Road construction comprehensive management and control method and system based on Internet of Things

Abstract

The invention discloses a road construction comprehensive management and control method and system based on the Internet of Things, and relates to the technical field of the Internet of Things, a shielding feature vector set Vft is constructed, a comprehensive shielding vision field index Ovf is further formed through model fusion construction, and a shielding risk score set OvfList with station point distribution features is output. Compared with a traditional construction safety management mode which is guided only based on static layout and personnel experience, the method provided by the invention has the advantages that high-shielding and high-conflict points are automatically screened by setting a risk threshold Topf, a high-risk point index set Rls is output, and a targeted enclosure structure optimization suggestion list Opl is generated; and finally, an improvement score Dsc generated through re-evaluation after optimization is realized, so that the actual improvement degree of an optimization effect is quantified, and the problems of direction misjudgment, high collision risk between pedestrians or between pedestrians and non-motor vehicles, poor pre-judgment of a path intersection area and the like caused by sight blocking due to enclosure are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an Internet of Things-based comprehensive road construction management and control method and system. Background Art

[0002] With the accelerating pace of urbanization, the construction of smart cities has become a crucial component of the current urban governance system. Within the macro-system of smart cities, intelligent management of urban infrastructure is one of its core pillars. Road construction and maintenance, as a key component in ensuring urban traffic flow and spatial renewal, are gradually being incorporated into a more refined and dynamic scheduling system. Especially in large and medium-sized cities, road construction operations involving arterial roads, transportation hubs, or high-traffic areas are no longer simply civil engineering activities, but rather an intelligent management and control process that requires coordinated response to the city's operational status. Therefore, "integrated road construction management and control" has gradually evolved into a multi-module integrated system that integrates perception, analysis, and response. IoT technology, serving as a bridge between the perception and interaction layers, is the key to realizing this system.

[0003] In actual urban road construction, fences, as a temporary physical barrier, ensure the enclosure and safety of the construction area. However, most deployment plans fail to fully consider their impact on line of sight between people and vehicles. Especially at intersections, narrow sidewalks, and temporary detours, fences create numerous blind spots, preventing pedestrians from approaching from different directions from foreseeing oncoming traffic. This can easily lead to physical conflicts such as scrapes, collisions, and cornering collisions. More seriously, these visual obstructions can also cause pedestrians to encounter small, fast-moving vehicles like non-motorized vehicles, bicycles, and scooters unexpectedly around turns. Unable to predict the direction and distance of other vehicles in advance, this often leads to dangerous collisions or evasive falls. These issues have become a frequent cause of pedestrian safety incidents, yet are considered a low priority in most construction planning schemes. The lack of specific monitoring or prediction mechanisms makes it difficult for management to promptly identify "high-risk obstruction points" and even more difficult to implement dynamic optimization. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a road construction comprehensive management and control method and system based on the Internet of Things, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a road construction comprehensive management and control method based on the Internet of Things, comprising the following steps: S1. Based on the Internet of Things, the spatial structure and crowd traffic behavior data of the road construction area are collected, and the structural parameter subset StructSet and the behavioral parameter subset BehavSet are extracted to form the original view data set Vfd of the construction area. S2. After feature extraction based on the original view data set Vfd, the feature vector of each station is calculated to construct an occlusion feature vector set Vft, including the occlusion rate Sor, the path conflict factor Cof, and the line of sight ambiguity Blu; S3. The feature vector Vft is input into the occlusion risk scoring model for training, and a comprehensive occlusion view index Ovf is constructed, which is combined into an occlusion risk score set OvfList for each station point; S4. Using the preset occlusion risk threshold Tovf, perform traversal comparison and determination on the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the determination results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; S5. Implement and apply the enclosure structure optimization suggestion list Opl, and collect a new occlusion risk score set OvfList (New). Then compare it with the occlusion risk score set OvfList of the station site before implementation to obtain the optimization improvement score Dsc. Based on the optimization improvement score Dsc, judge the effectiveness of the measures after implementation.

[0006] Preferably, said S1 includes S11; S11. Collect spatial projection data of road construction area fences and visible range information of station points through IoT devices, extract spatial structural parameters of each station point in the construction area, including actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, and form a structural parameter subset of all station points StructSet={Aov(k), Avw(k), Dag(k), Vag(k)|k∈N}, where N represents the total number of station points, Aov(k), Avw(k), Dag(k), and Vag(k) represent the actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, respectively; Among them, IoT devices include panoramic wide-angle cameras and 3D laser scanners; The actual occlusion area Aov is obtained by using a panoramic wide-angle camera and a three-dimensional laser scanner installed above the construction area to obtain real-time projection images of the construction fence at different angles, and extracting the occlusion area boundary through an image processing algorithm, which includes a graphic contour filling algorithm and a point cloud bounding volume division method; The theoretical visible range Avw of the station point is calculated by installing a 3D laser scanner and high-precision mapping equipment deployed at the edge of the construction area. Without considering any obstruction from fences, the laser scan is performed 180° forward of the station point to simulate the maximum visible area. Combined with the existing road structure map, the theoretical open field of view area is calculated by fanning out. The main viewing angle direction Vag of the station point is obtained by presetting the projection ray angle with the station point as the center of the circle and measuring the maximum continuous unobstructed angle from the left and right boundaries; The pedestrian direction angle Dag is obtained by capturing the crowd's movement trajectory through a panoramic wide-angle camera and combining it with the Ak path fitting algorithm to calculate the angle between the crowd's movement trajectory direction and the standing position direction.

