Intelligent building environment monitoring system and method based on Internet of Things information perception

Abstract

The invention discloses an intelligent building environment monitoring system and method based on Internet of Things information perception, and relates to the technical field of Internet of Things, and the method comprises the steps: building a BIM model of a building construction area, wearing a safety device with a positioning function and a speed measurement function on a building worker, obtaining a positioning track and a speed function, and carrying out the positioning track and the speed function; extracting a target track from the positioning track; dividing a calibration area, and extracting a first early warning area according to the condition that the moving object passes through the calibration area in the historical monitoring video; acquiring a historical collision record to obtain a second early warning area; a building construction area is divided into a plurality of target areas, early warning values of the target areas are obtained, and different early warning prompts are provided for target personnel in different target areas. According to the invention, through the corner position and the historical collision record, in combination with the current monitoring video, the area where danger is likely to occur in the building construction area is judged, and real-time and effective safety monitoring of the building construction area can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and specifically to a smart building environment monitoring system and method based on Internet of Things information perception. Background Technique

[0002] The interconnection of all things has brought about a transformation in the production mode. The Internet of Things technology has penetrated into various fields at an unprecedented speed and breadth, profoundly changing our way of life and work. With the rapid development of urban construction, the safety of construction sites has become a matter of great concern. Combining the Internet of Things with the building environment is of great significance for improving the safety level of construction sites and optimizing building management.

[0003] The patent with the publication number CN117196314A proposes a building construction safety monitoring system and method based on the Internet of Things, including: obtaining the comprehensive status information of the area where the target device is located; the comprehensive status information includes the device working environment information and the personnel working area information; obtaining the device status data of the target device and the physiological data information of the construction personnel working inside the target device; performing a comprehensive risk analysis based on the device status data and the physiological data information to obtain the corresponding safety risk assessment value; sending out corresponding notification push according to the safety risk assessment value; being able to monitor the safety status of the building construction site in real time, comprehensively monitor the construction site, timely discover potential safety hazards and send out warning signals, and perform automatic detection to improve the monitoring accuracy, warning accuracy, safety management level and efficiency; Although the above patent can realize the early warning of the construction area of the building construction site, it ignores the situation that not all areas of the construction area are construction personnel in actual operation. There may also be idlers who do not wear wearable devices and cannot obtain physiological data information in time. Since the danger of the construction site always exists, it will lead to the inability to conduct real-time and effective safety monitoring of the building construction area. Summary of the Invention

[0004] The purpose of the present invention is to provide a smart building environment monitoring system and method based on Internet of Things information perception to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: A smart building environment monitoring method based on Internet of Things information perception, including the following steps: Step S100: Establish a BIM model of the building construction area, wear safety devices with positioning and speed measurement functions on the building personnel, and establish a speed function of the speed changing with time. According to the positioning trajectory corresponding to the safety device history and the speed function, extract the target trajectory from the positioning trajectory; Step S200: Based on the corner positions in the construction area that are prone to blocking the line of sight, divide the calibration areas in the BIM model; obtain the historical surveillance videos of the construction area, analyze the situation of moving objects passing through the calibration areas in the surveillance videos, obtain the target value corresponding to each calibration area, and extract the first warning area from the calibration areas according to the target value; Step S300: Obtain the collision records of collisions between two different target objects in the historical construction area, and obtain the second warning area in the construction area according to the moving speeds of the target objects corresponding to the collision records; Step S400: According to the first warning area and the second warning area, divide the construction area into several target areas; extract and analyze the surveillance video of the current construction area, obtain the warning value of each target area, and give different warning prompts to the target personnel in different target areas according to the warning value.

[0006] Further, step S100 includes: Step S110: Install a positioning sensor and a speed sensor on the safety helmet worn by construction personnel. Obtain the positioning trajectory recorded by the positioning sensor and the speed function of the speed changing with time recorded by the speed sensor when the construction personnel walk while wearing the safety helmet; extract the start time T1 of a to-be-detected trajectory P in the positioning trajectory P and the end time T2 P , and take the time period between time T1 P and T2 P as the to-be-detected time period, and extract several sub-time periods in the to-be-detected time period; Step S120: Obtain the moving distance L corresponding to the to-be-detected trajectory P in a sub-time period d d ; extract the moving speed of the construction personnel at each moment in the sub-time period d from the speed function, and add them up and average to obtain the average speed V d , and further obtain the characteristic value of the sub-time period d, which is L d / V d , calculate the characteristic values of each sub-time period in the to-be-detected time period, and calculate the variance according to the characteristic values. If the variance is less than the preset variance threshold, then take the to-be-detected trajectory P as the target trajectory, and further obtain all target trajectories.

