Tunnel illumination control method and system based on video monitoring

Abstract

The invention belongs to the technical field of illumination control, and discloses a tunnel illumination control method and system based on video monitoring, and the method comprises the steps: recognizing a lamp, a lane and a vehicle based on a video image, and determining the type of the lane; dividing the tunnel into a plurality of detection areas, and calculating a conversion scale factor between a pixel distance and an actual distance; determining the speed of the vehicle and the arrival time of the vehicle to the next lamp by using a target tracking algorithm according to the vehicle identification result and the conversion scale factor; the road space occupancy rate of each detection area is calculated according to the vehicle identification result, the conversion scale factor and the lane type, so that the target color temperature and the corresponding target power of the lamps in each detection area are determined, and the plurality of lamps in front of the vehicle are controlled to work according to the target color temperature and the corresponding target power; real-time and refined illumination control based on actual traffic conditions can be realized, energy is effectively saved, and driving safety and energy utilization efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of lighting control, and in particular, to a tunnel lighting control method and system based on video monitoring. Background Art

[0002] As a key transportation facility, the internal lighting environment of a tunnel plays a crucial role in driving safety. The traditional tunnel lighting system has limitations. It often adopts a unified switch control method, and at the preset switch time, all the lamps in the tunnel are switched on and off uniformly, making it difficult to make real-time adjustments according to the actual traffic conditions and environmental changes. For example, all the lamps are often kept on when there is no vehicle passing through, resulting in a waste of electric power resources. In addition, in the existing traditional tunnel lighting system, generally only the on / off state and brightness of the lamps are controlled, and the color temperature is not adjusted according to the actual traffic conditions. In fact, different color temperatures have different effects on the driver's vision, and under the same luminous flux condition, different color temperatures require different powers. Using a unified color temperature for lighting is neither conducive to improving driving safety nor to improving energy utilization efficiency.

[0003] In view of the above problems, the existing technology urgently needs to be improved. Summary of the Invention

[0004] The purpose of the present application is to provide a tunnel lighting control method and system based on video monitoring, which can realize real-time and refined lighting control based on the actual traffic conditions, effectively save energy, and improve driving safety and energy utilization efficiency.

[0005] In a first aspect, the present application provides a tunnel lighting control method based on video monitoring, including the steps of: A1. Obtain video images in the tunnel for identifying lamps, driving lanes, and vehicles; A2. Determine the type of driving lane based on the driving lane recognition result; the type of driving lane includes straight or curved; A3. Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, the type of driving lane, and the lamp spacing; A4. According to the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to determine the position of the vehicle in each detection area to calculate the vehicle speed and predict the arrival time of the vehicle at the next lamp; A5. Calculate the road space occupancy rate of each detection area according to the vehicle recognition result, the conversion ratio factor, and the type of driving lane to determine the target color temperature and the corresponding target power of the lamps in each detection area; A6. Control the on / off, working color temperature, and working power of several lamps in front of the vehicle according to the speed, the lamp spacing, the arrival time, the target color temperature, and the target power.

[0006] Preferably, step A1 includes: A101. Obtain the original video image in the tunnel, perform preprocessing to obtain the preprocessed video image; the preprocessing includes grayscale conversion processing for converting a color image into a grayscale image, Gaussian filtering processing, and histogram equalization processing; A102. Use an object detection algorithm to identify the lamps and vehicles in the preprocessed video image; A103. Use the Canny algorithm to identify the driving lane in the preprocessed video image.

[0007] Preferably, step A2 includes: A201. Detect the identified driving lane through the Hough transform to determine whether the driving lane is a straight line; A202. If no straight line is detected, determine that the driving lane is a curve, and use the curve fitting method to fit the curve equation of the driving lane.

[0008] Preferably, step A3 includes: A301. Divide the tunnel into multiple detection areas along the length direction according to the preset lamp spacing; A302. Extract the pixel coordinates of the lamps according to the lamp recognition result; A303. If the driving lane is a straight line, calculate the average value of the straight-line pixel distances between adjacent lamps according to the pixel coordinates of the lamps as the lamp pixel spacing; A304. If the driving lane is a curve, calculate the average value of the curve pixel distances between adjacent lamps along the curve equation according to the pixel coordinates of the lamps and the curve equation of the driving lane as the lamp pixel spacing; A305. Calculate the conversion ratio factor between the pixel distance and the actual distance according to the lamp pixel spacing and the lamp spacing.

[0009] Preferably, step A4 includes: A401. According to the vehicle recognition result and the conversion ratio factor, use an object tracking algorithm to track the position of the vehicle in each detection area to obtain the movement trajectory of the vehicle; A402. Calculate the speed of the vehicle according to the movement trajectory; A403. Calculate the arrival time of the vehicle at the next lamp according to the current position of the vehicle and the position of the next lamp, in combination with the speed of the vehicle.

[0010] Preferably, step A5 includes: A501. Calculate the road area of each detection area according to the type of driving lane and the preset road width; A502. Calculate the actual area of the target detection frame of the vehicle according to the pixel size of the target detection frame of the vehicle and the conversion ratio factor, and use the actual area of the target detection frame of the vehicle as the occupied area of the vehicle, and calculate the total occupied area of all vehicles in each detection area; A503. Divide the total occupied area by the corresponding road area to obtain the road space occupancy rate of each detection area; A504. Compare the road space occupancy rate with the preset occupancy rate threshold to determine the target color temperature and the corresponding target power of the lamps in each detection area.

[0011] Preferably, step A504 includes: If the road space occupancy rate is greater than the first occupancy rate threshold, determine the target color temperature as the first preset color temperature; If the road space occupancy rate is less than the second occupancy rate threshold, determine the target color temperature as the second preset color temperature; the first occupancy rate threshold is greater than the second occupancy rate threshold, and the first preset color temperature is greater than the second preset color temperature; If the road space occupancy rate is between the second occupancy rate threshold and the first occupancy rate threshold, determine the target color temperature based on linear interpolation operation, or determine the target color temperature as the third preset color temperature; the third preset color temperature is greater than the second preset color temperature and less than the first preset color temperature; Obtain the light efficiency parameter corresponding to the determined target color temperature and the target value of luminous flux required by the tunnel lighting design; Divide the target value of luminous flux by the light efficiency parameter to obtain the target power corresponding to the target color temperature.

