Road construction state detection method and system based on dynamic data monitoring

Abstract

The invention discloses a road construction state detection method and system based on dynamic data monitoring. The method comprises the following steps: acquiring a road image acquired by a road traffic vehicle; according to the road image, target identification is carried out, and a road area, a construction area and construction element features are segmented; tracking the operation of the construction vehicle to determine the moving condition of the construction vehicle; determining a road construction state; when the road construction state belongs to a construction state, combining a fence feature, a construction vehicle feature, a constructor feature and a traffic cone feature in the target recognition result to form a multi-channel scene feature vector, and performing feature fusion; calculating a feature influence factor; calculating an environment weight factor; and determining a construction type according to the feature influence factor and the environment weight factor in combination with historical information. By implementing the method provided by the invention, the problems in the prior art can be solved, and the capabilities of urban governance and traffic early warning are improved.

Description

Technical Field

[0001] The invention relates to a road construction status detection method, and more specifically to a road construction status detection method and system based on dynamic data monitoring. Background Art

[0002] At present, the methods for detecting road construction behaviors mainly adopt target detection models or judgment methods based on multi-element detection. However, for target detection models, the accuracy of construction scene detection depends on the comprehensiveness of target detection models and labeled data, which makes the detection effect susceptible to data quality and model recognition rate. Secondly, a small number of devices can be used for efficient detection in specific scenarios, but this method lacks scalability and extensibility and is only applicable to consistent scenarios. In addition, the current mainstream methods often rely on single target detection, which is simple to operate and easy to expand, but cannot fully reflect the overall status of the construction scene. Although the judgment method based on multi-element detection can make up for the shortcomings of a single feature, it is still a simple superposition of multiple models and fails to effectively integrate the mutual influence of various elements.

[0003] Therefore, it is necessary to design a new method to achieve the integration of multiple elements, realize the positioning and judgment of construction scenes, and track and monitor the entire process to assist in the generation of decision-making information. It is suitable for different urban road conditions, quickly accesses and saves costs, and improves the ability of urban governance and traffic warning. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the prior art and provide a road construction status detection method and system based on dynamic data monitoring.

[0005] To achieve the above object, the present invention adopts the following technical solution: a road construction status detection method based on dynamic data monitoring, comprising: Acquire road images collected by road traffic vehicles; Performing target recognition and segmenting road areas, construction areas, and construction element features according to the road image to obtain target recognition results; Tracking the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle; Determine the road construction status according to a set decision tree based on the target recognition result and the movement of the construction vehicle; According to the road construction status, the construction element characteristics are integrated, and the characteristic influencing factors and environmental weight factors corresponding to the construction element characteristics are calculated based on the fusion results. The characteristic influencing factors, environmental weight factors and historical information are comprehensively judged to determine the construction type.

[0006] Its further technical solution is: According to the road construction status, the construction element characteristics are integrated, and the characteristic influencing factors and environmental weighting factors corresponding to the construction element characteristics are calculated according to the integration results. The characteristic influencing factors, environmental weighting factors and historical information are comprehensively judged to determine the construction type, including: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features; Calculate the characteristic influencing factor corresponding to the construction element characteristic according to the fusion result; Calculating the environmental weight factor corresponding to the construction element characteristics; A comprehensive judgment is made based on the characteristic influencing factors and environmental weight factors in combination with historical information to obtain the construction type.

[0007] Its further technical solution is: the decision tree includes eight different construction states and non-construction states, among which the construction states include: with fences; without fences, with construction vehicles, the construction vehicles are stationary, and there are construction personnel; without fences, with construction vehicles, the construction vehicles are stationary, there are no construction personnel, and there are traffic cones; without fences, without construction vehicles, with construction personnel, and with traffic cones; the non-construction states include: without fences, with construction vehicles, the construction vehicles are stationary, there are no construction personnel, and there are no traffic cones; without fences, with construction vehicles, and the construction vehicles are moving; without fences, without construction vehicles, there are construction personnel, and there are no traffic cones; without fences, without construction vehicles, and there are no construction personnel.

[0008] A further technical solution is: when the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result, including: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector; wherein the weight of each channel is represented by the segmentation result corresponding to the feature; The multi-channel scene feature vectors are fused by feature weights to obtain a fusion result.