[0007] Preferably, said S1 includes S12; S12. Using sensing devices deployed in the road construction area, obtain traffic behavior characteristic data of people in the construction site, extract the behavioral interaction parameters required to build the occlusion conflict analysis model, specifically including the path intersection angle Xag and the pedestrian flow density per unit time Dpt, and form a behavioral parameter subset BehavSet = {Dpt, Xag (m, w) | (m, w) ∈ M*M}, m ≠ w. This is then integrated with the structural parameter subset StructSet to obtain the original viewshed dataset Vfd of the construction area. The path intersection angle Xag is obtained by continuously capturing video images with a panoramic wide-angle camera; an edge module detects pedestrians in the image and tracks multiple targets; a sequence of trajectory points of each pedestrian is recorded to form a path set {P1, P2, ..., Pm|m∈M}, where M represents the total number of paths and Pm represents the mth path; a linear fit is then performed on each path in the path set to obtain a unit direction vector v, and the unit direction vector v of any two paths is calculated to obtain the path intersection angle Xag; The unit direction vector v is obtained by the following calculation formula: ; Where v(m) represents the unit direction vector of the mth path, x(m, end) and y(m, end) as well as x(m, start) and y(m, start) represent the coordinates of the end point and the starting point of the mth path respectively; The path intersection angle Xag is obtained by the following calculation formula: ; Where Xag(m, w) represents the path intersection angle between the mth path and the wth path, and arccos represents the inverse cosine function, which converts the cosine value into an angle value. The pedestrian flow density per unit time Dpt is obtained by the ratio between the number of pedestrians in the road construction area and the time interval within a fixed statistical time window.

[0008] Preferably, said S2 includes S21; S21. Perform feature extraction based on the original view data set Vfd. After extracting the structural parameter subset StructSet of each station point, extract the actual obstruction area Aov and the theoretical unobstructed visual range Avw, calculate the obstruction rate Sor of each station point, and quantify the degree of obstruction of each station point by the enclosure structure. The occlusion rate Sor is obtained by the following calculation formula: ; Where Sor(k) represents the occlusion rate of the k-th station, Aov(k) and Avw(k) represent the actual occlusion area Aov and the theoretical unobstructed visual range Avw of the k-th station, respectively.

[0009] Preferably, said S2 includes S22; S22. Feature extraction is performed based on the original visual field dataset Vfd. By extracting the behavioral parameter subset BehavSet and the structural parameter subset StructSet of each station point, key dynamic data reflecting the relationship between the path and direction of the crowd behavior is obtained. Then, the pedestrian flow density per unit time Dpt, the path intersection angle Xag, the passage direction angle Dag, and the main viewing direction Vag of the station point are extracted to construct the path conflict factor Cof and the visual ambiguity Blu. The results are then integrated with the occlusion rate Sor to obtain the occlusion feature vector set Vft. The path conflict factor Cof is obtained using the following calculation formula: ; Where Cof(m, w, k) represents the path conflict factor between path m and path w at the k-th station, skn represents the sine function, Dpt(k) represents the passenger flow density per unit time at the k-th station intersection, Dag(k) represents the travel direction angle at the k-th station, and Vag(k) represents the main viewing angle of the k-th station. The visual blur Blu is obtained by the following calculation formula: ; Where Blu(k) represents the line of sight ambiguity of the k-th station.

[0010] Preferably, said S3 includes S31; S31. Normalize the feature vector Vft to eliminate the dimensional differences between different data, obtain the standard path conflict factor Cofn, the standard line of sight blur Blun, and the standard occlusion rate Sorn, and then input them into the occlusion risk scoring model. Perform fusion training with each station k as a unit to construct a comprehensive indicator reflecting the degree of multi-dimensional occlusion risk impact, marked as the comprehensive occlusion view index Ovf(k) of the k-th station. After integrating all stations, obtain the occlusion risk score set OvfList={Ovf(k)|k∈N}, where N represents the total number of stations. The comprehensive occlusion view index Ovf(k) of the k-th station is obtained by the following model fusion training formula: ; Where N(k) represents the number of path pairs at the k-th station, which is calculated by the formula N(k)=|M(k)|*(||M(k)-1) / 2. M represents the total number of paths, Sorn(k) represents the standard occlusion rate of the k-th station, Cofn(k) represents the standard path conflict factor of the k-th station, and Blun(k) represents the standard line of sight ambiguity of the k-th station.

[0011] Preferably, said S4 includes S41; S41. Taking the total number of stations N as the traversal boundary, each comprehensive occlusion view index Ovf(k) in the occlusion risk score set OvfList is judged by comparing it with a preset occlusion risk threshold Tovf, and marking high-risk occlusion stations according to the comparison result. After the traversal is completed, all high-risk occlusion stations are integrated to obtain a high-risk point index set Rls. Stations with high risk of occlusion are marked by comparing: When the comprehensive occlusion view index Ovf (k) is greater than the occlusion risk threshold Tovf, the comparison result is a risk result, and the k-th station is marked as a high-risk occlusion station; When the comprehensive occlusion view index Ovf (k) ≤ the occlusion risk threshold Tovf, the comparison result is normal, the k-th station is not marked as a high-risk occlusion station, and the k-th station is eliminated.

[0012] Preferably, said S4 includes S42; S42. Based on the high-risk point index set Rls and combined with the original visual field dataset Vfd of the obstructed high-risk station site, generate a fence structure optimization suggestion for each obstructed high-risk station site. The fence structure optimization suggestion includes adjusting the fence layout form of the obstructed high-risk station site, adjusting the perspective window and translucent visual field area of ​​the obstructed high-risk station site, and adjusting the number of eye-catching signs guiding people to pass through the visual priority channel, and generating a fence structure optimization suggestion list Opl.

