Highway road condition positioning method

Abstract

The invention relates to the technical field of road condition monitoring, in particular to an expressway road condition positioning method, which comprises the following steps of: based on an expressway environment, shooting a road surface image of an expressway through shooting equipment, adjusting an exposure parameter of the shooting equipment according to weather and environment light source intensity in a shooting process, and adjusting the captured image to obtain a road surface image of the expressway; and the highway image definition is optimized to obtain optimized image information. According to the method, the road surface damage and accident areas are analyzed, the event areas are positioned, and the danger degree of the event is evaluated according to the distance between the damage and accident areas and the key position of the road, so that the judgment of the danger degree is more prospective and has emergency response capability, and the traffic flow information is combined to evaluate the influence of road congestion. The traffic congestion degree can be effectively predicted, more comprehensive data support is provided for traffic management, traffic scheduling is more efficient, the vehicle detention time is shortened, and the accident rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of road condition monitoring, and in particular to a method for locating road conditions on a highway. Background Art

[0002] The field of road condition monitoring technology aims to collect, process and distribute information about road traffic status in real time. The field of road condition monitoring technology uses various sensors, cameras and data transmission technologies to collect traffic flow and road condition data from highways and urban roads. Applications include video surveillance, speed and traffic flow monitoring, and automated accident detection systems. By analyzing data, traffic congestion, accidents, road construction or other factors affecting traffic flow can be identified. The information is fed back to drivers and relevant management departments through broadcasting, the Internet or direct communication to optimize traffic management and response strategies and improve road safety and efficiency.

[0003] Among them, the highway road condition positioning method is a technology specifically used for highway road conditions, which is used to monitor and evaluate road conditions in real time. This method uses integrated sensors and communication technologies to locate and report road conditions, such as traffic flow, accidents, road damage or other factors that affect traffic flow. Its main purpose is to provide drivers with instant road condition information, allowing drivers to avoid congested areas or dangerous sections of the road. It also provides data support for traffic management departments to facilitate more effective traffic scheduling and management, and improve driving efficiency and safety.

[0004] Traditional road condition positioning methods are difficult to quickly and accurately assess the real-time impact of accidents on traffic flow in terms of locating accident and damage locations. As a result, drivers and traffic management departments cannot obtain the most critical road condition information in real time, affecting the efficiency of traffic management and road safety. Therefore, under rapidly changing road conditions, existing technologies are difficult to provide sufficient support to respond to emergencies. The integration and analysis of road condition information in existing technologies mostly rely on relatively fixed algorithms and lack the ability to quickly adapt to actual traffic flow changes. As a result, during peak traffic periods or special events, information feedback is not timely enough and cannot effectively guide traffic management, increasing traffic congestion and accident rates. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method for locating highway road conditions.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for locating highway road conditions, comprising the following steps:

[0007] S1: Based on the highway environment, a road surface image of the highway is captured by a shooting device, and according to the weather and the intensity of the ambient light during the shooting process, the exposure parameters of the shooting device are adjusted, and the captured image is adjusted to optimize the clarity of the highway image and obtain optimized image information;

[0008] S2: Based on the optimized image information, the road surface damage and accident area are identified by analyzing the image, and the road surface damage and accident occupied lane range are analyzed to evaluate the road surface damage and accident severity, and obtain damage and accident severity status information;

[0009] S3: Based on the damage and accident information, the coordinates of the road damage and accident area on the highway map are calculated to locate the damage and accident location, and the danger level of the damage and accident is evaluated based on the distance between the damage and accident area and the key location of the highway, including curves, bridges and tunnels, combined with the severity of the damage and accident, to obtain positioning and danger assessment information;

[0010] S4: Based on the positioning and hazard assessment information, combined with the traffic flow information on the highway, the impact of damage and accidents on road congestion is assessed, the length of highway congestion is predicted, and a road condition analysis result is obtained.

[0011] The present invention is improved in that the method for adjusting the exposure parameters of the shooting device is:

[0012] S111: Based on the highway environment, the intensity of the ambient light source on the highway is measured in real time by using a light sensor of a shooting device to obtain a light intensity parameter;

[0013] S112: Based on the light intensity parameter and the basic exposure parameter of the shooting device, the following formula is used:

[0014]

[0015] Calculate the adjusted exposure parameter E, where k E and c E is the adjustment factor, a E is the temperature sensitivity coefficient, T ref is the reference temperature, E is the adjusted exposure parameter, T E Indicates the current ambient temperature, T ref is the reference temperature, L represents the ambient light intensity, and E0 is the basic exposure parameter;

[0016] S113: Based on the adjusted exposure parameter E, the exposure setting of the shooting device is adjusted in real time to obtain an adjusted shooting device.

