A pedestrian passage management method, system and storage medium based on big data

Abstract

The embodiment of the present application relates to the field of traffic management technology, and discloses a pedestrian passage management method, system and storage medium based on big data. The pedestrian passage management method based on big data of the present application controls the traffic indicator light of the target pedestrian passage to extend the green light passage time when the real-time vehicle traffic flow of the target pedestrian passage is less than the vehicle traffic flow threshold. In this way, by reducing the waiting time of pedestrians in the rain and improving the pedestrian traffic efficiency, the pedestrian traffic safety and comfort in rainy days are enhanced, while minimizing the interference with vehicle traffic.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to a pedestrian passage management method, system and storage medium based on big data. Background Art

[0002] As urbanization continues to accelerate, urban road traffic systems are facing increasingly severe challenges, especially in severe weather conditions, such as rainy days, where the safety and efficiency of pedestrian and vehicle traffic are particularly prominent. Rainy days not only reduce the road friction coefficient and increase the risk of vehicle driving, but also make pedestrians, especially those without rain gear, face greater difficulties and safety hazards. Traditional traffic light control systems often switch signals based on fixed time intervals, lack the ability to flexibly respond to real-time traffic conditions and weather conditions, and are unable to meet the complex and changeable traffic needs of pedestrians and vehicles under rainy conditions. Summary of the invention

[0003] The main purpose of the present invention is to provide a pedestrian passage traffic management method, system and storage medium based on big data, aiming to solve the technical problem that pedestrian passage traffic management in the prior art is difficult to meet the complex and changeable traffic needs of pedestrians and vehicles under rainy conditions.

[0004] To achieve the above-mentioned purpose, in a first aspect, an embodiment of the present application provides a pedestrian passage management method based on big data, which is applied to a pedestrian passage management system, wherein the pedestrian passage management system includes a camera device, a rain sensor and a traffic light arranged on the side of the pedestrian passage, and the method includes:

[0005] When the rain sensor detects that the rainfall at the target pedestrian passage is greater than or equal to the rainfall threshold, obtaining pedestrian information in the pedestrian waiting area of ​​the target pedestrian passage, wherein the pedestrian information includes the number of pedestrians and the proportion of pedestrians wearing rain gear;

[0006] Determine that the number of pedestrians is greater than or equal to a pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to a proportion threshold, and obtain the historical vehicle traffic flow of the target pedestrian passage in the current time period based on big data;

[0007] Correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period;

[0008] It is determined that the real-time vehicle traffic flow of the target pedestrian passage is less than a vehicle traffic flow threshold, and the traffic indicator light of the target pedestrian passage is controlled to extend the green light passage time.

[0009] In a possible implementation, the method further includes: determining that the real-time vehicle traffic flow of the target pedestrian passage is greater than or equal to a vehicle traffic flow threshold, and reducing the vehicle traffic flow merging into the target pedestrian passage from an upstream intersection.

[0010] In a possible implementation, reducing the traffic volume of vehicles merging into the target pedestrian passage at the upstream intersection includes:

[0011] Determine multiple candidate travel paths according to the current position and target position of the vehicle to be merged into the target pedestrian passage at the upstream intersection;

[0012] Allocating different travel weights to the plurality of candidate travel paths to obtain a target travel path;

[0013] The target traffic path and warning information are sent to vehicles at an upstream intersection that are about to merge into the target pedestrian passage. The warning information is used to prompt the driver to select the target traffic path for detour driving to reduce the traffic flow of vehicles merging into the target pedestrian passage at the upstream intersection.

[0014] In a possible implementation, the obtaining pedestrian information in a pedestrian waiting area of ​​the target pedestrian passage includes:

[0015] Acquire a target image captured by the camera device in a pedestrian waiting area of ​​the target pedestrian passage;

[0016] Performing target object recognition on the target image based on semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage;

[0017] Performing contour line extraction on the area above the head of each target object in the target image to obtain a first contour line, and performing contour line extraction on the area below the head of each target object in the target image to obtain a second contour line;

[0018] Matching the first contour line with a preset first reference contour line to obtain a first matching similarity, and matching the second contour line with a preset second reference contour line to obtain a second matching similarity;

[0019] Determine the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity;

[0020] The proportion of pedestrians wearing rain gear in the pedestrian waiting area of ​​the target pedestrian passage is determined according to the rain gear wearing status of each target object.

[0021] In a possible implementation, the performing target object recognition on the target image based on the semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage includes:

[0022] Determine that a difference between the number of pixels of a target semantic category of a first target object in the target image and the number of pixels of a target semantic category of a second target object in the target image is greater than a preset difference, and control the camera device to rotate in a preset direction;

[0023] After the camera device rotates in a preset direction, the difference between the number of pixels of the target semantic category of the first target object in the target image and the number of pixels of the target semantic category of the second target object in the target image is re-determined to be narrowed to a preset range, and the first target object and the second target object are determined to be pedestrians and the number of pedestrians is counted.

