factor corresponding to each waiting sub-area based on the surveillance video of the waiting area is:

[0018] S1: Number each waiting sub-area as 1, 2, ..., i, ..., n, and extract the surveillance video of each waiting sub-area from the surveillance video of the waiting area;

[0019] S2: Divide the surveillance video of each waiting sub-area into pictures of each waiting sub-area according to a preset number of frames;

[0020] S3: Focus the images of each waiting sub-area on the passenger boarding area;

[0021] S4: Identifying back features of each waiting passenger based on the images of each waiting sub-area, and comparing the features with back features corresponding to leaning behaviors stored in the database, thereby determining whether the waiting passenger has leaned. If so, identifying the object the waiting passenger is leaning on, and then determining whether the object is a subway door. If so, recording the waiting passenger as a door-leaning passenger, and obtaining an angle between the door-leaning passenger and the door, recording the angle as the leaning angle.

[0022] S5: matching the leaning angle of the passenger leaning against the door with the risk coefficients corresponding to the leaning angles stored in the database, thereby matching the risk coefficients of the leaning angles;

[0023] S6: Identifying hand features of each waiting passenger based on the images of each waiting sub-area, and comparing the hand features with hand features corresponding to throwing behaviors stored in a database to determine whether the waiting passenger has engaged in throwing behavior. If so, extracting throwing parameters of the waiting passenger from the images of the waiting sub-area, the throwing parameters including the type and volume of the thrown object.

[0024] S7: extracting the projectile type from the throwing parameters, and comparing it with the weight factors corresponding to the unit volume of each projectile type stored in the database, thereby matching the weight factors of the unit volume of the projectile type;

[0025] S8: Analyze the waiting behavior norm coefficient corresponding to the boarding area of ​​each waiting sub-area based on the volume of objects thrown by waiting passengers in each waiting sub-area, the weight factor of each unit volume of the object type, and the risk coefficient corresponding to the leaning angle of passengers leaning against the door. The calculation formula is: where η i represents the waiting behavior norm coefficient corresponding to the passenger boarding area of ​​the i-th waiting sub-area, v i ,λ i They represent the volume of objects thrown by waiting passengers in the i-th waiting sub-area and the weight factor of the unit volume of the object type, δ i represents the risk coefficient corresponding to the leaning angle of the passenger leaning against the door in the i-th waiting sub-area, where i represents the number of each waiting sub-area, i = 1, 2, ..., n;

[0026] S9: Focusing the images of each waiting sub-area on the passenger drop-off area;

[0027] S10: Comparing the images of each waiting sub-area with normal images of the passenger drop-off area stored in the database, thereby identifying abnormal conditions of each waiting sub-area, matching the abnormal conditions with risk factors corresponding to the abnormal conditions stored in the database, and then matching the risk factors corresponding to the abnormal conditions of each waiting sub-area;

[0028] S11: Analyze the safety factor corresponding to each waiting sub-area based on the risk factor of the abnormal state corresponding to each waiting sub-area and the waiting behavior standard coefficient corresponding to the boarding area of ​​each waiting sub-area. The calculation formula is: where μ i represents the safety factor corresponding to the i-th waiting sub-area, e represents the natural constant, γ i Represents the risk factor of the abnormal state corresponding to the i-th waiting sub-area.

[0029] Furthermore, the subway tunnel safety monitoring unit is used to perform safety monitoring on each tunnel sub-area at each monitoring time point, and the specific method is as follows:

[0030] A1: Use noise sensors to monitor noise in each tunnel sub-area at each monitoring time point;

[0031] A2: Use humidity sensors to monitor the humidity in each tunnel sub-area at each monitoring time point.

[0032] Furthermore, the subway tunnel safety analysis unit is used to analyze the safety monitoring results of each tunnel sub-area at each monitoring time point, and the specific analysis method is as follows:

[0033] B1: Number each tunnel sub-area as 1, 2, ..., x, ..., y;

[0034] B2: Number each monitoring time point as 1, 2, ..., d, ..., r;

[0035] B3: Obtain the noise decibel level of each tunnel sub-area at each monitoring time point;