[0013] Preferably, the S5 includes S51; S51. Implementing and applying the enclosure structure optimization suggestion list Opl. The implementation and application includes sending a notification to relevant operators to carry out actual deployment, collecting the original view data set Vfd for each high-risk occlusion site after the actual deployment, calculating and obtaining a new occlusion risk score set OvfList(New) after the actual deployment, and then comparing it with the occlusion risk score set OvfList before the actual deployment. After summarizing the differences, an optimization improvement score Dsc is obtained, and then the effectiveness of the measures after the actual deployment is determined based on the optimization improvement score Dsc. The actual post-deployment measures are judged by the following methods: When the optimization improvement score Dsc>0, it means that the implementation and application of the enclosure structure optimization suggestion list Opl is effective; When the optimization improvement score Dsc≤0, it means that the implementation of the fence structure optimization suggestion list Opl is invalid, and optimization measures such as fence shape adjustment, perspective window setting, prompt sign addition and path visual guidance reconstruction are carried out again.

[0014] An IoT-based comprehensive road construction management and control system, including a road construction network acquisition module, a construction feature extraction module, an occlusion risk analysis module, an occlusion judgment module, and an iterative optimization module; The road construction network collection module collects spatial structure and crowd traffic behavior data of the road construction area based on the Internet of Things, forming the original view data set Vfd of the construction area; The construction feature extraction module extracts features based on the original visual field dataset Vfd and constructs an occlusion feature vector set Vft, including an occlusion rate Sor, a path conflict factor Cof, and a visual ambiguity Blu; The occlusion risk analysis module inputs the feature vector Vft into the occlusion risk scoring model for training, constructs a comprehensive occlusion view index Ovf, and combines it into an occlusion risk score set OvfList for each station point; The occlusion judgment module uses the preset occlusion risk threshold Tovf to traverse and compare the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the judgment results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; The iterative optimization module applies the enclosure structure optimization suggestion list Opl, and then compares the occlusion risk score set OvfList of the station points before and after the application to obtain the optimization improvement score Dsc.

[0015] The present invention provides a road construction comprehensive management and control method and system based on the Internet of Things, which has the following beneficial effects: (1) Construct an occlusion feature vector set Vft, and further construct a comprehensive occlusion view index Ovf through model fusion, and output it as an occlusion risk score set OvfList with station point distribution characteristics. Compared with the traditional construction safety management method based only on static layout and personnel experience, by setting the risk threshold Tovf, high occlusion and high conflict points are automatically screened, and a high-risk point index set Rls is output and a targeted enclosure structure optimization suggestion list Opl is generated. Finally, the improvement score Dsc generated by re-evaluation after optimization is achieved to quantify the actual improvement of the optimization effect. The overall method effectively solves the problems mentioned in the background technology, such as direction misjudgment caused by line of sight obstruction caused by enclosures, high risk of collision between pedestrians or pedestrians and non-motor vehicles, and poor predictability of path intersection areas.

[0016] (2) By using the panoramic wide-angle camera and three-dimensional laser scanner in the IoT device to achieve multi-angle real-time acquisition, not only can spatial geometric parameters such as the actual occlusion area Aov and the theoretical visual range Avw of the station be obtained, but also the station's main viewing angle Vag and the pedestrian passage direction angle Dag reflected by the crowd's dynamic trajectory can be accurately extracted. At the same time, through the behavioral interaction parameters such as the path intersection angle Xag and the unit time crowd density Dpt calculated based on the crowd trajectory, a behavioral feature set reflecting the potential of traffic conflict is further constructed. After forming the structured data set Vfd, the above multi-dimensional parameters provide a highly realistic, quantifiable and traceable decision-making basis for subsequent occlusion risk modeling. It is particularly noteworthy that parameters such as the path intersection angle Xag are derived from the dynamic trajectory angle calculation and have long been neglected in existing traffic safety technologies. Because they rely on continuous visual perception and direction vector modeling, traditional solutions are difficult to obtain. This significantly improves the ability to identify the causes of local occlusion misjudgment and crowd conflict paths, and has strong interpretability and high adaptability.

[0017] (3) By normalizing the multi-dimensional parameters in the occlusion feature vector set Vft, a comprehensive occlusion view index Ovf (k) is constructed, which realizes the fusion expression of different types of occlusion risk factors under a unified scoring scale, and effectively solves the problem of the inability to quantify and unify the structural occlusion factors and dynamic traffic interference. Relying on the occlusion risk score set OvfList, with the total number of station points N as the index boundary, based on the set occlusion risk threshold Tovf, high-risk occlusion station points are efficiently screened out to form a high-risk point index set Rls. Then, combined with the specific structural layout of each risk point in the original view data set Vfd, the enclosure structure optimization suggestion list Opl is output, and the re-collected occlusion risk score set OvfList (New) is compared with the original score set OvfList to form an optimization improvement score Dsc, which is used to measure the actual effectiveness after deployment. This method not only achieves accurate identification of high-occlusion areas, but also forms a risk-strategy-feedback closed-loop path with the comprehensive occlusion view index Ovf (k) as the core. It has dynamic response capabilities and verifiable effects, and is significantly superior to traditional manual experience judgment and single-time path optimization strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the steps of a comprehensive road construction management and control method based on the Internet of Things of the present invention; Figure 2 This is a schematic diagram of a block diagram of a comprehensive road construction management and control system based on the Internet of Things of the present invention; Figure 3 Schematic diagram of the distribution trend of the comprehensive obstruction view index Ovf(k) at each station. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] Example 1: The present invention provides a comprehensive road construction management and control method based on the Internet of Things. Figure 1 , including the following steps: S1. Based on the Internet of Things, the spatial structure and crowd traffic behavior data of the road construction area are collected, and the structural parameter subset StructSet and the behavioral parameter subset BehavSet are extracted to form the original view data set Vfd of the construction area. S2. After feature extraction based on the original view data set Vfd, the feature vector of each station is calculated to construct an occlusion feature vector set Vft, including the occlusion rate Sor, the path conflict factor Cof, and the line of sight ambiguity Blu; S3. The feature vector Vft is input into the occlusion risk scoring model for training, and a comprehensive occlusion view index Ovf is constructed, which is combined into an occlusion risk score set OvfList for each station point; S4. Using the preset occlusion risk threshold Tovf, perform traversal comparison and determination on the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the determination results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; S5. Implement and apply the enclosure structure optimization suggestion list Opl, and collect a new occlusion risk score set OvfList (New). Then compare it with the occlusion risk score set OvfList of the station site before implementation to obtain the optimization improvement score Dsc. Based on the optimization improvement score Dsc, judge the effectiveness of the measures after implementation.