[0024] In a possible implementation, determining the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity includes:

[0025] Preliminarily determining the type of rain gear worn by the target object according to the first matching similarity and the second matching similarity;

[0026] Allocating the influence weights of the first matching similarity and the second matching similarity on the target matching similarity according to the type of rain gear;

[0027] Obtaining a target matching similarity according to the first matching similarity, the second matching similarity and the corresponding influence weights;

[0028] The rain gear wearing status of each target object is determined according to the target matching similarity.

[0029] In a possible implementation, allocating the influence weights of the first matching similarity and the second matching similarity on the target matching similarity according to the rain gear type includes:

[0030] When the initially determined type of rain gear is an umbrella or a rain hat, determining that the influence weight of the first matching similarity on the target matching similarity is greater than the influence weight of the second matching similarity on the target matching similarity;

[0031] When the initially determined type of rain gear is a raincoat, it is determined that the influence weight of the first matching similarity on the target matching similarity is less than the influence weight of the second matching similarity on the target matching similarity.

[0032] In a possible implementation, the correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period includes:

[0033] Obtaining the proportion of traffic from the upstream intersection merging into the target pedestrian passage and the distance between the upstream intersection and the target pedestrian passage;

[0034] Determine that the proportion of traffic from the upstream intersection merging into the target pedestrian passage is greater than or equal to a traffic proportion threshold, and that the distance between the upstream intersection and the target pedestrian passage is less than or equal to a distance threshold, and perform a positive correction on the historical vehicle traffic flow to obtain a real-time vehicle traffic flow in the current time period;

[0035] Determine that the proportion of traffic from the upstream intersection merging into the target pedestrian passage is less than a traffic proportion threshold, or that the distance between the upstream intersection and the target pedestrian passage is greater than a distance threshold, and perform a negative correction on the historical vehicle traffic flow to obtain the real-time vehicle traffic flow for the current time period.

[0036] In the second aspect, an embodiment of the present application also provides a pedestrian passage management system, including: a camera device, a rain sensor and a traffic light arranged on the side of the pedestrian passage, and also includes a memory and a processor, the memory is used to store program code, and the processor is used to call the program code to execute the method described in the first aspect.

[0037] In a third aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are performed.

[0038] Different from the prior art, the pedestrian passage management method based on big data provided by the embodiment of the present application first uses a rain sensor to monitor the rainfall at the target pedestrian passage in real time. When the rainfall reaches or exceeds the preset rainfall threshold, it indicates that the current environment has a certain impact on the passage of pedestrians (especially pedestrians who do not carry rain gear). Then, the number of pedestrians and the proportion of rain gear wearing in the pedestrian waiting area are obtained by image recognition and other technical means. If the number of pedestrians and the proportion of rain gear wearing meet the preset conditions at the same time, it indicates that there are currently a large number of pedestrians who need to pass through the pedestrian passage quickly and safely, and most of them may not have made sufficient rain protection preparations and have high requirements for the passage time. Then, the big data platform is used to query and obtain the historical vehicle traffic flow of the target pedestrian passage in the current time period as a reference for evaluating the current traffic conditions. Considering the dynamic variability of traffic flow, the system also performs real-time correction of the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain a more accurate real-time vehicle traffic flow in the current time period. Finally, when it is confirmed that the real-time vehicle traffic flow is lower than the preset vehicle traffic flow threshold and there are a large number of pedestrians who urgently need to cross the pedestrian passage, the system automatically extends the green light duration by controlling the traffic lights of the target pedestrian passage. In this way, by reducing the waiting time of pedestrians in the rain and improving the efficiency of pedestrian passage, the safety and comfort of pedestrian passage in rainy conditions are enhanced, while minimizing the interference with vehicle passage. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of the state of the pedestrian passage traffic plane layout in some embodiments of the present application;

[0041] Figure 2 This is a flow chart of a pedestrian passage management method based on big data in some embodiments of the present application;

[0042] Figure 3 This is a flow chart of step S300 of the pedestrian passage management method based on big data in some embodiments of the present application;

[0043] Figure 4 This is a schematic diagram of the hardware structure of the pedestrian passage management system in some embodiments of the present application.

[0044] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0047] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0048] As urbanization continues to accelerate, urban road traffic systems are facing increasingly severe challenges, especially in severe weather conditions, such as rainy days, where the safety and efficiency of pedestrian and vehicle traffic are particularly prominent. Rainy days not only reduce the road friction coefficient and increase the risk of vehicle driving, but also make pedestrians, especially those without rain gear, face greater difficulties and safety hazards. Traditional traffic light control systems often switch signals based on fixed time intervals, lack the ability to flexibly respond to real-time traffic conditions and weather conditions, and are unable to meet the complex and changeable traffic needs of pedestrians and vehicles under rainy conditions.

[0049] In response to the above problems, the present application proposes a pedestrian passage management method based on big data, which is applied to a pedestrian passage traffic management system, which includes a camera device 100, a rain sensor 200 and a traffic light 300 arranged on the side of the pedestrian passage. The camera device 100 is used to intelligently identify pedestrians in the pedestrian waiting area, such as identifying the number of pedestrians and / or the wearing of rain gear by pedestrians; the rain sensor 200 is used to detect the amount of rainfall, for example, it can be a rain sensor based on optical principles; the traffic light 300 is used to indicate whether pedestrians can pass or are prohibited from passing in the target pedestrian passage.