[0007] In this solution, the duration of each sub-time period is the same. The reason for judging according to the characteristic value here is that when construction personnel walk normally, the moving speed is uniform, and the moving distance corresponding to the to-be-detected trajectory should be balanced with the moving speed of the construction personnel. If there is a large difference in the characteristic values between multiple sub-time periods, that is, the variance is large, it indicates that the to-be-detected trajectory may have abnormal records, and then this to-be-detected trajectory cannot be used as a normal target trajectory for the processing and analysis of the following steps.

[0008] Further, step S200 includes: Step S210: Obtain the corner positions within the building construction area, and in the BIM model, take the area with a radius of r1 centered at the corner positions as the calibration area; obtain the surveillance videos within the historical Q days of the building construction area, perform target detection on the moving vehicles in the surveillance videos, and obtain the rectangular area R corresponding to a certain moving vehicle C in the surveillance screen C , obtain a certain calibration area R0 and the rectangular area R C The moment when they first come into contact is used as the first characteristic moment, and the area of the rectangular area R C at the first characteristic moment is obtained. If the length of a certain target trajectory Y t within the calibration area R0 is greater than k1×r1, and a certain positioning point P t within the trajectory Y t is less than k2×r1 away from the center of the calibration area R0, where k1 and k2 are the first length coefficient and the second length coefficient, then the trajectory Y t is used as the marked trajectory, and the moment corresponding to the positioning point P t is used as the second characteristic moment; Step S220: Obtain the area of the calibration area R0 and the rectangular area of each moving vehicle at the first characteristic moment within the historical Q days; obtain all the first characteristic moments and second characteristic moments involved in the calibration area R0 within the historical Q days, sort all the characteristic moments in chronological order, take any two adjacent second characteristic moments as a combination, a total of M combinations are obtained, and the number of first characteristic moments between the two second characteristic moments corresponding to each combination is obtained; Furthermore, the target value of the calibration area R0 is obtained as , where e is the natural constant, W1 and W2 are the first weight and the second weight respectively, U is the number of moving vehicles in contact with the calibration area R0, S u is the area corresponding to the rectangular area of the u-th moving vehicle, M is the number of combinations, N m is the number of first characteristic moments between the two second characteristic moments corresponding to the m-th combination; if the target value TA is greater than the preset numerical threshold, then the calibration area R0 is used as the first warning area, and then all the first warning areas are obtained.

[0009] Further, step S300 includes: Step S310: Obtain the collision records of any two target objects in history. The target objects include personnel, moving vehicles, and construction machinery and equipment. Extract the target objects A and B corresponding to a certain collision record X, take the moment when A and B collide as T0, and extract the surveillance video with a time period F before the collision moment T0 as the starting point. If only one of A and B is a moving object, obtain the average speed V1 of the moving object within the time period F according to the surveillance video, and the speed V2 at the moment immediately before the collision moment T0. If V2 / V1 is greater than the preset ratio threshold, then regard the collision record X as the target record. In this solution, according to the different uses of each piece of equipment in the construction site area, they are divided into two categories: moving vehicles and construction machinery and equipment. The moving vehicles and construction machinery and equipment in the construction site are two different tools. Among them, the core function of the moving vehicle is transportation, which is used for the horizontal movement or short-distance transfer of personnel, materials, construction waste, etc., including dump trucks, concrete mixers, loaders, forklifts, commuter buses, etc.; while the core function of the construction machinery and equipment is construction operation, which is the equipment directly participating in the engineering operation and generally does not move easily, including tower cranes, mixers, steel processing machinery, and pump trucks. However, no matter which type of equipment, it will pose a collision threat to the workers in the construction site area. Step S320: If both A and B are moving objects, obtain the average speeds V1 A and V1 B of A and B respectively within the time period F according to the surveillance video, A and the speeds V2 B at the moment immediately before the collision moment T0 A / V1 A and V2 B / V1 B If any one of the ratios is greater than the ratio threshold, then regard the collision record X as the target record. Furthermore, obtain all the target records, and use the area with the collision position in the target record as the center and a radius of r2 as the second warning area.