[0009] A further technical solution is: fusing the feature weights of the multi-channel scene feature vectors to obtain a fusion result, including: The feature weights of the multi-channel scene feature vectors are fused by at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion to obtain a fusion result.

[0010] A further technical solution is: calculating the characteristic influencing factor corresponding to the construction element characteristic according to the fusion result includes: use Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

[0011] A further technical solution is: the calculation of the environmental weight factor corresponding to the construction element feature includes: Calculating relevant parameters of the construction element characteristics; Using a priori parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain a processing result; The processing result is subjected to Softmax processing to obtain an environment weight factor.

[0012] A further technical solution is: a comprehensive judgment is made based on the characteristic influencing factors and the environmental weight factors in combination with historical information to obtain the construction type, including: Applying a sigmoid function to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result; The construction type is determined according to the activation result and the environmental weight factor combined with historical information.

[0013] A further technical solution is: determining the construction type according to the activation result and the environmental weight factor combined with historical information includes: use Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; and is 0.5, It refers to the degree of influence of historical data; Activation result.

[0014] The present invention also provides a road construction status detection device based on dynamic data monitoring, comprising: An image acquisition unit, used to acquire a road image collected by a road traffic vehicle; An identification and segmentation unit, used to perform target identification and segment the road area, construction area, and construction element features according to the road image to obtain a target identification result; A tracking unit, used to track the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle; A state determination unit, configured to determine the road construction state according to a set decision tree in combination with the target recognition result and the movement of the construction vehicle; A fusion unit, for, when the road construction state belongs to the construction state, combining the construction element features to form a multi-channel scene feature vector, and fusing the feature weights to obtain a fusion result; A feature influence factor calculation unit, used to calculate the feature influence factor corresponding to the construction element feature according to the fusion result; An environmental weight factor calculation unit, used to calculate the environmental weight factor corresponding to the construction element characteristics; The comprehensive judgment unit is used to make a comprehensive judgment based on the characteristic influencing factors and the environmental weight factors in combination with historical information to obtain the construction type.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains road images through the camera on the urban public transportation vehicle, performs target recognition and segmentation, extracts construction-related features, and then uses multi-target tracking technology to monitor the movement of the construction vehicle, and uses a decision tree in combination with the target recognition result to determine the construction status. If it is in a construction state, various features are combined to form a multi-channel scene feature vector, and feature weight fusion is performed. Then, the feature influencing factor and the environmental weight factor are calculated according to the fusion result, and a comprehensive judgment is made in combination with historical information to finally derive the construction type. This process can adapt to different urban road conditions, quickly access, save costs, and improve urban governance and traffic warning capabilities.

[0016] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0018] Figure 1A schematic diagram of a flow chart of a road construction status detection method based on dynamic data monitoring provided by an embodiment of the present invention; Figure 2 A schematic diagram of a decision tree provided by an embodiment of the present invention; Figure 3 A schematic diagram of target segmentation provided by an embodiment of the present invention; Figure 4 A schematic diagram of network output improved by an embodiment of the present invention; Figure 5 A schematic diagram of Gaussian fusion provided by an embodiment of the present invention; Figure 6 A schematic diagram of regional mean feature fusion provided by an embodiment of the present invention; Figure 7 A schematic diagram of regional clustering mode feature fusion provided by an embodiment of the present invention; Figure 8 A schematic diagram of regional median feature fusion provided by an embodiment of the present invention; Fig. 9 A schematic diagram of a dual-layer dynamic feature activation fusion provided by an embodiment of the present invention; Fig.10 A schematic flow chart of a road construction status detection method based on dynamic data monitoring provided by another embodiment of the present invention; Fig.11 A schematic block diagram of a road construction status detection device based on dynamic data monitoring provided by an embodiment of the present invention; Fig.12 A schematic block diagram of a road construction status detection device based on dynamic data monitoring provided by another embodiment of the present invention; Fig.13 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] See also Figure 1 , Figure 1 A schematic flow chart of a road construction status detection method based on dynamic data monitoring provided by an embodiment of the present invention. The road construction status detection method based on dynamic data monitoring is applied to a server, which exchanges data with a camera on a public transportation vehicle, uses the camera of a city public transportation vehicle to obtain road images, realizes target recognition and region segmentation; implements multi-target tracking of construction vehicles to grasp their dynamic movement; determines the road construction status through a decision tree based on the target recognition results and the vehicle movement; if the status is construction, combines multi-channel scene feature vectors and performs feature weight fusion; calculates feature influencing factors and environmental weight factors for comprehensive judgment; records target recognition results to form historical information for subsequent analysis; applies various fusion methods to improve the feature weight fusion effect and ensure accuracy; realizes rapid judgment and decision support of construction types through the combination of real-time data analysis and historical information, and is suitable for diverse urban road conditions.