[0050] Specifically, the camera device 100, the rain sensor 200 and the traffic light 300 can all be installed at a position higher than the road surface, such as a street light pole, a traffic sign pole or a special bracket. In one embodiment, the camera device 100, the rain sensor 200 and the traffic light 300 are all installed on the light pole of the traffic light, thereby reducing the installation cost.

[0051] like Figure 1 As shown, Figure 1 The schematic diagram of the state of the pedestrian passage traffic plane layout in some embodiments of the present application. In the figure, RT is the pedestrian passage, RD is the pedestrian waiting area of ​​the pedestrian passage, SL is the upstream intersection, and L is the distance between the target pedestrian passage and the upstream intersection.

[0052] like Figure 1-Figure 3 As shown, the following takes the pedestrian passage management system executing the pedestrian passage management method based on big data as an example for explanation. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order from here. Figure 2 The method includes the following steps S100 to S400:

[0053] Step S100, when the rain sensor detects that the rainfall at the target pedestrian passage is greater than or equal to the rainfall threshold, obtaining pedestrian information in the pedestrian waiting area of ​​the target pedestrian passage, wherein the pedestrian information includes the number of pedestrians and the proportion of pedestrians wearing rain gear;

[0054] Specifically, the embodiment of the present application first uses the rain sensor 200 to monitor the rainfall at the target pedestrian passage in real time, and the monitoring data of the rain sensor 200 provides data support for subsequent intelligent decision-making. When it is detected that the rainfall reaches or exceeds the preset rainfall threshold, it indicates that the current environment has a certain impact on the passage of pedestrians, especially pedestrians who are not carrying rain gear. That is, pedestrians who are not carrying rain gear need to pass through the target pedestrian passage as soon as possible to reach the target location to avoid the rain. Subsequently, the pedestrian information in the pedestrian waiting area can be obtained through technical means such as image recognition and infrared sensing. The pedestrian information includes the number of pedestrians and the proportion of pedestrians wearing rain gear. The accuracy of pedestrian information provides accurate data support for subsequent intelligent decision-making.

[0055] In one embodiment, the step of: obtaining pedestrian information in a pedestrian waiting area of ​​the target pedestrian passage comprises: obtaining a target image captured by the camera device in the pedestrian waiting area of ​​the target pedestrian passage; performing target object recognition on the target image based on semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage; performing contour line extraction on an area above the head of each target object in the target image to obtain a first contour line, and performing contour line extraction on an area below the head of each target object in the target image to obtain a second contour line; matching the first contour line with a preset first reference contour line to obtain a first matching similarity, and matching the second contour line with a preset second reference contour line to obtain a second matching similarity; determining the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity; determining the rain gear wearing ratio of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage according to the rain gear wearing status of each target object.

[0056] Specifically, the embodiment of the present application first uses a camera device 100 installed in the pedestrian waiting area of ​​the target pedestrian passage to capture images of the area regularly or in real time to obtain a target image. During the shooting process of the camera device, it is ensured as much as possible that the viewing angle, resolution and light conditions of the camera device 100 can clearly capture the full body features of the pedestrian. Then, semantic segmentation technology (such as DeepLab, Mask R-CNN, etc.) is applied to process the collected target image to distinguish different objects in the image (such as pedestrians, buildings, trees, etc.). Through semantic segmentation, the pedestrian part in the image is extracted, and the total number of pedestrians in the pedestrian waiting area is calculated. For each identified pedestrian target, image processing is further performed to extract the contours above the head (first contour line) and below the head (second contour line). The part above the head usually includes a rain hat, an umbrella, etc. that may indicate the wearing of rain gear, and the part below the head usually includes a raincoat, etc. that may indicate the wearing of rain gear. The preset first reference contour line can be the contour line of a common rain hat or umbrella, and the second reference contour line can be the contour line of a raincoat. The first contour line of each pedestrian target is matched with the first reference contour line, and the matching similarity is calculated (such as using the Hausdorff distance between contours); similarly, the second contour line is matched with the second reference contour line, and the second matching similarity is calculated. Then, it can be determined whether each pedestrian is wearing rain gear according to the threshold judgment of the first matching similarity and the second matching similarity. For example, if the first matching similarity is higher than a certain threshold, it can be considered that the pedestrian is wearing a rain hat or umbrella; if the second matching similarity is also high, it may be further confirmed that he is wearing a raincoat. Comprehensively considering the first matching similarity and the second matching similarity, the wearing of pedestrians' rain gear can be more accurately judged. If the first matching similarity and the second matching similarity are both low, it can be considered that the pedestrian is neither wearing a rain hat or umbrella nor a raincoat. In this way, the number of pedestrians wearing rain gear is counted, and the number of pedestrians wearing rain gear is divided by the total number of pedestrians to obtain the proportion of pedestrians wearing rain gear.

