A method and system for deploying edge sensing nodes in a deterministic network

Abstract

The present invention is applicable to the field of node deployment technology, and in particular to an edge perception node deployment method and system in a deterministic network, the method comprising: drawing a traffic plan in an area, marking intersections, reading the duration of traffic light signals at each of the intersections, defining intersections with durations greater than a preset threshold as high-flow intersections; collecting pedestrian crossing monitoring videos at high-flow intersections within a single traffic light cycle, configuring the corresponding relationship between pedestrian spacing and traffic light travel time, selecting a standard time from the traffic light travel time, and sorting all high-flow intersections in the order of pedestrian spacing from small to large under the standard time to obtain a list of intersection traffic. The present invention can share network resources and reduce the burden of data traffic transmission by determining to read public service signals, and can also offset the deployment position of edge perception nodes, greatly reducing deployment costs and improving deployment flexibility.

Description

Technical Field

[0001] The present invention relates to the field of node deployment technology, and in particular to a method and system for deploying edge perception nodes in a deterministic network. Background Art

[0002] Deterministic networks are typically used in application scenarios that require extremely high reliability and predictability, such as smart transportation, which requires the high stability, low latency, and high reliability characteristics of deterministic networks.

[0003] The deployment of edge perception nodes can ensure that sensors and devices can respond and process data quickly, further reducing latency and improving reliability. For example, edge perception devices (such as cameras, radar sensors, and wireless communication devices) are deployed at multiple intersections, and all edge perception devices are connected through a deterministic network. Data from different intersections can be integrated in real time to form a global view, thereby achieving refined monitoring and management of the entire transportation network.

[0004] However, in the above process, the real-time data collected by the edge sensing device may cause data loss or delay if the bandwidth is insufficient during transmission, affecting the monitoring and processing effects; therefore, "how to determine the deployment location of the edge sensing device and use public service signals for offset and data transmission" is the technical problem that the present invention needs to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for deploying edge sensing nodes in a deterministic network to solve the problem of "how to determine the deployment location of edge sensing devices and use public service signals for offset and data transmission" raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for deploying edge sensing nodes in a deterministic network, the method comprising:

[0008] Draw a traffic plan in the area and mark the intersections, read the duration of the traffic light signal at each intersection, and define the intersections with a duration greater than a preset threshold as high-traffic intersections;

[0009] Collect pedestrian crossing surveillance videos at high-flow intersections within a single traffic light cycle, configure the corresponding relationship between pedestrian spacing and traffic light travel time, select a standard time from the traffic light travel time, and sort all high-flow intersections in the order of pedestrian spacing from small to large under the standard time to obtain a list of intersection pedestrian flows;

[0010] Count the number of edge sensing nodes that need to be deployed, select the same number of high-traffic intersections from the front column of the intersection traffic list, and define them as planning locations, determine the service areas at the planning locations, select several candidate deployment locations, read the public service signals at each of the candidate deployment locations, and compare the best network coverage points in the candidate deployment locations to obtain the target deployment locations.

[0011] Furthermore, the steps of drawing a traffic plan in the area, marking the intersections, reading the duration of the traffic light signal at each intersection, and defining the intersections with a duration greater than a preset threshold as high-traffic intersections include:

[0012] In the traffic plan, time-sensitive facilities are marked, wherein the time-sensitive facilities at least include: schools, office buildings and shopping malls;

[0013] The intersection corresponding to the time-sensitive facility is added to the high-traffic intersection.

[0014] Furthermore, the step of configuring the correspondence between the distance between pedestrians and the traffic light travel time includes:

[0015] According to a preset time step, a plurality of snapshots are captured from the pedestrian crossing monitoring video, and labels generated by the traffic light passing time are inserted into the snapshots;

[0016] Extracting pedestrian features from the snapshot and calculating the distance between pedestrians;

[0017] A corresponding relationship between the snapshot, the traffic light passing time and the pedestrian distance is configured.

[0018] Furthermore, the method further comprises:

[0019] Based on the pedestrian distance, generating an adjustment suggestion for the duration;

[0020] The adjustment suggestion is uploaded to the preset platform.