[0017] The present invention is improved in that the step of obtaining the optimized image information is:

[0018] S121: photographing a road surface image of a highway based on the adjusted photographing device to obtain a basic highway image;

[0019] S122: Based on the basic highway image, extract the average brightness of the current image, and combine it with the adjusted exposure parameter E through the formula:

[0020]

[0021] Calculate the ambient contrast adjustment coefficient C env , where L avg is the average brightness of the current image, E is the adjusted exposure parameter, C env is the ambient contrast adjustment factor;

[0022] S123: Based on the environmental contrast adjustment coefficient C env , through the formula:

[0023]

[0024] Calculate the adjusted brightness value I adj , get the optimized image information, where I adj is the adjusted brightness value, I is the pixel brightness value of the basic highway image, α I is the adjustment coefficient, β I is the smoothing parameter, I mid is the median brightness value of the image.

[0025] The present invention is improved in that the method for identifying road damage and accident areas is:

[0026] S211: Based on the optimized image information, by formula:

[0027]

[0028] Calculate the edge strength E(x,y) of the pixel point, where represents the image gradient at position (x, y), σ L is the standard deviation of the global brightness of the image, μ L is the average value of the global brightness of the image, λ is the weight coefficient, and E(x,y) represents the edge strength at position (x,y) in the image;

[0029] S212: Based on the edge strength E(x, y), the edge strength is compared with a preset edge threshold, and the pixel points exceeding the preset edge threshold are marked as damage and accident location edges, the road surface damage and accident area are identified, and the road surface damage and accident area information is obtained.

[0030] The present invention is improved in that the steps of obtaining the damage and accident severity status information are:

[0031] S221: Based on the road damage and accident area information, by analyzing the ratio of the number of pixels in the damaged area to the total number of lane pixels in the image, identifying the percentage of lanes covered by the damaged and accident areas, and obtaining damage and accident coverage information;

[0032] S222: Based on the damage and accident coverage information, by formula:

[0033]

[0034] Calculate the severity index S, where A S is the area of ​​the region, p S is the percentage of the area in the lane, d S is the distance from the region to the nearest lane edge, γ S is the traffic flow density adjustment coefficient, T S is the total lane area, S is the severity index;

[0035] S223: Based on the severity index S, the road surface damage and the severity of the accident are evaluated according to the value of S, and damage and accident severity status information is obtained.

[0036] The present invention is improved in that the method for locating the damage and accident position is:

[0037] S311: extracting the damage and accident areas in the image based on the damage and accident information, and acquiring the image shooting position and angle data to obtain coordinate association data;

[0038] S312: Based on the coordinate association data, by formula:

[0039]

[0040] Calculate the location coordinates of the damage and accident on the highway map to obtain the damage and accident location information, where P img are the pixel coordinates of the damaged and accident areas in the image, M P is the transformation matrix from image coordinates to map coordinates, C P is the offset vector in the transformation, K P is the adjustment parameter.

[0041] The present invention is improved in that the steps of obtaining the positioning and risk assessment information are as follows:

[0042] S321: Based on the damage and accident location information, collect key location data on the highway, the key locations including coordinates of curves, bridges and tunnels, and obtain hazard association data;

[0043] S322: Based on the hazard association data, combined with the damage and the severity of the accident, a formula is used;

[0044]

[0045] Calculate the danger index D, where d min is the distance from the damaged area to the nearest critical location, h is the height difference factor, S is the severity index, and k D is the curve sensitivity parameter, θ D is the threshold parameter, D is the danger index, and e is the base of the natural logarithm;

[0046] S323: Based on the danger level index D, according to the value of D, the danger level of damage and accident is evaluated to obtain positioning and danger assessment information.