[0012] Preferably, step A6 includes: A601. Determine a plurality of lamps located in front of the vehicle as the target lamp group according to the speed and the lamp spacing; A602. Determine the turn-on time and turn-off time of the target lamp group according to the arrival time; A603. Turn on the target lamp group at the turn-on time, and make the working color temperature of the target lamp group equal to the corresponding target color temperature, and the working power equal to the corresponding target power; A604. If it is detected that the vehicle arrives at the target lamp group before the turn-off time, calculate a delay time according to the speed of the vehicle, and delay the turn-off of the target lamp group; if the vehicle does not arrive at the target lamp group at the turn-off time, turn off the target lamp group.

[0013] Preferably, after step A603 and before step A604, it further includes: By means of an image detection method, it is detected whether the lamps in the target lamp group are successfully turned on, and an abnormal warning is issued when they are not successfully turned on.

[0014]

[0014] In a second aspect, the present application provides a tunnel lighting control system based on video surveillance, including a plurality of lamps arranged at intervals along the tunnel, several cameras, and a control terminal; The cameras are used to collect video images inside the tunnel and send them to the control terminal; The control terminal is used to execute: Identify the lamps, the driving lane, and the vehicle according to the video images; Determine the type of the driving lane based on the recognition result of the driving lane; the types of the driving lane include straight or curved; Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, the type of the driving lane, and the lamp spacing; According to the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to determine the position of the vehicle in each detection area, so as to calculate the speed of the vehicle and predict the arrival time of the vehicle at the next lamp; Calculate the road space occupancy rate of each detection area according to the vehicle recognition result, the conversion ratio factor, and the type of the driving lane, so as to determine the target color temperature and the corresponding target power of the lamps in each detection area; Control the on / off, the working color temperature, and the working power of several lamps in front of the vehicle according to the speed, the lamp spacing, the arrival time, the target color temperature, and the target power.

[0015]

[0015] Beneficial effects: The tunnel lighting control method and system based on video surveillance provided by the present application obtain traffic information through video surveillance, and dynamically adjust the on / off, color temperature, and power of the lamps based on this information, so as to achieve lighting on demand, and can realize real-time and refined lighting control based on the actual traffic conditions, effectively save energy, and improve driving safety and energy utilization efficiency. Description of the Drawings

[0016] Figure 1 Figure 1 It is a flowchart of the tunnel lighting control method based on video surveillance provided by an embodiment of the present application.

[0017] Figure 2 Figure 2 It is a schematic structural diagram of the tunnel lighting control system based on video surveillance provided by an embodiment of the present application.

[0018]

[0018] Reference numerals: 1, lamp; 2, camera; 3, control terminal. Specific Embodiments

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , a tunnel lighting control method based on video surveillance in some embodiments of the present application, includes the steps: A1. Obtain video images in the tunnel for identifying lamps, driving lanes, and vehicles; A2. Determine the type of driving lane based on the driving lane recognition result; the type of driving lane includes straight or curved; A3. Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, driving lane type, and lamp spacing; A4. According to the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to determine the position of the vehicle in each detection area to calculate the vehicle speed and predict the arrival time of the vehicle at the next lamp; A5. Calculate the road space occupancy rate of each detection area according to the vehicle recognition result, conversion ratio factor, and driving lane type to determine the target color temperature and corresponding target power of the lamps in each detection area; A6. Control the on / off, working color temperature, and working power of several lamps in front of the vehicle according to the speed, lamp spacing, arrival time, target color temperature, and target power.

[0022] The core of the present application is to use video surveillance to obtain real-time traffic information and, based on this information, achieve on-demand, local, and multi-parameter (on / off, color temperature, power) control of tunnel lamps, thereby achieving energy conservation and providing a suitable lighting environment.

[0023] The working process and principle of this application are as follows: by obtaining real-time video images in the tunnel and dynamically and regionally controlling the tunnel lighting based on the image analysis results.

[0024] Specifically, in step A1, video images in the tunnel are obtained, which are the basic data for subsequent processing. By analyzing these video images, the lamps, driving lanes, and vehicles in the images are identified. The lamp identification provides the position information of the lighting equipment, the driving lane identification provides the geometric structure information of the road, and the vehicle identification provides the dynamic information of traffic participants.

[0025] Based on the driving lane identification result, in step A2, the type of the driving lane is determined. The driving lane type is divided into straight or curved, which provides a geometric basis for accurately calculating distances and dividing regions subsequently.

[0026] In step A3, according to the spacing between lamps (which can be obtained according to the design requirements of tunnel lighting or pre-measured), the tunnel is divided into multiple detection regions along the length direction, so that each region corresponds to one or a group of lamps, realizing regional control of lighting. Based on the lamp identification result, the driving lane type, and the lamp spacing, the conversion scale factor between the pixel distance and the actual distance is calculated. Among them, based on the lamp identification result, the pixel position of the lamp can be obtained, and then according to the driving lane type, the corresponding calculation method is used to calculate the pixel distance between lamps, and then the ratio of the lamp spacing to this pixel distance is calculated to obtain the conversion scale factor between the pixel distance and the actual distance, providing support for accurately calculating the speed and road space occupancy rate subsequently.

[0027] According to the vehicle identification result, in step A4, the target tracking algorithm is used to determine the position of the vehicle in each detection region. By continuously tracking the position change of the vehicle, the real-time speed of the vehicle is calculated. Further, according to the current position of the vehicle and the position of the next lamp, combined with the speed of the vehicle, the arrival time of the vehicle at the next lamp is predicted. Predicting the vehicle arrival time enables the system to proactively adjust the lighting state.

[0028] According to the vehicle identification result, the conversion scale factor, and the driving lane type, in step A5, the road space occupancy rate is calculated. Through the identified vehicle information, the space proportion occupied by the vehicle on the road is estimated. Combining the driving lane type (which affects the road area calculation), the road space occupancy rate is calculated to reflect the traffic congestion degree. Based on the road space occupancy rate, the appropriate target color temperature and the corresponding target power are determined. Associating the lighting parameters with the traffic density enables the lighting to adapt to different traffic conditions. For example, when the road is congested, the color temperature is increased to enhance the driver's attention and help them better cope with the congested road conditions; when the road is unobstructed, the color temperature is decreased to make the driver's visual experience more comfortable and reduce visual fatigue during long driving.

