Road illuminance optimization method and system

Abstract

The invention relates to the technical field of illumination, in particular to a road illuminance optimization method and system, and the method comprises the steps: obtaining the road information and video image information of a target road; obtaining an illumination point position set corresponding to the target road based on the road information; obtaining target object information corresponding to the target road based on the video image; acquiring a target position and a moving speed of the target object based on the target object information; obtaining a target illumination point position based on the target position and the illumination point position set; if the moving speed is greater than zero, generating a first illuminance optimization method based on the moving speed and the target illumination point position; and if the moving speed is equal to zero, generating a second illuminance optimization method based on the target illumination point position. According to the invention, the control accuracy of the road illumination is improved, so that the power consumption is reduced and the traffic safety is improved.

Description

Technical Field

[0001] This application relates to the field of lighting technology, and in particular to a method and system for optimizing road lighting intensity. Background Technology

[0002] With the continuous development of urban transportation construction, road lighting systems, as an important infrastructure to ensure nighttime driving safety and pedestrian safety, have attracted much attention regarding their operational efficiency and lighting quality. Currently, most traditional road lighting control methods adopt fixed lighting modes, that is, controlling the lighting equipment along the road to maintain a constant illumination level according to preset times (such as from dusk to the early morning of the next day) or light intensity thresholds. However, this fixed lighting mode has obvious drawbacks: on the one hand, when there are no vehicles, pedestrians or other target objects on the road, or when there are few target objects, continuous high illumination will cause a lot of energy waste, which does not meet the current development needs of energy conservation and emission reduction; on the other hand, when there are moving target objects on the road, the fixed illumination cannot be dynamically adjusted according to the position and movement of the target objects, which may lead to insufficient lighting in the area where the target objects are located, or excessive lighting in non-target areas, which not only affects the lighting experience, but may also increase traffic safety hazards. Summary of the Invention

[0003] To help improve the accuracy of road lighting control, thereby reducing power consumption and improving traffic safety, this application provides a road lighting optimization method and system.

[0004] Firstly, this application provides a method for optimizing road lighting intensity, which adopts the following technical solution: A method for optimizing road lighting intensity includes: Acquire road information and video image information of the target road; Based on the road information, obtain the set of lighting point locations corresponding to the target road; Based on the video images, obtain the target object information corresponding to the target road; Based on the target object information, the target object's target position and movement speed are obtained; Based on the target location and the set of lighting point locations, the location of the target lighting point is obtained; If the moving speed is greater than zero, a first illumination optimization method is generated based on the moving speed and the position of the target illumination point; If the moving speed is zero, a second illumination optimization method is generated based on the target illumination point position.

[0005] By adopting the above technical solution, firstly, road information of the target road is obtained through an urban traffic management database or a GIS geographic information system, while simultaneously acquiring real-time video image information through high-definition cameras along the road. Next, based on the installation coordinates of the lighting equipment in the road information, all lighting points covering the entire target road section are selected, forming a set of lighting point locations including the unique identifier of each lighting point, its lane location, and its rated brightness. Then, the video images are analyzed, and the pixel coordinates are converted to the actual road location of the target object, and the movement speed is calculated. Afterward, the straight-line distance between the actual location of the target object and each lighting point in the lighting point location set is calculated, determining the 1-2 closest lighting points as the target lighting point locations. Finally, the optimization direction is determined based on the target object's movement speed. If the movement speed is greater than 0, a first illumination optimization method adapted to the moving scene is generated by combining the speed and the target lighting points; if the movement speed is equal to 0, a second illumination optimization method adapted to the stationary scene is generated based on the target lighting points, completing the entire process from information acquisition to dynamic dimming.

[0006] By employing dynamic control logic for on-demand lighting, the shortcomings of traditional fixed lighting modes are effectively addressed: on the one hand, it eliminates the need to maintain constant high brightness across the entire road segment, allowing for precise adjustment of lighting only in the area where the target object is located, significantly reducing energy waste during periods without targets and aligning with the development needs of energy conservation and emission reduction; on the other hand, it can differentiate and optimize lighting based on the movement status (moving / stationary) of the target object, avoiding issues such as lag in lighting in areas with moving objects or over-lighting in areas with stationary objects, thus significantly improving the safety of nighttime road traffic; simultaneously, the entire process is based on real-time collected road information and video images for dynamic decision-making, requiring no manual intervention, adapting to different road types and traffic scenarios, possessing strong practicality and universality, and providing a feasible technical solution for the intelligent upgrading of road lighting systems.

[0007] Optionally, if the moving speed is greater than zero, the method for generating a first illumination optimization based on the moving speed and the position of the target illumination point includes: If the moving speed is greater than zero, then determine whether the moving speed exceeds the first speed threshold; If the moving speed is greater than or equal to the first speed threshold, the target object is marked as a dangerous object; Based on the location of the target lighting point corresponding to the dangerous object and the moving speed, the location of the buffer lighting point is obtained; Based on the target illumination point position and the buffer illumination point position, a first illumination optimization method is generated; If the moving speed is less than the first speed threshold, then the target number of the target object is obtained; If the number of targets is equal to 1, then a first illumination optimization method is generated based on the location of the target illumination point.

[0008] Optionally, after determining the number of targets for a target object if the moving speed is less than the first speed threshold, the method further includes: If the number of targets is greater than 1, then obtain the correspondence between different target objects; If the correspondence is a same-direction relationship, then the speed difference between different target objects is obtained; If the speed difference is greater than or equal to a preset speed threshold, then the relative position change between different target objects is obtained; If the relative position change is one of relative proximity, then the relative distance is obtained; Based on the location of the target illumination point and the relative distance, a first illumination optimization method is obtained.

[0009] Optionally, after obtaining the correspondence between different target objects if the number of targets is greater than 1, the method further includes: If the correspondence is a reverse relationship, determine whether the position of the lighting point corresponding to the target road is the middle of the target road; If the location of the illumination point is the middle of the target road, then a first illumination optimization method is generated based on the location of the first target illumination point and the location of the second target illumination point; If the location of the lighting point is not in the middle of the target road, then it is determined whether there is a median strip on the target road; If the target road has a median strip, a first illumination optimization method is generated based on the positions of the first target illumination point and the second target illumination point. If the target road does not have a median strip, then obtain the position of the first target lighting point corresponding to the first target object and the position of the second target lighting point corresponding to the second target object; A first illumination optimization method is generated based on the positions of the first target illumination point and the second target illumination point.

[0010] Optionally, if the target road does not have a median strip, the method for generating the first illumination optimization based on the positions of the first and second target illumination points includes: Based on the positions of the first and second target lighting points, the relative distance between the first target object and the second target object is obtained; Obtain the sum of the movement speeds between the first target object and the second target object; Based on the speed of movement and the relative distance, a first estimated travel time is obtained; If the first estimated movement time is less than or equal to the first time threshold, then the position of the intermediate lighting point is obtained based on the position of the first target lighting point and the position of the second target lighting point; A first illumination optimization method is obtained based on the location of the first target illumination point, the location of the second target illumination point, and the location of the intermediate illumination point.