[0047] The present invention is improved in that the steps of obtaining the road condition analysis result are:

[0048] S411: Based on the positioning and risk assessment information, the location, time and type data of the damaged and accident areas are extracted, and the traffic flow data of the highway where the damaged and accident areas are located is collected through traffic monitoring equipment, including vehicle speed, traffic density and lane occupancy rate, to obtain congestion-related data;

[0049] S412: Based on the congestion-related data, by formula:

[0050]

[0051] Calculate the predicted congestion length Y and get the traffic analysis result, where Y is the predicted congestion length, e is the base of the natural logarithm, and q Y is the traffic volume of the highway, v Y is the average vehicle speed, λ Y is the adjustment coefficient, D is the risk index, α Y is the sensitivity parameter, C Y is the traffic capacity, T Y is the critical traffic flow.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, the incident area is located by analyzing the road damage and accident area, and the danger level of the incident is evaluated based on the distance between the damage and accident area and the key position of the highway, so that the judgment of the danger level is more forward-looking and has emergency response capabilities. Combined with the traffic flow information, the impact of road congestion is evaluated, and the degree of traffic congestion can be effectively predicted, providing more comprehensive data support for traffic management, making traffic scheduling more efficient, helping to shorten vehicle detention time, and reducing the accident rate, thereby improving the safety and smoothness of road use. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of the method of the present invention;

[0055] Figure 2 A flow chart for adjusting exposure parameters of a photographing device according to the present invention;

[0056] Figure 3 A flow chart for obtaining optimized image information for the present invention;

[0057] Figure 4 Flow chart for identifying road surface damage and accident areas for the present invention;

[0058] Figure 5 A flow chart for obtaining damage and accident severity status information for the present invention;

[0059] Figure 6 Flow chart for locating damage and accident locations for the present invention;

[0060] Figure 7 A flow chart for obtaining positioning and hazard assessment information for the present invention;

[0061] Figure 8 The present invention is a flow chart for obtaining the road condition analysis result. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0064] See also Figure 1 The present invention provides a technical solution: a method for locating highway road conditions, comprising the following steps:

[0065] S1: Based on the highway environment, a road surface image of the highway is captured by a shooting device, and according to the weather and the intensity of the ambient light during the shooting process, the exposure parameters of the shooting device are adjusted, and the captured image is adjusted to optimize the clarity of the highway image and obtain optimized image information;

[0066] S2: Based on the optimized image information, the road surface damage and accident area are identified by analyzing the image, and the road surface damage and accident occupied lane range are analyzed to evaluate the road surface damage and accident severity, and obtain damage and accident severity status information;

[0067] S3: Based on the damage and accident information, the coordinates of the road damage and accident areas on the highway map are calculated to locate the damage and accident locations. The damage and accident areas are evaluated based on the distances between the damage and accident areas and key locations on the highway, including curves, bridges, and tunnels, combined with the severity of the damage and accidents, to obtain the location and hazard assessment information.

[0068] S4: Based on the positioning and hazard assessment information, combined with the traffic flow information on the highway, the impact of damage and accidents on road congestion is assessed, the length of highway congestion is predicted, and the road condition analysis results are obtained;

[0069] The optimized image information includes enhanced road texture details, adjusted light reflection and optimized color saturation. The damage and accident severity information includes the identified road damage range and the area affected by the accident. The positioning and hazard assessment information includes the damage location coordinates, distance data of key locations and risk level information of damage and accidents. The road condition analysis results include the predicted congestion length, expected congestion duration and the number of affected lanes.

[0070] See also Figure 2 , the method to adjust the exposure parameters of the shooting device is:

[0071] S111: Based on the highway environment, the intensity of the ambient light source on the highway is measured in real time by using a light sensor of a shooting device to obtain a light intensity parameter;

[0072] S112: Based on the light intensity parameter and the basic exposure parameter of the shooting device, the following formula is used:

[0073]

[0074] Calculate the adjusted exposure parameter E, where k E and c E is the adjustment factor, a E is the temperature sensitivity coefficient, T ref is the reference temperature, E is the adjusted exposure parameter, T E Indicates the current ambient temperature, T ref is the reference temperature, L represents the ambient light intensity, and E0 is the basic exposure parameter;

[0075] S113: Based on the adjusted exposure parameter E, the exposure setting of the shooting device is adjusted in real time to obtain the adjusted shooting device.

[0076] formula:

[0077]

[0078] Parameter details and how to obtain them:

[0079] Light intensity L: This is the ambient light intensity measured by the light sensor installed on the camera. The sensor continuously monitors the light intensity and transmits the data to the processor in real time for subsequent calculations. For example, in a well-lit environment, L can be 2000 lux.