[0029] Finally, based on the predicted arrival time of the vehicle at the next lamp, the determined target color temperature, and the corresponding target power, step A6 determines several lamps in front of the vehicle as control objects and controls the on / off states, working color temperatures, and working powers of these lamps. This is the final execution step of the method, which converts the information obtained from the previous analysis and calculation into specific control instructions to achieve lighting on demand and intelligent dimming and color adjustment.

[0030] Through the above solution, the present application can dynamically adjust the lighting according to the real-time traffic conditions in the tunnel, avoid unnecessary lighting when there is no vehicle or low traffic flow, and reduce energy consumption. At the same time, the color temperature and power of the lighting are adjusted according to the traffic density to provide a lighting effect that matches the actual traffic environment, improving driving safety and the visual comfort of drivers. Thus, the problem that the traditional tunnel lighting system cannot adjust the lighting in real time according to the actual traffic conditions, resulting in energy waste and poor lighting effects, is solved.

[0031] In some embodiments, step A1 includes: A101. Obtain the original video image in the tunnel, perform preprocessing, and obtain the preprocessed video image; the preprocessing includes grayscale conversion processing for converting a color image into a grayscale image, Gaussian filtering processing, and histogram equalization processing; A102. Use an object detection algorithm to identify the lamps and vehicles in the preprocessed video image; A103. Use the Canny algorithm to identify the driving lane in the preprocessed video image.

[0032] Among them, in step A101, the grayscale conversion converts the color image into a grayscale image, simplifies the image data, reduces the computational complexity, and eliminates the interference that may be brought by color information, making the subsequent feature extraction and recognition more focused on the structure and brightness information of the image. The Gaussian filtering processing is used to smooth the image, remove the noise in the image, reduce the influence of the noise on the recognition result, and improve the stability of the recognition. The histogram equalization processing is used to enhance the contrast of the image. Especially in a tunnel environment with uneven illumination or low contrast, by stretching the distribution of pixel values, the target features in the image become more prominent, which is beneficial for the subsequent recognition algorithm to work more effectively. Through these preprocessing steps, the original video image is optimized into a preprocessed image that is more suitable for object and feature recognition.

[0033] Among them, in step A102, the target detection algorithm usually has strong feature learning and classification capabilities and is suitable for identifying objects with certain shape and texture features, such as lamps and vehicles. Applying the target detection algorithm to the preprocessed (such as noise reduction and contrast enhancement) image can improve the detection rate and accuracy of lamps and vehicles, ensuring reliable acquisition of these key information. Thus, it provides more accurate input for determining the lamp spacing based on the lamp recognition result and determining the vehicle position, calculating the speed, and predicting the arrival time based on the vehicle recognition result. The target detection algorithm can use the YOLO algorithm, but is not limited thereto.

[0034] Among them, in step A103, the Canny algorithm is a classic edge detection algorithm that is insensitive to noise and can detect clear edges in the image. The driving lane usually appears as a line with obvious edges in the image, and using the Canny algorithm can effectively extract this edge information to identify the driving lane. For example, the intensity of the edge can be determined by setting two thresholds. Applying the Canny algorithm to the preprocessed (such as grayscale conversion and noise reduction) image can more accurately detect the edges of the driving lane, thus providing accurate basic data for determining the type of driving lane and calculating the road space occupancy rate based on the driving lane recognition result. By using different recognition algorithms for different recognition objects, the overall recognition efficiency and effect are improved.

[0035] Through the above technical solutions, this application overcomes the problems of uneven illumination and noise interference encountered when directly using the original video image for recognition. The grayscale conversion processing reduces the data dimension and simplifies the processing process. The Gaussian filtering processing effectively suppresses image noise and improves the image quality. The histogram equalization processing enhances the image contrast, making the target features in the image clearer. Using the target detection algorithm to identify lamps and vehicles and the Canny algorithm to identify the driving lane, these algorithms are selected according to the characteristics of their respective recognition objects, improving the recognition accuracy. Thus, it provides a reliable recognition result for subsequent tunnel lighting control.

[0036] In some embodiments, step A2 includes: A201. Detect the recognized driving lane through the Hough transform to determine whether the driving lane is a straight line; A202. If no straight line is detected, determine that the driving lane is a curve and use the curve fitting method to fit the curve equation of the driving lane.

[0037] Among them, in step A201, the recognized driving lane is detected by the Hough transform to determine whether the driving lane is a straight line. The Hough transform is an image processing algorithm applicable to detecting straight lines in images (its detection process is a prior art and will not be elaborated here). By performing the Hough transform on the recognized driving lane in step A1, it can be analyzed whether it conforms to the mathematical characteristics of a straight line, thereby determining whether the driving lane is a straight line. This is the first step in determining the type of driving lane.

[0038] Among them, step A202 is a branch process based on the previous judgment result. If a straight line cannot be detected by the Hough transform in step A201, it is determined that the driving lane is a curve. In order to perform accurate calculations based on the curve characteristics subsequently, this step further adopts a curve fitting method. Curve fitting can obtain a continuous curve equation from the recognized discrete driving lane pixel points through mathematical methods. For example, methods such as polynomial fitting or spline fitting can be used to fit the curve equation.

[0039] This application provides a method for objectively determining whether a driving lane is a straight line by introducing the Hough transform. If it is determined to be a curve, its mathematical equation is obtained through curve fitting. This makes the determination of the driving lane type have a clear technical basis. Accurately determining the driving lane type enables the subsequent calculations of the pixel spacing of lamps and the road space occupancy rate based on the driving lane type to adopt geometric models suitable for straight lines or curves, improving the accuracy of these calculations.