[0011] Optionally, obtaining the location of the buffer lighting point based on the target lighting point location corresponding to the dangerous object and the moving speed includes: Based on the road information, the adjacent distance between adjacent lighting points is obtained; Based on the video image information and the moving speed, estimate the total braking distance of the target object; The target buffer quantity is obtained based on the total braking distance and the adjacent distance; Based on the target illumination point location and the target buffer quantity, the buffer illumination point location is obtained.

[0012] Optionally, estimating the total braking distance of the target object based on the video image information and the moving speed includes: Call the reaction time under different states; The reaction distance is obtained based on the reaction time and the moving speed; Based on the video image information, the road type of the target road is obtained; Based on the road type, obtain the adhesion coefficient corresponding to the target object; Based on the adhesion coefficient, the braking acceleration is obtained; Based on the braking acceleration and the moving speed, the braking distance is obtained; The total braking distance is obtained based on the reaction distance and the braking process distance.

[0013] Optionally, if the moving speed is equal to zero, the method for generating a second illumination optimization based on the target illumination point position includes: If the moving speed is zero, then obtain the target illumination level corresponding to the target illumination point position; If the target illumination is greater than or equal to the first illumination threshold, then the environmental information corresponding to the target illumination point is obtained; Based on the environmental information, obtain the residential area information associated with the target lighting point, as well as the target vehicle flow and target pedestrian flow corresponding to the target lighting point at the current time; The second illumination optimization method is generated based on the residential area information, the target vehicle flow, and the target pedestrian flow.

[0014] Optionally, the method for generating the second illumination optimization based on the residential area information, the target vehicle flow, and the target pedestrian flow includes: Based on the residential information, the location, size, and building height of the residential area are obtained; Based on the location of the target lighting point and the location of the residential area, the target distance is obtained; Illuminance score is obtained based on the target distance, the size of the settlement, the building height of the settlement, the target vehicle flow, and the target pedestrian flow; Based on the illuminance score, the second illuminance optimization method is generated.

[0015] Secondly, this application also discloses a road lighting optimization system, which adopts the following technical solution: A road lighting optimization system, comprising: The first acquisition module is used to acquire road information and video image information of the target road; The second acquisition module is used to acquire a set of lighting point locations corresponding to the target road based on the road information; The third acquisition module is used to acquire target object information corresponding to the target road based on the video image; The fourth acquisition module is used to acquire the target position and moving speed of the target object based on the target object information; The fifth acquisition module is used to acquire the position of the target illumination point based on the target position and the set of illumination point positions; If the moving speed is greater than zero, the first generation module is used to generate a first illumination optimization method based on the moving speed and the position of the target illumination point. If the moving speed is zero, the second generation module is used to generate a second illumination optimization method based on the position of the target illumination point.

[0016] In summary, this application includes the following beneficial technical effects: By employing dynamic control logic for on-demand lighting, the shortcomings of traditional fixed lighting modes are effectively addressed: on the one hand, it eliminates the need to maintain constant high brightness across the entire road segment, allowing for precise adjustment of lighting only in the area where the target object is located, significantly reducing energy waste during periods without targets and aligning with the development needs of energy conservation and emission reduction; on the other hand, it can differentiate and optimize lighting based on the movement status (moving / stationary) of the target object, avoiding issues such as lag in lighting in areas with moving objects or over-lighting in areas with stationary objects, thus significantly improving the safety of nighttime road traffic; simultaneously, the entire process is based on real-time collected road information and video images for dynamic decision-making, requiring no manual intervention, adapting to different road types and traffic scenarios, possessing strong practicality and universality, and providing a feasible technical solution for the intelligent upgrading of road lighting systems. Attached Figure Description

[0017] Figure 1 This is a main flowchart of a road lighting optimization method according to an embodiment of this application; Figure 2 If the moving speed is greater than zero, then the flowchart shows the steps of the method to generate the first illumination optimization based on the moving speed and the position of the target illumination point; Figure 3 This is a flowchart of the steps for generating the first illumination optimization method when the moving speed is less than the first speed threshold, the number of target objects is greater than 1, and the correspondence between the target objects is in the same direction. Figure 4 This is a flowchart of the steps for generating the first illumination optimization method when the moving speed is less than the first speed threshold, the number of target objects is greater than 1, and the target objects are in a counterpart relationship. Figure 5 If the target road does not have a median strip, then a flowchart of the steps for generating the first illumination optimization method based on the positions of the first and second target illumination points is provided. Figure 6 This is a flowchart illustrating the steps to obtain the location of a buffer lighting point based on the location and movement speed of the target lighting point corresponding to the hazardous object. Figure 7 This is a flowchart of the steps for estimating the total braking distance of a target object based on video image information and movement speed. Figure 8 If the moving speed is zero, then the flowchart shows the steps of the method to generate the second illumination optimization based on the target illumination point position; Figure 9 This is a flowchart of the steps for generating a second lighting brightness optimization method based on residential area information, target vehicle flow, and target pedestrian flow. Figure 10 This is a block diagram of a road lighting optimization system according to an embodiment of this application.

[0018] Explanation of reference numerals in the attached figures: 1. First acquisition module; 2. Second acquisition module; 3. Third acquisition module; 4. Fourth acquisition module; 5. Fifth acquisition module; 6. First generation module; 7. Second generation module. Detailed Implementation

[0019] Firstly, this application discloses a method for optimizing road lighting intensity.

[0020] Reference Figure 1 A method for optimizing road lighting intensity includes steps S101 to S107: Step S101: Obtain road information and video image information of the target road.

[0021] Specifically, in this embodiment, road information is obtained through an urban traffic management database or a GIS geographic information system, including road length, number of lanes, median strip setup, lighting equipment installation coordinates, and road type; video image information is collected in real time by high-definition cameras deployed along the road, with a collection frequency of no less than 25 frames per second, to ensure that the dynamics of target objects such as vehicles and pedestrians can be clearly captured.

[0022] Step S102: Based on road information, obtain the set of lighting point locations corresponding to the target road.

[0023] Specifically, in this embodiment, based on the installation coordinates of lighting equipment in the road information, the location coordinates of all lighting equipment (such as streetlights) covering the entire target road section are filtered out to form a set of lighting point locations. The set needs to be labeled with the unique identifier of each lighting point (such as "L-058"), the lane side (north side / south side / median strip) it is located on, and its rated power, etc. For example, if the target road is a 1-kilometer-long two-way four-lane road, with one 150W high-pressure sodium lamp installed every 30 meters on both sides and one 100W LED lamp installed every 50 meters in the median strip, the set of lighting point locations includes the coordinate information of 88 lighting points in total, including 68 on both sides (34 on the north side and 34 on the south side) and 20 in the middle (such as "L-058: 480 meters from the starting point (north side), rated brightness 40 lux").

[0024] Step S103: Based on the video image, obtain the target object information corresponding to the target road.