[0080] Basic exposure parameter E0: It is a parameter preset according to the camera model and manufacturing specifications, which can usually be found in the camera's technical manual. For most commercial cameras, this value can be adjusted between 100 and 800, depending on the camera's default settings and the user's custom settings.

[0081] Ambient temperature T E :The ambient temperature is obtained through the temperature sensor, which is installed on the shooting device and feeds the temperature data back to the processor in real time.

[0082] Reference temperature T ref : A preset standard temperature used as a reference point for calculations.

[0083] Exposure response coefficient k E and c E , temperature sensitivity coefficient a E:The coefficients are set based on equipment characteristics and environmental adaptability experience. The values ​​are based on previous experimental data and manufacturer's recommendations.

[0084] Calculation Example

[0085] Assume that the light intensity L is 2000 lux, the basic exposure parameter E0 is set to 400, and the ambient temperature T E At 30℃, k E Set to 0.1, c E is 1.5, a E is 0.05, reference temperature T ref is 20℃.

[0086] Calculation process:

[0087]

[0088] The calculated exposure parameter E is 400.51, which means that in the current environment, the camera should adjust its exposure setting to about 400.51 to ensure a clear image of the highway road surface. This value is slightly increased compared to the basic exposure parameter, mainly to adapt to higher ambient temperature and light intensity, and to ensure that the image quality will not be reduced due to changes in environmental factors.

[0089] See also Figure 3 , the steps to obtain optimized image information are:

[0090] S121: photographing a road surface image of the expressway based on the adjusted photographing equipment to obtain a basic highway image;

[0091] S122: Based on the basic highway image, the average brightness of the current image is extracted, combined with the adjusted exposure parameter E, through the formula:

[0092]

[0093] Calculate the ambient contrast adjustment coefficient C env , where L avg is the average brightness of the current image, E is the adjusted exposure parameter, C env is the ambient contrast adjustment factor;

[0094] S123: Adjust coefficient C based on environmental contrast env , through the formula:

[0095]

[0096] Calculate the adjusted brightness value I adj , get the optimized image information, where I adj is the adjusted brightness value, I is the pixel brightness value of the basic highway image, αI is the adjustment coefficient, β I is the smoothing parameter, I mid is the median brightness value of the image.

[0097] formula:

[0098]

[0099] and

[0100]

[0101] Parameter meaning and acquisition method:

[0102] Exposure parameter E: exposure parameter of the shooting device, calculated in the previous step.

[0103] Average brightness L avg : Obtained by performing pixel-level brightness analysis on the captured original image. The average brightness is the arithmetic mean of all pixel brightness values.

[0104] Original image pixel brightness I: The brightness value of each pixel obtained directly from the image data.

[0105] Contrast adjustment strength parameter α I and smoothing parameter β I : Parameters are preset according to the needs of image processing to adjust the sensitivity and smoothness of the contrast adjustment function.

[0106] Image middle brightness value I mid : is the median brightness of the image, which can be obtained by sorting the brightness of all pixels and taking the median.

[0107] Calculation Example

[0108] Assume the following parameter values:

[0109] Exposure parameter E = 200

[0110] Average brightness L avg =120

[0111] Contrast adjustment strength α I =0.05

[0112] Smoothing parameter β I =10

[0113] Image middle brightness I mid =100

[0114] Calculate the ambient contrast adjustment coefficient C env :

[0115]

[0116] For an assumed pixel brightness value of I=150, apply the contrast adjustment function:

[0117]

[0118] The calculated adjusted pixel brightness I adj The value is 150.43, which means that the original brightness value of 150 is slightly increased after contrast adjustment, which visually enhances the contrast of the image and makes the image details more obvious, especially in the case of strong ambient light or high exposure. This subtle adjustment helps to improve the overall image quality.

[0119] See also Figure 4 , the method to identify road damage and accident areas is:

[0120] S211: Based on the optimized image information, the formula is:

[0121]

[0122] Calculate the edge strength E(x,y) of the pixel point, where represents the image gradient at position (x, y), σ L is the standard deviation of the global brightness of the image, μ L is the average value of the global brightness of the image, λ is the weight coefficient, and E(x,y) represents the edge strength at position (x,y) in the image;

[0123] S212: Based on the edge strength E(x, y), the preset edge threshold is compared, and the pixel points exceeding the preset edge threshold are marked as damage and accident location edges, the road surface damage and accident area are identified, and the road surface damage and accident area information is obtained.