[0040] In some embodiments, step A3 includes: A301. Divide the tunnel into multiple detection regions along the length direction according to the preset lamp spacing; A302. Extract the pixel coordinates of the lamps according to the lamp recognition result; A303. If the driving lane is a straight line, calculate the average value of the straight-line pixel distances between adjacent lamps according to the pixel coordinates of the lamps as the lamp pixel spacing; A304. If the driving lane is a curve, calculate the average value of the curve pixel distances along the curve equation between adjacent lamps according to the pixel coordinates of the lamps and the curve equation of the driving lane as the lamp pixel spacing; A305. Calculate the conversion ratio factor between the pixel distance and the actual distance according to the lamp pixel spacing and the lamp spacing.

[0041] Among them, in step A301, the number of lamps included in each detection region can be preset, and the length of a single detection region is determined according to this number and the preset lamp spacing, thereby dividing the detection regions according to this length.

[0042] Among them, in step A302, the pixel coordinates of the lamps are extracted. The lamp recognition result can provide the position information of the lamp in the image. Extracting the pixel coordinates of the lamp is the basis for subsequent distance calculation. For example, the center point coordinates of the lamp target detection box can be extracted as the pixel coordinates of the lamp, or the centroid coordinates of the lamp area can be extracted.

[0043] Furthermore, steps A303 and A304 perform different pixel distance calculations according to the type of driving lane determined in step A2. Step A2 determines whether the driving lane is a straight line or a curve, and fits the curve equation when it is a curve.

[0044] If step A2 determines that the driving lane is a straight line, then step A303 is executed. In step A303, according to the extracted pixel coordinates of adjacent lamps, the straight-line distance between them is calculated. For example, the Euclidean distance formula can be used to calculate the straight-line distance between pixel coordinates. In order to obtain a more accurate conversion scale factor estimation result, the straight-line pixel distances between multiple pairs of adjacent lamps can be calculated and their average value can be used as the effective lamp pixel spacing.

[0045] If step A2 determines that the driving lane is a curve, then step A304 is executed. In step A304, using the extracted pixel coordinates of adjacent lamps and the curve equation of the driving lane fitted in step A2, the pixel distance along the curve equation between adjacent lamps is calculated. For example, the pixel coordinates of adjacent lamps are projected onto the curve equation, and the arc length between the two projection points is calculated to obtain the pixel distance along the curve equation. Similarly, the average value of the pixel distances along the curve between multiple pairs of adjacent lamps can be calculated as the effective lamp pixel spacing to improve the estimation accuracy of the lamp pixel spacing.

[0046] Thus, different distance calculation methods are selected according to the type of driving lane, avoiding the error caused by simply using the straight-line distance in the curved section, and making the determination of the lamp pixel spacing more accurate.

[0047] Finally, step A305 divides the preset lamp spacing by the lamp pixel spacing calculated in step A303 or A304 to obtain the conversion scale factor between the pixel distance and the actual distance.

[0048] Through the above technical solution, the present application solves the problem that in the process of determining the conversion scale factor, especially when the lane type is a curve, simply calculating the straight-line distance between lamps leads to inaccurate determination of the conversion scale factor. By adopting different distance calculation methods according to the lane type, that is, calculating the straight-line distance when it is a straight line and calculating the distance along the curve when it is a curve, this solution can more accurately obtain the actual pixel interval of the lamps, and further more accurately estimate the conversion scale factor. Thereby, the accuracy of determining the conversion scale factor is improved, providing more reliable support for subsequent steps such as vehicle position determination, speed calculation, and arrival time prediction, and improving the accuracy of these steps.

[0049] In some embodiments, step A4 includes: A401. According to the vehicle recognition result and the conversion scale factor, use the target tracking algorithm to track the position of the vehicle in each detection area and obtain the movement trajectory of the vehicle; A402. Calculate the speed of the vehicle according to the movement trajectory; A403. According to the current position of the vehicle and the position of the next lamp, combined with the speed of the vehicle, calculate the arrival time of the vehicle at the next lamp.

[0050] Among them, in step A401, the vehicle recognition result provides the initial pixel position information of the vehicle at a certain moment. The target tracking algorithm is applied to a continuous sequence of video frames to continuously determine the pixel position of the vehicle at different time points, and then converted into a spatial position according to the conversion scale factor. By connecting the spatial positions of the vehicle at consecutive time points, the movement trajectory of the vehicle can be constructed. For example, a Kalman filter, optical flow method, or deep learning tracker can be used to achieve continuous tracking of the vehicle. Obtaining the movement trajectory of the vehicle provides continuous historical data on the movement of the vehicle, which provides a basis for subsequent speed calculation and arrival time prediction.

[0051] Furthermore, in step A402, after obtaining the movement trajectory of the vehicle, the speed of the vehicle can be calculated based on the trajectory data. For example, the instantaneous speed can be obtained by calculating the ratio of the position change between two adjacent time points to the time interval, or the average speed can be obtained by averaging the position changes over a period of time. Calculating the speed based on the continuous movement trajectory can reduce the influence of single-frame image recognition errors on speed calculation, thereby obtaining more accurate speed information.

[0052] Among them, in step A403, the current position of the vehicle can be obtained from the latest data point of the movement trajectory. The position of the next lamp is pre-determined or obtained through lamp recognition. Combining with the vehicle speed calculated in step A402, using basic kinematic principles, for example, dividing the distance between the current position of the vehicle and the position of the next lamp (wherein, in step A201, if the detected driving lane is a straight line, the straight line fitting method can also be used to fit the straight line equation of the driving lane; thus here, if the driving lane is a straight line, this distance refers to the actual distance corresponding to the straight line distance between the projection points of the current position of the vehicle and the position of the next lamp on this straight line equation; if the driving lane is a curve, this distance refers to the actual distance corresponding to the arc length between the projection points of the current position of the vehicle and the position of the next lamp on the curve equation) by the vehicle speed can be used to predict the time required for the vehicle to reach the next lamp. Clearly associating and calculating the current position of the vehicle, the target position (at the next lamp), and the vehicle speed ensures the logic and accuracy of the arrival time prediction.

[0053] In the above technical solution, by clearly using the target tracking algorithm to obtain the continuous movement trajectory of the vehicle, the continuity and accuracy of the vehicle position information are improved. Calculating the vehicle speed based on the continuous movement trajectory can more accurately reflect the actual movement state of the vehicle and reduce the speed calculation error. Using the current position of the vehicle, the position of the next lamp, and the calculated vehicle speed to predict the arrival time provides a reliable and accurate input for subsequent lamp control based on the arrival time, thereby improving the timeliness and accuracy of lamp control.