[0010] Further, step S400 includes: Step S410: Take the intersection range of the first warning area and the second warning area as the third warning area, and set the levels of the first, second, and third warning areas to 1, 2, and 3. Regard the adjacent warning areas in the construction area as a target area, and thus obtain several target areas, and the level of each target area is the value corresponding to the maximum warning area level among them; Step S420: According to the surveillance video, obtain the number B of moving vehicles passing through a certain target area H within the time period D before the current moment in the construction area, and thus obtain the warning value Z H =G H (2 - e-B ) and then obtain the warning value of each target area, and based on the warning value, give different warning prompts to the target personnel in different target areas.

[0011] A smart building environment monitoring system based on Internet of Things information perception, including a target trajectory extraction module, a first warning area extraction module, a second warning area acquisition module, and a warning prompt module; Target trajectory extraction module: used to establish a BIM model of the building construction area, wear safety equipment with positioning and speed measurement functions on construction personnel, and establish a speed function of speed changing with time. According to the positioning trajectory and speed function corresponding to the safety equipment history, extract the target trajectory from the positioning trajectory; First warning area extraction module: used to divide the calibration area in the BIM model based on the corner positions in the building construction area that are prone to blocking the line of sight; obtain the historical monitoring video of the building construction area, analyze the situation of moving objects passing through the calibration area in the monitoring video, obtain the target value corresponding to each calibration area, and extract the first warning area from the calibration area according to the target value; Second warning area acquisition module: used to obtain the collision records of collisions between two different target objects in the historical building construction area, and obtain the second warning area in the building construction area according to the moving speeds of the target objects corresponding to the collision records; Warning prompt module: used to divide the building construction area into several target areas according to the first warning area and the second warning area; extract and analyze the monitoring video of the current building construction area, obtain the warning value of each target area, and based on the warning value, give different warning prompts to the target personnel in different target areas.

[0012] Furthermore, the target trajectory extraction module includes a to-be-detected period judgment unit and a target trajectory extraction unit; To-be-detected period judgment unit: used to install a positioning sensor and a speed sensor on the safety helmet worn by construction personnel, obtain the positioning trajectory and speed function, and obtain the to-be-detected period according to a certain to-be-detected trajectory in the positioning trajectory; Target trajectory extraction unit: used to obtain the moving distance of the to-be-detected trajectory during the to-be-detected period and the average speed during the to-be-detected period, and then judge whether the to-be-detected trajectory is a target trajectory, and then obtain all target trajectories.

[0013] Furthermore, the warning prompt module includes a target area division unit and a warning prompt unit; Target area division unit: used to take the intersection range of the first warning area and the second warning area as the third warning area, and divide the building construction area into several target areas according to the first warning area, the second warning area, and the third warning area; Early warning prompt unit: used to extract and analyze the monitoring video of the current construction area, obtain the early warning value of each target area, and give different early warning prompts to the target personnel in different target areas according to the early warning value.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a smart building environment monitoring system and method based on Internet of Things information perception, including: establishing a BIM model of the construction area, wearing safety devices with positioning and speed measurement functions on construction personnel to obtain the positioning trajectory and speed function, and extracting the target trajectory from the positioning trajectory; dividing and calibrating areas, extracting the first early warning area according to the situation of moving objects passing through the calibrated area in the historical monitoring video; obtaining the historical collision records to obtain the second early warning area; dividing the construction area into several target areas, obtaining the early warning value of the target area, and giving different early warning prompts to the target personnel in different target areas. Through the corner positions and historical collision records, combined with the current monitoring video, the present invention can judge the areas prone to danger in the construction area and can realize real-time and effective safety monitoring of the construction area. Description of the Drawings

[0015] Figure 1 It is a flow chart of a smart building environment monitoring method based on Internet of Things information perception according to the present invention; Figure 2 It is a structural diagram of a smart building environment monitoring system based on Internet of Things information perception according to the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment: As Figure 1 shown, the present invention provides a technical solution for a smart building environment monitoring method based on Internet of Things information perception, including the following steps: Step S100: Establish a BIM model of the construction area, wear safety devices with positioning and speed measurement functions on construction personnel, and establish a speed function of the speed changing with time. According to the positioning trajectory and speed function corresponding to the safety device history, extract the target trajectory from the positioning trajectory.