[0057] It is understandable that since the camera device 100 cannot take into account the 360° shooting range, there are certain shooting blind spots, that is, the camera device 100 cannot capture the full body features of all pedestrians in the pedestrian waiting area of ​​the target pedestrian passage. Therefore, if a small number of pixels of a target object are detected as pedestrian targets based on semantic segmentation technology, it is necessary to further determine whether the target object is a pedestrian target to improve the accuracy of target detection. Based on this, in one embodiment, the step of: performing target object recognition on the target image based on semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage includes:

[0058] Determine that a difference between the number of pixels of a target semantic category of a first target object in the target image and the number of pixels of a target semantic category of a second target object in the target image is greater than a preset difference, and control the camera device to rotate in a preset direction;

[0059] After the camera device rotates in a preset direction, the difference between the number of pixels of the target semantic category of the first target object in the target image and the number of pixels of the target semantic category of the second target object in the target image is re-determined to be narrowed to a preset range, and the first target object and the second target object are determined to be pedestrians and the number of pedestrians is counted.

[0060] Specifically, the embodiment of the present application first uses semantic segmentation technology to perform a deep analysis on the target image captured by the camera device 100 to distinguish and identify various target objects in the image and their corresponding semantic categories, including but not limited to pedestrians, vehicles, buildings, etc. In this initial stage, the system can identify all potential pedestrian target objects in the target image. However, due to the viewing angle limitation or shooting blind spot of the camera device 100, some pedestrian target objects may be only partially captured in the picture, which causes these objects to show only a small number of pedestrian feature pixels in the result of semantic segmentation. In contrast, those pedestrian target objects that are completely captured will have more pedestrian feature pixels. In order to accurately distinguish these suspected pedestrian target objects from the real pedestrian target objects, the present application introduces a comparison mechanism. Specifically, the system calculates the difference between the number of pedestrian feature pixels of each suspected pedestrian target object (such as the first target object) and the number of pedestrian feature pixels of the known complete or relatively complete pedestrian target object (such as the second target object, which has a large number of pedestrian feature pixels) in the image. If the difference exceeds the preset difference threshold, the system will infer that the reason why the first target object only contains a small number of pedestrian feature pixels is probably because the camera's perspective fails to capture it completely. To compensate for this deficiency, the system will then control the camera 100 to rotate and adjust in a preset direction (such as left, right, up or down) in the hope of capturing the target object more completely under the new perspective. After the camera adjusts its position and reshoots, the system again applies the semantic segmentation technology to process the new target image and recalculates the difference between the number of pedestrian feature pixels of the suspected pedestrian target object and the number of pedestrian feature pixels of other target objects in the image. If the difference calculated this time has been reduced to within the preset range, the system will confirm that the adjusted camera 100 has successfully captured the suspected pedestrian target object more completely in the picture, and these objects now do have enough pedestrian feature pixels, so they can be formally identified as pedestrian target objects. Once a target object is confirmed to be a pedestrian, the system will count it in the pedestrian count. In this way, by dynamically adjusting the shooting angle of the camera device and re-detecting, the system can more accurately count the number of pedestrians in the waiting area of ​​the pedestrian passage.

[0061] In one embodiment, in order to further improve the accuracy of monitoring the rain gear wearing status of the target object, the step of determining the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity includes:

[0062] Preliminarily determining the type of rain gear worn by the target object according to the first matching similarity and the second matching similarity;

[0063] Allocating the influence weights of the first matching similarity and the second matching similarity on the target matching similarity according to the type of rain gear;

[0064] Obtaining a target matching similarity according to the first matching similarity, the second matching similarity and the corresponding influence weights;

[0065] The rain gear wearing status of each target object is determined according to the target matching similarity.

[0066] Specifically, since umbrellas and rain hats mainly cover the head area, the first matching similarity (the area above the head) is more critical for judging the wearing condition of these two types of rain gear. Therefore, when the type of rain gear is an umbrella or a rain hat, the influence weight assigned to the first matching similarity should be greater than the influence weight of the second matching similarity. Since raincoats cover the whole body, especially the area below the head, the second matching similarity (the area below the head) is more important in judging the wearing condition of raincoats. Therefore, when the type of rain gear is a raincoat, the influence weight assigned to the second matching similarity should be greater than the influence weight of the first matching similarity.

[0067] For example, if the matching similarity of a target pedestrian wearing a rain hat or umbrella is 60% through image detection, and the matching similarity of wearing a raincoat is 40%, since the first matching similarity is greater than the second matching similarity, the system preliminarily determines the type of rain gear worn by the target pedestrian as an umbrella or rain hat. At this time, the influence weight assigned to the first matching similarity should be greater than the influence weight of the second matching similarity, for example, an influence weight of 80% is assigned to the first matching similarity, and an influence weight of 20% is assigned to the second matching similarity. Then, the first matching similarity and the second matching similarity are combined according to their corresponding influence weights using the weighted average method to obtain a target matching similarity = 60% * 80% + 40% * 20% = 56%. At this time, since the target matching similarity is greater than 50%, the type of rain gear worn by the target pedestrian is finally determined to be an umbrella or rain hat. If the target matching similarity finally calculated is less than 50%, the type of rain gear worn by the target pedestrian cannot be determined as an umbrella or rain hat, that is, it is determined that the target pedestrian is not wearing rain gear.