[0024] Figure 1 FIG. 1 is a flow chart of a road construction status detection method based on dynamic data monitoring provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110 to S180.

[0025] S110: Acquire a road image collected by road traffic vehicles.

[0026] In this embodiment, the road image is a dynamic image of the road collected by road traffic vehicles.

[0027] Cameras installed on public transportation vehicles (such as buses and taxis) are used to collect and analyze the road conditions ahead. The equipment needs to operate in an environment with a wide field of view to ensure that clear images are collected, and the focus and GPS sensor are adjusted to confirm the accuracy of the location information. At fixed time intervals, the cameras on urban public transportation vehicles will continuously collect images, collect n images, and form a road image.

[0028] S120, performing target recognition and segmenting road areas, construction areas, and construction element features according to the road image to obtain target recognition results.

[0029] In this embodiment, the target recognition result includes the road area, the construction area, and the image area corresponding to the construction element features, wherein the construction element features include multiple types of features such as fences, construction vehicles, construction workers, and traffic cones.

[0030] Specifically, deep learning technology is used to segment these images and identify six types of targets: road area, construction area, fence, construction vehicle, construction worker and traffic cone. The segmented and identified images are as follows: Figure 3 shown.

[0031] Among them, road area characteristics refer to lanes and sidewalks.

[0032] Construction Area Features: Identify where construction is taking place.

[0033] Fence features: used to isolate the construction area, protect the safety of passers-by and prevent interference.

[0034] Construction Vehicles Features: Vehicles used on construction sites, such as excavators and transporters.

[0035] Construction personnel characteristics: Workers and managers involved in construction work to ensure the progress of the project.

[0036] Traffic cone feature: used to guide and warn pedestrians and vehicles, usually set up near construction sites to draw attention.

[0037] Specifically, it can be used Calculate the corresponding features, It is the output of the neural network corresponding to the deep learning technology, reflecting the superposition of multiple features. Under the influence of the convolution activation map, the mapping relationship between the position of the target and its features is relatively stable and usually shows similarity. Therefore, the target representation area is not only suitable for target detection and segmentation, but also can provide support for subsequent fine type judgment.

[0038] By comparing images collected by the same bus at different time points (such as 9 a.m. and 6 p.m.), it is possible to infer the cycle and status of road construction, assess the size of the construction area, the presence of fences, and the number of personnel and equipment on site, thereby providing strong data support for traffic management and construction planning.

[0039] S130: Track the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle.

[0040] In this embodiment, the movement of the construction vehicle includes two situations: the construction vehicle is moving or stationary.

[0041] Specifically, a motion reference system is established to more accurately capture and analyze the motion state of the construction vehicle; the motion reference system is set relative to the motion state of the observer, which means that the system will track the position of the surrounding construction vehicles based on the motion trajectory of the bus.

[0042] The real-time location information of the bus is obtained through sensors (such as GPS and accelerometers), thereby setting a dynamic reference frame so that the system can update the position in real time; multi-target tracking algorithms (such as Kalman filter, SORT, DeepSORT, etc.) are used to identify and track multiple construction vehicles; from the continuous image stream captured by the camera, construction vehicles are identified and a unique ID is assigned to each vehicle to achieve continuous tracking.

[0043] By analyzing the trajectory of the construction vehicle, its status is determined to be "running" or "stationary". The "running" status means that the construction vehicle is moving and may be under construction or relocating; the "stationary" status means that the vehicle is stopped.

[0044] The multi-target tracking method under the motion reference system can not only accurately monitor the operating status of construction vehicles, but also provide a scientific basis for traffic management and construction scheduling, and improve the overall construction management efficiency and safety.