[0054] In some embodiments, step A5 includes: A501. Calculate the road area of each detection area according to the type of driving lane and the preset road width; A502. Calculate the actual area of the target detection frame of the vehicle according to the pixel size and conversion ratio factor of the target detection frame of the vehicle, and use the actual area of the target detection frame of the vehicle as the occupied area of the vehicle to calculate the total occupied area of all vehicles in each detection area; A503. Divide the total occupied area by the corresponding road area to obtain the road space occupancy rate of each detection area; A504. Compare the road space occupancy rate with the preset occupancy rate threshold to determine the target color temperature and corresponding target power of the lamps in each detection area.

[0055] Among them, in step A501, calculating the road area of each detection area according to the lane type and the preset road width can provide an accurate basis for calculating the subsequent road space occupancy rate. The lane type can be a straight line or a curve identified by an image processing method. The preset road width is a fixed value obtained according to the actual tunnel design or measurement. When the lane is a straight line, the road area can be calculated according to the straight-line length and the road width of the detection area. When the lane is a curve, the road area can be calculated according to the curve length and the road width of the detection area, or other geometric calculation methods can be adopted. Thus, it can adapt to tunnel sections with different geometric shapes.

[0056] Among them, in step A502, the target detection box of the vehicle is a rectangular area where the vehicle recognition algorithm marks the position and size of the vehicle in the image. The pixel width and pixel height of the target detection box can be converted into the actual width and actual height according to the conversion ratio factor, and then the actual area can be calculated. Using the actual area of the target detection box as the occupied area of the vehicle is a feasible method to quantify the space occupied by the vehicle on the road from the video image. By accumulating the actual areas of the target detection boxes of all recognized vehicles in the same detection area, the total occupied area of the vehicles on the road in this detection area at the current moment can be obtained.

[0057] Among them, in step A503, for each detection area, dividing the total sum of the occupied areas of the vehicles by the calculated road area to obtain the road space occupancy rate. The road space occupancy rate is a dimensionless ratio value, which quantitatively reflects the density of vehicles on the current road in the detection area. A higher occupancy rate indicates traffic congestion, and a lower occupancy rate indicates sparse (smooth) traffic.

[0058] Among them, in step A504, comparing the calculated road space occupancy rate with the preset occupancy rate threshold to determine the target color temperature and the corresponding target power of the lighting. For example, when the traffic density is high, a color temperature that helps improve the driver's alertness can be adopted, and when the traffic density is low, a more comfortable color temperature can be adopted. In this way, the color temperature of the lighting can be dynamically adjusted according to the actual traffic density.

[0059] This method reflects the traffic density by quantitatively calculating the road space occupancy rate, and based on this, dynamically adjusts the color temperature and power of the lighting. This is different from the traditional fixed lighting or only brightness adjustment scheme, and can more precisely match the lighting parameters with the actual traffic conditions. Associating the calculated road space occupancy rate with preset rules (such as thresholds or interpolation) directly obtains the lighting parameters applicable to the current traffic conditions, providing a key input for subsequent controlling the on / off, working color temperature, and working power of individual lamps. This dynamic adjustment based on the actual traffic density helps improve energy utilization efficiency while ensuring driving safety and visual comfort.

[0060] Preferably, step A504 may include: If the road space occupancy rate is greater than the first occupancy rate threshold, determine the target color temperature as the first preset color temperature; If the road space occupancy rate is less than the second occupancy rate threshold, determine the target color temperature as the second preset color temperature; the first occupancy rate threshold is greater than the second occupancy rate threshold, and the first preset color temperature is greater than the second preset color temperature; If the road space occupancy rate is between the second occupancy rate threshold and the first occupancy rate threshold, determine the target color temperature based on linear interpolation operation, or determine the target color temperature as the third preset color temperature; the third preset color temperature is greater than the second preset color temperature and less than the first preset color temperature; Obtain the light efficiency parameter corresponding to the determined target color temperature and the target value of luminous flux required by the tunnel lighting design; Divide the target value of luminous flux by the light efficiency parameter to obtain the target power corresponding to the target color temperature.

[0061] Among them, the calculated road space occupancy rate is used to determine the target color temperature and the corresponding target power. Specifically, compare the calculated road space occupancy rate with the preset first occupancy rate threshold and second occupancy rate threshold. For example, the first occupancy rate threshold can be set to 80%, and the second occupancy rate threshold can be set to 50%. If the road space occupancy rate is greater than the first occupancy rate threshold, it indicates that the traffic flow in the tunnel is large. At this time, determine the target color temperature as the higher first preset color temperature, such as 6500K. The higher color temperature helps to improve the visual clarity of the driver, enhance visual acuity and alertness, thereby improving driving safety. If the road space occupancy rate is less than the second occupancy rate threshold, it indicates that the traffic flow in the tunnel is small. At this time, determine the target color temperature as the lower second preset color temperature, such as 5000K. The lower color temperature helps to create a more comfortable visual environment, thereby improving visual comfort.

[0062] Among them, when the road space occupancy rate is between the second occupancy rate threshold and the first occupancy rate threshold, that is, when the traffic flow is at a medium level, there are two ways to determine the target color temperature. One way is to determine the target color temperature based on linear interpolation. According to the specific value of the occupancy rate within this range, an interpolated target color temperature between the second preset color temperature and the first preset color temperature is obtained through interpolation calculation. For example, when the occupancy rate is S, a target color temperature between the second preset color temperature and the first preset color temperature can be calculated through the linear interpolation formula CT = CT2 + (CT1 - CT2) * (S - S2) / (S1 - S2), where CT is the target color temperature, CT1 is the first preset color temperature, CT2 is the second preset color temperature, S1 is the first occupancy rate threshold, and S2 is the second occupancy rate threshold. Another way is to directly set the target color temperature to the third preset color temperature, which is set to be greater than the second preset color temperature and less than the first preset color temperature, such as 5700K. Both of these methods enable the selection of a moderate color temperature under medium traffic flow.