[0018] Step S110: Install a positioning sensor and a speed sensor on the safety helmet worn by construction workers. When a construction worker walks while wearing the safety helmet, obtain the positioning trajectory recorded by the positioning sensor and the speed function of the speed changing with time recorded by the speed sensor; extract the start time T1 of a to-be-detected trajectory P in the positioning trajectory. P and the end time T2 P , and take the time period between time T1 P and T2 P as the to-be-detected time period, and extract several sub-time periods within the to-be-detected time period; Step S120: Obtain the moving distance L corresponding to a sub-time period d of the to-be-detected trajectory P d ; extract the moving speed of the construction worker at each moment within the sub-time period d from the speed function, and add them up and average to obtain the average speed V d , and then obtain the characteristic value of the sub-time period d, which is L d / V d , calculate the characteristic values of each sub-time period within the to-be-detected time period, and calculate the variance based on the characteristic values. If the variance is less than a preset variance threshold, take the to-be-detected trajectory P as the target trajectory, and then obtain all target trajectories.

[0019] In this solution, the duration of each sub-time period is the same. The judgment is made based on the characteristic value because when a construction worker walks normally, the moving speed is uniform, and the moving distance corresponding to the to-be-detected trajectory should be balanced with the moving speed of the construction worker. If there is a large difference in the characteristic values between multiple sub-time periods, that is, the variance is large, it indicates that the to-be-detected trajectory may have abnormal records, and then this to-be-detected trajectory cannot be used as a normal target trajectory for the processing and analysis of the following steps.

[0020] Step S200: Based on the corner positions in the construction area that are prone to blocking the line of sight, divide the calibration areas in the BIM model; obtain the historical surveillance videos of the construction area, analyze the situation of moving objects passing through the calibration areas in the surveillance videos, obtain the target value corresponding to each calibration area, and extract the first warning area from the calibration areas according to the target value; Step S210: Obtain the corner positions in the construction area, and in the BIM model, take the area with a corner position as the center and a radius of r1 as the calibration area; obtain the historical surveillance videos of the construction area within Q days, perform target detection on the moving vehicles in the surveillance videos, and obtain the rectangular area R corresponding to a certain moving vehicle C in the surveillance screen C , obtain the moment when a certain calibration area R0 just comes into contact with the rectangular area R C as the first characteristic moment, and obtain the area of the rectangular area R C at the first characteristic moment; If a certain target trajectory Yt is greater than k1×r1 within the calibration region R0, and for a certain positioning point P t within the trajectory Y t the distance between it and the center of the calibration region R0 is less than k2×r1, where k1 and k2 are the first length coefficient and the second length coefficient, then the trajectory Y t is used as a marked trajectory, and the moment corresponding to the positioning point P t is used as the second characteristic moment; Step S220: Obtain the area of the calibration region R0 and the rectangular region of each moving vehicle at the first characteristic moment within the historical Q days; Obtain all the first characteristic moments and second characteristic moments involved in the calibration region R0 within the historical Q days, sort all the characteristic moments in chronological order, take any two adjacent second characteristic moments as a combination, a total of M combinations are obtained, and obtain the number of first characteristic moments between the two second characteristic moments corresponding to each combination; Furthermore, the target value of the calibration region R0 is obtained as , where e is the natural constant, W1 and W2 are the first weight and the second weight respectively, U is the number of moving vehicles in contact with the calibration region R0, S u is the area of the rectangular region corresponding to the u-th moving vehicle among them, M is the number of combinations, and N m is the number of first characteristic moments between the two second characteristic moments corresponding to the m-th combination; If the target value TA is greater than the preset numerical threshold, then the calibration region R0 is used as the first warning region, and then all the first warning regions are obtained.

[0021] It should be noted that for the function y = 1 - e -x when x takes values x≥0, y takes values in the range [0, 1), and it is a function where y increases as x increases. And when x is small, the increase rate of y is larger than that when x is large. In this solution, the target value is judged based on the region area S u and the quantity N m , and the region area S u and the quantity N m are the keys to judging the size of the target value. Since the region area S u represents the size of the vehicles passing through the calibration region R0, and the quantity N m represents the number of people between two adjacent vehicles passing through the calibration region R0. When the region area S u and the quantity N m are larger, it indicates that the calibration region R0 needs to be warned. And when the region area S u and the quantity N m are small, the target value of the calibration region R0 should also be made as large as possible. Therefore, here the function y = 1 - e -xDesign is carried out, and W1 and W2 are used as the first weight and the second weight, and their specific values should be determined according to the actual situation.