[0124] formula:

[0125]

[0126] Parameter details and how to obtain them:

[0127] Image Gradient It is the rate of change of brightness of an image at each pixel (x, y), usually calculated by an image processing algorithm such as the Sobel operator. This operator determines the horizontal and vertical gradients of each pixel by performing a convolution operation on the image, thereby estimating the edge strength of the entire image.

[0128] The standard deviation of global brightness σ L : This indicates the degree of variation in the brightness of the image, which is obtained by calculating the standard deviation of the brightness values ​​of all pixels. The larger the standard deviation, the more drastic the brightness variation of the image.

[0129] The average value of global brightness μ L : is the average brightness value of all pixels in the image, calculated by summing all pixel values ​​and dividing by the total number of pixels. The value reflects the overall brightness level of the image.

[0130] Weight coefficient λ: It is a preset adjustment parameter used to adjust the influence of local contrast and plays a key role in adjusting the sensitivity of edge detection. The setting of the parameter depends on the specific application requirements and the characteristics of the image.

[0131] Calculation example:

[0132] Assume that the global brightness average μ of the image L is 100, and the global brightness standard deviation σ L is 15, and the weight coefficient λ is set to 0.2. Consider a pixel (x, y) with a gradient is 50.

[0133] Calculate the edge strength E(x,y) of the point:

[0134]

[0135] The calculated edge strength E(x,y) is approximately 1.98, which indicates that the image has a relatively high edge strength at this pixel (x,y). This value can be used to identify the exact location of road damage and accidents in the image in further analysis. Areas with higher edge strength usually correspond to the presence of physical boundaries in the image, such as road damage or accident scenes.

[0136] See also Figure 5 , the steps to obtain damage and accident severity status information are:

[0137] S221: Based on the road damage and accident area information, by analyzing the ratio of the number of pixels in the damaged area to the total number of lane pixels in the image, identifying the lane percentage covered by the damaged and accident areas, and obtaining damage and accident coverage information;

[0138] S222: Based on the damage and accident coverage information, by the formula:

[0139]

[0140] Calculate the severity index S, where A S is the area of ​​the region, p S is the percentage of the area in the lane, d S is the distance from the region to the nearest lane edge, γ S is the traffic flow density adjustment coefficient, T S is the total lane area, S is the severity index;

[0141] S223: Based on the severity index S, the road surface damage and the severity of the accident are evaluated according to the value of S, and damage and accident severity status information is obtained.

[0142] formula:

[0143]

[0144] Parameter meaning and acquisition method:

[0145] A S : The area of ​​the damaged accident area is usually obtained by analyzing the number of pixels in the damaged area through image processing software and converting it into actual area units.

[0146] p S : The percentage of the damaged accident area to the entire lane, calculated by dividing the number of pixels in the damaged area by the number of pixels in the total lane and then multiplying by 100. This calculation directly reflects the area ratio of the damaged area relative to the entire lane.

[0147] d S : The distance from the damaged accident area to the nearest lane edge, usually calculated by image processing software from the pixel distance from the damaged edge to the lane boundary, and then converted to the actual distance based on the scale of the image.

[0148] γ S : Traffic density adjustment factor, which is a parameter set based on road type and traffic volume data, used to adjust the impact assessment of damage on traffic flow. It can be obtained from traffic survey data or road usage statistics.

[0149] T S : Total lane area, measured by the lane length and width in the image, and then the total area is calculated. This is usually calculated from ground markings or known road dimension data.

[0150] Calculation example:

[0151] Assumed parameters:

[0152] Damaged area A S = 50 square meters, the percentage of damage to the lane p S = 25%, the distance from the damage to the nearest lane edge d S =2 meters, traffic flow density adjustment coefficient γ S =1.2, total lane area T S =200 square meters.

[0153] Calculation process:

[0154]

[0155] The calculated damage severity index S≈2.675 indicates the severity of the damaged area relative to the entire lane and the potential impact on traffic flow. The higher this value, the more severe the damage or accident is on the lane, and it may be necessary to prioritize repairs or take traffic management measures. This index helps road maintenance departments determine the priority of repairs and the traffic control measures that need to be taken.