[0025] Specifically, AI image recognition algorithms (such as the YOLOv8 object detection model) are used to analyze video images, identify, and extract target object information. In this embodiment, target objects include vehicles (such as cars, trucks, and electric vehicles) and pedestrians, and target object information covers object type, contour features, and pixel coordinates in the image.

[0026] Step S104: Based on the target object information, obtain the target object's target position and movement speed.

[0027] Specifically, in this embodiment, the pixel coordinates of the target object in the video image are converted into the actual position of the road (such as 500 meters away from the starting point of the road, near the north lane, etc.) through the "pixel coordinate-actual position conversion" algorithm; the moving speed is calculated by the position change of the target object in 3 consecutive video images, and the formula is "moving speed = position difference between adjacent frames / frame interval time". For example, if the target object moves 3 meters in 0.12 seconds (3 frame interval, 25 frames / second), the moving speed is 25 meters / second.

[0028] Step S105: Obtain the target illumination point position based on the target position and the set of illumination point positions.

[0029] Specifically, in this embodiment, the straight-line distance between the actual location of the target object and each lighting point in the set of lighting point locations is calculated, and the one or two closest lighting points are selected as the target lighting point locations. For example, if the target object is located 500 meters from the road, and the nearby lighting points are located at 480 meters and 510 meters respectively, then the target lighting point locations are the two lighting points at 480 meters and 510 meters.

[0030] Step S106: If the moving speed is greater than zero, then generate a first illumination optimization method based on the moving speed and the position of the target illumination point.

[0031] Specifically, in this embodiment, a movement speed greater than zero indicates that the target object is in a moving state (such as a moving vehicle or a walking pedestrian). The core of the first illumination optimization method is "on-demand illumination"—increasing the brightness of illumination points around the target object, such as target illumination points and buffer illumination points, while keeping non-target areas at low brightness (such as 30% of the rated brightness). At the same time, the illumination range is adjusted according to the movement speed to avoid illumination lag or over-illumination.

[0032] Step S107: If the moving speed is zero, then generate a second illumination optimization method based on the target illumination point position.

[0033] Specifically, in this embodiment, a movement speed of zero indicates that the target object is stationary (such as a vehicle parked on the roadside, a pedestrian waiting to cross the road, or an obstacle on the road). The core of the second illumination optimization method is "fixed illumination," which means that there is no need to expand the illumination range. The brightness of the target illumination point is adjusted only according to the type of target object and the surrounding environment. This avoids energy waste caused by prolonged high brightness and improves road safety.

[0034] The road illumination optimization method provided in this embodiment first obtains road information of the target road through an urban traffic management database or a GIS geographic information system, and simultaneously acquires video image information in real time through high-definition cameras along the road. Next, based on the installation coordinates of the lighting equipment in the road information, all lighting points covering the entire target road section are selected, forming a set of lighting point locations including the unique identifier of each lighting point, its lane location, and its rated brightness. Then, the video images are analyzed, and the pixel coordinates are converted into the actual road location of the target object, and the moving speed is calculated. Afterwards, the straight-line distance between the actual location of the target object and each lighting point in the lighting point location set is calculated, and the 1 to 2 closest lighting points are determined as the target lighting point locations. Finally, the optimization direction is determined based on the moving speed of the target object. If the moving speed is greater than 0, a first illumination optimization method adapted to the moving scene is generated by combining the speed and the target lighting points; if the moving speed is equal to 0, a second illumination optimization method adapted to the stationary scene is generated based on the target lighting points, completing the entire process from information acquisition to dynamic dimming.

[0035] By employing dynamic control logic for on-demand lighting, the shortcomings of traditional fixed lighting modes are effectively addressed: on the one hand, it eliminates the need to maintain constant high brightness across the entire road segment, allowing for precise adjustment of lighting only in the area where the target object is located, significantly reducing energy waste during periods without targets and aligning with the development needs of energy conservation and emission reduction; on the other hand, it can differentiate and optimize lighting based on the movement status (moving / stationary) of the target object, avoiding issues such as lag in lighting in areas with moving objects or over-lighting in areas with stationary objects, thus significantly improving the safety of nighttime road traffic; simultaneously, the entire process is based on real-time collected road information and video images for dynamic decision-making, requiring no manual intervention, adapting to different road types and traffic scenarios, possessing strong practicality and universality, and providing a feasible technical solution for the intelligent upgrading of road lighting systems.

[0036] Reference Figure 2 In one embodiment of this example, if the moving speed is greater than zero in step S106, the method for generating the first illumination optimization based on the moving speed and the target illumination point position includes steps S201 to S206: Step S201: If the movement speed is greater than zero, determine whether the movement speed exceeds the first speed threshold.

[0037] Specifically, the first speed threshold is a pre-set criterion used to distinguish whether the target object is a high-speed moving object or a low-speed moving object. In this embodiment, the first speed threshold can be set to 60km / h.

[0038] Step S202: If the moving speed is greater than or equal to the first speed threshold, then mark the target object as a dangerous object.

[0039] Specifically, in this embodiment, a dangerous object refers to a high-speed moving object that may pose a safety hazard, such as a vehicle traveling at a speed exceeding 60 km / h.

[0040] Step S203: Based on the target lighting point position and movement speed corresponding to the dangerous object, obtain the buffer lighting point position.

[0041] Specifically, in this embodiment, the buffer lighting point position refers to the additional lighting point added in front of the target lighting point position in the direction of movement. For example, for a vehicle traveling eastward, in addition to the target lighting point, 1 to 3 lighting points on the east side also need to be lit.

[0042] Step S204: Generate a first illumination optimization method based on the target illumination point position and the buffer illumination point position.

[0043] Specifically, the first illumination optimization method is to increase the brightness at the target illumination point to 100% of the rated brightness, increase the brightness at the buffer illumination point to 80%, and keep the remaining illumination points at 30%, so as to ensure that the entire path of the dangerous object is bright.

[0044] Step S205: If the moving speed is less than the first speed threshold, then obtain the target number of the target object.

[0045] Specifically, in this embodiment, the target number is counted using an AI image recognition algorithm. For example, if two electric vehicles and three pedestrians are identified in the same frame of an image, then the target number is 5.

[0046] Step S206: If the number of targets is equal to 1, then generate the first illumination optimization method based on the target illumination point position.

[0047] Specifically, in this embodiment, the lighting requirements of a single slow-moving object (such as a pedestrian walking alone) are low. The brightness of the target lighting point is increased to 70% to 80% of the rated brightness (70% for pedestrians and 80% for electric vehicles), while the remaining lighting points are kept at 30% of the rated brightness to avoid excessive energy consumption.

[0048] The road illumination optimization method provided in this embodiment first determines whether the speed exceeds a preset first speed threshold. If the moving speed is greater than or equal to the first speed threshold, the target object is marked as a dangerous object with a high safety hazard. Then, based on the target illumination point position corresponding to the dangerous object and the current moving speed, the position of the buffer illumination point that needs to be lit is further calculated. Then, based on the target illumination point position and the buffer illumination point position, a first illumination optimization method for high-speed dangerous objects is generated. If the moving speed is less than the first speed threshold, the number of targets of the target object is counted by video image recognition. If the number of targets is equal to 1, a first illumination optimization method adapted to a single low-speed object is generated only based on the target illumination point position corresponding to the target object, thus completing the differentiated illumination optimization control for moving objects with different speeds and different numbers.