[0045] S140, determining the road construction status according to a set decision tree in combination with the target recognition result and the movement status of the construction vehicle.

[0046] In this embodiment, the road construction status refers to whether the road is currently under construction or non-construction.

[0047] Specifically, see Figure 2 The decision tree includes eight different construction states and non-construction states, among which the construction state includes: with fence; without fence, with construction vehicle, construction vehicle is stationary, with construction personnel; without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, with traffic cones; without fence, without construction vehicle, with construction personnel, with traffic cones; the non-construction state includes: without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, without traffic cones; without fence, with construction vehicle, construction vehicle is moving; without fence, without construction vehicle, with construction personnel, without traffic cones; without fence, without construction vehicle, without construction personnel.

[0048] The decision tree can refine different construction states, enabling the system to accurately distinguish various construction scenarios, such as the presence or absence of fences and the status of construction vehicles. Using decision trees to analyze construction states can not only improve the level of intelligent construction management, but also provide strong support for urban traffic and safety management.

[0049] S150. According to the road construction status, the construction element characteristics are integrated, and the characteristic influencing factors and environmental weighting factors corresponding to the construction element characteristics are calculated according to the integration results. The characteristic influencing factors, environmental weighting factors and historical information are comprehensively judged to determine the construction type.

[0050] In one embodiment, the above-mentioned step S150 may include steps S151 - S154 .

[0051] S151. When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features.

[0052] In this embodiment, the fusion result refers to a comprehensive feature representation formed by fusing the feature weights of multi-channel scene feature vectors.

[0053] In one embodiment, the above-mentioned step S151 may include steps S1511~S1512.

[0054] S1511. When the road construction state is under construction, the construction element features are combined to form a multi-channel scene feature vector; wherein the weight of each channel is represented by the segmentation result corresponding to the feature.

[0055] In this embodiment, the four element features of fence feature, construction vehicle feature, construction worker feature, and traffic cone feature are used to form feature vectors of four channels. This structure allows the system to process different types of information at the same time, thereby providing a richer scene description.

[0056] The generation of the weight coefficient matrix depends on the segmentation result of each element, which is usually achieved through a binary mask.

[0057] Taking the construction vehicle as an example, the segmentation result generates a binary image, in which the pixel value of the vehicle area is 1 (with weight), and the pixel value of the area outside the vehicle is 0 (without weight); similarly, the segmentation result corresponding to the construction vehicle feature generates a binary image, in which the pixel value of the area where the construction vehicle feature is located is 1, and the others are 0; the segmentation result corresponding to the construction staff feature generates a binary image, in which the pixel value of the area where the construction staff feature is located is 1, and the others are 0; the segmentation result corresponding to the traffic cone feature generates a binary image, in which the pixel value of the area where the traffic cone feature is located is 1, and the others are 0.

[0058] S1512: Fusing the multi-channel scene feature vectors by feature weights to obtain a fusion result.

[0059] In this embodiment, at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion is used to fuse the feature weights of the multi-channel scene feature vector to obtain a fusion result.

[0060] Specifically, Gaussian fusion calculation mainly uses Gaussian matrix for fusion, such as Figure 5 As shown in the figure, the network output is multiplied by the corresponding Gaussian matrix and then the sum is the final eigenvalue. The right side is a Gaussian matrix, and the sum of all elements is 1. The Gaussian fusion process mainly calculates the Gaussian weights corresponding to the features, using , where A is the weight amplitude, the weight of the fence feature is set to 7, the weight of the vehicle feature is set to 5, the weight of the construction worker feature is set to 3, and the weight of the traffic cone feature is set to 1. Other feature fusion methods can be calculated independently without manually specifying the weight coefficient. The coordinates of the center, is the variance.

[0061] Regional mean feature fusion is the result matrix of the neural network output, in which the mean of the feature values ​​of different regions is used as the weight of feature fusion, that is, the final feature value. Figure 6 As shown, the right side is the mean matrix.

[0062] Regional clustering mode feature fusion is to classify the features in the region according to the smallest interval, and the feature interval with the largest number is used as the final feature weight, such as Figure 7 As shown, the mode of the statistical network output is used as the final eigenvalue.