[0156] See also Figure 6 , the method to locate damage and accident locations is:

[0157] S311: extracting the damage and accident areas in the image based on the damage and accident information, and obtaining the image shooting position and angle data to obtain coordinate association data;

[0158] S312: Based on the coordinate association data, the formula is:

[0159]

[0160] Calculate the location coordinates of the damage and accident on the highway map to obtain the damage and accident location information, where P img are the pixel coordinates of the damaged and accident areas in the image, M P is the transformation matrix from image coordinates to map coordinates, C P is the offset vector in the transformation, K P is the adjustment parameter.

[0161] formula:

[0162]

[0163] Parameter meaning and acquisition method:

[0164] P img : It is the coordinate of the damaged and accident area in the image. It is obtained directly from the analysis process by the image analysis software, usually in pixel units, representing the position of the damaged area on the image.

[0165] M P : is the transformation matrix from image coordinates to map coordinates. It is used to accurately map image coordinates to map coordinates, based on the specific device parameters and geo-calibration operation settings at the time of image capture. The matrix is ​​usually calculated in GIS software using ground control points and image capture parameters.

[0166] C P : It is the offset vector in the conversion process, which is used to adjust the coordinate deviation caused by geographic positioning and image acquisition angle to ensure the accuracy of positioning. It is usually set according to the error measured during the calibration process.

[0167] K P: It is an adjustment parameter used to balance the transformation accuracy and the impact of actual geographic variation. It is a preset value based on the specific application scenario and accuracy requirements of the image, which helps to adjust the flexibility of the coordinate transformation process.

[0168] Calculation example:

[0169] Assume that in an image containing road damage, the pixel coordinates P of the damaged location are img is (200,300). The transformation matrix M P and the offset vector C P And adjust the parameter K P They are respectively set as:

[0170] K P =2

[0171] Calculation process:

[0172]

[0173] The calculated map coordinates P map =(6,5.67) represents the specific coordinates of the damage and accident locations on the highway map. The coordinates allow the road maintenance team to accurately locate and assess the damage location, allowing for more effective repair and management.

[0174] See also Figure 7 ,The steps to obtain positioning and hazard assessment information are:

[0175] S321: Based on the damage and accident location information, collect key location data on the highway, the key locations including the coordinates of curves, bridges and tunnels, and obtain hazard association data;

[0176] S322: Based on the hazard association data, combined with the damage and accident severity, through a formula;

[0177]

[0178] Calculate the danger index D, where d min is the distance from the damaged area to the nearest critical location, h is the height difference factor, S is the severity index, and k D is the curve sensitivity parameter, θ D is the threshold parameter, D is the danger index, and e is the base of the natural logarithm;

[0179] S323: Based on the danger level index D, the danger level of damage and accidents is evaluated according to the value of D, and positioning and danger assessment information is obtained.

[0180] formula;

[0181]

[0182] Parameter meaning and acquisition method:

[0183] d min : Minimum distance, which represents the straight-line distance from the damaged area to the nearest critical location. This parameter is usually obtained through GIS, using a known map coordinate system and geospatial analysis to calculate the shortest path from the damaged point to the critical location.

[0184] h: Height difference factor, which represents the height difference of the damage point relative to the critical location. This usually becomes important when structures such as viaducts or tunnels are involved, and can be obtained through topographic maps or elevation data.

[0185] S: Damage and accident severity index, calculated by the previous steps.

[0186] k D and θ D k: A parameter used to adjust the impact of damage severity on the hazard assessment curve. D is the gain factor, which determines the sensitivity of the curve, and θ D is the threshold value, which determines the deviation of the curve. The parameters are set based on historical data analysis and risk assessment experience to optimize the response of the model.

[0187] Calculation example:

[0188] Assume the following situation:

[0189] Distance d from the damaged area to the nearest critical location min = 50 meters, height difference h = 10 meters, damage severity S = 3, gain factor k D =0.5, threshold θ D =2.5.

[0190] Calculation process:

[0191]

[0192] The calculated danger index D≈28.66 indicates the potential threat level posed by the damaged or accident area to the surrounding environment and traffic safety under given conditions. The higher the value, the greater the threat posed by the damage or accident to highway safety, and the priority should be given to emergency measures or repairs.