[0036] B4: Compare the noise decibels of each tunnel sub-area at each monitoring time point with the permissible noise decibels stored in the database, and analyze the noise pollution coefficient corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: in represents the noise pollution coefficient of the x-th tunnel sub-area at the d-th monitoring time point, DB xd represents the noise decibel of the x-th tunnel sub-area at the d-th monitoring time point, DB represents the tunnel allowable noise decibel, x represents the number of each tunnel sub-area, x = 1, 2, ..., y, d represents the number of each monitoring time point, d = 1, 2, ..., r;

[0037] B5: Obtain the humidity of each tunnel sub-area at each monitoring time point;

[0038] B6: Compare the humidity of each tunnel sub-area at each monitoring time point with the tunnel safety humidity stored in the database, and analyze the humidity risk factor corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: where σ xd represents the humidity hazard coefficient of the x-th tunnel sub-area at the d-th monitoring time point, α xd represents the humidity of the x-th tunnel sub-area at the d-th monitoring time point, and α′ represents the tunnel safety humidity.

[0039] Furthermore, the air quality monitoring unit is used to monitor the air quality parameters of each carriage at each carriage monitoring time point.

[0040] Furthermore, the air quality parameters include temperature, humidity and smoke concentration.

[0041] Furthermore, the specific method for monitoring the air quality parameters of each carriage at each carriage monitoring time point is:

[0042] C1: Use temperature sensors to monitor the temperature of each carriage at each monitoring time point;

[0043] C2: Use humidity sensors to monitor the humidity in each carriage at each monitoring time point;

[0044] C3: Use smoke sensors to monitor the smoke concentration in each carriage at each monitoring time point.

[0045] Furthermore, the air quality analysis unit is used to analyze the air quality parameters of each carriage at each monitoring time point, and the specific analysis method is as follows:

[0046] D1: Number each carriage as 1, 2, ..., h, ..., j;

[0047] D2: Obtain the humidity of each carriage at each monitoring time point;

[0048] D3: Compare the humidity of each carriage at each monitoring time point with the carriage safety temperature stored in the database one by one, and analyze the temperature safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: where ω hd represents the temperature safety factor corresponding to the hth carriage at the dth monitoring time point, β hd represents the temperature of the h-th carriage at the d-th monitoring time point, β′ represents the carriage safety temperature, and h represents the number of each carriage, h = 1, 2, ..., j;

[0049] D4: Obtain the humidity of each carriage at each monitoring time point;

[0050] D5: Compare the humidity of each carriage at each monitoring time point with the carriage safety humidity stored in the database one by one, and analyze the humidity safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: where θ hd represents the humidity safety factor corresponding to the hth carriage at the dth monitoring time point, c hd represents the humidity of the h-th carriage at the d-th monitoring time point, and c′ represents the safe humidity of the carriage;

[0051] D6: Obtain the smoke concentration of each carriage at each monitoring time point;

[0052] D7: Compare the smoke concentration of each carriage at each monitoring time point with the allowable smoke concentration stored in the database one by one, and analyze the smoke concentration safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: in represents the smoke concentration safety factor corresponding to the hth carriage at the dth monitoring time point, g hd It represents the smoke concentration in the h-th carriage at the d-th monitoring time point, and g′ represents the allowable smoke concentration in the carriage.

[0053] Furthermore, the specific method for issuing corresponding warnings based on the safety factors corresponding to the waiting sub-areas, the analysis results of the subway tunnel safety analysis unit, and the air quality analysis unit is as follows:

[0054] F1: Compare the safety factor corresponding to each waiting sub-area with the preset waiting sub-area safety warning value. If the safety factor corresponding to a waiting sub-area is less than or equal to the waiting sub-area safety warning value, obtain the waiting sub-area number and issue a warning to the relevant personnel;

[0055] F2: Compare the noise pollution coefficient and humidity pollution coefficient of each tunnel sub-area at each monitoring time point with the preset noise pollution warning value and humidity pollution warning value. If the noise pollution coefficient and humidity pollution coefficient of a tunnel sub-area at a certain monitoring time point are greater than or equal to the noise pollution warning value and humidity pollution warning value, respectively, the number of the tunnel sub-area and the monitoring time point are obtained, and the corresponding tunnel noise abnormality warning and tunnel humidity abnormality warning are issued to relevant personnel.

[0056] F3: Compare the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to each carriage at each monitoring time point with the preset temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value. If the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to a certain carriage at a certain monitoring time point are less than or equal to the temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value, obtain the carriage number and the monitoring time point, and issue corresponding carriage temperature abnormality warning, carriage humidity abnormality warning, and carriage smoke concentration abnormality warning to relevant personnel.