[0049] By employing a two-tiered judgment logic based on speed threshold grading and object quantity differentiation, refined matching of lighting requirements for moving objects is achieved. On the one hand, additional buffer lighting points are set for high-speed hazardous objects, covering their longer braking distances and illuminating their travel paths in advance, significantly reducing the risk of blind spots during high-speed driving and improving driving safety. On the other hand, lighting control is simplified for individual low-speed objects, requiring only the target lighting point to meet the needs, avoiding energy waste caused by excessive lighting and balancing safety and energy conservation requirements. At the same time, the grading judgment criteria are clear and quantifiable, requiring no complex algorithm iterations, facilitating engineering applications, further improving the practicality and reliability of lighting optimization in moving scenarios, and providing a more precise technical path for road lighting control in different dynamic scenarios.

[0050] Reference Figure 3In one embodiment of this example, if the moving speed is less than the first speed threshold in step S205, then after obtaining the target number of the target object, steps S301 to S305 are further included: Step S301: If the number of targets is greater than 1, obtain the correspondence between different target objects.

[0051] Specifically, in this embodiment, the correspondence is determined by the direction of movement of the target object. The same direction relationship means that all objects move in the same direction (such as all moving west), and the opposite direction relationship means that some objects move in opposite directions (such as some moving east and some moving west).

[0052] Step S302: If the correspondence is in the same direction, then obtain the speed difference between different target objects.

[0053] Specifically, the speed difference is the difference between different target objects. For example, two cars traveling in the same direction have speeds of 50 m / s and 30 m / s respectively, and the speed difference is 20 m / s.

[0054] Step S303: If the speed difference is greater than or equal to the preset speed threshold, then obtain the relative position change between different target objects.

[0055] Specifically, the preset speed threshold is a pre-set standard for judging whether the relative speed between different target objects is too high. In this embodiment, the preset speed threshold can be set to 30 meters per second. If the speed difference exceeds this value, it indicates that there may be a risk of rear-end collision.

[0056] Step S304: If the relative position changes to be relatively closer, then obtain the relative distance.

[0057] Specifically, in this embodiment, the change in relative position is analyzed through continuous frame images. If the distance between the following vehicle and the preceding vehicle decreases from 100 meters to 50 meters, it is determined that they are relatively close, and the relative distance is 50 meters.

[0058] Step S305: Based on the target illumination point position and relative distance, obtain the first illumination optimization method.

[0059] Specifically, in this embodiment, the illumination range is adjusted based on the relative distance. When the relative distance is close, for example, less than or equal to a certain distance threshold (e.g., 50 meters), all illumination points between the two vehicles are additionally illuminated, in addition to the target illumination points of each vehicle, and the brightness of all points is increased to the rated brightness to remind the following vehicle to maintain a safe distance. When the relative distance is far, for example, greater than 50 meters, only the target illumination points of each vehicle are kept at the rated brightness, and the brightness of the remaining illumination points is less than the rated brightness, for example, 30% of the rated brightness. Of course, in this embodiment, the time it takes for the following vehicle to catch up with the preceding vehicle can also be calculated based on the relative distance and speed difference between the two vehicles, and the brightness of different illumination points can be set according to this time.

[0060] The road illumination optimization method provided in this embodiment obtains the correspondence between different target objects by analyzing the motion direction vector of the target objects in the video image. If the correspondence is in the same direction, the speed difference between different target objects is calculated. Then, it is determined whether the speed difference is greater than or equal to a preset speed threshold. If the speed difference meets the threshold, the position change of the target objects is tracked by continuous multi-frame video images to obtain the relative position change between different target objects. If the relative position change is relatively close, the actual relative distance between each target object is further calculated. Finally, based on the previously determined target illumination point position and the currently obtained relative distance, a first illumination optimization method adapted to the same direction, high speed difference, and relatively close scene is generated to complete the precise illumination control of high-risk scenes with multiple low-speed objects in the same direction.

[0061] Through a progressive logic of correspondence judgment, speed difference screening, relative position tracking, and relative distance quantification, accurate identification and lighting response for high-risk scenarios are achieved. On the one hand, lighting is optimized only for specific high-risk combination scenarios of same direction, high speed difference, and relative proximity, avoiding over-lighting of risk-free same-direction multi-object scenarios and further reducing power consumption. On the other hand, the lighting range is dynamically adjusted based on relative distance, which can illuminate areas where rear-end collisions may occur in advance, helping drivers to detect the movement of vehicles in front earlier, shortening reaction time, and significantly reducing the probability of rear-end collisions in same-direction driving. At the same time, the entire process is based on objective data judgment of video images, avoiding subjective experience errors, improving the scientific nature and reliability of lighting optimization, and perfecting the lighting safety assurance system in multi-object low-speed movement scenarios.

[0062] Reference Figure 4 In one embodiment of this example, after obtaining the correspondence between different target objects in step S301 if the number of targets is greater than 1, steps S401 to S404 are further included: Step S401: If the correspondence is a reverse relationship, determine whether the position of the lighting point corresponding to the target road is the middle of the target road.

[0063] Step S402: If the location of the illumination point is the middle of the target road, then generate a first illumination optimization method based on the location of the first target illumination point and the location of the second target illumination point.

[0064] Specifically, when the illumination point is in the middle of the road, it indicates that the target road is a two-way road with a median strip in the middle. Therefore, the safety between vehicles is relatively high. It is only necessary to adjust the first and second target illumination points to their rated brightness to ensure that the field of vision in front of each of the two target objects is clear. There is no need to adjust the brightness of other illumination points to their rated brightness to avoid wasting electricity. In this embodiment, the positions of the first and second target illumination points respectively represent the target illumination point positions corresponding to two vehicles traveling in opposite directions. For example, the position of the first target illumination point represents the target illumination point position corresponding to a vehicle traveling from west to east, and the position of the second illumination point represents the target illumination point position corresponding to a vehicle traveling from east to west.

[0065] Step S403: If the location of the lighting point is not in the middle of the target road, then determine whether there is a median strip on the target road.

[0066] Step S404: If there is no median strip on the target road, then generate a first illumination optimization method based on the positions of the first target illumination point and the second target illumination point.

[0067] Specifically, in this embodiment, when there is a median strip, the two opposing target objects interfere with each other less, and the safety between vehicles is relatively high. It is only necessary to adjust the first target illumination point and the second target illumination point to their rated brightness to keep the field of vision in front of each of the two target objects clear. There is no need to adjust the brightness of other illumination points to their rated brightness to avoid wasting electricity. When there is no median strip, the two opposing target objects interfere with each other more, and it is necessary to further set the first illumination optimization method according to the position of the first target illumination point and the position of the second target illumination point.