[0021] In this embodiment, the original visual field dataset Vfd of the construction area is collected based on the IoT terminal, and the structural parameter subset and the behavioral parameter subset are combined to extract the occlusion rate Sor, the path conflict factor Cof and the line of sight blur Blu, and construct the occlusion feature vector set Vft. The comprehensive occlusion visual field index Ovf is further constructed through model fusion, and the output is an occlusion risk score set OvfList with station site distribution characteristics. Compared with the traditional construction safety management method that is guided only by static layout and personnel experience, the method of the present invention automatically filters high-occlusion and high-conflict points by setting a risk threshold Tovf, outputs a high-risk point index set Rls and generates a targeted enclosure structure optimization suggestion list Opl, and finally realizes the improvement score Dsc generated by re-evaluation after optimization, which is used to quantify the actual improvement of the optimization effect. The overall method effectively solves the problems mentioned in the background technology, such as misjudgment of direction caused by obstruction of vision caused by fencing, high risk of collision between pedestrians or pedestrians and non-motor vehicles, and poor predictability of path intersection areas. It has the significant advantages of quantifiable risk modeling, visual control strategy, and iterative optimization feedback. It is particularly suitable for intelligent and refined dynamic management scenarios of visual safety of crowd passage in complex construction environments.

[0022] Example 2: Specifically: S1 includes S11; S11. Collect spatial projection data of road construction area fences and visible range information of station points through IoT devices, extract spatial structural parameters of each station point in the construction area, including actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, and form a structural parameter subset of all station points StructSet={Aov(k), Avw(k), Dag(k), Vag(k)|k∈N}, where N represents the total number of station points, Aov(k), Avw(k), Dag(k), and Vag(k) represent the actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, respectively; Among them, IoT devices include panoramic wide-angle cameras and 3D laser scanners; The actual occlusion area Aov is obtained by using a panoramic wide-angle camera and a three-dimensional laser scanner installed above the construction area to obtain real-time projection images of the construction fence at different angles, and extracting the occlusion area boundary through an image processing algorithm, which includes a graphic contour filling algorithm and a point cloud bounding volume division method; The theoretical visible range Avw of the station point is calculated by installing a 3D laser scanner and high-precision mapping equipment deployed at the edge of the construction area. Without considering any obstruction from fences, the laser scan is performed 180° forward of the station point to simulate the maximum visible area. Combined with the existing road structure map, the theoretical open field of view area is calculated by fanning out. The main viewing angle direction Vag of the station point is obtained by presetting the projection ray angle with the station point as the center of the circle and measuring the maximum continuous unobstructed angle from the left and right boundaries; The pedestrian direction angle Dag is obtained by capturing the crowd movement trajectory through a panoramic wide-angle camera and combining it with the Ak path fitting algorithm. The Ak path fitting algorithm includes using SORT trajectory tracking to calculate the angle between the crowd movement trajectory direction and the standing position direction.

[0023] Said S1 includes S12; S12. Using sensing devices deployed in the road construction area, obtain traffic behavior characteristic data of people in the construction site, extract the behavioral interaction parameters required to build the occlusion conflict analysis model, specifically including the path intersection angle Xag and the pedestrian flow density per unit time Dpt, and form a behavioral parameter subset BehavSet = {Dpt, Xag (m, w) | (m, w) ∈ M*M}, m ≠ w. This is then integrated with the structural parameter subset StructSet to obtain the original viewshed dataset Vfd of the construction area. The path intersection angle Xag is obtained by continuously capturing video images with a panoramic wide-angle camera; an edge module detects pedestrians in the image and tracks multiple targets; a sequence of trajectory points of each pedestrian is recorded to form a path set {P1, P2, ..., Pm|m∈M}, where M represents the total number of paths and Pm represents the mth path; a linear fit is then performed on each path in the path set to obtain a unit direction vector v, and the unit direction vector v of any two paths is calculated to obtain the path intersection angle Xag; The unit direction vector v is obtained by the following calculation formula: ; Wherein, v(m) represents the unit direction vector of the m-th path, which is specifically obtained by dividing the direction vector formed by the starting point and the end point of the path by its modulus. The modulus is the Euclidean norm of the direction vector, which represents its geometric length in the plane rectangular coordinate system. x(m, end) and y(m, end) as well as x(m, start) and y(m, start) represent the path end point coordinates and path starting point coordinates of the m-th path, respectively. The path end point coordinates specifically represent the path end point coordinates (x(m, end), y(m, end)), x and y represent the x-axis coordinate and y-axis coordinate of the path end point, respectively. The path starting point coordinates specifically represent (x(m, start), y(m, start)), x and y represent the x-axis coordinate and y-axis coordinate of the path starting point, respectively. The path intersection angle Xag is obtained by the following calculation formula: ; Where Xag(m, w) represents the intersection angle between the mth and wth paths, and arccos represents the inverse cosine function, which converts cosine values ​​into angle values. The smaller the intersection angle Xag(m, w) between the mth and wth paths, the closer the two directions are, and the paths may pass in parallel. When it approaches 90°, it is a high-risk intersection angle, indicating that there may be a collision point between the paths. The pedestrian flow density per unit time Dpt is obtained by the ratio between the number of pedestrians in the road construction area and the time interval within a fixed statistical time window, which is used to reflect the instantaneous pedestrian flow intensity and traffic density in the road construction area.