[0068] Step S200: determining that the number of pedestrians is greater than or equal to a pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to a proportion threshold, and obtaining the historical vehicle traffic flow of the target pedestrian passage in the current time period based on big data;

[0069] Specifically, when it is determined that the number of pedestrians is greater than or equal to the preset pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to the set proportion threshold, it means that the pedestrian flow in the current target pedestrian passage is large, and most pedestrians may not be well prepared for rain. Therefore, in order not to affect the passage of vehicles, necessary measures can be taken to allow pedestrians who are not prepared for rain to pass as quickly as possible to find a target place to hide from the rain, thereby improving the pedestrian experience and safety in a rainy environment.

[0070] Therefore, when it is determined that the number of pedestrians is greater than or equal to the pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to the proportion threshold, the historical vehicle traffic flow of the target pedestrian channel in the current time period can be obtained based on big data to provide accurate data support for whether to extend the green light duration in the future. The vehicle traffic flow represents the number of vehicles passing within a preset time period (such as every hour, every half hour, etc.). The larger the vehicle traffic flow, the heavier the vehicle traffic task of the road section, and the less time can be given to pedestrians to pass. Conversely, more time can be given to pedestrians to pass.

[0071] Step S300: Correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period;

[0072] In one embodiment, the step S300: correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period includes:

[0073] S310, obtaining the proportion of traffic flow from the upstream intersection merging into the target pedestrian passage and the distance between the upstream intersection and the target pedestrian passage;

[0074] S320, determining that the proportion of the traffic flow from the upstream intersection merging into the target pedestrian passage is greater than or equal to a traffic flow proportion threshold, and that the distance between the upstream intersection and the target pedestrian passage is less than or equal to a distance threshold, and performing a positive correction on the historical vehicle traffic flow to obtain a real-time vehicle traffic flow in the current time period;

[0075] S330, determining that the proportion of traffic from the upstream intersection merging into the target pedestrian passage is less than a traffic proportion threshold, or that the distance between the upstream intersection and the target pedestrian passage is greater than a distance threshold, and performing a negative correction on the historical vehicle traffic flow to obtain the real-time vehicle traffic flow for the current time period.

[0076] Specifically, the embodiment of the present application first obtains the traffic flow ratio of the upstream intersection traffic flow merging into the target pedestrian passage through a traffic monitoring system or a data analysis platform. This ratio reflects how much of the vehicles at the upstream intersection will flow to the target area. At the same time, the actual distance between the upstream intersection and the target pedestrian passage is obtained, and this distance is a key factor in evaluating the impact range of the traffic flow merging. Then it is determined whether the obtained traffic flow ratio is greater than or equal to the preset traffic flow ratio threshold. This threshold is used to determine whether the traffic flow at the upstream intersection has a significant contribution to the vehicle traffic flow in the target area. At the same time, it is checked whether the distance between the upstream intersection and the target pedestrian passage is less than or equal to the preset distance threshold. This distance threshold is used to ensure that the traffic flow at the upstream intersection can reach and affect the vehicle traffic flow in the target area within a reasonable time. If the traffic flow ratio of the upstream intersection traffic flow merging into the target pedestrian passage is greater than or equal to the traffic flow ratio threshold, and the distance between the upstream intersection and the target pedestrian passage is less than or equal to the distance threshold, it means that the traffic flow at the upstream intersection has a significant and direct impact on the vehicle traffic flow of the target pedestrian passage. Therefore, it is necessary to perform a positive correction on the historical vehicle traffic flow. For example, based on the traffic ratio and distance factors, a correction factor or correction value can be appropriately added on the basis of the historical vehicle traffic flow to obtain the real-time vehicle traffic flow in the current time period. If the traffic ratio is less than the traffic ratio threshold, or the distance between the upstream intersection and the target pedestrian passage is greater than the distance threshold, it means that the traffic at the upstream intersection has little or no direct impact on the vehicle traffic flow in the target area. In this case, it is necessary to make a negative correction to the historical vehicle traffic flow or keep it unchanged. Negative correction can reduce a correction factor or correction value based on the historical vehicle traffic flow according to the specific situation. For example, if the impact is very small or no, the historical vehicle traffic flow is directly used as an approximation of the real-time vehicle traffic flow in the current time period. However, in some cases, for conservative estimation, the historical traffic value can be slightly reduced to reflect potential uncertainties or changes. In this way, the accuracy and reliability of the real-time vehicle traffic flow calculation can be ensured to provide more accurate data support for subsequent decisions on whether to extend the green light passage time.