[0193] See also Figure 8 , the steps to obtain the traffic analysis results are:

[0194] S411: Based on the positioning and risk assessment information, the location, time and type data of the damaged and accident areas are extracted, and the traffic flow data of the highway where the damaged and accident areas are located is collected through traffic monitoring equipment, including vehicle speed, traffic density and lane occupancy rate, to obtain congestion-related data;

[0195] S412: Based on the congestion-related data, the formula:

[0196]

[0197] Calculate the predicted congestion length Y and get the traffic analysis result, where Y is the predicted congestion length, e is the base of the natural logarithm, and q Y is the traffic volume of the highway, v Y is the average vehicle speed, λ Y is the adjustment coefficient, D is the risk index, α Y is the sensitivity parameter, C Y is the traffic capacity, T Y is the critical traffic flow.

[0198] formula:

[0199]

[0200] Parameter details and how to obtain them:

[0201] q Y : Traffic flow on a highway, which indicates the number of vehicles passing a specific point per hour. It is measured in real time by a traffic monitoring system before and after an accident and is used to assess the impact of an accident on traffic capacity.

[0202] v Y : Average vehicle speed, which indicates the average speed of vehicles on the road when the accident occurred. It is measured in real time before and after the accident by traffic monitoring equipment, and is key to calculating the dynamic changes of traffic flow.

[0203] λ Y : An adjustment factor for the criticality index, used to adjust the estimated impact of an accident on traffic flow according to its criticality. This factor is based on an impact analysis of historical accident data associated with accident types.

[0204] D: Danger index, which reflects the direct impact of accident severity on traffic flow, is usually calculated based on the type and severity of the accident. It is extracted from accident reports and on-site assessment data.

[0205] α Y :Adjust the sensitivity parameter of traffic flow. This parameter controls the response speed and accuracy of the model and is often set based on standard models of traffic engineering and field survey data.

[0206] C Y :Traffic capacity, the maximum number of vehicles a road can accommodate within a specified time, which is usually calculated based on road design data and historical traffic statistics provided by the transportation department.

[0207] T Y : Critical traffic flow, that is, when the traffic flow reaches this value, traffic congestion begins to be significant. This threshold is set by the transportation department based on the characteristics of the road section and historical traffic flow data.

[0208] Calculation example:

[0209] Assume that at the time of the accident:

[0210] Traffic flow Y = 1500 vehicles / hour, average speed v Y = 60 km / h, danger index D = 0.8, adjustment coefficient λ Y =0.015, sensitivity parameter α Y =0.03, traffic capacity C Y =2200 vehicles / hour, critical flow rate T Y =1800 vehicles / hour.

[0211] Calculation process:

[0212]

[0213] The calculated congestion length is about 0.3 kilometers, reflecting the expected length of the traffic congestion area under given accident conditions. This data provides important information about the scope of the accident, which helps traffic management departments to formulate effective traffic dispatch and emergency response plans.

[0214] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for locating highway road conditions, characterized in that: The following steps are involved: Based on the highway environment, a road surface image of the highway is captured by a shooting device, and according to the weather and the intensity of the ambient light during the shooting process, the exposure parameters of the shooting device are adjusted, and the captured image is adjusted to optimize the clarity of the highway image and obtain optimized image information; Based on the optimized image information, the road surface damage and accident area are identified by analyzing the image, and the road surface damage and accident occupied lane range are analyzed to evaluate the road surface damage and accident severity, and obtain damage and accident severity status information; Based on the damage and accident information, the coordinates of the road damage and accident area on the highway map are calculated to locate the damage and accident location, and the danger level of the damage and accident is evaluated based on the distance between the damage and accident area and key locations of the highway, including curves, bridges and tunnels, combined with the severity of the damage and accident, to obtain positioning and danger assessment information; Based on the positioning and hazard assessment information, combined with the traffic flow information on the highway, the impact of damage and accidents on road congestion is assessed, the length of highway congestion is predicted, and the road condition analysis result is obtained.

2. The highway road condition positioning method according to claim 1, characterized in that: The method for adjusting the exposure parameters of the shooting device is: Based on the highway environment, the light sensor of the shooting device is used to measure the ambient light intensity on the highway in real time to obtain the light intensity parameters; Based on the light intensity parameter and the basic exposure parameter of the shooting device, the formula is: Calculate the adjusted exposure parameter E, where k E and c E is the adjustment factor, a E is the temperature sensitivity coefficient, T ref is the reference temperature, E is the adjusted exposure parameter, T E Indicates the current ambient temperature, T ref is the reference temperature, L represents the ambient light intensity, and E0 is the basic exposure parameter; Based on the adjusted exposure parameter E, the exposure setting of the shooting device is adjusted in real time to obtain an adjusted shooting device.