[0063] After determining the target color temperature, it is necessary to determine the target power corresponding to this target color temperature. This is achieved by obtaining the light efficiency parameter of the lamp corresponding to the determined target color temperature and the target value of the luminous flux required by the tunnel lighting design. The light efficiency parameter reflects the efficiency of the lamp in converting electrical energy into light energy at a specific color temperature, usually in lumens per watt (lm / W), and can be obtained in advance through experiments or by referring to the technical manual of the lamp. At different color temperatures, the light efficiency parameters of the same lamp may be different. The target value of the luminous flux required by the tunnel lighting design is a preset lighting level that needs to be achieved. For example, the luminous flux provided by each lamp needs to be 10,000 lumens (i.e., 10,000 lm). By dividing the target value of the luminous flux by the light efficiency parameter corresponding to the obtained target color temperature, the electrical power required to achieve this luminous flux, that is, the target power, can be calculated. In mainstream LED lamps, generally, as the color temperature increases, the light efficiency parameter also increases. For example, if the target color temperature is 6500K and the corresponding light efficiency parameter is 120 lm / W, then the target power is 10,000 lm / 120 lm / W ≈ 83.3W. If the target color temperature is 5000K and the corresponding light efficiency parameter is 100 lm / W, then the target power is 10,000 lm / 100 lm / W = 100W. Thus, it can be seen that at high color temperatures, energy consumption can also be reduced. Therefore, the corresponding target power can be calculated according to different target color temperatures to ensure that while providing the required lighting level, the power output can be adjusted according to the color temperature difference.

[0064] In the above technical solution, by setting the occupancy threshold and the preset color temperature, and introducing linear interpolation or the third preset color temperature, the refined grading or smooth adjustment of the color temperature is achieved, enabling the adjustment of lighting parameters to better match the actual traffic conditions. Further, by obtaining the luminous efficacy parameters corresponding to the target color temperature and calculating the target power in combination with the target luminous flux value, it is ensured that the lighting requirements can be met at different color temperatures, and at the same time, the power is adjusted according to the luminous efficacy differences at different color temperatures, improving the energy utilization efficiency.

[0065] In some embodiments, step A6 includes: A601. Determine a plurality of lamps located in front of the vehicle as the target lamp group according to the speed and the lamp spacing; A602. Determine the turn-on time and the turn-off time of the target lamp group according to the arrival time; A603. Turn on the target lamp group at the turn-on time, and make the working color temperature of the target lamp group equal to the corresponding target color temperature, and the working power equal to the corresponding target power; A604. If it is detected that the vehicle arrives at the target lamp group before the turn-off time, calculate a delay time according to the speed of the vehicle, and delay the turn-off of the target lamp group; if the vehicle does not arrive at the target lamp group at the turn-off time, turn off the target lamp group.

[0066] Among them, in step A601, the speed of the vehicle can be multiplied by a preset reference time value to obtain an extended distance, and then using the next lamp as the starting lamp, according to the lamp spacing, determine the lamp whose distance from the starting lamp in front of the vehicle is not less than the extended distance as the end lamp, and take all the lamps from the starting lamp to the end lamp (including the starting lamp and the end lamp) as the target lamp group.

[0067] Among them, in step A602, according to the predicted time for the vehicle to reach the next lamp, the turn-on time (i.e., the turn-on moment) and the initial turn-off time (i.e., the initial turn-off moment) of the target lamp group can be determined. For example, the turn-on time can be set to a fixed duration before the predicted arrival time of the vehicle to ensure that the lamps are lit when the vehicle enters the lighting area. The initial turn-off time can be set to the predicted arrival time of the vehicle plus a preset delay duration. Thus, the preliminary lighting control on-demand based on prediction information is realized.

[0068] Among them, in step A603, when the determined turn-on time arrives, the target lamp group is activated. At the same time, the working color temperature and the working power of the target lamp group are set to the calculated target color temperature and target power. In this way, the lighting state of the lamps is not only related to the presence of the vehicle, but also matches the actual traffic density and demand.

[0069] Furthermore, in step A604, to improve the accuracy and safety of the shutdown control, a dynamic adjustment mechanism based on the actual state of the vehicle is introduced. If the system detects and confirms that the vehicle has reached the area where the target lamp group is located before the initially determined shutdown time arrives, this indicates that the vehicle has arrived as expected or earlier. At this time, the system will not immediately turn off the lamps according to the initially determined shutdown time. Instead, a delay time is calculated based on the current actual speed of the vehicle. This delay time can be calculated according to the length of the illumination area of the target lamp group and the vehicle speed to ensure that the lamps continue to illuminate until the vehicle safely leaves the area. For example, if the vehicle speed is fast, the calculated delay time may be short; if the speed is slow, the delay time will be extended accordingly. The target lamp group will be turned off after the initially determined shutdown time plus the calculated delay time. This delay shutdown strategy based on the actual speed effectively avoids the problem of premature lamp extinction caused by prediction errors or speed changes, ensuring driving safety.

[0070] On the other hand, if the system detects that the vehicle has not reached the area where the target lamp group is located when the initially determined shutdown time arrives, this may mean that the vehicle speed is much lower than predicted or there is a large deviation in the prediction. In this case, to avoid unnecessary energy waste, the system will turn off the target lamp group according to the initially determined shutdown time. This ensures that the target lamp group will not remain on for a long time when there is no vehicle in need of illumination.

[0071] By combining the predicted arrival time for preliminary planning and making dynamic adjustments based on the actual arrival situation and speed of the vehicle, especially the fine control of the shutdown timing, this solution overcomes the limitations of relying solely on prediction, making the tunnel lighting control more flexible, safe, and energy-efficient.

[0072] Through the above technical solution, this application solves the problems that may be caused by relying solely on predicting the vehicle arrival time to control the lamp switch. By determining the turn-on and turn-off times according to the predicted arrival time, on-demand lighting is achieved, avoiding energy waste caused by the lamps remaining on for a long time when the vehicle has not arrived. By introducing a delay shutdown mechanism based on the real-time speed of the vehicle, it is ensured that the lamps continuously provide illumination during the vehicle passing through the lighting area, effectively avoiding the impact of sudden lamp extinction on driving safety. By turning off the lamps when the preset shutdown time arrives but the vehicle has not arrived, the energy use is further optimized. This solution improves the accuracy, flexibility, and safety of tunnel lighting control, enabling the lighting system to better adapt to the actual traffic conditions.