[0068] The road illumination optimization method provided in this embodiment further determines whether the location of the illumination point corresponding to the target road is in the middle of the road. If the illumination point is in the middle of the road, a first illumination optimization method adapted to the middle lighting layout is directly generated based on the location of the first target illumination point corresponding to the first target object and the location of the second target illumination point corresponding to the second target object. If the illumination point is not in the middle of the road, it further determines whether there is a median strip on the target road. If there is no median strip, the location of the first target illumination point exclusive to the first target object and the location of the second target illumination point exclusive to the second target object are first determined. Then, based on these two illumination point locations, a first illumination optimization method that takes into account the visibility clarity of both opposing sides is generated, thereby completing the precise control of illumination under different road conditions for multiple low-speed objects.

[0069] This embodiment achieves differentiated lighting control for scenarios with multiple low-speed objects traveling in opposite directions. On the one hand, for low-risk scenarios with intermediate lighting points or median strips, the lighting optimization logic is simplified, focusing only on the target lighting points of each oncoming object, avoiding over-illumination of unnecessary areas and reducing energy waste. On the other hand, for high-risk scenarios without median strips, the exclusive target lighting points of each oncoming object are clearly defined, ensuring clear visibility for both parties and effectively reducing the risk of oncoming collisions. At the same time, the entire judgment process is closely integrated with the inherent attributes of the road, requiring no complex dynamic data calculations, resulting in high decision-making efficiency and strong feasibility. This ensures both oncoming driving safety and energy-saving requirements, further improving the lighting optimization system for low-speed movement scenarios with multiple objects.

[0070] Reference Figure 5 In one embodiment of this example, if the target road does not have a median strip in step S404, the method for generating the first illumination optimization based on the positions of the first and second target illumination points includes steps S501 to S505: Step S501: Based on the positions of the first target illumination point and the second target illumination point, obtain the relative distance between the first target object and the second target object.

[0071] Specifically, in this embodiment, the relative distance is the straight-line distance between the actual locations of the opposing objects. For example, if the object on the east side is 100 meters away from the road and the object on the west side is 500 meters away, the relative distance is 400 meters.

[0072] Step S502: Obtain the sum of the movement speeds between the first target object and the second target object.

[0073] Specifically, in this embodiment, the sum of movement speeds is the sum of the absolute values ​​of the speeds of the opposing objects. For example, if the speed of the object on the east side is 40 m / s (eastward) and the speed of the object on the west side is 40 m / s (westward), the sum of movement speeds is 80 m / s.

[0074] Step S503: Based on the movement speed and relative distance, obtain the first estimated movement time.

[0075] Specifically, the first estimated movement time = relative distance / movement speed, for example, 400 meters ÷ 80 meters / second = 5 seconds, that is, it is estimated that they will meet in 5 seconds; in this embodiment, the first estimated movement time is the time when the first target object and the second target object meet.

[0076] Step S504: If the first estimated movement time is less than or equal to the first time threshold, then the position of the intermediate lighting point is obtained based on the position of the first target lighting point and the position of the second target lighting point.

[0077] Specifically, the first time threshold is a pre-set criterion for judging whether the first estimated movement time is too short. In this embodiment, the first time threshold can be 10 seconds; the intermediate lighting point position is all lighting point positions between the first target lighting point position and the second target lighting point position.

[0078] Step S505: Based on the position of the first target illumination point, the position of the second target illumination point, and the position of the intermediate illumination point, obtain the first illumination optimization method.

[0079] Specifically, in this embodiment, the brightness of the first target lighting point, the second target lighting point, and the intermediate lighting point are all increased to the rated brightness (100%), and the warning lights on the road edge are triggered to remind the two target objects to slow down and avoid them.

[0080] The road illumination optimization method provided in this embodiment calculates the actual relative distance between two target objects through coordinate conversion; then, it combines the moving speeds of the two target objects to obtain the sum of their moving speeds; subsequently, it divides the relative distance by the sum of their moving speeds to calculate the first estimated movement time for the two target objects to meet; next, it determines whether the first estimated movement time is less than or equal to a preset first time threshold. If the threshold condition is met, it uses the positions of the first and second target illumination points as a reference to determine all illumination points between the two as intermediate illumination point positions; finally, it integrates the positions of the first, second, and intermediate illumination points to generate a first illumination optimization method adapted to high-risk scenarios with no median strip and short encounter times, thus completing precise lighting control in high-risk scenarios with opposing relationships and no median strip.

[0081] By quantifying relative distance, speed, and encounter time, dynamic perception and lighting response to collision risks in oncoming scenarios without median barriers are achieved. On the one hand, the intermediate lighting point is only illuminated when the encounter time reaches a threshold (high risk), avoiding excessive lighting during low-risk periods and further reducing energy consumption. On the other hand, illuminating the intermediate lighting point in the encounter area in advance provides sufficient predictive visibility for both targets, shortens driver reaction time, and significantly reduces the probability of oncoming collisions in scenarios without median barriers. At the same time, using the quantified time threshold as the basis for lighting adjustment avoids subjective judgment errors, improves the scientific nature and accuracy of lighting optimization, strengthens safety in high-risk scenarios, takes into account energy-saving needs, and improves the lighting optimization logic in extreme scenarios with multiple low-speed objects in oncoming relationships.

[0082] Reference Figure 6 In one embodiment of this invention, step S203, based on the target illumination point position and moving speed corresponding to the dangerous object, obtains the buffer illumination point position, including steps S601 to S604: Step S601: Based on road information, obtain the adjacent distance between adjacent lighting points.

[0083] Specifically, in this embodiment, the adjacent distance is the straight-line distance between two adjacent lighting points in the set of lighting point locations.

[0084] Step S602: Estimate the total braking distance of the target object based on video image information and movement speed.

[0085] Specifically, in this embodiment, the total braking distance refers to the total distance from when the target object detects danger to when it comes to a complete stop, including the reaction distance and the braking process distance.

[0086] Step S603: Obtain the target buffer quantity based on the total braking distance and adjacent distances.

[0087] Specifically, the target buffer quantity is a multiple of the adjacent distance corresponding to the total braking distance. In this embodiment, the target buffer quantity = rounded up (total braking distance / adjacent distance). For example, if the total braking distance is 70 meters and the adjacent distance is 30 meters, then 70 ÷ 30 ≈ 2.33, which is rounded up to 3, that is, the target buffer quantity is 3.

[0088] Step S604: Obtain the location of the buffer lighting point based on the location of the target lighting point and the number of target buffers.

[0089] Specifically, in this embodiment, starting from the target lighting point of the dangerous object, a number of target buffer lighting points are selected sequentially along the direction of movement as buffer lighting points. For example, if the target lighting point is at 500 meters (moving eastward), then the buffer lighting points are at 530 meters, 560 meters, and 590 meters.