3. The highway road condition positioning method according to claim 2, characterized in that: The steps for obtaining the optimized image information are as follows: Based on the adjusted shooting equipment, shooting a road surface image of the expressway to obtain a basic highway image; Based on the basic highway image, the average brightness of the current image is extracted, combined with the adjusted exposure parameter E, through the formula: Calculate the ambient contrast adjustment coefficient C env , where L avg is the average brightness of the current image, E is the adjusted exposure parameter, C env is the ambient contrast adjustment factor; Based on the environmental contrast adjustment coefficient C env , through the formula: Calculate the adjusted brightness value I adj , get the optimized image information, where I adj is the adjusted brightness value, I is the pixel brightness value of the basic highway image, α I is the adjustment coefficient, β I is the smoothing parameter, I mid is the median brightness value of the image.

4. The highway road condition positioning method according to claim 1, characterized in that: The method for identifying road damage and accident areas is: Based on the optimized image information, by formula: Calculate the edge strength of the pixel point E9x,y), where represents the image gradient at position 9x,y), σ L is the standard deviation of the global brightness of the image, μ L is the average value of the global brightness of the image, λ is the weight coefficient, and E(x,y) represents the edge strength at position (x,y in the image; Based on the edge strength E(x, y), it is compared with the preset edge threshold, and the pixel points exceeding the preset edge threshold are marked as damage and accident location edges, the road damage and accident area are identified, and the road damage and accident area information is obtained.

5. The highway road condition positioning method according to claim 4, characterized in that: The steps for obtaining the damage and accident severity status information are as follows: Based on the road damage and accident area information, by analyzing the ratio of the number of pixels in the damaged area to the total number of lane pixels in the image, the percentage of lanes covered by the damaged and accident areas is identified to obtain damage and accident coverage information; Based on the damage and accident coverage information, the formula: Calculate the severity index S, where A S is the area of ​​the region, p S is the percentage of the area in the lane, d S is the distance from the region to the nearest lane edge, γ S is the traffic flow density adjustment coefficient, T S is the total lane area, S is the severity index; Based on the severity index S, the road damage and the severity of the accident are evaluated according to the value of S, and the damage and accident severity status information is obtained.

6. The highway road condition positioning method according to claim 1, characterized in that: The method for locating damage and accident locations is: Based on the damage and accident information, extract the damage and accident area in the image, obtain the image shooting position and angle data, and obtain coordinate association data; Based on the coordinates associated data, by the formula: Calculate the location coordinates of the damage and accident on the highway map to obtain the damage and accident location information, where P img are the pixel coordinates of the damaged and accident areas in the image, M P is the transformation matrix from image coordinates to map coordinates, C P is the offset vector in the transformation, K P is the adjustment parameter.

7. The highway road condition positioning method according to claim 6, characterized in that: The steps for obtaining the positioning and risk assessment information are as follows: Based on the damage and accident location information, collect key location data on the highway, the key locations including the coordinates of curves, bridges and tunnels, and obtain hazard association data; Based on the hazard association data, combined with the damage and accident severity, through the formula; Calculate the danger index D, where d min is the distance from the damaged area to the nearest critical location, h is the height difference factor, S is the severity index, and k D is the curve sensitivity parameter, θ D is the threshold parameter, D is the danger index, and e is the base of the natural logarithm; Based on the danger level index D, the danger level of damage and accidents is evaluated according to the value of D, and positioning and danger assessment information is obtained.

8. The highway road condition positioning method according to claim 1, characterized in that: The steps for obtaining the traffic condition analysis result are as follows: Based on the positioning and risk assessment information, the location, time and type data of the damaged and accident areas are extracted, and the traffic flow data of the highway where the damaged and accident areas are located is collected through traffic monitoring equipment, including vehicle speed, traffic density and lane occupancy rate, to obtain congestion-related data; Based on the congestion-related data, the formula: Calculate the predicted congestion length Y and get the traffic analysis result, where Y is the predicted congestion length, e is the base of the natural logarithm, and q Y is the traffic volume of the highway, v Y is the average vehicle speed, λ Y is the adjustment coefficient, D is the risk index, α Y is the sensitivity parameter, C Y is the traffic capacity, T Y is the critical traffic flow.

Images