[0057] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0058] (1) The subway operation safety monitoring and analysis of the present invention not only comprehensively monitors and analyzes the air quality in subway tunnels and subway cars, but also monitors and analyzes the behavior of waiting passengers in the subway waiting area. The analysis dimensions are relatively diversified, thereby ensuring the accuracy of the analysis of subway tunnel safety, waiting passenger behavior in the waiting area and air quality in the subway, thereby ensuring the safe and efficient operation of the subway.

[0059] (2) The subway operation safety monitoring and analysis of the present invention can monitor and analyze not only the temperature and smoke of each compartment in terms of air quality monitoring inside the subway car, but also the humidity, thereby ensuring that the humidity inside each compartment meets the comfortable humidity for the human body, thereby increasing the driver's comfort, thereby reducing the impact of unsuitable humidity on the driver's driving behavior, thereby reducing the occurrence of unsafe subway operation due to improper driving behavior, and reducing the incidence of driving accidents caused by improper driving behavior.

[0060] (3) The subway operation safety monitoring and analysis of the present invention can monitor and analyze not only the noise in the subway tunnel, but also the humidity in the subway tunnel. The analysis is relatively comprehensive, thereby avoiding the phenomenon that water seepage and leakage in the subway tunnel are not repaired by the staff, reducing the occurrence of dangerous subway operation due to water accumulation in the subway tunnel, thereby ensuring the normal operation of the subway. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0062] Figure 1 This is a schematic diagram of a subway operation safety inspection system based on intelligence and image analysis according to the present invention.

[0063] Figure 2 This is a schematic diagram of the subway tunnel safety analysis module of the present invention.

[0064] Figure 3 Schematic diagram of the subway internal air quality analysis module of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0066] Reference Figure 1 As shown, the present invention provides a subway operation safety inspection system based on intelligence and image analysis, including: a target area division module, a waiting area safety analysis module, a subway tunnel safety analysis module, a subway internal air quality analysis module, a database and an early warning terminal;

[0067] The target area division module is connected to the waiting area safety analysis module and the subway tunnel safety analysis module respectively. The waiting area safety analysis module, the subway tunnel safety analysis module and the subway internal air quality analysis module are all connected to the database and the early warning terminal.

[0068] The target area division module is used to divide the target area into a waiting area and an inner area of ​​the tunnel, divide the waiting area into waiting sub-areas, and obtain monitoring videos of the waiting area;

[0069] In a specific embodiment, the target area is a subway riding area.

[0070] The waiting area safety analysis module is used to analyze the safety factor corresponding to each waiting sub-area based on the waiting area surveillance video;

[0071] In a specific embodiment, the specific analysis method of analyzing the safety factor corresponding to each waiting sub-area based on the surveillance video of the waiting area is:

[0072] S1: Number each waiting sub-area as 1, 2, ..., i, ..., n, and extract the surveillance video of each waiting sub-area from the surveillance video of the waiting area;

[0073] S2: Divide the surveillance video of each waiting sub-area into pictures of each waiting sub-area according to a preset number of frames;

[0074] S3: Focus the images of each waiting sub-area on the passenger boarding area;

[0075] S4: Identifying back features of each waiting passenger based on the images of each waiting sub-area, and comparing the features with back features corresponding to leaning behaviors stored in the database, thereby determining whether the waiting passenger has leaned. If so, identifying the object the waiting passenger is leaning on, and then determining whether the object is a subway door. If so, recording the waiting passenger as a door-leaning passenger, and obtaining an angle between the door-leaning passenger and the door, recording the angle as the leaning angle.

[0076] S5: matching the leaning angle of the passenger leaning against the door with the risk coefficients corresponding to the leaning angles stored in the database, thereby matching the risk coefficients of the leaning angles;

[0077] S6: Identifying hand features of each waiting passenger based on the images of each waiting sub-area, and comparing the hand features with hand features corresponding to throwing behaviors stored in a database to determine whether the waiting passenger has engaged in throwing behavior. If so, extracting throwing parameters of the waiting passenger from the images of the waiting sub-area, the throwing parameters including the type and volume of the thrown object.