[0021] Furthermore, the step of selecting a standard time from the traffic light travel time, and sorting all high-flow intersections in the order of pedestrian spacing from small to large under the standard time to obtain an intersection pedestrian flow list includes:

[0022] Based on the corresponding relationship, determining the pedestrian spacing under the standard time;

[0023] Each of the high-flow intersections is divided into a number of traffic directions, and the traffic directions are used to refine the intersection pedestrian flow list.

[0024] Further, the step of reading the public service signal at each of the candidate deployment locations includes:

[0025] Find out the source of the public service signal, obtain control authority, and slice the source;

[0026] Establish a private network channel between the edge sensing node and the source.

[0027] Furthermore, the step of comparing the best network coverage point among the candidate deployment locations to obtain the target deployment location includes:

[0028] Configuring performance parameters of each of the public service signals to determine high-quality signals;

[0029] The target deployment position is offset based on a source corresponding to the high-quality signal.

[0030] Furthermore, the system comprises:

[0031] A definition module is used to draw a traffic plan in the area, mark the intersections, read the duration of the traffic light signal at each intersection, and define the intersection with a duration greater than a preset threshold as a high-traffic intersection;

[0032] A module is obtained, which is used to collect pedestrian crossing monitoring videos at high-flow intersections within a single traffic light cycle, configure the corresponding relationship between the pedestrian spacing and the traffic light travel time, select the standard time from the traffic light travel time, and sort all high-flow intersections according to the order of the pedestrian spacing from small to large under the standard time to obtain a pedestrian flow list at the intersection;

[0033] The statistical module is used to count the number of edge sensing nodes that need to be deployed, select the same number of high-traffic intersections from the front column of the intersection traffic list, and define them as planning locations, determine the service area at the planning location, select several candidate deployment locations, read the public service signal at each candidate deployment location, and compare the best network coverage point in the candidate deployment location to obtain the target deployment location.

[0034] Furthermore, the definition module includes:

[0035] A marking unit, used to mark time-sensitive facilities in the traffic plan, wherein the time-sensitive facilities at least include: schools, office buildings and shopping malls;

[0036] An adding unit, used to add the intersection corresponding to the time-sensitive facility to the high-flow intersection;

[0037] An insertion unit, used to extract a plurality of snapshots from the pedestrian crossing monitoring video according to a preset time step, and insert a label generated by the traffic light passing time into the snapshot;

[0038] A calculation unit, used to extract pedestrian features from the snapshot and calculate the distance between pedestrians;

[0039] The corresponding unit is used to configure the corresponding relationship between the snapshot, the traffic light passing time and the pedestrian distance.

[0040] Furthermore, the obtaining module includes:

[0041] A determination unit, configured to determine the pedestrian spacing under the standard time according to the corresponding relationship;

[0042] The refinement unit is used to divide each of the high-flow intersections into a plurality of traffic directions, and refine the intersection pedestrian flow list using the traffic directions.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By identifying high-traffic intersections, we can prioritize coverage of high-traffic areas, optimize resource allocation, and strengthen public safety monitoring. By building a list of intersection traffic, we can ensure that edge nodes are deployed preferentially at intersections with high traffic, greatly improving the service quality in high-traffic areas. By determining the planned location, we can provide decision support for the deployment of edge perception nodes. By reading public service signals, we can share network resources and reduce the burden of data traffic transmission. At the same time, we can also offset the deployment location of edge perception nodes, greatly reducing deployment costs and ensuring the stability of data transmission in edge perception nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method for deploying edge sensing nodes in a deterministic network provided by an embodiment of the present invention;

[0046] Figure 2 A first sub-flow diagram of a method for deploying edge sensing nodes in a deterministic network provided by an embodiment of the present invention;

[0047] Figure 3 A second sub-flow diagram of the edge sensing node deployment method in a deterministic network provided by an embodiment of the present invention;

[0048] Figure 4 A third sub-flow diagram of the edge sensing node deployment method in a deterministic network provided by an embodiment of the present invention;

[0049] Figure 5A block diagram of the edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention;

[0050] Figure 6 A block diagram of the components of a definition module in an edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention;

[0051] Figure 7 A block diagram of the components of a module in an edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention;

[0052] Figure 8 A block diagram of the composition of a statistical module in an edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In Example 1, Figure 1 The implementation process of the edge sensing node deployment method in a deterministic network provided by an embodiment of the present invention is shown, and is described in detail below:

[0055] S100: Draw a traffic plan in the area and mark the intersections, read the duration of the traffic light signal at each intersection, and define the intersections with a duration greater than a preset threshold as high-traffic intersections.