[0024] In this embodiment, by constructing a raw view data set Vfd, comprising a structural parameter subset StructSet and a behavioral parameter subset BehavSet, a two-dimensional fusion modeling foundation for occluding structures and crowd behavior patterns within a construction area is established. Compared to previous approaches to traffic safety assessment that rely on plan drawings or static path pre-sets, the present method utilizes panoramic wide-angle cameras and 3D laser scanners in IoT devices to achieve multi-angle real-time data acquisition. This not only captures spatial geometric parameters such as the actual occlusion area Aov and the theoretical visual range Avw of each station, but also accurately extracts the station's primary viewing angle Vag and the pedestrian's direction of travel Dag, as reflected by the crowd's dynamic trajectory. Furthermore, behavioral interaction parameters such as the path intersection angle Xag and the pedestrian flow density per unit time Dpt, calculated based on crowd trajectories, further construct a behavioral feature set reflecting the potential for traffic conflicts. These multi-dimensional parameters, once formed into the structured data set Vfd, provide a highly realistic, quantifiable, and traceable decision-making foundation for subsequent occlusion risk modeling. It is particularly noteworthy that parameters such as the path intersection angle Xag are derived from dynamic trajectory angle calculations and have long been neglected in existing traffic safety technologies. Because they rely on continuous visual perception and directional vector modeling, traditional solutions are difficult to obtain. By integrating such parameters into the dynamic modeling process of construction scenes for the first time, the ability to identify the causes of local occlusion misjudgments and crowd conflict paths has been significantly improved, and it has strong interpretability and high adaptability.

[0025] Example 3: Specifically: S2 includes S21; S21. Perform feature extraction based on the original view data set Vfd. After extracting the structural parameter subset StructSet of each station point, extract the actual obstruction area Aov and the theoretical unobstructed visual range Avw, calculate the obstruction rate Sor of each station point, and quantify the degree of obstruction of each station point by the enclosure structure. The occlusion rate Sor is obtained by the following calculation formula: ; Where Sor(k) represents the occlusion rate of the k-th station, Aov(k) and Avw(k) represent the actual occlusion area Aov and the theoretical unobstructed visual range Avw of the k-th station, respectively.

[0026] Said S2 includes S22; S22. Feature extraction is performed based on the original visual field dataset Vfd. By extracting the behavioral parameter subset BehavSet and the structural parameter subset StructSet of each station point, key dynamic data reflecting the relationship between the crowd behavior path and direction are obtained. Then, the pedestrian flow density per unit time Dpt, the path intersection angle Xag, the passage direction angle Dag, and the main viewing angle Vag of the station point are extracted to construct the path conflict factor Cof and the line of sight ambiguity Blu, which are used as measurement parameters of the behavioral intersection intensity and the visual perception error, respectively. Through angle calculation and density correction, the conflict risk caused by visual occlusion and path overlap of pedestrians in the real construction scene is reflected. Then, it is integrated with the occlusion rate Sor to form a multi-dimensional risk factor, comprehensively modeling the occlusion passage safety status of the station point, and obtaining the occlusion feature vector set Vft. The path conflict factor Cof is obtained using the following calculation formula: ; Where Cof(m, w, k) represents the path conflict factor between path m and path w at the kth station, skn represents the sine function, Dpt(k) represents the pedestrian flow density per unit time at the kth station intersection, Dag(k) represents the travel direction angle at the kth station, and Vag(k) represents the station main viewing direction at the kth station. The denominator is added with 1 to avoid the denominator being zero and to suppress high deviation directions. The actual physical meaning of this formula is: it actually measures: the intersection angle formed between the two paths in the spatial structure × the current pedestrian flow density × the degree of matching between behavior and perspective. When the path intersection angle is large, the pedestrian flow density is high, and the perspective and direction consistency are high, the conflict factor value is the largest, indicating the existence of significant path intersection collision potential. The visual blur Blu is obtained by the following calculation formula: ; Where Blu(k) represents the line of sight blur at the kth station. The actual physical meaning of this formula is that it measures the degree of deviation between the structural visual direction and the actual direction of pedestrian flow at a station. The larger the value, the more inconsistent the line of sight "direction" at this location is with the actual direction of pedestrian flow, which can easily lead to risks such as pedestrians misjudging their paths, failing to see oncoming people, and causing pauses or conflicts.

[0027] In this embodiment, the occlusion rate Sor is constructed by the ratio of the actual occlusion area Aov in the structural parameter subset StructSet to the theoretical unobstructed visual range Avw, which realizes the refined quantification of the degree of occlusion of the station under a specific viewing angle for the first time. The path conflict factor Cof and the line of sight blur Blu are constructed to form an occlusion feature vector set Vft containing three-dimensional risk factors. Not only does it achieve unified modeling of the static occlusion degree and dynamic behavior conflict, but it also makes a breakthrough by incorporating the directional error of pedestrian traffic behavior into the occlusion modeling logic, and has the ability to sensitively capture the path intersection risk, direction judgment confusion and occlusion aggregation trend in high-density areas. Compared with the coarse-grained processing method of traditional solutions that can only perceive "whether there is occlusion or not", the three-factor modeling strategy provides a highly structured and multi-variable expression dimension for occlusion risk, which is particularly suitable for achieving accurate and quantifiable risk pre-assessment in highly dynamic intersection scenarios.

[0028] Example 4: Please refer to Figure 1 and Figure 3 Specifically: S3 includes S31; S31. Normalize the feature vector Vft to eliminate the dimensional differences between different data, obtain the standard path conflict factor Cofn, the standard line of sight blur Blun, and the standard occlusion rate Sorn, and then input them into the occlusion risk scoring model. Perform fusion training with each station k as a unit to construct a comprehensive indicator reflecting the degree of multi-dimensional occlusion risk impact, marked as the comprehensive occlusion view index Ovf(k) of the k-th station. After integrating all stations, obtain the occlusion risk score set OvfList={Ovf(k)|k∈N}, where N represents the total number of stations. The comprehensive occlusion view index Ovf(k) of the k-th station is obtained by the following model fusion training formula: ; Where N(k) represents the number of path pairs at the k-th station, which is calculated by the formula N(k)=|M(k)|*(||M(k)-1) / 2. M represents the total number of paths, Sorn(k) represents the standard occlusion rate of the k-th station, Cofn(k) represents the standard path conflict factor of the k-th station, and Blun(k) represents the standard line of sight ambiguity of the k-th station.