[0073] It should be noted that in step A6, when there are multiple vehicles targeting one of the target lamps of the same lamp group simultaneously, the opening time, closing time, and delay time are calculated for each relevant vehicle according to the above steps. If there is a contradiction in the control state of controlling the target lamp based on the calculation results, for example, according to the calculation result of vehicle A, the target lamp should be in the off state at time t, and according to the calculation result of vehicle B, the target lamp should be in the on state at time t, then the target lamp is kept in the on state at the corresponding moment to ensure the driving safety of each vehicle.

[0074] Preferably, after step A603 and before step A604, the following may further be included: A605. Detect whether the lamps in the target lamp group are successfully turned on by an image detection method, and issue an abnormal warning when they are not successfully turned on.

[0075] Among them, after issuing the instruction to turn on the lamp and before deciding to turn off the lamp, a detection link for the actual turning-on state of the lamp is added, which solves the problem that the lamp may not work properly according to the instruction. Specifically, by the image detection method, the video image is used to analyze whether the lamps in the target lamp group emit light, so as to judge whether they are successfully turned on. For example, after identifying the lamps in the target lamp group, calculate the average pixel brightness in the target detection frame of the lamp and compare it with the preset brightness threshold. If it is higher than the preset brightness threshold, it is determined that the lamp is successfully turned on; otherwise, it is determined that the lamp is not successfully turned on. This detection method based on visual feedback can directly verify the actual working state of the lamp. If it is found in the detection that at least one lamp fails to be successfully turned on, the system will issue an abnormal warning to facilitate timely troubleshooting and ensure the reliability of tunnel lighting and driving safety.

[0076] Through the above technical solutions, this application solves the problem that simply issuing the turn-on instruction cannot ensure that the lamp is actually successfully turned on and works properly. By adding a lamp state detection link based on video images, it can directly verify whether the lamp emits light normally according to the instruction. Thus, problems such as lamp failures or communication abnormalities can be discovered in time, and they can be processed by issuing abnormal warning prompts. This ensures the reliability of the tunnel lighting system, improves the effectiveness of lighting, and thus guarantees driving safety.

[0077] Reference Figure 2 , this application provides a tunnel lighting control system based on video monitoring, including a plurality of lamps 1 arranged at intervals along the tunnel, several cameras 2, and a control terminal 3; The camera 2 is used to collect video images in the tunnel and send them to the control terminal 3; The control terminal 3 is used to execute: Identify the lamps 1, the driving lane, and the vehicle according to the video image (for the specific process, refer to step A1 in the previous text); Determine the type of the driving lane based on the recognition result of the driving lane; the types of the driving lane include straight or curved (for the specific process, refer to step A2 in the previous text); Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, the type of the driving lane, and the lamp spacing (for the specific process, refer to step A3 in the previous text); Based on the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to determine the position of the vehicle in each detection area, so as to calculate the speed of the vehicle and predict the arrival time of the vehicle at the next lamp (for the specific process, refer to step A4 in the previous text); Calculate the road space occupancy rate of each detection area based on the vehicle recognition result, the conversion ratio factor, and the type of the driving lane, so as to determine the target color temperature and the corresponding target power of the lamps in each detection area (for the specific process, refer to step A5 in the previous text); Control the on / off, working color temperature, and working power of several lamps in front of the vehicle according to the speed, lamp spacing, arrival time, target color temperature, and target power (for the specific process, refer to step A6 in the previous text).

[0078] In summary, the present application has at least the following advantages: 1. Multi-region collaborative detection to avoid monitoring blind spots: The prior art usually relies on a single detection means (such as radar or infrared sensor), which is prone to monitoring blind spots in some areas, resulting in inaccurate lamp control; while the present invention can realize the comprehensive monitoring of the vehicle position and speed in the tunnel by integrating video detection and multi-region speed measurement technology, avoiding the misjudgment problem of the lighting system caused by the uncertainty of vehicle speed in the unmonitored area, and ensuring the accuracy and reliability of lighting control; 2. Dynamically adjust the lamp turning-on time and color temperature: The prior art usually controls the lamps based on a preset time schedule or a fixed mode, and cannot adapt to the changes in the actual traffic flow and vehicle driving state; while the present invention can dynamically adjust the turning-on and turning-off time and color temperature of the lamps by real-time monitoring of the vehicle speed and position and combining with the target tracking technology, ensuring the lighting effect while reducing energy consumption, and improving the driving safety and energy utilization efficiency; 3. Intelligent anomaly detection and status monitoring: The monitoring of the working status of the lamps in the prior system is relatively limited, and it is difficult to detect and handle faults in a timely manner; the present invention continuously analyzes the working status of the lamps through video data, can detect anomalies and issue alarms in the first time, significantly improves the reliability and maintenance efficiency of the system, and reduces the maintenance cost; 4. Automatically generate detection areas and simplify deployment: Compared with the prior art, the present invention can automatically generate detection areas according to the spacing of tunnel lighting fixtures without manual setting, simplifying the system deployment and debugging processes, improving the flexibility and adaptability of the system, and reducing the system deployment cost and time. 5. Fine-grained lighting control and optimize energy utilization: The present invention realizes fine-grained lighting control by calculating the road space occupancy rate in the detection area, adjusts the lighting intensity and color temperature as needed, further optimizes energy utilization, reduces the operating cost, and provides a more comfortable visual environment for drivers at the same time.

[0079] The above are only the embodiments of the present application and are not used to limit the protection scope of the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A tunnel lighting control method based on video surveillance, characterized in that Including the steps: A1. Obtain video images inside the tunnel for identifying lamps, driving lanes, and vehicles; A2. Determine the type of driving lane based on the recognition result of the driving lane; the type of driving lane includes straight or curved; A3. Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, the type of driving lane, and the lamp spacing; A4. According to the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to determine the position of the vehicle in each detection area for calculating the vehicle speed and predicting the arrival time of the vehicle at the next lamp; A5. Calculate the road space occupancy rate of each detection area according to the vehicle recognition result, the conversion ratio factor, and the type of driving lane for determining the target color temperature and corresponding target power of the lamps in each detection area; A6. Control the on / off, working color temperature, and working power of several lamps in front of the vehicle according to the speed, the lamp spacing, the arrival time, the target color temperature, and the target power.