[0056] Based on the actual road conditions in the area, draw up a traffic plan for the area, and mark the location of each intersection and the roads it connects. Determine the duration of traffic light signals at each intersection through a data acquisition system (such as traffic monitoring cameras, sensors, etc.) or a map service provider. The duration mainly refers to the duration of the red light in each direction. If the red light duration is greater than the preset threshold, it means that the traffic flow at the intersection is large, and there is a high demand for vehicles and pedestrians to cross the street. The intersection is defined as a high-traffic intersection, and the preset threshold is set by professionals.

[0057] S200: Collect monitoring videos of pedestrians crossing the street at high-traffic intersections within a single traffic light cycle, configure the corresponding relationship between the distance between pedestrians and the traffic light travel time, select the standard time from the traffic light travel time, and sort all high-traffic intersections in the order of the distance between pedestrians from small to large under the standard time to obtain a list of pedestrian flows at the intersections.

[0058] Through installed surveillance cameras or drones, etc., pedestrian crossing surveillance videos at high-traffic intersections are collected, and several snapshots are taken from them. The distance between pedestrians in the snapshots and the corresponding traffic light travel time are calculated; the standard time is determined, where the standard time is mainly used to compare the distance between pedestrians at different intersections under the same traffic light travel time; based on the comparison results, all high-traffic intersections are sorted in order of the distance between pedestrians from small to large, and a list of intersection pedestrian flows is obtained.

[0059] For example, there are four intersections A, B, C and D in a certain area. The red light duration of intersection A is 25 seconds, that of intersection B is 45 seconds, that of intersection C is 60 seconds, and that of intersection D is 99 seconds. If the preset threshold is 40 seconds, then intersections B, C and D are defined as high-traffic intersections. In other words, intersections B, C and D have a large flow of people. Pedestrian crossing surveillance videos of intersections B, C and D are collected. When the traffic light at intersection B turns red, the countdown starts from 45 seconds. 45 snapshots are taken in seconds to calculate the The distance between pedestrians in each snapshot; and in this way, the distance between pedestrians in the snapshots of C and D is calculated; when the standard time is 20 seconds, the distance between pedestrians in the 20th snapshot at the intersections of B, C and D is calculated. If the distance between pedestrians at B is about 2 meters, C is about 50 centimeters, and there are no pedestrians at D, it means that the flow of people at intersection C is larger, because there are still many people passing through the intersection 20 seconds after the red light comes on. Then sort them in the order of C-B-D to get the intersection flow list.

[0060] In the above example, there is a great deal of randomness in a single comparison of the four intersections A, B, C and D, and multiple comparisons are required.

[0061] S300: Count the number of edge sensing nodes that need to be deployed, select the same number of high-traffic intersections from the front column of the intersection traffic list, and define them as planning locations, determine the service areas at the planning locations, select several candidate deployment locations, read the public service signals at each of the candidate deployment locations, and compare the best network coverage points in the candidate deployment locations to obtain the target deployment locations.

[0062] According to the pre-established deployment plan, the number of edge sensing nodes that need to be deployed is determined, and the same number of high-traffic intersections are selected from the front of the intersection traffic list and determined as the planned locations. The planned locations are the areas where edge sensing nodes are about to be deployed; however, the specific deployment locations of the edge sensing nodes in the planned locations also need to be determined.

[0063] At the intersection corresponding to the planned location, the service area of ​​the edge perception node to be deployed is determined, and based on the service area, several candidate deployment locations are determined, and the public service signal at each candidate deployment location is read. The optimal network coverage point is determined based on parameters such as the strength, bandwidth, and delay of the public service signal, and the optimal network coverage point is determined as the target deployment location of the edge perception node; the optimal network coverage point is the one with the best public service signal among the candidate deployment locations, and the sources of the public service signal include large facilities such as hotels, shopping malls, and office buildings near the intersection.