[0063] like Figure 8 As shown in Figure 1, regional median feature fusion is to sort the features output by the network, and the median feature is used as the final feature weight.

[0064] The dual-layer dynamic feature activation fusion outputs two feature matrices of the same shape for each target, one of which represents the confidence of the target and the other represents the weight. The weight and rationality can only be determined when the confidence is activated. If the confidence is low, there is no need to determine the feature weight. Finally, the mean of the activated area is used as the final weight. Fig. 9As shown in the figure, the two matrices on the right, the first matrix is ​​the Gaussian matrix M1, the matrix value from the boundary to the center point is (0-n), n is the mean of the network output. The second Gaussian matrix M2, the sum of all elements is 1. First, the network output is compared with all elements of M1, that is, the corresponding features, and the elements whose network output results are greater than M1 are counted, and the remaining elements are discarded. Then the retained elements are summed with the Gaussian matrix M2, and the value is used as the final eigenvalue. That is, M1 acts as a filter, and only the results whose thresholds meet the requirements in the network output are filtered.

[0065] Through different fusion methods (such as Gaussian fusion, regional mean, mode and median feature fusion), various feature information can be effectively integrated to improve the model's ability to understand complex scenes.

[0066] Fusion methods such as regional mean and cluster mode feature fusion do not require manual specification of weights, which enhances the adaptability of the system and can automatically adapt to the feature distribution of different scenarios.

[0067] The two-layer dynamic feature activation fusion method can dynamically filter features according to confidence, effectively suppress the influence of noise and irrelevant features, and improve the rationality of feature selection.

[0068] The combination of multiple fusion methods enables the model to select the most appropriate feature fusion strategy according to specific task requirements and improve overall performance.

[0069] By adopting different fusion strategies, the model can be more robust in the face of data changes or uncertainties and maintain good performance.

[0070] S152. Calculate the characteristic influencing factor corresponding to the construction element characteristic according to the fusion result.

[0071] In this embodiment, the characteristic influencing factor refers to a relative degree indicating the construction level in the current scenario.

[0072] Specifically, using Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

[0073] The fusion results are finally Operation, that is, activation operation. The graphs corresponding to the fence features, construction vehicle features, construction worker features, and traffic cone features are summed.

[0074] The above steps can quantify the influence of each feature in a specific scenario, which helps to accurately evaluate the construction environment and improve the effectiveness of safety management and decision support.

[0075] S153. Calculate the environmental weight factor corresponding to the construction element characteristics.

[0076] In this embodiment, the environmental weight factors are used to evaluate the relative importance of each feature to construction safety and efficiency in a specific environment, specifically, the degree of influence of each feature on the overall construction status in the construction environment. They can help identify which features are more important in the current environment, thereby providing support for subsequent decision-making.

[0077] In one embodiment, the above-mentioned step S1530 may include steps S1531 to S1533.

[0078] S1531. Calculate the relevant parameters of the construction element characteristics.

[0079] In this embodiment, when judging the construction level, in addition to focusing on the feature dimensions, it is also necessary to consider the proportion of each element in the construction scene, because these factors directly affect the safety and efficiency of the construction. The specific steps are as follows: Calculate the area enclosed by the fence :First, measure the total area of ​​the area enclosed by the fence. This provides basic data for subsequent judgment.

[0080] Segment lanes and calculate lane width : Within the fenced area, identify the lanes and measure their width. Lane width is an important factor affecting the flow and safety of construction vehicles.

[0081] Calculate vehicle footprint : Count the number of vehicles in the construction area and calculate their total footprint based on vehicle type and size. This helps assess the level of congestion on the construction site.

[0082] Calculate the number of construction workers :Record the number of people on the construction site. The density of people is closely related to construction safety.

[0083] Calculate the area of ​​the polygon enclosed by traffic cones Traffic cones are often used to indicate the boundaries of construction areas. Based on the location of the traffic cones, the area of ​​the polygonal area enclosed by them is calculated to understand the effectiveness and safety of traffic guidance.

[0084] Through these calculations, various elements of the construction scenario can be comprehensively considered, so as to more accurately judge the construction level and potential risks.