[0077] It should be noted that the present application does not directly rely on real-time vehicle traffic flow statistics for the target pedestrian channel, but rather utilizes traffic information from upstream intersections and combines historical vehicle traffic flow data to perform intelligent corrections to estimate in advance the real-time vehicle traffic flow of the target pedestrian channel in the current time period, providing more accurate and timely advance data support for the decision to extend the green light duration, thereby enabling the system to make advance control strategies for extending the green light duration.

[0078] Step S400: Determine that the real-time vehicle traffic flow of the target pedestrian passage is less than a vehicle traffic flow threshold, and control the traffic indicator light of the target pedestrian passage to extend the green light passage time.

[0079] Specifically, if the real-time vehicle traffic flow is less than the vehicle traffic flow threshold, and this state lasts for a period of time (such as the traffic flow in the preset time window is lower than the threshold), it means that the vehicle traffic pressure on the current road is relatively small, and the green light time can be appropriately extended to allow more pedestrians who have not made rain protection preparations to pass through the pedestrian passage as soon as possible, thereby avoiding pedestrians waiting for the green light for a long time in the rain.

[0080] Exemplarily, extending the green light duration may specifically be controlling the red-green light switching frequency of the traffic indicator 300. For example, the original red-green light cycle of 60 seconds (30 seconds red light + 30 seconds green light) is adjusted to a red-green light cycle of 70 seconds (20 seconds red light + 50 seconds green light).

[0081] In other embodiments, if it is determined that the real-time vehicle traffic flow of the target pedestrian passage is greater than or equal to the vehicle traffic flow threshold, it indicates that the vehicle traffic pressure on the current road is relatively large. If the green light duration of the target pedestrian passage is extended at this time, the vehicle traffic pressure on the current road will be further aggravated. Therefore, in order not to affect the vehicle traffic pressure on the current road and to provide more pedestrians who are not prepared for rain, sufficient travel time is provided, and the present application achieves the above-mentioned goal by reducing the vehicle traffic flow from the upstream intersection into the target pedestrian passage.

[0082] Exemplarily, the traffic flow of vehicles merging into the target pedestrian passage at the upstream intersection can be reduced by intercepting them through the traffic lights at the upstream intersection, but this method has certain drawbacks, for example, it causes traffic pressure on vehicles at the upstream intersection. Therefore, in one embodiment, reducing the traffic flow of vehicles merging into the target pedestrian passage at the upstream intersection includes: determining multiple candidate passage paths according to the current position and target position of the vehicle to be merged into the target pedestrian passage at the upstream intersection; assigning different traffic weights to the multiple candidate passage paths to obtain the target passage path; sending the target passage path and warning information to the vehicle to be merged into the target pedestrian passage at the upstream intersection, and the warning information is used to prompt the driver to select the target passage path for detour to reduce the traffic flow of vehicles merging into the target pedestrian passage at the upstream intersection.

[0083] Specifically, the embodiment of the present application can first use technical means such as GPS, vehicle identification system or traffic monitoring system to obtain the current position of the vehicle to be merged into the target pedestrian passage at the upstream intersection in real time; based on the urban road network data, analyze the potential travel paths that can avoid the peak area or congested section of the target pedestrian passage from the upstream intersection; then generate multiple candidate travel paths based on the road network structure, the current position of the vehicle and the target position of the vehicle. These paths should take into account the road type (such as expressway, main road, secondary road, etc.), road conditions (such as congestion level, construction conditions, etc.) and traffic rules (such as restrictions, prohibitions, etc.). A comprehensive evaluation is performed on each candidate travel path, and the factors considered may include driving distance, expected travel time, road congestion, traffic signal control, road safety level, etc. According to the evaluation results, a travel weight is assigned to each candidate path. Paths with higher weights usually mean shorter travel time, lower congestion risk or higher road safety. Based on the travel weight, multiple candidate travel paths with the highest weights are selected to connect to form a target travel path.

[0084] For example, when a vehicle travels from the current position C1 to the target position C2, there are multiple candidate paths in between, and the multiple candidate paths are connected to form a target pass path. Therefore, the system of the present application will select the target pass path with the highest sum or multiplication of the pass weights to pass through to reach the target position. In order to make the vehicle avoid the target pedestrian passage as much as possible, the pass weight of the candidate path passing through the target pedestrian passage is set to the lowest, for example, 1, and the pass weight of other candidate paths in good condition can be 2, and the pass weight of other candidate paths in better condition can be 5.

[0085] After analyzing and obtaining the target path of the vehicle, the target path and warning information are sent via wireless communication to vehicles waiting to merge into the target pedestrian passage at the upstream intersection, so as to prompt the driver to choose the target path for detour to reduce the traffic volume of vehicles merging into the target pedestrian passage at the upstream intersection, thereby alleviating the vehicle traffic pressure on the target pedestrian passage, thereby providing sufficient travel time for pedestrians who have not made rain protection preparations.