[0029] Example of calculating the comprehensive obstruction view index Ovf(k) at station k=002: Corresponding path set: M(k)={P1,P2,P3}, that is, the number of paths is 3; The possible path pairs are: (P1, P2), (P1, P3), (P2, P3) and (P1, P2), i.e. 3 pairs in total; Therefore, the number of path pairs existing at the kth station point is N(k) = 3; Obtain the standard line of sight blur Blun (k) = 0.46; standard occlusion rate Sorn (k) = 0.58; standard path conflict factor Cofn (k) = {Cofn (P1, P2, k) = 0.71, Cofn (P1, P3, k) = 0.64, Cofn (P2, P3, k) = 0.82}; Substitute the comprehensive occlusion view index Ovf(k) of the k-th station into the following model fusion training formula: Substituting into the summation terms: ∑(0.58+0.71+0.46)+(0.58+0.64+0.46)+(0.58+0.82+0.46)=1.75+168+1.86=5.29; Divide by the number of path pairs: =5.29 / 3≈1.763; Said S4 includes S41; S41. Taking the total number of stations N as the traversal boundary, each comprehensive occlusion view index Ovf(k) in the occlusion risk score set OvfList is judged by comparing it with a preset occlusion risk threshold Tovf, and marking high-risk occlusion stations according to the comparison result. After the traversal is completed, all high-risk occlusion stations are integrated to obtain a high-risk point index set Rls. Stations with high risk of occlusion are marked by comparing: When the comprehensive occlusion view index Ovf (k) is greater than the occlusion risk threshold Tovf, the comparison result is a risk result, and the k-th station is marked as a high-risk occlusion station; When the comprehensive occlusion view index Ovf (k) ≤ the occlusion risk threshold Tovf, the comparison result is normal, the k-th station is not marked as a high-risk occlusion station, and the k-th station is eliminated.

[0030] Said S4 includes S42; S42. Based on the high-risk point index set Rls and combined with the original visual field dataset Vfd of the obstructed high-risk station site, generate a fence structure optimization suggestion for each obstructed high-risk station site. The fence structure optimization suggestion includes adjusting the fence layout form of the obstructed high-risk station site, adjusting the perspective window and translucent visual field area of ​​the obstructed high-risk station site, and adjusting the number of eye-catching signs guiding people to pass through the visual priority channel, and generating a fence structure optimization suggestion list Opl.

[0031] The S5 includes S51; S51. Implementing and applying the enclosure structure optimization suggestion list Opl. The implementation and application includes sending a notification to relevant operators to carry out actual deployment, collecting the original view data set Vfd for each high-risk occlusion site after the actual deployment, calculating and obtaining a new occlusion risk score set OvfList(New) after the actual deployment, and then comparing it with the occlusion risk score set OvfList before the actual deployment. After summarizing the differences, an optimization improvement score Dsc is obtained, and then the effectiveness of the measures after the actual deployment is determined based on the optimization improvement score Dsc. The actual post-deployment measures are judged by the following methods: When the optimization improvement score Dsc>0, it means that the implementation and application of the enclosure structure optimization suggestion list Opl is effective; When the optimization improvement score Dsc≤0, it means that the implementation of the fence structure optimization suggestion list Opl is invalid, and optimization measures such as fence shape adjustment, perspective window setting, prompt sign addition and path visual guidance reconstruction are carried out again.

[0032] In this embodiment, a comprehensive occlusion view index Ovf(k) is constructed by normalizing the multidimensional parameters in the occlusion feature vector set Vft. This achieves a unified scoring scale for the integration of different types of occlusion risk factors, effectively resolving the issue of the lack of quantification and unification between structural occlusion factors and dynamic traffic interference. Relying on the occlusion risk score set OvfList, with the total number of stations N as the index boundary, and based on the set occlusion risk threshold Tovf, high-risk occlusion stations are efficiently screened to form a high-risk point index set Rls. Furthermore, based on the specific structural layout of each risk point in the original view dataset Vfd, a list of recommended enclosure structure optimization recommendations Opl is generated to guide differentiated remediation measures, including enclosure layout adjustments, perspective window modifications, and the addition of guidance prompts. The newly collected occlusion risk score set OvfList(New) is compared with the original score set OvfList to generate an optimization score Dsc, which is used to measure the actual effectiveness of the deployment. This method not only achieves accurate identification of high-occlusion areas, but also forms a risk-strategy-feedback closed-loop path with the comprehensive occlusion view index Ovf(k) as the core. It has dynamic response capabilities and verifiable effects, and is significantly superior to traditional manual experience judgment and single path optimization strategies. It is particularly suitable for urban construction areas with complex visual intersections and severe mixed traffic of people and vehicles, and can achieve continuous self-assessment and strategy regeneration capabilities for construction traffic safety.

[0033] Example 5: A road construction integrated management and control system based on the Internet of Things, please refer to Figure 2 ,Specifically: including road construction network acquisition module, construction feature extraction module, occlusion risk analysis module, occlusion judgment module and iterative optimization module; The road construction network collection module collects spatial structure and crowd traffic behavior data of the road construction area based on the Internet of Things, forming the original view data set Vfd of the construction area; The construction feature extraction module extracts features based on the original visual field dataset Vfd and constructs an occlusion feature vector set Vft, including an occlusion rate Sor, a path conflict factor Cof, and a visual ambiguity Blu; The occlusion risk analysis module inputs the feature vector Vft into the occlusion risk scoring model for training, constructs a comprehensive occlusion view index Ovf, and combines it into an occlusion risk score set OvfList for each station point; The occlusion judgment module uses the preset occlusion risk threshold Tovf to traverse and compare the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the judgment results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; The iterative optimization module applies the enclosure structure optimization suggestion list Opl, and then compares the occlusion risk score set OvfList of the station points before and after the application to obtain the optimization improvement score Dsc.