[0064] In Example 2, Figure 2 The implementation process of the edge sensing node deployment method in the deterministic network provided by the embodiment of the present invention is shown. The following is a detailed description of the steps of drawing a traffic plan in the area, marking the intersections, reading the duration of the traffic light signal at each intersection, and defining the intersections with a duration greater than a preset threshold as high-traffic intersections, as follows:

[0065] S101: Marking time-sensitive facilities in the traffic plan, wherein the time-sensitive facilities include at least schools, office buildings and shopping malls.

[0066] In the traffic plan, time-sensitive facilities are marked, where the characteristic of time-sensitive facilities is that they may generate a large flow of people during specific periods of time.

[0067] S102: Add the intersection corresponding to the time-sensitive facility to the high-traffic intersection.

[0068] Perform pedestrian flow analysis on the intersections corresponding to time-sensitive facilities, and determine the position of the corresponding intersection in the intersection pedestrian flow list to determine whether it is necessary to deploy an edge perception node at this intersection.

[0069] In Example 3, Figure 2 The implementation process of the edge sensing node deployment method in the deterministic network provided by the embodiment of the present invention is shown. The steps of configuring the corresponding relationship between the pedestrian spacing and the traffic light travel time are described in detail as follows:

[0070] S103: extracting a plurality of snapshots from the pedestrian crossing surveillance video according to a preset time step, and inserting labels generated by the traffic light passing time into the snapshots;

[0071] According to the preset time step, multiple snapshots are captured, where the preset time step is 1 second. If the traffic light passage time is longer, it can also be 5 seconds, or longer; the traffic light passage time corresponding to each snapshot is determined; in other words, a snapshot is captured every 1 second, or a snapshot is captured every 5 seconds.

[0072] S104: Extract pedestrian features from the snapshot and calculate the distance between pedestrians.

[0073] By using image processing technology and deep learning models, the pedestrian features in the snapshots are extracted, and by selecting reference objects and using pixel coordinate calculation methods, the distance between pedestrians in each snapshot is determined.

[0074] S105: configuring a correspondence between the snapshot, the traffic light passing time and the pedestrian distance.

[0075] In Example 4, Figure 3 The implementation process of the edge sensing node deployment method in the deterministic network provided by the embodiment of the present invention is shown. The following is a detailed description of the steps of selecting the standard time from the traffic light travel time, and sorting all high-flow intersections according to the order of pedestrian spacing from small to large under the standard time to obtain the intersection pedestrian flow list, as follows:

[0076] S201: Based on the corresponding relationship, determine the pedestrian distance under the standard time.

[0077] Determine the standard time and the pedestrian distance corresponding to the standard time in each snapshot.

[0078] S202: Divide each of the high-flow intersections into a plurality of traffic directions, and refine the intersection pedestrian flow list using the traffic directions.

[0079] In real life, there may be a situation where the pedestrian flow in a single direction at a certain intersection is large, but the pedestrian flow in the other three directions is small; therefore, the high-flow intersection can be divided into 3 or 4 or more traffic directions, and the number of traffic directions is determined by the type of high-flow intersection. If the high-flow intersection is T-shaped, there are 3 traffic directions, and if the high-flow intersection is cross-shaped, there are 4 traffic directions.

[0080] In Example 5, Figure 4 The implementation process of the edge sensing node deployment method in the deterministic network provided by the embodiment of the present invention is shown. The steps of reading the public service signal at each candidate deployment location are described in detail as follows:

[0081] S301: Find out the source of the public service signal, obtain control authority, and slice the source.

[0082] Identify and locate the facilities or equipment that provide public service signals, which are defined as sources. The sources can be shopping malls, hotels, or street stores, etc., and obtain control over the sources through authorization, agreement, or cooperation. Divide the public service signals into multiple independent subsets or time periods so that they can be flexibly managed and scheduled according to different needs. For example, divide the public service signals into multiple slices, and only use fewer slices during daily periods, so as to ensure that the facilities corresponding to the source can use network services normally while transmitting data to the edge sensing nodes.

[0083] S302: Building a private network channel between the edge sensing node and the source.