[0085] S1532. Use priori parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain processing results.

[0086] In this embodiment, the processing result includes the following contents: Intermediate weight of enclosure feature ; Intermediate weights for construction vehicle features ; Intermediate weights of construction area characteristics ; The median weight of the traffic cone feature ; in, , , , is a priori parameter.

[0087] The above steps only limit the weights of the four elements of fence features, construction vehicle features, construction area features and traffic cone features to a relatively fixed range, and normalize them to between 0 and 1.

[0088] S1533. Perform Softmax processing on the processing result to obtain an environment weight factor.

[0089] Specifically, using ; ; ; , perform sofmax on the above weights to obtain the environmental weight factor , , .

[0090] The above steps can fully understand the construction environment and help identify potential risks by calculating the relevant parameters of features such as fences, construction vehicles, construction workers and traffic cones; the use of prior parameters and normalization processing allows various features to be compared on the same scale, which helps to make more scientific decisions; by quantifying the degree of congestion and the density of people at the construction site, it is possible to predict possible safety hazards in advance and take corresponding measures; by calculating the environmental weight factor, the most important factors in the construction process can be identified, thereby optimizing the allocation of manpower and material resources and improving construction efficiency; this method allows the weights to be dynamically updated according to real-time data, making construction management more flexible and adaptable to changing site conditions.

[0091] The feature influencing factors and environmental weight factors are presented in the segmented image to form a heat map, such as Figure 4 As shown, it can be used to classify construction types.

[0092] S154. Perform a comprehensive judgment based on the characteristic influencing factors and the environmental weight factors in combination with historical information to obtain a construction type.

[0093] In this embodiment, the construction type includes construction behavior categories, which can be specifically divided into three types: small-scale construction, medium-scale construction, and large-scale construction.

[0094] In this embodiment, construction is a continuous process, so it is necessary to not only rely on the currently collected image data, but also refer to historical information to obtain a more comprehensive judgment. The current vehicle collection sequence image is a complete monitoring, but by comparing with the historical collection data, the accuracy of recognition can be improved.

[0095] In one embodiment, the above-mentioned step S154 may include steps S1541~S1542.

[0096] S1541. Apply the sigmoid function to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result.

[0097] In this embodiment, the activation result refers to the value of the feature influence factor after conversion by the sigmoid function, and these values ​​will be limited to between 0 and 1 to facilitate subsequent processing; Specifically, the introduction of the β weight (valued at 0.5) and the Sigmoid activation function can effectively comprehensively evaluate the four element features (such as enclosure area, lane width, vehicle footprint, and number of construction personnel). Through the Sigmoid function, when the four features are obvious, the activation result is close to 1, indicating that the construction behavior is continuing; when the features are small, the activation result is small, indicating that the construction activity is weakening; if the features are extremely insignificant and the result is close to 0, it means that the construction is nearly completed.

[0098] Specifically, the network output is a feature matrix h*w*4, where 4 represents the elements, including fence features, construction vehicle features, personnel features, and traffic cone features. The feature matrix is ​​normalized to between 0 and 1 through sigmoid, and the feature vectors corresponding to the four mask regions are counted.

[0099] Prior to this, the characteristics of each channel were statistically analyzed by using "Gaussian weighting method" or "regional mean feature fusion" or "regional cluster mode feature fusion" or "regional median feature fusion" or "double-layer dynamic feature activation fusion" to determine the characteristic influencing factors corresponding to the construction element characteristics. , , , , at this time, the eigenvalue can be positive, negative or 0, not between 0 and 1. Then the four elements are weighted and summed, and normalized to between 0 and 1 by sigmoid method, tanh function normalization method or linear normalization method. This part.

[0100] Linear Normalization , where xMin and xMax are the estimated maximum values. For example, if the image size is 100*100, xMin can be estimated to be -10000 and xMax to be 10000. That is, when the feature matrix is ​​all -1, the sum is -10000, and when the feature matrix is ​​all 1, the sum is 10000.

[0101] Linear normalization can effectively integrate the influence of various features and improve the scientificity and accuracy of overall construction management.

[0102] S1542. Determine the construction type according to the activation result and the environmental weight factor combined with historical information.

[0103] Specifically, using Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; and is 0.5, It refers to the degree of influence of historical data; Activation result.