[0034] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive road construction management and control method based on the Internet of Things, characterized by: The following steps are involved: S1. Based on the Internet of Things, the spatial structure and crowd traffic behavior data of the road construction area are collected, and the structural parameter subset StructSet and the behavioral parameter subset BehavSet are extracted to form the original view data set Vfd of the construction area. S2. After feature extraction based on the original view data set Vfd, the feature vector of each station is calculated to construct an occlusion feature vector set Vft, including the occlusion rate Sor, the path conflict factor Cof, and the line of sight ambiguity Blu; S3. The feature vector Vft is input into the occlusion risk scoring model for training, and a comprehensive occlusion view index Ovf is constructed, which is combined into an occlusion risk score set OvfList for each station point; S4. Using the preset occlusion risk threshold Tovf, perform traversal comparison and determination on the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the determination results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; S5. Implement and apply the enclosure structure optimization suggestion list Opl, and collect a new occlusion risk score set OvfList (New). Then compare it with the occlusion risk score set OvfList of the station site before implementation to obtain the optimization improvement score Dsc. Based on the optimization improvement score Dsc, judge the effectiveness of the measures after implementation.

2. The method for comprehensive road construction management and control based on the Internet of Things according to claim 1, characterized in that: Said S1 includes S11; S11. Collect spatial projection data of road construction area fences and visible range information of station points through IoT devices, extract spatial structural parameters of each station point in the construction area, including actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, and form a structural parameter subset of all station points StructSet={Aov(k), Avw(k), Dag(k), Vag(k)|k∈N}, where N represents the total number of station points, Aov(k), Avw(k), Dag(k), and Vag(k) represent the actual occlusion area Aov, theoretical visible range Avw of the station point, pedestrian passage direction angle Dag, and main viewing direction Vag of the station point, respectively; Among them, IoT devices include panoramic wide-angle cameras and 3D laser scanners; The actual occlusion area Aov is obtained by using a panoramic wide-angle camera and a three-dimensional laser scanner installed above the construction area to obtain real-time projection images of the construction fence at different angles, and extracting the occlusion area boundary through an image processing algorithm, which includes a graphic contour filling algorithm and a point cloud bounding volume division method; The theoretical visible range Avw of the station point is calculated by installing a 3D laser scanner and high-precision mapping equipment deployed at the edge of the construction area. Without considering any obstruction from fences, the laser scan is performed 180° forward of the station point to simulate the maximum visible area. Combined with the existing road structure map, the theoretical open field of view area is calculated by fanning out. The main viewing angle direction Vag of the station point is obtained by presetting the projection ray angle with the station point as the center of the circle and measuring the maximum continuous unobstructed angle from the left and right boundaries; The pedestrian direction angle Dag is obtained by capturing the crowd's movement trajectory through a panoramic wide-angle camera and combining it with the Ak path fitting algorithm to calculate the angle between the crowd's movement trajectory direction and the standing position direction.

3. The method for comprehensive road construction management and control based on the Internet of Things according to claim 2, characterized in that: Said S1 includes S12; S12. Using sensing devices deployed in the road construction area, obtain traffic behavior characteristic data of people in the construction site, extract the behavioral interaction parameters required to build the occlusion conflict analysis model, specifically including the path intersection angle Xag and the pedestrian flow density per unit time Dpt, and form a behavioral parameter subset BehavSet = {Dpt, Xag (m, w) | (m, w) ∈ M*M}, m ≠ w. This is then integrated with the structural parameter subset StructSet to obtain the original viewshed dataset Vfd of the construction area. The path intersection angle Xag is continuously captured by a panoramic wide-angle camera to capture video images; The edge module detects pedestrians and tracks multiple targets in the image. It records the trajectory point sequence of each pedestrian to form a path set {P1, P2, ..., Pm|m∈M}, where M represents the total number of paths and Pm represents the mth path. It then performs a linear fit on each path in the path set to obtain a unit direction vector v. The unit direction vector v of any two paths is calculated to obtain the path intersection angle Xag. The unit direction vector v is obtained by the following calculation formula: ； Where v(m) represents the unit direction vector of the mth path, x(m, end) and y(m, end) as well as x(m, start) and y(m, start) represent the coordinates of the end point and the starting point of the mth path respectively; The path intersection angle Xag is obtained by the following calculation formula: ； Where Xag(m, w) represents the path intersection angle between the mth path and the wth path, and arccos represents the inverse cosine function, which converts the cosine value into an angle value. The pedestrian flow density per unit time Dpt is obtained by the ratio between the number of pedestrians in the road construction area and the time interval within a fixed statistical time window.

4. The method for comprehensive road construction management and control based on the Internet of Things according to claim 3, characterized in that: Said S2 includes S21; S21. Perform feature extraction based on the original view data set Vfd. After extracting the structural parameter subset StructSet of each station point, extract the actual obstruction area Aov and the theoretical unobstructed visual range Avw, calculate the obstruction rate Sor of each station point, and quantify the degree of obstruction of each station point by the enclosure structure. The occlusion rate Sor is obtained by the following calculation formula: ； Where Sor(k) represents the occlusion rate of the k-th station, Aov(k) and Avw(k) represent the actual occlusion area Aov and the theoretical unobstructed visual range Avw of the k-th station, respectively.