[0022] Step S300: Obtain the collision records of collisions between two different target objects in the historical construction area. According to the moving speeds of the target objects corresponding to the collision records, obtain the second warning area in the construction area. Step S310: Obtain the collision records of collisions between any two target objects in history. The target objects include personnel, moving vehicles, and construction machinery and equipment. Extract the target objects A and B corresponding to a certain collision record X, take the moment of collision between A and B as T0, and extract the surveillance video with a time period F starting from the collision moment T0. If only one of A and B is a moving object, obtain the average speed V1 of the moving object within the time period F and the speed V2 at the moment immediately before the collision moment T0 according to the surveillance video. If V2 / V1 is greater than the preset ratio threshold, then regard the collision record X as the target record. In this solution, according to the different uses of each device in the construction site area, it is divided into two categories: moving vehicles and construction machinery and equipment. The moving vehicles and construction machinery and equipment in the construction site are two different tools. Among them, the core function of the moving vehicle is transportation, which is used for the horizontal movement or short-distance transfer of personnel, materials, construction waste, etc., including dump trucks, concrete mixers, loaders, forklifts, commuter buses, etc.; while the core function of the construction machinery and equipment is construction operation, which is directly involved in the engineering operation equipment and generally does not move easily, including tower cranes, mixers, steel processing machinery, pump trucks. However, no matter which type of equipment, it will pose a collision threat to the workers in the construction site area.

[0023] Step S320: If both A and B are moving objects, obtain the average speeds V1 A and V1 B of A and B respectively within the time period F according to the surveillance video, and the speeds V2 A and V2 B at the moment immediately before the collision moment T0. If any one of the ratios of V2 A / V1 A and V2 B / V1 B is greater than the ratio threshold, then regard the collision record X as the target record; thus obtain all the target records, and use the area with the collision position in the target record as the center and a radius of r2 as the second warning area.

[0024] Step S400: Divide the construction area into several target areas according to the first warning area and the second warning area; extract and analyze the surveillance videos of the current construction area to obtain the warning value of each target area, and based on the warning value, give different warning prompts to the target personnel in different target areas.

[0025] Step S410: Take the intersection range of the first warning area and the second warning area as the third warning area, and set the levels of the first, second, and third warning areas to 1, 2, and 3 respectively. Consider adjacent warning areas in the construction area as one target area, thus obtaining several target areas, and the level of each target area is the value corresponding to the highest warning area level among them; Step S420: According to the surveillance video, obtain the number B of moving vehicles passing through a certain target area H within the time period D before the current moment in the construction area, and then obtain the warning value Z of the target area H H =G H (2 - e -B ), and then obtain the warning value of each target area, and based on the warning value, give different warning prompts to the target personnel in different target areas.

[0026] Since the value of G H is 1, 2, or 3, and the value range of 2 - e -B is [1, 2), then the value range of Z H is from 1 to 6. In this embodiment, when the warning value of the target area is from 1 to 3, it is a low - risk warning, prompting the target personnel to maintain normal vigilance and avoid laxity; when it is from 3 to 5, it is a medium - risk warning, prompting the target personnel to pay key attention and initiate preventive measures; when it is from 5 to 6, it is a high - risk warning, prompting the target personnel to make a mandatory emergency response and evacuate or dispose quickly.

[0027] The present invention also provides an intelligent building environment monitoring system based on Internet of Things information perception, as Figure 2 shown, including: a target trajectory extraction module, a first warning area extraction module, a second warning area acquisition module, and a warning prompt module; The target trajectory extraction module: is used to establish a BIM model of the construction area, wear safety devices with positioning and speed - measuring functions on construction personnel, and establish a speed function of the speed changing with time. According to the historical positioning trajectory corresponding to the safety device and the speed function, extract the target trajectory from the positioning trajectory; The first early warning area extraction module: used to divide the calibration area in the BIM model based on the corner positions in the construction area that are prone to blocking the line of sight; obtain the historical surveillance videos of the construction area, analyze the situation of moving objects passing through the calibration area in the surveillance videos, obtain the target value corresponding to each calibration area, and extract the first early warning area from the calibration areas according to the target value; The second early warning area acquisition module: used to obtain the collision records of collisions occurring between two different target objects in the historical construction area, and obtain the second early warning area in the construction area according to the moving speeds of the target objects corresponding to the collision records; The early warning prompt module: used to divide the construction area into several target areas according to the first early warning area and the second early warning area; extract and analyze the surveillance videos of the current construction area, obtain the early warning value of each target area, and give different early warning prompts to the target personnel in different target areas according to the early warning value.