[0078] S7: extracting the projectile type from the throwing parameters, and comparing it with the weight factors corresponding to the unit volume of each projectile type stored in the database, thereby matching the weight factors of the unit volume of the projectile type;

[0079] S8: Analyze the waiting behavior norm coefficient corresponding to the boarding area of ​​each waiting sub-area based on the volume of objects thrown by waiting passengers in each waiting sub-area, the weight factor of each unit volume of the object type, and the risk coefficient corresponding to the leaning angle of passengers leaning against the door. The calculation formula is: where η i represents the waiting behavior norm coefficient corresponding to the passenger boarding area of ​​the i-th waiting sub-area, v i ,λ i They represent the volume of objects thrown by waiting passengers in the i-th waiting sub-area and the weight factor of the unit volume of the object type, δ i represents the risk coefficient corresponding to the leaning angle of the passenger leaning against the door in the i-th waiting sub-area, where i represents the number of each waiting sub-area, i = 1, 2, ..., n;

[0080] S9: Focusing the images of each waiting sub-area on the passenger drop-off area;

[0081] S10: Comparing the images of each waiting sub-area with normal images of the passenger drop-off area stored in the database, thereby identifying abnormal conditions of each waiting sub-area, matching the abnormal conditions with risk factors corresponding to the abnormal conditions stored in the database, and then matching the risk factors corresponding to the abnormal conditions of each waiting sub-area;

[0082] It should be noted that the normal image of the passenger drop-off area is a picture without other items in the passenger drop-off area.

[0083] It should be noted that the abnormal state is the presence of other items in the passenger drop-off area, such as suitcases, school bags, gift bags, etc.

[0084] S11: Analyze the safety factor corresponding to each waiting sub-area based on the risk factor of the abnormal state corresponding to each waiting sub-area and the waiting behavior standard coefficient corresponding to the boarding area of ​​each waiting sub-area. The calculation formula is: where μ i represents the safety factor corresponding to the i-th waiting sub-area, e represents the natural constant, γ i Represents the risk factor of the abnormal state corresponding to the i-th waiting sub-area.

[0085] It should be noted that the behavior of waiting passengers in the subway waiting area and whether there are any abnormalities in the disembarkation area in the subway waiting area have a certain impact on the safety of subway operation. If waiting passengers lean against the door or throw objects into the subway, or if there are any abnormalities in the disembarkation area in the waiting area, it will not only endanger the personal safety of waiting passengers, but will also affect the boarding time of waiting passengers to a certain extent, and affect the departure time of the subway, which may easily cause large errors in subway operation time and thus cause transportation accidents. Therefore, it is necessary to monitor and analyze the behavior of waiting passengers in the waiting area.

[0086] The subway tunnel safety analysis module is used to analyze the subway tunnel safety, referring to Figure 2 As shown, the subway tunnel safety analysis module includes a subway tunnel safety monitoring unit and a subway tunnel safety analysis unit;

[0087] In a specific embodiment, the subway tunnel safety monitoring unit is used to perform safety monitoring on each tunnel sub-area at each monitoring time point, and the specific method is as follows:

[0088] A1: Use noise sensors to monitor noise in each tunnel sub-area at each monitoring time point;

[0089] A2: Use humidity sensors to monitor the humidity in each tunnel sub-area at each monitoring time point.

[0090] In a specific embodiment, the subway tunnel safety analysis unit is used to analyze the safety monitoring results of each tunnel sub-area at each monitoring time point, and the specific analysis method is:

[0091] B1: Number each tunnel sub-area as 1, 2, ..., x, ..., y;

[0092] B2: Number each monitoring time point as 1, 2, ..., d, ..., r;

[0093] B3: Obtain the noise decibel level of each tunnel sub-area at each monitoring time point;

[0094] B4: Compare the noise decibels of each tunnel sub-area at each monitoring time point with the permissible noise decibels stored in the database, and analyze the noise pollution coefficient corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: in represents the noise pollution coefficient of the x-th tunnel sub-area at the d-th monitoring time point, DB xd represents the noise decibel of the x-th tunnel sub-area at the d-th monitoring time point, DB represents the tunnel allowable noise decibel, x represents the number of each tunnel sub-area, x = 1, 2, ..., y, d represents the number of each monitoring time point, d = 1, 2, ..., r;

[0095] B5: Obtain the humidity of each tunnel sub-area at each monitoring time point;

[0096] B6: Compare the humidity of each tunnel sub-area at each monitoring time point with the tunnel safety humidity stored in the database, and analyze the humidity risk factor corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: where σ xd represents the humidity hazard coefficient of the x-th tunnel sub-area at the d-th monitoring time point, α xd represents the humidity of the x-th tunnel sub-area at the d-th monitoring time point, and α′ represents the tunnel safety humidity.