[0084] Build a private network channel to ensure the security of data transmission in edge sensing nodes.

[0085] In Example 6, Figure 4 The implementation process of the edge sensing node deployment method in the deterministic network provided by the embodiment of the present invention is shown. The steps of reading the public service signal at each candidate deployment location are described in detail as follows:

[0086] S303: Configure performance parameters of each of the public service signals to determine a high-quality signal.

[0087] When there are multiple public service signals at the candidate deployment location, performance parameters including signal strength, bandwidth, delay, throughput, packet loss rate, and signal-to-noise ratio are collected, and high-quality signals are determined from the public service signals.

[0088] S304: offset the target deployment position based on the source corresponding to the high-quality signal.

[0089] The location (source) of the high-quality signal is determined, and based on this location, the target deployment location of the edge sensing node is offset, so that the target deployment location is closer to the public service signal with excellent performance parameters.

[0090] In Example 7, different from Example 1, in this embodiment of the present invention, the method further includes:

[0091] Based on the pedestrian distance, generating an adjustment suggestion for the duration;

[0092] The adjustment suggestion is uploaded to the preset platform.

[0093] Based on the distance between pedestrians, the adjustment suggestions for the duration of the red light are determined and uploaded to a preset platform, which can be a traffic management department platform; for example, the red light duration at a certain intersection is 40 seconds, but 35 seconds after the red light comes on, the distance between pedestrians is still less than 50 centimeters, which means that the intersection has a large flow of people and the red light duration should be increased to ensure that pedestrians have enough time to pass through the intersection.

[0094] Figure 5 The structure block diagram of the edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention is shown. The edge sensing node deployment system 1 in the deterministic network includes:

[0095] A definition module 11 is used to draw a traffic plan in the area, mark the intersections, read the duration of the traffic light signal at each intersection, and define the intersection with a duration greater than a preset threshold as a high-traffic intersection;

[0096] Obtaining module 12, for collecting pedestrian crossing monitoring videos at high-flow intersections within a single traffic light cycle, configuring the corresponding relationship between the distance between pedestrians and the traffic light travel time, selecting a standard time from the traffic light travel time, and sorting all high-flow intersections in the order of the distance between pedestrians from small to large under the standard time, to obtain a list of intersection pedestrian flows;

[0097] The statistical module 13 is used to count the number of edge sensing nodes that need to be deployed, select the same number of high-traffic intersections from the front column of the intersection traffic list, and define them as planning locations, determine the service area at the planning location, select several candidate deployment locations, read the public service signal at each of the candidate deployment locations, and compare the best network coverage point in the candidate deployment locations to obtain the target deployment location.

[0098] Figure 6 The structure diagram of the edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention is shown, and the definition module 11 includes:

[0099] A marking unit 111 is used to mark time-sensitive facilities in the traffic plan, wherein the time-sensitive facilities at least include: schools, office buildings and shopping malls;

[0100] An adding unit 112, configured to add the intersection corresponding to the time-sensitive facility to the high-flow intersection;

[0101] The inserting unit 113 is used to extract a plurality of snapshots from the pedestrian crossing monitoring video according to a preset time step, and insert a label generated by the traffic light passing time into the snapshot;

[0102] A calculation unit 114, configured to extract pedestrian features from the snapshot and calculate the distance between pedestrians;

[0103] The corresponding unit 115 is used to configure the corresponding relationship between the snapshot, the traffic light passing time and the pedestrian distance.

[0104] Figure 7 The structure diagram of the edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention is shown, and the obtaining module 12 includes:

[0105] A determination unit 121, configured to determine the pedestrian spacing under the standard time according to the corresponding relationship;

[0106] The refinement unit 122 is used to divide each of the high-flow intersections into a plurality of traffic directions, and refine the intersection pedestrian flow list using the traffic directions.

[0107] Figure 8 The structure block diagram of the edge sensing node deployment system in a deterministic network provided by an embodiment of the present invention is shown, and the statistical module 13 includes:

[0108] The slicing unit 131 is used to find out the source of the public service signal, obtain control authority, and slice the source;

[0109] A building unit 132 is used to build a private network channel between the edge sensing node and the source

[0110] The corresponding unit 133 is used to configure the performance parameters of each of the public service signals to determine a high-quality signal;

[0111] The offset unit 134 is configured to offset the target deployment position according to a source corresponding to the high-quality signal.