5. The method for comprehensive road construction management and control based on the Internet of Things according to claim 4, characterized in that: Said S2 includes S22; S22. Feature extraction is performed based on the original visual field dataset Vfd. By extracting the behavioral parameter subset BehavSet and the structural parameter subset StructSet of each station point, key dynamic data reflecting the relationship between the path and direction of the crowd behavior is obtained. Then, the pedestrian flow density per unit time Dpt, the path intersection angle Xag, the passage direction angle Dag, and the main viewing direction Vag of the station point are extracted to construct the path conflict factor Cof and the visual ambiguity Blu. The results are then integrated with the occlusion rate Sor to obtain the occlusion feature vector set Vft. The path conflict factor Cof is obtained using the following calculation formula: ； Where Cof(m, w, k) represents the path conflict factor between path m and path w at the k-th station, skn represents the sine function, Dpt(k) represents the passenger flow density per unit time at the k-th station intersection, Dag(k) represents the travel direction angle at the k-th station, and Vag(k) represents the main viewing angle of the k-th station. The visual blur Blu is obtained by the following calculation formula: ； Where Blu(k) represents the line of sight ambiguity of the k-th station.

6. The method for comprehensive road construction management and control based on the Internet of Things according to claim 5, characterized in that: Said S3 includes S31; S31. Normalize the feature vector Vft to eliminate the dimensional differences between different data, obtain the standard path conflict factor Cofn, the standard line of sight blur Blun, and the standard occlusion rate Sorn, and then input them into the occlusion risk scoring model. Perform fusion training with each station k as a unit to construct a comprehensive indicator reflecting the degree of multi-dimensional occlusion risk impact, marked as the comprehensive occlusion view index Ovf(k) of the k-th station. After integrating all stations, obtain the occlusion risk score set OvfList={Ovf(k)|k∈N}, where N represents the total number of stations. The comprehensive occlusion view index Ovf(k) of the k-th station is obtained by the following model fusion training formula: ； Where N(k) represents the number of path pairs at the k-th station, which is calculated by the formula N(k)=|M(k)|*(||M(k)-1) / 2. M represents the total number of paths, Sorn(k) represents the standard occlusion rate of the k-th station, Cofn(k) represents the standard path conflict factor of the k-th station, and Blun(k) represents the standard line of sight ambiguity of the k-th station.

7. The method for comprehensive road construction management and control based on the Internet of Things according to claim 6, characterized in that: Said S4 includes S41; S41. Taking the total number of stations N as the traversal boundary, each comprehensive occlusion view index Ovf(k) in the occlusion risk score set OvfList is judged by comparing it with a preset occlusion risk threshold Tovf, and marking high-risk occlusion stations according to the comparison result. After the traversal is completed, all high-risk occlusion stations are integrated to obtain a high-risk point index set Rls. Stations with high risk of occlusion are marked by comparing: When the comprehensive occlusion view index Ovf (k) is greater than the occlusion risk threshold Tovf, the comparison result is a risk result, and the k-th station is marked as a high-risk occlusion station; When the comprehensive occlusion view index Ovf (k) ≤ the occlusion risk threshold Tovf, the comparison result is normal, the k-th station is not marked as a high-risk occlusion station, and the k-th station is eliminated.

8. The method for comprehensive road construction management and control based on the Internet of Things according to claim 7, characterized in that: Said S4 includes S42; S42. Based on the high-risk point index set Rls and combined with the original visual field dataset Vfd of the obstructed high-risk station site, generate a fence structure optimization suggestion for each obstructed high-risk station site. The fence structure optimization suggestion includes adjusting the fence layout form of the obstructed high-risk station site, adjusting the perspective window and translucent visual field area of ​​the obstructed high-risk station site, and adjusting the number of eye-catching signs guiding people to pass through the visual priority channel, and generating a fence structure optimization suggestion list Opl.

9. The method for comprehensive road construction management and control based on the Internet of Things according to claim 1, characterized in that: The S5 includes S51; S51. Implementing and applying the enclosure structure optimization suggestion list Opl. The implementation and application includes sending a notification to relevant operators to carry out actual deployment, collecting the original view data set Vfd for each high-risk occlusion site after the actual deployment, calculating and obtaining a new occlusion risk score set OvfList(New) after the actual deployment, and then comparing it with the occlusion risk score set OvfList before the actual deployment. After summarizing the differences, an optimization improvement score Dsc is obtained, and then the effectiveness of the measures after the actual deployment is determined based on the optimization improvement score Dsc. The actual post-deployment measures are judged by the following methods: When the optimization improvement score Dsc>0, it means that the implementation and application of the enclosure structure optimization suggestion list Opl is effective; When the optimization improvement score Dsc≤0, it means that the implementation of the fence structure optimization suggestion list Opl is invalid, and optimization measures such as fence shape adjustment, perspective window setting, prompt sign addition and path visual guidance reconstruction are carried out again.

10. A road construction integrated management and control system based on the Internet of Things, applied to the road construction integrated management and control method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: It includes road construction network acquisition module, construction feature extraction module, occlusion risk analysis module, occlusion judgment module and iterative optimization module; The road construction network collection module collects spatial structure and crowd traffic behavior data of the road construction area based on the Internet of Things, forming the original view data set Vfd of the construction area; The construction feature extraction module extracts features based on the original visual field dataset Vfd and constructs an occlusion feature vector set Vft, including an occlusion rate Sor, a path conflict factor Cof, and a visual ambiguity Blu; The occlusion risk analysis module inputs the feature vector Vft into the occlusion risk scoring model for training, constructs a comprehensive occlusion view index Ovf, and combines it into an occlusion risk score set OvfList for each station point; The occlusion judgment module uses the preset occlusion risk threshold Tovf to traverse and compare the occlusion risk score set OvfList, obtain all station points marked as high-risk points in the judgment results, form a high-risk point index set Rls, and generate a fence structure optimization suggestion list Opl based on the high-risk point index set Rls; The iterative optimization module applies the enclosure structure optimization suggestion list Opl, and then compares the occlusion risk score set OvfList of the station points before and after the application to obtain the optimization improvement score Dsc.

Images