[0097] It should be noted that the noise and humidity in subway tunnels have a certain impact on the safe operation of the subway. If the noise in the subway tunnel does not meet the standards, it means that the subway may have a malfunction or problem during operation. If the humidity in the subway tunnel does not meet the requirements, it means that there may be water seepage or leakage in the subway tunnel. If it is not dealt with in time, it will affect the safety of subway operation. Therefore, it is necessary to monitor and analyze the noise and humidity in the subway tunnel.

[0098] The subway operation safety monitoring and analysis of the present invention can monitor and analyze not only the noise in the subway tunnel, but also the humidity in the subway tunnel. The analysis is relatively comprehensive, thereby avoiding the phenomenon that water seepage and leakage in the subway tunnel are not repaired by the staff, reducing the occurrence of dangerous subway operation due to water accumulation in the subway tunnel, thereby ensuring the normal operation of the subway.

[0099] The subway internal air quality analysis module is used to analyze the internal air quality of the subway. Figure 3As shown, the subway internal air quality analysis module includes an air quality monitoring unit and an air quality analysis unit;

[0100] In a specific embodiment, the air quality monitoring unit is used to monitor the air quality parameters of each carriage at each carriage monitoring time point.

[0101] In a specific embodiment, the air quality parameters include temperature, humidity and smoke concentration.

[0102] In a specific embodiment, the specific method for monitoring the air quality parameters of each carriage at each carriage monitoring time point is:

[0103] C1: Use temperature sensors to monitor the temperature of each carriage at each monitoring time point;

[0104] C2: Use humidity sensors to monitor the humidity in each carriage at each monitoring time point;

[0105] C3: Use smoke sensors to monitor the smoke concentration in each carriage at each monitoring time point.

[0106] It should be noted that if the temperature, humidity and smoke concentration in the subway car do not meet the standards, it will affect the air quality in the subway, and in turn affect the driver's comfort. As a result, there may be deviations in driving behavior due to low driving comfort. Therefore, it is necessary to monitor the temperature, humidity and smoke concentration in the subway car.

[0107] In a specific embodiment, the air quality analysis unit is used to analyze the air quality parameters of each carriage at each monitoring time point, and the specific analysis method is:

[0108] D1: Number each carriage as 1, 2, ..., h, ..., j;

[0109] D2: Obtain the humidity of each carriage at each monitoring time point;

[0110] D3: Compare the humidity of each carriage at each monitoring time point with the carriage safety temperature stored in the database one by one, and analyze the temperature safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: where ω hd represents the temperature safety factor corresponding to the hth carriage at the dth monitoring time point, β hd represents the temperature of the h-th carriage at the d-th monitoring time point, β′ represents the carriage safety temperature, and h represents the number of each carriage, h = 1, 2, ..., j;

[0111] D4: Obtain the humidity of each carriage at each monitoring time point;

[0112] D5: Compare the humidity of each carriage at each monitoring time point with the carriage safety humidity stored in the database one by one, and analyze the humidity safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: where θ hd represents the humidity safety factor corresponding to the hth carriage at the dth monitoring time point, c hd represents the humidity of the h-th carriage at the d-th monitoring time point, and c′ represents the safe humidity of the carriage;

[0113] D6: Obtain the smoke concentration of each carriage at each monitoring time point;

[0114] D7: Compare the smoke concentration of each carriage at each monitoring time point with the allowable smoke concentration stored in the database one by one, and analyze the smoke concentration safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: in represents the smoke concentration safety factor corresponding to the hth carriage at the dth monitoring time point, g hd It represents the smoke concentration in the h-th carriage at the d-th monitoring time point, and g′ represents the allowable smoke concentration in the carriage.

[0115] The subway operation safety monitoring and analysis of the present invention can monitor and analyze the air quality in each car not only for the temperature and smoke, but also for the humidity, thereby ensuring that the humidity in each car meets the human body's comfortable humidity, thereby improving the driver's comfort, thereby reducing the impact of inappropriate humidity on the driver's driving behavior, thereby reducing the occurrence of unsafe subway operations due to improper driving behavior, and reducing the incidence of driving accidents caused by improper driving behavior.