[0104] In this embodiment, in addition to the simple superposition of the characteristic influencing factors corresponding to the construction element characteristics, the environmental factors are also considered. The environmental factors are multiplied and summed with the corresponding characteristic influencing factors. .

[0105] In fact, first give The result is named Res1. The result is named Res2; α*Res1+β*Res2 (where α and β are both 0.5), which represents the detection result of the current vehicle. The result factor of the current detection and the historical result factor are k and 1-k respectively. k is set to 0.9, indicating that the confidence of the current result is very high. 1-k is 0.1, indicating that the historical results are for reference only (the historical results are the results of the previous vehicle, and the results of the current vehicle can become the historical results of the next vehicle detection results, which are relative concepts). In this way, the historical results and the current results are combined to judge this scene. The final value range of p is 0-1. The results can be classified according to the value of level P. For example, 0-0.3 represents a small construction site, 0.3-0.6 represents a medium-sized construction site, and 0.6-1 represents a large construction site.

[0106] By combining current and historical data, using environmental weight factors and characteristic influencing factors, the accuracy and credibility of construction type determination are improved. It can more comprehensively reflect the site conditions, make classification more accurate, help optimize construction management and resource allocation, and ultimately improve safety and efficiency.

[0107] The above-mentioned road construction status detection method based on dynamic data monitoring obtains road images through the camera on the urban public transportation vehicle, performs target recognition and segmentation, and extracts construction-related features. Then, multi-target tracking technology is used to monitor the movement of the construction vehicle, and the construction status is determined by using a decision tree in combination with the target recognition result. If it is in a construction state, various features are combined to form a multi-channel scene feature vector, and feature weight fusion is performed. Then, the feature influencing factor and environmental weight factor are calculated according to the fusion result, and a comprehensive judgment is made in combination with historical information to finally obtain the construction type. This process can adapt to different urban road conditions, quickly access, save costs, and improve urban governance and traffic warning capabilities.

[0108] Fig.10 FIG. 1 is a flow chart of a road construction status detection method based on dynamic data monitoring provided by another embodiment of the present invention. Fig.10 As shown, the road construction status detection method based on dynamic data monitoring of this embodiment includes steps S210-S260. Steps S210-S250 are similar to steps S110-S150 in the above embodiment, and will not be repeated here. The following is a detailed description of step S260 added in this embodiment.

[0109] S260: Record the target recognition result to form historical information.

[0110] Specifically, the current classification features are continuously updated to the cloud platform to form historical information These data can not only be used to determine whether there is construction in the current scene and the scale of the construction type, but also provide a basis for the comprehensive judgment of subsequent vehicles at the current location. Subsequent vehicles can combine historical information with real-time data to make more accurate analysis and decisions.

[0111] Fig.11 is a schematic block diagram of a road construction status detection device 300 based on dynamic data monitoring provided by an embodiment of the present invention. Fig.11 As shown, corresponding to the above road construction status detection method based on dynamic data monitoring, the present invention also provides a road construction status detection device 300 based on dynamic data monitoring. The road construction status detection device 300 based on dynamic data monitoring includes a unit for executing the above road construction status detection method based on dynamic data monitoring, and the device can be configured in a server. Fig.11 The road construction status detection device 300 based on dynamic data monitoring includes an image acquisition unit 301, a recognition and segmentation unit 302, a tracking unit 303, a status determination unit 304, and a construction type determination unit 305.

[0112] The image acquisition unit 301 is used to acquire a road image collected by a road traffic vehicle; the recognition and segmentation unit 302 is used to perform target recognition and segment the road area, construction area, and construction element features based on the road image to obtain a target recognition result; the tracking unit 303 is used to track the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle; the state determination unit 304 is used to determine the road construction state according to a set decision tree based on the target recognition result and the movement of the construction vehicle; the construction type determination unit 305 is used to fuse the construction element features according to the road construction state, and calculate the feature influencing factors and environmental weighting factors corresponding to the construction element features according to the fusion results, and make a judgment based on the comprehensive feature influencing factors, environmental weighting factors and historical information to determine the construction type.