[0090] The road illumination optimization method provided in this embodiment extracts the actual straight-line distance (i.e., adjacent distance) between two adjacent illumination points in the illumination point location set based on target road information. Then, combined with video image information and the determined target object's moving speed, it estimates the total braking distance required for the target object to come to a complete stop from the point of danger detection. Subsequently, it calculates the number of target buffers that need to be additionally illuminated by dividing the total braking distance by the adjacent distance and rounding up. Finally, starting from the target illumination point location corresponding to the dangerous object, it sequentially selects the target buffer number of adjacent illumination points along its moving direction to determine the buffer illumination point location. This provides a precise illumination range basis for the subsequent generation of the first illumination optimization method, thus completing the scientific delineation of the buffer illumination points for dangerous objects.

[0091] On the one hand, by calculating the target buffer quantity using adjacent distances and total braking distances, the buffer lighting range is ensured to fully cover the braking distance of the hazardous object, avoiding blind spots for the driver during braking due to insufficient lighting and significantly reducing safety hazards at high speeds. On the other hand, the buffer quantity is determined solely based on actual braking needs, without adding unnecessary lighting points, thus avoiding energy waste caused by excessive lighting and balancing safety and energy conservation requirements. Furthermore, the entire calculation process relies on inherent road information (adjacent distances) and dynamic data of the target object (moving speed), making it logically clear, quantifiable, and free from subjective experience, with strong applicability. This provides a scientific and reliable buffer range delineation scheme for lighting optimization in high-speed hazardous object scenarios.

[0092] Reference Figure 7 In one embodiment of this example, step S602, which estimates the total braking distance of the target object based on video image information and movement speed, includes steps S701 to S707: Step S701: Call the reaction time under different states.

[0093] Specifically, in this embodiment, the reaction time is the time from when the driver or pedestrian notices the danger to when they begin to brake. According to traffic regulations, the driver's reaction time is set to 1.5 seconds, and the pedestrian's reaction time is set to 0.8 seconds.

[0094] Step S702: Obtain the reaction distance based on the reaction time and movement speed.

[0095] Specifically, reaction distance = reaction time × movement speed. For example, if the vehicle speed is 20 meters per second (72 kilometers per hour) and the reaction time is 1.5 seconds, then the reaction distance = 1.5 × 20 = 30 meters. In this embodiment, the target object is considered to be moving at a constant speed during the reaction time.

[0096] Step S703: Obtain the road type of the target road based on video image information.

[0097] Specifically, road type refers to the attribute type of the target road. In this embodiment, the road surface material (such as asphalt, cement) and weather effects (such as dry, wet) are identified through video images. For example, it is identified as "dry asphalt road surface".

[0098] Step S704: Based on the road type, obtain the adhesion coefficient corresponding to the target object.

[0099] Specifically, in this embodiment, the adhesion coefficient is determined according to the road type. It can be set based on experience or relevant industry data. For example, the adhesion coefficient is 0.8 for dry asphalt pavement, 0.5 for wet asphalt pavement, and 0.2 for icy and snowy pavement.

[0100] Step S705: Obtain braking acceleration based on the adhesion coefficient.

[0101] Specifically, in this embodiment, the braking acceleration is determined by the ground adhesion coefficient μ and the gravitational acceleration g (≈9.8 m / s²). 2 The braking acceleration is determined to be equal to the gravitational acceleration multiplied by the adhesion coefficient, with the gravitational acceleration taken as 9.8 m / s². 2 For example, when the coefficient of adhesion is 0.8, the braking acceleration is 9.8 × 0.8 = 7.84 m / s. 2 .

[0102] Step S706: Obtain the braking distance based on braking acceleration and moving speed.

[0103] Specifically, the braking process distance refers to the distance traveled by the target object from the start of braking to its stop. In this embodiment, the braking process distance = (moving speed) / (moving speed) 2 (2 × braking acceleration), for example, if the speed is 20 m / s, the braking acceleration is 7.84 m / s. 2 Then the braking distance = (20 2 ) / (2×7.84)≈25.51 meters.

[0104] Step S707: Obtain the total braking distance based on the reaction distance and braking process distance.

[0105] Specifically, in this embodiment, the total braking distance = reaction distance + braking process distance, for example, 30 meters + 25.51 meters ≈ 55.51 meters, that is, it takes about 56 meters for the vehicle to stop from detecting danger.

[0106] The road illumination optimization method provided in this embodiment first presets the reaction time corresponding to the target object according to traffic engineering specifications; then, combined with the moving speed of the target object, the reaction distance before braking after the target object detects the danger is calculated by multiplying the reaction time by the moving speed; subsequently, based on video image information, the road type of the target road is determined by image recognition technology; a preset adhesion coefficient between the target object and the road surface is matched according to different road types; the braking acceleration of the target object is calculated by combining the adhesion coefficient with the gravitational acceleration; then, the braking process distance of the target object from the start of braking to complete stop is calculated; finally, the reaction distance and the braking process distance are added together to obtain the total braking distance of the target object.

[0107] On the one hand, the total braking distance is broken down into reaction distance and braking process distance, calculated separately based on the characteristics of the target object (reaction time) and the actual road conditions (adhesion coefficient). This avoids the errors of a single estimation method, ensuring that the total braking distance is highly matched with the actual scenario. This provides reliable data support for the reasonable setting of buffer lighting points, thereby ensuring the clarity of vision during the braking process of dangerous objects at high speeds and reducing safety risks. On the other hand, the adhesion coefficient is dynamically adjusted according to the road type, making the estimation results adaptable to different weather and road conditions, thus improving the universality of the method. At the same time, the entire calculation process is based on traffic engineering principles and objective data, with rigorous logic and reproducibility, avoiding interference from subjective experience. This provides a precise basis for subsequent lighting optimization and further enhances the scientific nature and safety of lighting control in high-speed scenarios, taking into account both energy-saving and safety requirements.

[0108] Reference Figure 8 In one embodiment of this example, if the moving speed is zero in step S107, the method for generating a second illumination optimization based on the target illumination point position includes steps S801 to S804: Step S801: If the moving speed is zero, obtain the target illumination corresponding to the target illumination point position.

[0109] Specifically, a high-precision light sensor (measurement range 0-100 lux, accuracy ±1 lux) is pre-installed at the target illumination point. When the detected target object's movement speed is 0, the light sensor collects the actual illumination at a height of 1.5 meters below the illumination point (pedestrian eye level) in real time, which is the target illumination. For example, if the target illumination point corresponding to a car parked on the roadside is "L-062", the sensor collects a target illumination of 35 lux, and simultaneously transmits the data to the edge computing node for subsequent judgment.

[0110] Step S802: If the target illumination is greater than or equal to the first illumination threshold, then obtain the environmental information corresponding to the target illumination point.

[0111] Specifically, in this embodiment, environmental information is a multi-dimensional set of information surrounding the target lighting point and influencing the decision on lighting brightness. It mainly includes information related to residential areas (such as the location, size, and building height of residential areas), traffic flow information (dynamic traffic data of the area covered by the target lighting point at the current moment, such as the target vehicle flow and the target pedestrian flow), and time period and weather auxiliary information (such as the current moment and weather conditions).

[0112] Step S803: Based on environmental information, obtain information on residential areas associated with the target lighting point, as well as the target vehicle flow and target pedestrian flow corresponding to the target lighting point at the current moment.