2. The tunnel lighting control method based on video monitoring according to claim 1, wherein Step A1 includes: A101. Obtain the original video images inside the tunnel, perform preprocessing to obtain the preprocessed video images; the preprocessing includes gray conversion processing for converting color images to grayscale images, Gaussian filtering processing, and histogram equalization processing; A102. Use the target detection algorithm to identify lamps and vehicles in the preprocessed video images; A103. Use the Canny algorithm to identify the driving lanes in the preprocessed video images.

3. The tunnel lighting control method based on video monitoring according to claim 1, wherein Step A2 includes: A201. Detect the recognized driving lane through the Hough transform to determine whether the driving lane is straight; A202. If no straight line is detected, determine that the driving lane is curved, and use the curve fitting method to fit the curve equation of the driving lane.

4. The tunnel lighting control method based on video monitoring according to claim 3, characterized in that Step A3 includes: A301. Divide the tunnel into multiple detection areas along the length direction according to the preset lamp spacing; A302. Extract the pixel coordinates of the lamps according to the lamp recognition result; A303. If the driving lane is straight, calculate the average value of the straight pixel distances between adjacent lamps according to the pixel coordinates of the lamps as the lamp pixel spacing; A304. If the driving lane is curved, calculate the average value of the curve pixel distances between adjacent lamps along the curve equation according to the pixel coordinates of the lamps and the curve equation of the driving lane as the lamp pixel spacing; A305. Calculate the conversion ratio factor between the pixel distance and the actual distance according to the lamp pixel spacing and the lamp spacing.

5. The tunnel lighting control method based on video monitoring according to claim 1, wherein Step A4 includes: A401. According to the vehicle recognition result and the conversion ratio factor, use the target tracking algorithm to track the position of the vehicle in each detection area to obtain the moving trajectory of the vehicle; A402. Calculate the vehicle speed according to the moving trajectory; A403. According to the current position of the vehicle and the position of the next lamp, combined with the vehicle speed, calculate the arrival time of the vehicle at the next lamp.

6. The tunnel lighting control method based on video monitoring according to claim 1, characterized in that Step A5 includes: A501. Calculate the road area of each detection area according to the type of driving lane and the preset road width; A502. Calculate the actual area of the target detection frame of the vehicle according to the pixel size of the target detection frame of the vehicle and the conversion ratio factor, and use the actual area of the target detection frame of the vehicle as the occupied area of the vehicle, and calculate the total sum of the occupied areas of all vehicles in each detection area; A503. Divide the total sum of the occupied areas by the corresponding road area to obtain the road space occupancy rate of each detection area; A504. Compare the road space occupancy rate with a preset occupancy rate threshold to determine the target color temperature and the corresponding target power of the lamps in each detection area.

7. The tunnel lighting control method based on video monitoring according to claim 6, characterized in that Step A504 includes: If the road space occupancy rate is greater than the first occupancy rate threshold, determine the target color temperature as the first preset color temperature; If the road space occupancy rate is less than the second occupancy rate threshold, determine the target color temperature as the second preset color temperature; the first occupancy rate threshold is greater than the second occupancy rate threshold, and the first preset color temperature is greater than the second preset color temperature; If the road space occupancy rate is between the second occupancy rate threshold and the first occupancy rate threshold, determine the target color temperature based on linear interpolation calculation, or determine the target color temperature as the third preset color temperature; the third preset color temperature is greater than the second preset color temperature and less than the first preset color temperature; Obtain the light efficiency parameter corresponding to the determined target color temperature and the target value of the luminous flux required for tunnel lighting design; Divide the target value of the luminous flux by the light efficiency parameter to obtain the target power corresponding to the target color temperature.

8. The tunnel lighting control method based on video monitoring according to claim 1, characterized in that Step A6 includes: A601. Determine a plurality of lamps located in front of the vehicle as the target lamp group according to the speed and the lamp spacing; A602. Determine the turn-on time and the turn-off time of the target lamp group according to the arrival time; A603. Turn on the target lamp group at the turn-on time, and make the working color temperature of the target lamp group equal to the corresponding target color temperature, and the working power equal to the corresponding target power; A604. If it is detected that the vehicle arrives at the target lamp group before the turn-off time, calculate a delay time according to the speed of the vehicle, and delay the turn-off of the target lamp group; if the vehicle does not arrive at the target lamp group at the turn-off time, turn off the target lamp group.

9. The tunnel lighting control method based on video surveillance according to claim 8, wherein After step A603 and before step A604, it further includes: A605. Detect whether the lamps in the target lamp group are successfully turned on by an image detection method, and issue an abnormal warning when they are not successfully turned on.

10. A tunnel lighting control system based on video surveillance, characterized in that, It includes a plurality of lamps arranged at intervals along the tunnel, several cameras, and a control terminal; The cameras are used to collect video images in the tunnel and send them to the control terminal; The control terminal is used to execute: Identify lamps, driving lanes, and vehicles according to the video images; Determine the type of the driving lane based on the driving lane recognition result; the type of the driving lane includes a straight line or a curve; Divide the tunnel into multiple detection areas according to the preset lamp spacing, and calculate the conversion ratio factor between the pixel distance and the actual distance based on the lamp recognition result, the type of the driving lane, and the lamp spacing; Based on the vehicle recognition result and the conversion scale factor, use the target tracking algorithm to determine the position of the vehicle in each detection area, so as to calculate the speed of the vehicle and predict the arrival time of the vehicle at the next lamp; According to the vehicle recognition result, the conversion scale factor and the type of driving lane, calculate the road space occupancy rate of each detection area to determine the target color temperature and the corresponding target power of the lamps in each detection area; Based on the speed, the lamp spacing, the arrival time, the target color temperature and the target power, control the on / off, working color temperature and working power of several lamps in front of the vehicle.

Images