[0028] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights involved.

Claims

1. A smart building environment monitoring method based on Internet of Things information perception, characterized in that: The following steps are involved: Step S100: Establish a BIM model of the construction area, wear safety equipment with positioning and speed measurement functions on construction personnel, establish a speed function of speed change over time, and extract the target trajectory from the positioning trajectory according to the positioning trajectory corresponding to the history of the safety equipment and the speed function; Step S200: dividing the calibration area in the BIM model based on the corner positions of the building construction area that are easy to block the line of sight; Obtain historical surveillance videos of the construction area, analyze the situation of moving objects in the surveillance videos passing through the calibration area, obtain the target value corresponding to each calibration area, and extract the first warning area from the calibration area according to the target value; Step S300: obtaining a historical collision record of collision between two different target objects in the construction area, and obtaining a second warning area in the construction area according to the moving speed of the target object corresponding to the collision record; Step S400: Dividing the construction area into a number of target areas according to the first warning area and the second warning area; The surveillance video of the current construction area is extracted and analyzed to obtain the warning value of each target area, and different warning prompts are given to the target personnel in different target areas according to the warning value.

2. According to claim 1, a smart building environment monitoring method based on Internet of Things information perception is characterized in that: Step S100 includes: Step S110: Install a positioning sensor and a speed sensor on the helmet worn by the construction personnel, obtain the positioning trajectory recorded by the positioning sensor when the construction personnel wear the helmet and the speed function recorded by the speed sensor when the speed changes over time; extract the starting time T1 of a certain track P to be detected in the positioning trajectory P and end time T2 P , set time T1 P and T2 P As the period to be detected, and extract several sub-periods in the period to be detected; Step S120: Obtain the moving distance L corresponding to the detected track P in a certain sub-period d d ; Extract the moving speed of the construction personnel at each moment in the sub-period d in the speed function, and add the average value to get the average speed V d , and then the characteristic value of the sub-period d is obtained, which is L d / V d , calculate the characteristic value of each sub-period in the time period to be detected, and calculate the variance according to the characteristic value. If the variance is less than the preset variance threshold, the trajectory P to be detected is taken as the target trajectory, and then all target trajectories are obtained.

3. The method for monitoring the environment of a smart building based on information perception of the Internet of Things according to claim 1, characterized in that: Step S200 includes: Step S210: Obtain the corner position in the construction area, and use the area with the corner position as the center and a radius of r1 as the calibration area in the BIM model; obtain the surveillance video of the construction area in the past Q days, perform target detection on the moving vehicles in the surveillance video, and obtain the rectangular area R corresponding to a certain moving vehicle C in the surveillance picture. C , get a certain calibration area R0 and a rectangular area R C The moment of contact is taken as the first characteristic moment, and the rectangular area R is obtained C The area of ​​the region at the first characteristic moment; If a target trajectory Y t The length of the calibration area R0 is greater than k1×r1, and the trajectory Y t Any positioning point P within t The distance between the center of the calibration area R0 is less than k2×r1, k1 and k2 are the first length coefficient and the second length coefficient, then the trajectory Y t As the marker trajectory, the positioning point P t The corresponding moment is taken as the second characteristic moment; Step S220: Obtain the area of ​​the calibrated area R0 and the rectangular area of ​​each moving vehicle within the historical Q days at the first characteristic moment; obtain all the first characteristic moments and second characteristic moments involved in the calibrated area R0 within the historical Q days, sort all the characteristic moments in chronological order, take any two adjacent second characteristic moments as a combination, obtain M combinations in total, and obtain the number of first characteristic moments between the two second characteristic moments corresponding to each combination; Then the target value of the calibration area R0 is obtained as , where e is a natural constant, W1 and W2 are the first weight and the second weight respectively, U is the number of mobile vehicles in contact with the calibration area R0, S u is the area of ​​the rectangular area corresponding to the u-th moving vehicle, M is the number of combinations, N m is the number of first characteristic moments between two second characteristic moments corresponding to the mth combination; if the target value TA is greater than the preset numerical threshold, the calibrated area R0 is used as the first warning area, and then all the first warning areas are obtained.