[0086] Based on this, the embodiment of the present application provides a pedestrian passage management method based on big data. First, a rain sensor is used to monitor the rainfall at the target pedestrian passage in real time. When the rainfall reaches or exceeds the preset rainfall threshold, it indicates that the current environment has a certain impact on the passage of pedestrians (especially pedestrians who do not carry rain gear). Then, the number of pedestrians and the proportion of rain gear wearing in the pedestrian waiting area are obtained by image recognition and other technical means. If the number of pedestrians and the proportion of rain gear wearing meet the preset conditions at the same time, it indicates that there are currently a large number of pedestrians who need to pass through the pedestrian passage quickly and safely, and most of them may not have made sufficient rain protection preparations and have high requirements for the passage time. Then, the big data platform is used to query and obtain the historical vehicle traffic flow of the target pedestrian passage in the current time period as a reference for evaluating the current traffic conditions. Considering the dynamic variability of traffic flow, the system also performs real-time correction of the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain a more accurate real-time vehicle traffic flow in the current time period. Finally, when it is confirmed that the real-time vehicle traffic flow is lower than the preset vehicle traffic flow threshold and there are a large number of pedestrians who urgently need to cross the pedestrian passage, the system automatically extends the green light duration by controlling the traffic lights of the target pedestrian passage. When it is confirmed that the real-time vehicle traffic flow is higher than the preset vehicle traffic flow threshold, the system remotely interacts with the vehicles at the upstream intersection to prompt the driver to choose the target traffic path for detour to reduce the vehicle traffic flow from the upstream intersection to the target pedestrian passage, thereby alleviating the vehicle traffic pressure on the target pedestrian passage and providing sufficient travel time for pedestrians who are not prepared for rain. In this way, by reducing the waiting time of pedestrians in the rain and improving the efficiency of pedestrian traffic, the safety and comfort of pedestrian traffic in rainy conditions can be enhanced, while minimizing interference with vehicle traffic.

[0087] Please see attached Figure 4 , Figure 4 A schematic diagram of the hardware structure of a pedestrian passage management system provided for some embodiments of the present application; the pedestrian passage management system provided in the embodiments of the present application also includes a memory 400 and a processor 500, wherein the memory 400 is used to store program code, and the processor 500 is used to call the program code to execute the method described above.

[0088] Among them, the processor 500 is used to provide computing and control capabilities to control the pedestrian passage management system to perform corresponding tasks, for example, to control the pedestrian passage management system to perform the pedestrian passage management method based on big data in any of the above method embodiments, the method comprising: when the rain sensor detects that the rainfall at the target pedestrian passage is greater than or equal to the rainfall threshold, obtaining pedestrian information in the pedestrian waiting area of ​​the target pedestrian passage, wherein the pedestrian information includes the number of pedestrians and the proportion of pedestrians wearing rain gear; determining that the number of pedestrians is greater than or equal to the pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to the proportion threshold, obtaining the historical vehicle traffic flow of the target pedestrian passage in the current time period based on big data; correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow of the current time period; determining that the real-time vehicle traffic flow of the target pedestrian passage is less than the vehicle traffic flow threshold, and controlling the traffic indicator light of the target pedestrian passage to extend the green light passage time.

[0089] The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0090] The memory 400 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the traffic road emergency indication method in the embodiment of the present application. The processor 500 can implement the traffic road emergency indication method in any of the above method embodiments by running the non-transitory software programs, instructions and modules stored in the memory 400.

[0091] Specifically, the memory 400 may include a volatile memory (VM), such as a random access memory (RAM); the memory 400 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD) or other non-transitory solid-state storage device; the memory 400 may also include a combination of the above types of memory.

[0092] In summary, the pedestrian passage management system of the present applicant adopts the technical solution of any one of the above-mentioned traffic road emergency indication method embodiments, and therefore, has at least the beneficial effects brought by the technical solution of the above-mentioned embodiments, which will not be described one by one here.

[0093] The embodiment of the present application also provides a computer-readable storage medium, such as a memory including a program code, and the program code can be executed by a processor to complete the traffic road emergency indication method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0094] The present application also provides a computer program product, which includes one or more program codes stored in a computer-readable storage medium. The processor of the pedestrian passage management system reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the traffic road emergency indication method provided in the above embodiment.

[0095] A person skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be accomplished by hardware or by hardware associated with a program code, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0096] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] Through the description of the above implementation methods, ordinary technicians in this field can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Ordinary technicians in this field can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0098] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A pedestrian passage management method based on big data, characterized in that: Applied to a pedestrian passageway management system, the pedestrian passageway management system includes a camera device, a rain sensor and a traffic light arranged on the side of the pedestrian passageway, and the method includes: When the rain sensor detects that the rainfall at the target pedestrian passage is greater than or equal to the rainfall threshold, obtaining pedestrian information in the pedestrian waiting area of ​​the target pedestrian passage, wherein the pedestrian information includes the number of pedestrians and the proportion of pedestrians wearing rain gear; Determine that the number of pedestrians is greater than or equal to a pedestrian number threshold, and the proportion of pedestrians wearing rain gear is less than or equal to a proportion threshold, and obtain the historical vehicle traffic flow of the target pedestrian passage in the current time period based on big data; Correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period; It is determined that the real-time vehicle traffic flow of the target pedestrian passage is less than a vehicle traffic flow threshold, and the traffic indicator light of the target pedestrian passage is controlled to extend the green light passage time.