[0113] Specifically, in this embodiment, the residential information is obtained by querying residential data within a 500-meter radius of the target lighting point through the GIS system, including the name, location, size, and floor height of the residential area; the target vehicle and pedestrian traffic is counted through video image recognition. The monitoring screen covered by the target lighting point is analyzed using frame difference method and target tracking algorithm to count the number of vehicles and pedestrians passing through the area in the current 10 minutes, and invalid targets in non-road areas are filtered out.

[0114] Step S804: Based on the residential area information, target vehicle flow, and target pedestrian flow, generate a second lighting brightness optimization method.

[0115] Specifically, in this embodiment, the generation logic focuses on balancing safety requirements with energy conservation and light pollution prevention requirements. If the residential area is close (≤300 meters) and large (≥500 households), and the current time is after 22:00 (residents' rest period), the lighting intensity needs to be appropriately reduced even if the traffic flow is slightly high. If the target traffic flow is ≥20 vehicles / 10 minutes or the pedestrian flow is ≥15 people / 10 minutes, the lighting intensity needs to be maintained to avoid safety hazards. For example, in the current scenario, the residential area is 280 meters away, with 620 households, and the time is 21:30 (not a deep rest period). The traffic flow is 12 vehicles / 10 minutes and the pedestrian flow is 7 people / 10 minutes. The final optimization method is to reduce the brightness of the target lighting point from the rated brightness to 80% of the rated brightness, which satisfies basic safety lighting while reducing light interference to residents.

[0116] The road illumination optimization method provided in this embodiment collects the current actual illumination of the target illumination point in real time using a high-precision light sensor deployed at the target illumination point location. Then, it determines whether the target illumination is greater than or equal to a preset first illumination threshold. If the threshold condition is met, it further obtains the environmental information corresponding to the target illumination point. Finally, it comprehensively analyzes residential information, target vehicle flow, and target pedestrian flow to generate a second illumination optimization method adapted to the static object scene, thereby completing the dynamic adjustment of illumination brightness in the static object scene.

[0117] On the one hand, sufficient brightness scenes are first selected by using a first illumination threshold to avoid blindly dimming stationary areas with insufficient brightness, thus ensuring basic safety. On the other hand, dynamic adjustments are made based on environmental information. Brightness is reduced in scenes near residential areas and during rest periods to reduce light pollution, while brightness is maintained in scenes with high traffic and pedestrian flow to avoid safety hazards, thus balancing the needs of safe lighting with light pollution prevention and energy conservation. At the same time, environmental information acquisition relies on existing GIS systems and video recognition technology, with real-time and accurate data. No additional equipment is required, resulting in low implementation costs and high efficiency. This effectively solves the problems of excessive brightness in traditional fixed lighting in stationary scenes, which leads to waste and light interference with residents, thus improving the scientific nature and practicality of lighting control in stationary scenes.

[0118] Reference Figure 9 In one embodiment of this example, step S804, based on residential area information, target vehicle flow, and target pedestrian flow, generates a second illumination optimization method, which includes steps S901 to S904: Step S901: Based on the residential area information, obtain the location, size, and floor height of the residential area.

[0119] Specifically, through the spatial query interface of the GIS system, the latitude and longitude coordinates of the target lighting point are input, the query radius is set to 500 meters, and all residential data are filtered out. The location of a residential point refers to its specific geographical coordinates (latitude, longitude, or planar coordinates), used to calculate the distance to the target lighting point; the size of a residential point refers to the density of residence measured by the number of households or population; a larger size means more people are affected by the light; the building height of a residential point refers to the general height of the buildings in the target residential point. For example, if a residential point has 18 buildings, 10 of which are 18 stories and 8 are 8 stories, then the building height of this residential point is set to 18 stories, with each floor calculated at 3 meters, resulting in a building height of 54 meters.

[0120] Step S902: Obtain the target distance based on the location of the target lighting point and the location of the residential area.

[0121] Specifically, the target distance refers to the straight-line distance between the target lighting point and the residential area, which is calculated by converting latitude and longitude coordinates. In this embodiment, the coordinate point of the target residential area closest to the target lighting point is selected for calculation.

[0122] Step S903: Obtain the illuminance score based on the target distance, the size of the residential area, the building height of the residential area, the target vehicle flow, and the target pedestrian flow.

[0123] Specifically, in this embodiment, the influencing factors are divided into two categories: traffic demand and resident impact. Traffic demand includes target vehicle flow and target pedestrian flow; resident impact includes the size of the residential area, the building height of the residential area, and the target distance.

[0124] Traffic demand is categorized into low, medium, and high levels. Low level indicates a traffic flow of ≤10 vehicles / 10 minutes and a pedestrian flow of ≤5 people / 10 minutes, with a traffic demand score of 1 point. Medium level indicates a traffic flow of 11-20 vehicles / 10 minutes and / or a pedestrian flow of 6-15 people / 10 minutes, with a traffic demand score of 2 points. High level indicates a traffic flow of ≥21 vehicles / 10 minutes and / or a pedestrian flow of ≥16 people / 10 minutes, with a traffic demand score of 3 points.

[0125] The impact score for residents is determined based on the degree of impact: low, medium, or high. Specifically, if the number of households in the residential area is ≤300, the building height is ≤15 meters, and the distance to the property is ≥300 meters, the impact on residents is considered low, and the score is 1 point. If the number of households in the residential area is 301-1000, the building height is 16-30 meters, and the distance to the property is 100-299 meters, the impact on residents is considered medium, and the score is 2 points. If the number of households in the residential area is ≥1001+, the building height is ≥31 meters, and the distance to the property is ≤99 meters, the impact on residents is considered high, and the score is 3 points.

[0126] Step S904: Generate a second illumination optimization method based on the illuminance score.

[0127] Specifically, in this embodiment, a pre-set correspondence between different illuminance fractions and the brightness of the illumination point is established. Therefore, the brightness adjustment range of the target illumination point can be determined based on the range of illuminance fraction F.

[0128] The road lighting optimization method provided in this embodiment extracts the location, size, and floor height of residential areas based on residential area information. Then, it calculates the target distance between the target lighting point and the residential area using coordinates. Subsequently, it substitutes the residential area size, floor height, target traffic flow, target pedestrian flow, and target distance into a preset illuminance score calculation formula to calculate a quantified illuminance score. Finally, based on the numerical range of the illuminance score, it generates a second lighting optimization method adapted to the current scene, thus achieving precise lighting control based on multi-dimensional quantified data in static object scenes.

[0129] On the one hand, qualitative information such as the size of residential areas and the height of buildings is transformed into calculable quantitative parameters. Combined with dynamic data such as traffic flow and pedestrian flow, an objective illuminance score is derived through formulas. This avoids the errors caused by relying on subjective experience in traditional lighting control, making brightness adjustments more based on evidence and consistent. On the other hand, the illuminance score can comprehensively balance safety requirements and light pollution prevention / energy saving requirements. It avoids excessive or insufficient brightness caused by a single factor and accurately matches the lighting needs of different scenarios. This further enhances the universality and applicability of the second illuminance optimization method, providing a reliable technical path for the intelligent and refined control of lighting in static scenes.