[0116] The subway operation safety monitoring and analysis of the present invention not only comprehensively monitors and analyzes the air quality in subway tunnels and subway cars, but also monitors and analyzes the behavior of waiting passengers in the subway waiting area. The analysis dimensions are relatively diversified, thereby ensuring the accuracy of the analysis of subway tunnel safety, waiting passenger behavior in the waiting area and air quality in the subway, thereby ensuring the safe and efficient operation of the subway.

[0117] The database is used to store back features corresponding to leaning behavior, risk coefficients corresponding to each leaning angle, hand features corresponding to throwing behavior, weight factors corresponding to each unit volume of each type of thrown object, normal images of the passenger disembarkation area, risk factors corresponding to each abnormal state, allowable noise decibels in the tunnel, safe humidity in the tunnel, and safe temperature, safe humidity, and allowable smoke concentration in the carriage.

[0118] The early warning terminal is used to issue corresponding early warnings based on the safety factors corresponding to each waiting sub-area, the analysis results of the subway tunnel safety analysis unit and the air quality analysis unit.

[0119] In a specific embodiment, the specific method for issuing corresponding warnings based on the safety factors corresponding to the waiting sub-areas, the analysis results of the subway tunnel safety analysis unit, and the air quality analysis unit is as follows:

[0120] F1: Compare the safety factor corresponding to each waiting sub-area with the preset waiting sub-area safety warning value. If the safety factor corresponding to a waiting sub-area is less than or equal to the waiting sub-area safety warning value, obtain the waiting sub-area number and issue a warning to the relevant personnel;

[0121] F2: Compare the noise pollution coefficient and humidity pollution coefficient of each tunnel sub-area at each monitoring time point with the preset noise pollution warning value and humidity pollution warning value. If the noise pollution coefficient and humidity pollution coefficient of a tunnel sub-area at a certain monitoring time point are greater than or equal to the noise pollution warning value and humidity pollution warning value, respectively, the number of the tunnel sub-area and the monitoring time point are obtained, and the corresponding tunnel noise abnormality warning and tunnel humidity abnormality warning are issued to relevant personnel.

[0122] F3: Compare the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to each carriage at each monitoring time point with the preset temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value. If the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to a certain carriage at a certain monitoring time point are less than or equal to the temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value, obtain the carriage number and the monitoring time point, and issue corresponding carriage temperature abnormality warning, carriage humidity abnormality warning, and carriage smoke concentration abnormality warning to relevant personnel.

[0123] It should be noted that the present invention issues corresponding warnings based on the safety factors corresponding to each waiting sub-area, the noise pollution coefficient and humidity pollution coefficient corresponding to each tunnel sub-area at each monitoring time point, and the temperature safety factor, humidity safety factor and smoke concentration safety factor corresponding to each carriage at each monitoring time point. This allows staff to know more accurately where the problem occurs, and to provide solutions to the warnings in a timely manner, thereby improving the efficiency of staff in performing corresponding maintenance.

[0124] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A subway operation safety inspection system based on intelligence and image analysis, characterized by: include: Target area division module, waiting area safety analysis module, subway tunnel safety analysis module, subway internal air quality analysis module, database and early warning terminal; The target area division module is used to divide the target area into a waiting area and an inner area of ​​the tunnel, divide the waiting area into waiting sub-areas, and obtain monitoring videos of the waiting area; The waiting area safety analysis module is used to analyze the safety factor corresponding to each waiting sub-area based on the waiting area surveillance video; The subway tunnel safety analysis module is used to analyze the subway tunnel safety, and the subway tunnel safety analysis module includes a subway tunnel safety monitoring unit and a subway tunnel safety analysis unit; The subway internal air quality analysis module is used to analyze the internal air quality of the subway, and the subway internal air quality analysis module includes an air quality monitoring unit and an air quality analysis unit; The database is used to store back features corresponding to leaning behaviors, risk coefficients corresponding to various leaning angles, hand features corresponding to throwing behaviors, weight factors corresponding to unit volumes of various types of thrown objects, normal images of the passenger drop-off area, risk factors corresponding to various abnormal conditions, allowable noise decibels in the tunnel, safe humidity in the tunnel, and safe temperature, safe humidity, and allowable smoke concentration in the carriage; The early warning terminal is used to issue corresponding early warnings based on the safety factors corresponding to each waiting sub-area, the analysis results of the subway tunnel safety analysis unit and the air quality analysis unit.

2. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The target area is a subway riding area.

3. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The specific analysis method of analyzing the safety factor corresponding to each waiting sub-area based on the surveillance video of the waiting area is as follows: S1: Number each waiting sub-area , and extract the surveillance video of each waiting sub-area from the surveillance video of the waiting area; S2: Divide the surveillance video of each waiting sub-area into pictures of each waiting sub-area according to a preset number of frames; S3: Focus the images of each waiting sub-area on the passenger boarding area; S4: Identifying back features of each waiting passenger based on the images of each waiting sub-area, and comparing the features with back features corresponding to leaning behaviors stored in the database, thereby determining whether the waiting passenger has leaned. If so, identifying the object the waiting passenger is leaning on, and then determining whether the object is a subway door. If so, recording the waiting passenger as a door-leaning passenger, and obtaining an angle between the door-leaning passenger and the door, recording the angle as the leaning angle. S5: matching the leaning angle of the passenger leaning against the door with the risk coefficients corresponding to the leaning angles stored in the database, thereby matching the risk coefficients of the leaning angles; S6: Identifying hand features of each waiting passenger based on the images of each waiting sub-area, and comparing the hand features with hand features corresponding to throwing behaviors stored in a database to determine whether the waiting passenger has engaged in throwing behavior. If so, extracting throwing parameters of the waiting passenger from the images of the waiting sub-area, the throwing parameters including the type and volume of the thrown object. S7: extracting the projectile type from the throwing parameters, and comparing it with the weight factors corresponding to the unit volume of each projectile type stored in the database, thereby matching the weight factors of the unit volume of the projectile type; S8: Analyze the waiting behavior norm coefficient corresponding to the boarding area of ​​each waiting sub-area based on the volume of objects thrown by waiting passengers in each waiting sub-area, the weight factor of each unit volume of the object type, and the risk coefficient corresponding to the leaning angle of passengers leaning against the door. The calculation formula is: ,in Indicates the The waiting behavior norm coefficient corresponding to the passenger boarding area of ​​the waiting sub-area is 、 Respectively represent The volume of objects thrown by waiting passengers in each waiting sub-area, and the weight factor per unit volume of each object type, Indicates the The risk coefficient corresponding to the leaning angle of the passengers leaning against the door in each waiting sub-area is: Indicates the number of each waiting sub-area, ; S9: Focusing the images of each waiting sub-area on the passenger drop-off area; S10: Comparing the images of each waiting sub-area with normal images of the passenger drop-off area stored in the database, thereby identifying abnormal conditions of each waiting sub-area, matching the abnormal conditions with risk factors corresponding to the abnormal conditions stored in the database, and then matching the risk factors corresponding to the abnormal conditions of each waiting sub-area; S11: Analyze the safety factor corresponding to each waiting sub-area based on the risk factor of the abnormal state corresponding to each waiting sub-area and the waiting behavior standard coefficient corresponding to the boarding area of ​​each waiting sub-area. The calculation formula is: ,in Indicates the The safety factor corresponding to the waiting sub-area is represents a natural constant, Indicates the Each waiting sub-area corresponds to a risk factor of abnormal status.

4. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The subway tunnel safety monitoring unit is used to perform safety monitoring on each tunnel sub-area at each monitoring time point, and the specific method is as follows: A1: Use noise sensors to monitor noise in each tunnel sub-area at each monitoring time point; A2: Use humidity sensors to monitor the humidity in each tunnel sub-area at each monitoring time point.

5. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The subway tunnel safety analysis unit is used to analyze the safety monitoring results of each tunnel sub-area at each monitoring time point. The specific analysis method is as follows: B1: Number each tunnel sub-area ; B2: Number each monitoring time point ; B3: Obtain the noise decibel level of each tunnel sub-area at each monitoring time point; B4: Compare the noise decibels of each tunnel sub-area at each monitoring time point with the permissible noise decibels stored in the database, and analyze the noise pollution coefficient corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: ,in Indicates the The tunnel sub-area is in The noise pollution coefficient corresponding to each monitoring time point is: Indicates the The tunnel sub-area is in The noise decibel at each monitoring time point, Indicates the noise decibel allowed in the tunnel. Indicates the number of each tunnel sub-area, , Indicates the number of each monitoring time point, ; B5: Obtain the humidity of each tunnel sub-area at each monitoring time point; B6: Compare the humidity of each tunnel sub-area at each monitoring time point with the tunnel safety humidity stored in the database, and analyze the humidity risk factor corresponding to each tunnel sub-area at each monitoring time point based on this. The calculation formula is: ,in Indicates the The tunnel sub-area is in The humidity risk coefficient corresponding to each monitoring time point is: Indicates the The tunnel sub-area is in The humidity at each monitoring time point, Indicates tunnel safety humidity.

6. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The air quality monitoring unit is used to monitor the air quality parameters of each carriage at each carriage monitoring time point.

7. The subway operation safety inspection system based on intelligence and image analysis according to claim 6 is characterized by: The air quality parameters include temperature, humidity and smoke concentration.

8. The subway operation safety inspection system based on intelligence and image analysis according to claim 6 is characterized by: The specific method for monitoring the air quality parameters of each carriage at each carriage monitoring time point is: C1: Use temperature sensors to monitor the temperature of each carriage at each monitoring time point; C2: Use humidity sensors to monitor the humidity in each carriage at each monitoring time point; C3: Use smoke sensors to monitor the smoke concentration in each carriage at each monitoring time point.

9. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The air quality analysis unit is used to analyze the air quality parameters of each carriage at each monitoring time point. The specific analysis method is as follows: D1: Number each carriage as ; D2: Obtain the humidity of each carriage at each monitoring time point; D3: Compare the humidity of each carriage at each monitoring time point with the carriage safety temperature stored in the database one by one, and analyze the temperature safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: ,in Indicates the Carriage No. The temperature safety factor corresponding to each monitoring time point is: Indicates the Carriage No. The temperature at each monitoring time point, Indicates the safe temperature of the car compartment. Indicates the number of each carriage. ; D4: Obtain the humidity of each carriage at each monitoring time point; D5: Compare the humidity of each carriage at each monitoring time point with the carriage safety humidity stored in the database one by one, and analyze the humidity safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: ,in Indicates the Carriage No. The humidity safety factor corresponding to each monitoring time point is: Indicates the Carriage No. The humidity at each monitoring time point, Indicates the safe humidity of the carriage; D6: Obtain the smoke concentration of each carriage at each monitoring time point; D7: Compare the smoke concentration of each carriage at each monitoring time point with the allowable smoke concentration stored in the database one by one, and analyze the smoke concentration safety factor corresponding to each carriage at each monitoring time point based on this. The calculation formula is: ,in Indicates the Carriage No. The smoke concentration safety factor corresponding to each monitoring time point is: Indicates the Carriage No. The smoke concentration at each monitoring time point, Indicates the allowable smoke concentration in the cabin.

10. The subway operation safety inspection system based on intelligence and image analysis according to claim 1 is characterized by: The specific method for issuing corresponding warnings based on the safety factors corresponding to each waiting sub-area, the analysis results of the subway tunnel safety analysis unit, and the air quality analysis unit is as follows: F1: Compare the safety factor corresponding to each waiting sub-area with the preset waiting sub-area safety warning value. If the safety factor corresponding to a waiting sub-area is less than or equal to the waiting sub-area safety warning value, obtain the waiting sub-area number and issue a warning to the relevant personnel; F2: Compare the noise pollution coefficient and humidity pollution coefficient of each tunnel sub-area at each monitoring time point with the preset noise pollution warning value and humidity pollution warning value. If the noise pollution coefficient and humidity pollution coefficient of a tunnel sub-area at a certain monitoring time point are greater than or equal to the noise pollution warning value and humidity pollution warning value, respectively, the number of the tunnel sub-area and the monitoring time point are obtained, and the corresponding tunnel noise abnormality warning and tunnel humidity abnormality warning are issued to relevant personnel. F3: Compare the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to each carriage at each monitoring time point with the preset temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value. If the temperature safety factor, humidity safety factor, and smoke concentration safety factor corresponding to a certain carriage at a certain monitoring time point are less than or equal to the temperature safety warning value, humidity safety warning value, and smoke concentration safety warning value, obtain the carriage number and the monitoring time point, and issue corresponding carriage temperature abnormality warning, carriage humidity abnormality warning, and carriage smoke concentration abnormality warning to relevant personnel.

Images