2. The pedestrian passage management method based on big data according to claim 1, characterized in that: The method further comprises: Determine that the real-time vehicle traffic flow of the target pedestrian passage is greater than or equal to a vehicle traffic flow threshold, and reduce the vehicle traffic flow merging into the target pedestrian passage from an upstream intersection.

3. The pedestrian passage management method based on big data as claimed in claim 2 is characterized in that: The reducing the vehicle traffic flow from the upstream intersection into the target pedestrian passage comprises: Determine multiple candidate travel paths according to the current position and target position of the vehicle to be merged into the target pedestrian passage at the upstream intersection; Allocating different travel weights to the plurality of candidate travel paths to obtain a target travel path; The target traffic path and warning information are sent to vehicles at an upstream intersection that are about to merge into the target pedestrian passage. The warning information is used to prompt the driver to select the target traffic path for detour driving to reduce the traffic flow of vehicles merging into the target pedestrian passage at the upstream intersection.

4. The pedestrian passage management method based on big data according to claim 1, characterized in that: The obtaining of pedestrian information in a pedestrian waiting area of ​​the target pedestrian passage includes: Acquire a target image captured by the camera device in a pedestrian waiting area of ​​the target pedestrian passage; Performing target object recognition on the target image based on semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage; Performing contour line extraction on the area above the head of each target object in the target image to obtain a first contour line, and performing contour line extraction on the area below the head of each target object in the target image to obtain a second contour line; Matching the first contour line with a preset first reference contour line to obtain a first matching similarity, and matching the second contour line with a preset second reference contour line to obtain a second matching similarity; Determine the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity; The proportion of pedestrians wearing rain gear in the pedestrian waiting area of ​​the target pedestrian passage is determined according to the rain gear wearing status of each target object.

5. The pedestrian passage management method based on big data according to claim 4 is characterized in that: The target object recognition is performed on the target image based on the semantic segmentation technology to obtain the number of pedestrians in the pedestrian waiting area of ​​the target pedestrian passage, including: Determine that a difference between the number of pixels of a target semantic category of a first target object in the target image and the number of pixels of a target semantic category of a second target object in the target image is greater than a preset difference, and control the camera device to rotate in a preset direction; After the camera device rotates in a preset direction, the difference between the number of pixels of the target semantic category of the first target object in the target image and the number of pixels of the target semantic category of the second target object in the target image is re-determined to be narrowed to a preset range, and the first target object and the second target object are determined to be pedestrians and the number of pedestrians is counted.

6. The pedestrian passage management method based on big data according to claim 4 is characterized in that: Determining the rain gear wearing status of each target object according to the first matching similarity and the second matching similarity includes: Preliminarily determining the type of rain gear worn by the target object according to the first matching similarity and the second matching similarity; Allocating the influence weights of the first matching similarity and the second matching similarity on the target matching similarity according to the type of rain gear; Obtaining a target matching similarity according to the first matching similarity, the second matching similarity and the corresponding influence weights; The rain gear wearing status of each target object is determined according to the target matching similarity.

7. The pedestrian passage management method based on big data according to claim 6 is characterized in that: The allocating the influence weights of the first matching similarity and the second matching similarity on the target matching similarity according to the rain gear type includes: When the initially determined type of rain gear is an umbrella or a rain hat, determining that the influence weight of the first matching similarity on the target matching similarity is greater than the influence weight of the second matching similarity on the target matching similarity; When the initially determined type of rain gear is a raincoat, it is determined that the influence weight of the first matching similarity on the target matching similarity is less than the influence weight of the second matching similarity on the target matching similarity.

8. The pedestrian passage management method based on big data according to claim 1, characterized in that: The correcting the historical vehicle traffic flow according to the traffic information of the upstream intersection of the target pedestrian passage to obtain the real-time vehicle traffic flow in the current time period includes: Obtaining the proportion of traffic from the upstream intersection merging into the target pedestrian passage and the distance between the upstream intersection and the target pedestrian passage; Determine that the proportion of traffic from the upstream intersection merging into the target pedestrian passage is greater than or equal to a traffic proportion threshold, and that the distance between the upstream intersection and the target pedestrian passage is less than or equal to a distance threshold, and perform a positive correction on the historical vehicle traffic flow to obtain a real-time vehicle traffic flow in the current time period; Determine that the proportion of traffic from the upstream intersection merging into the target pedestrian passage is less than a traffic proportion threshold, or that the distance between the upstream intersection and the target pedestrian passage is greater than a distance threshold, and perform a negative correction on the historical vehicle traffic flow to obtain the real-time vehicle traffic flow for the current time period.

9. A pedestrian passage management system, characterized in that: include: The camera device, rain sensor and traffic light arranged on the side of the pedestrian walkway also include a memory and a processor, the memory is used to store program code, and the processor is used to call the program code to execute the method according to any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images