4. The method for monitoring the environment of a smart building based on information perception of the Internet of Things according to claim 1, characterized in that: Step S300 includes: Step S310: Obtain historical collision records of collisions between any two target objects, the target objects including personnel, mobile vehicles and construction machinery and equipment; extract target objects A and B corresponding to a certain collision record X, take the time when A and B collide as T0, and extract the monitoring video of the time period F before the collision time T0; if only one of A and B is a mobile object, obtain the average speed V1 of the mobile object in the time period F and the speed V2 at the moment before the collision time T0 according to the monitoring video, and if V2 / V1 is greater than a preset ratio threshold, then take the collision record X as the target record; Step S320: If A and B are both moving objects, obtain the average speed V1 of A and B in time period F according to the surveillance video A and V1 B , and the velocity V2 at the moment before the collision time T0 A and V2 B , if V2 is satisfied A / V1 A and V2 B / V1 B If any ratio in is greater than the ratio threshold, the collision record X is taken as the target record; then all the target records are obtained, and the area with the collision position in the target record as the center and the radius r2 is taken as the second warning area.

5. The method for monitoring the environment of a smart building based on information perception of the Internet of Things according to claim 1, characterized in that: Step S400 includes: Step S410: The intersection of the first warning area and the second warning area is taken as the third warning area, and the levels of the first, second and third warning areas are set to 1, 2 and 3, and the adjacent warning areas in the construction area are taken as a target area, thereby obtaining a plurality of target areas, and the level of each target area is the value corresponding to the maximum warning area level; Step S420: According to the monitoring video, the number of moving vehicles B passing through a target area H in the construction area before the current time period D is obtained, and then the warning value of the target area H is obtained as Z H =G H (2-e -B ), and then obtain the warning value of each target area, and according to the warning value, give different warning prompts to the target personnel in different target areas.

6. A smart building environment monitoring system, used to execute a smart building environment monitoring method based on Internet of Things information perception as described in any one of claims 1 to 5, characterized in that: The system includes a target trajectory extraction module, a first warning area extraction module, a second warning area acquisition module and a warning prompt module; Target trajectory extraction module: used to establish a BIM model of the construction area, wear safety equipment with positioning and speed measurement functions on construction personnel, and establish a speed function of speed change over time. According to the positioning trajectory corresponding to the history of the safety equipment and the speed function, the target trajectory is extracted from the positioning trajectory; The first warning area extraction module is used to divide the calibration area in the BIM model based on the corner positions of the construction area that are easy to block the line of sight; Obtain historical surveillance videos of the construction area, analyze the situation of moving objects in the surveillance videos passing through the calibration area, obtain the target value corresponding to each calibration area, and extract the first warning area from the calibration area according to the target value; The second warning area acquisition module is used to obtain the collision record of the collision between two different target objects in the construction area, and obtain the second warning area in the construction area according to the moving speed of the target object corresponding to the collision record; Early warning prompt module: used to divide the construction area into several target areas according to the first early warning area and the second early warning area; The surveillance video of the current construction area is extracted and analyzed to obtain the warning value of each target area, and different warning prompts are given to the target personnel in different target areas according to the warning value.

7. The intelligent building environment monitoring system according to claim 6, characterized in that: The target trajectory extraction module includes a detection period judgment unit and a target trajectory extraction unit; The detection period judgment unit is used to install a positioning sensor and a speed sensor on the safety helmet worn by the construction personnel, obtain the positioning trajectory and the speed function, and obtain the detection period according to a certain detection trajectory in the positioning trajectory; Target trajectory extraction unit: used to obtain the moving distance of the trajectory to be detected during the detection period and the average speed during the detection period, and then determine whether the trajectory to be detected is the target trajectory, and then obtain all target trajectories.

8. The intelligent building environment monitoring system according to claim 6, characterized in that: The early warning prompt module includes a target area division unit and an early warning prompt unit; Target area division unit: used to take the intersection of the first warning area and the second warning area as the third warning area, and divide the construction area into several target areas according to the first warning area, the second warning area and the third warning area; Early warning prompt unit: used to extract and analyze the monitoring video of the current construction area, obtain the early warning value of each target area, and issue different early warning prompts to the target personnel in different target areas according to the early warning value.

Images