[0130] It is worth noting that in this embodiment, if the number of target objects within a unit distance (100 meters) on the target road exceeds a certain number (e.g., 5), the streetlights at all lighting points in the section will maintain their rated brightness. If there are different situations or areas that overlap, the method with higher brightness will be implemented.

[0131] Secondly, this application also discloses a road lighting optimization system.

[0132] Reference Figure 10 A road lighting optimization system, comprising: The first acquisition module 1 is used to acquire road information and video image information of the target road; The second acquisition module 2 is used to acquire the set of lighting point locations corresponding to the target road based on road information; The third acquisition module 3 is used to acquire target object information corresponding to the target road based on video images; The fourth acquisition module 4 is used to acquire the target position and movement speed of the target object based on the target object information; The fifth acquisition module 5 is used to acquire the position of the target illumination point based on the target position and the set of illumination point positions; If the moving speed is greater than zero, the first generation module 6 is used to generate a first illumination optimization method based on the moving speed and the position of the target illumination point. If the moving speed is zero, the second generation module 7 is used to generate a second illumination optimization method based on the target illumination point position.

[0133] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for optimizing road lighting, characterized in that, The method comprises: obtaining road information and video image information of a target road; based on the road information, obtaining a set of lighting point positions corresponding to the target road; based on the video image, obtaining target object information corresponding to the target road; based on the target object information, obtaining a target position and a moving speed of a target object; based on the target position and the set of lighting point positions, obtaining a target lighting point position; if the moving speed is greater than zero, generating a first lighting intensity optimization method based on the moving speed and the target lighting point position; if the moving speed is equal to zero, generating a second lighting intensity optimization method based on the target lighting point position.

2. A road lighting level optimization method according to claim 1, characterized in that, The method of generating a first lighting intensity optimization method based on the moving speed and the target lighting point position if the moving speed is greater than zero comprises: if the moving speed is greater than zero, determining whether the moving speed exceeds a first speed threshold; if the moving speed is greater than or equal to the first speed threshold, marking the target object as a dangerous object; based on the target lighting point position corresponding to the dangerous object and the moving speed, obtaining a buffer lighting point position; based on the target lighting point position and the buffer lighting point position, generating a first lighting intensity optimization method; if the moving speed is less than the first speed threshold, obtaining a target number of target objects; if the target number is equal to 1, generating a first lighting intensity optimization method based on the target lighting point position.

3. A method of optimizing road lighting levels according to claim 2, characterized in that, The method further comprises, after obtaining a target number of target objects if the moving speed is less than the first speed threshold: if the target number is greater than 1, obtaining a corresponding relationship between different target objects; if the corresponding relationship is a same-direction relationship, obtaining a speed difference between different target objects; if the speed difference is greater than or equal to a preset speed threshold, obtaining a relative position change between different target objects; if the relative position change is a relative approach, obtaining a relative distance; based on the target lighting point position and the relative distance, obtaining a first lighting intensity optimization method.

4. A road lighting level optimization method according to claim 3, characterized in that, The method further comprises, after obtaining a corresponding relationship between different target objects if the target number is greater than 1: if the corresponding relationship is an opposite-direction relationship, determining whether the lighting point position corresponding to the target road is a middle of the target road; if the lighting point position is the middle of the target road, generating a first lighting intensity optimization method based on a first target lighting point position and a second target lighting point position; if the lighting point position is not the middle of the target road, determining whether the target road has a separation belt; if the target road does not have a separation belt, generating a first lighting intensity optimization method based on the first target lighting point position and the second target lighting point position.

5. A method of optimizing road lighting levels according to claim 4, characterized in that, The method of generating a first lighting intensity optimization method based on the first target lighting point position and the second target lighting point position if the target road does not have a separation belt comprises: based on the first target lighting point position and the second target lighting point position, obtaining a relative distance between a first target object and a second target object; acquiring a moving speed sum between the first target object and the second target object; acquiring a first estimated moving time based on the moving speed sum and the relative distance; if the first estimated moving time is less than or equal to a first time threshold, acquiring an intermediate lighting point position based on the first target lighting point position and a second target lighting point position; acquiring a first lighting degree optimization method based on the first target lighting point position, the second target lighting point position and the intermediate lighting point position.

6. The method of claim 2, wherein, the acquiring the buffer lighting point position based on the target lighting point position corresponding to the dangerous object and the moving speed comprises: acquiring a neighboring distance between neighboring lighting point positions based on the road information; estimating a total braking distance of the target object based on the video image information and the moving speed; acquiring a target buffer quantity based on the total braking distance and the neighboring distance; acquiring the buffer lighting point position based on the target lighting point position and the target buffer quantity.

7. A method of optimizing road lighting levels according to claim 6, characterized in that, the estimating the total braking distance of the target object based on the video image information and the moving speed comprises: calling a reaction time in different states; acquiring a reaction distance based on the reaction time and the moving speed; acquiring a road type of the target road based on the video image information; acquiring an adhesion coefficient corresponding to the target object based on the road type; acquiring a braking acceleration based on the adhesion coefficient; acquiring a braking process distance based on the braking acceleration and the moving speed; acquiring the total braking distance based on the reaction distance and the braking process distance.

8. The method of claim 1, wherein, if the moving speed is equal to zero, the acquiring the second lighting degree optimization method based on the target lighting point position comprises: if the moving speed is equal to zero, acquiring a target lighting degree corresponding to the target lighting point position; if the target lighting degree is greater than or equal to a first lighting degree threshold, acquiring environment information corresponding to the target lighting point; acquiring resident point information associated with the target lighting point and a target vehicle flow and a target people flow corresponding to the target lighting point at a current time based on the environment information; generating the second lighting degree optimization method based on the resident point information, the target vehicle flow and the target people flow.

9. A method of optimizing road lighting levels according to claim 8, characterized in that, the generating the second lighting degree optimization method based on the resident point information, the target vehicle flow and the target people flow comprises: acquiring a resident point position, a resident point scale and a resident point floor height based on the resident point information; acquiring a target distance based on the target lighting point position and the resident point position; acquiring an illumination score based on the target distance, the resident point scale, the resident point floor height, the target vehicle flow and the target people flow; generating the second lighting degree optimization method based on the illumination score.

10. A road lighting level optimization system characterized by, comprises: a first acquiring module (1) configured to acquire road information and video image information of a target road; a second acquiring module (2) configured to acquire a set of lighting point positions corresponding to the target road based on the road information; A third obtaining module (3) is configured to obtain target object information corresponding to the target road based on the video image; A fourth obtaining module (4) is configured to obtain a target position and a moving speed of a target object based on the target object information; A fifth obtaining module (5) is configured to obtain a target lighting point position based on the target position and the set of lighting point positions; A first generating module (6) is configured to generate a first lighting degree optimization method based on the moving speed and the target lighting point position if the moving speed is greater than zero; A second generating module (7) is configured to generate a second lighting degree optimization method based on the target lighting point position if the moving speed is equal to zero.

Images