[0112] The definition module 11 is mainly used to complete step S100, the acquisition module 12 is mainly used to complete step S200, and the statistics module 13 is mainly used to complete step S300;

[0113] The marking unit 111 is mainly used to complete step S101, the adding unit 112 is mainly used to complete step S102, the inserting unit 113 is mainly used to complete step S103, the calculating unit 114 is mainly used to complete step S104, and the corresponding unit 115 is mainly used to complete step S105;

[0114] The determination unit 121 is mainly used to complete step S201, and the refinement unit 122 is mainly used to complete step S202;

[0115] The slicing unit 131 is mainly used to complete step S301, the building unit 132 is mainly used to complete step S302, the corresponding unit 133 is mainly used to complete step S303, and the offset unit 134 is mainly used to complete step S304.

[0116] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0118] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for deploying edge sensing nodes in a deterministic network, characterized in that: The method comprises: Draw a traffic plan in the area and mark the intersections, read the duration of the traffic light signal at each intersection, and define the intersections with a duration greater than a preset threshold as high-traffic intersections; Collect pedestrian crossing surveillance videos at high-flow intersections within a single traffic light cycle, configure the corresponding relationship between pedestrian spacing and traffic light travel time, select a standard time from the traffic light travel time, and sort all high-flow intersections in the order of pedestrian spacing from small to large under the standard time to obtain a list of intersection pedestrian flows; Count the number of edge sensing nodes that need to be deployed, select the same number of high-traffic intersections from the front column of the intersection traffic list, and define them as planning locations, determine the service area at the planning location, select a number of candidate deployment locations, read the public service signal at each of the candidate deployment locations, and compare the best network coverage point in the candidate deployment location to obtain the target deployment location, wherein the source of the public service signal includes at least: hotels, shopping malls and office buildings near the intersection; The step of reading the public service signal at each candidate deployment location comprises: Find out the source of the public service signal, obtain control authority, and divide the public service signal into multiple subsets or time periods; Building a private network channel between the edge sensing node and the source; The step of comparing the best network coverage point among the candidate deployment locations to obtain the target deployment location includes: Collecting performance parameters of each of the public service signals to determine high-quality signals; The target deployment position is offset based on a source corresponding to the high-quality signal.

2. The method for deploying edge sensing nodes in a deterministic network according to claim 1, characterized in that: The steps of drawing a traffic plan in the area, marking the intersections, reading the duration of the traffic light signal at each intersection, and defining the intersections with a duration greater than a preset threshold as high-traffic intersections include: In the traffic plan, time-sensitive facilities are marked, wherein the time-sensitive facilities at least include: schools, office buildings and shopping malls; The intersection corresponding to the time-sensitive facility is added to the high-traffic intersection.

3. The method for deploying edge sensing nodes in a deterministic network according to claim 1, characterized in that: The step of configuring the correspondence between the distance between pedestrians and the traffic light travel time comprises: According to a preset time step, a plurality of snapshots are captured from the pedestrian crossing monitoring video, and labels generated by the traffic light passing time are inserted into the snapshots; Extracting pedestrian features from the snapshot and calculating the distance between pedestrians; A corresponding relationship between the snapshot, the traffic light passing time and the pedestrian distance is configured.

4. The method for deploying edge sensing nodes in a deterministic network according to claim 3, characterized in that: The method further comprises: Based on the pedestrian distance, generating an adjustment suggestion for the duration; The adjustment suggestion is uploaded to the preset platform.

5. The method for deploying edge sensing nodes in a deterministic network according to claim 1, characterized in that: The step of selecting a standard time from the traffic light travel time, and sorting all high-flow intersections in the order of pedestrian distance from small to large under the standard time to obtain an intersection pedestrian flow list comprises: Based on the corresponding relationship, determining the pedestrian spacing under the standard time; Each of the high-flow intersections is divided into a number of traffic directions, and the traffic directions are used to refine the intersection pedestrian flow list.

Images