[0113] In one embodiment, the construction type determination unit 305 includes: A fusion subunit is used for combining construction element features to form a multi-channel scene feature vector when the road construction state belongs to the construction state, and fusing feature weights to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features; A feature influence factor calculation subunit, used for calculating the feature influence factor corresponding to the construction element feature according to the fusion result; An environmental weight factor calculation subunit, used to calculate the environmental weight factor corresponding to the construction element characteristics; The comprehensive judgment subunit is used to make a comprehensive judgment based on the characteristic influencing factors and the environmental weight factors in combination with historical information to obtain the construction type.

[0114] In one embodiment, the fusion unit comprises: A combination module is used to combine the construction element features to form a multi-channel scene feature vector when the road construction state belongs to the construction state; wherein the weight of each channel is represented by the segmentation result corresponding to the feature; a weight fusion module is used to fuse the feature weights of the multi-channel scene feature vector to obtain a fusion result.

[0115] In one embodiment, the weight fusion module is used to fuse the feature weights of the multi-channel scene feature vector using at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion to obtain a fusion result.

[0116] In one embodiment, the feature impact factor calculation unit is used to adopt Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

[0117] In one embodiment, the environment weight factor calculation subunit includes: A parameter calculation module is used to calculate the relevant parameters of the construction element characteristics; a normalization module is used to use prior parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain a processing result; a processing module is used to perform Softmax processing on the processing result to obtain an environmental weight factor.

[0118] In one embodiment, the comprehensive judgment subunit includes: An activation module, used for applying a sigmoid function to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result; The determination module is used to determine the construction type according to the activation result and the environmental weight factor combined with historical information. Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; is 0.5, It refers to the degree of influence of historical data; Activation result.

[0119] Fig.12 FIG. 3 is a schematic block diagram of a road construction status detection device 300 based on dynamic data monitoring provided by another embodiment of the present invention. Fig.12 As shown, the road construction status detection device 300 based on dynamic data monitoring of this embodiment is based on the above embodiment and a recording unit is added.

[0120] The recording unit 306 is used to record the target recognition result to form historical information.

[0121] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned road construction status detection device 300 based on dynamic data monitoring and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0122] The above-mentioned road construction state detection device 300 based on dynamic data monitoring can be implemented in the form of a computer program. The computer program can be used in Fig.13 Runs on the computer device shown.

[0123] See also Fig.13 , Fig.13 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0124] See also Fig.13 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0125] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a road construction status detection method based on dynamic data monitoring.

[0126] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0127] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a road construction status detection method based on dynamic data monitoring.

[0128] The network interface 505 is used to communicate with other devices over the network. Fig.13 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: Acquire a road image collected by a road traffic vehicle; perform target recognition and segment the road area, construction area, and construction element features based on the road image to obtain a target recognition result; use a multi-target tracking method to track the construction vehicle to determine the movement of the construction vehicle; determine the road construction status based on a set decision tree in combination with the target recognition result and the movement of the construction vehicle; according to the road construction status, fuse the construction element features, and calculate the feature influencing factors and environmental weighting factors corresponding to the construction element features based on the fusion results, and make a judgment based on the comprehensive feature influencing factors, environmental weighting factors, and historical information to determine the construction type.

[0130] Among them, the decision tree includes eight different construction states and non-construction states, among which the construction state includes: with fence; without fence, with construction vehicle, construction vehicle is stationary, with construction personnel; without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, with traffic cones; without fence, without construction vehicle, with construction personnel, with traffic cones; the non-construction state includes: without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, without traffic cones; without fence, with construction vehicle, construction vehicle is moving; without fence, without construction vehicle, with construction personnel, without traffic cones; without fence, without construction vehicle, without construction personnel.

[0131] In one embodiment, when the processor 502 implements the step of fusing the construction element features according to the road construction status, calculating the feature influencing factors and the environmental weighting factors corresponding to the construction element features according to the fusion results, and making a judgment based on the feature influencing factors and the environmental weighting factors and historical information to determine the construction type, the processor 502 specifically implements the following steps: When the road construction status belongs to the construction status, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features; the feature influence factors corresponding to the construction element features are calculated according to the fusion results; the environmental weight factors corresponding to the construction element features are calculated; and a comprehensive judgment is made based on the feature influence factors and the environmental weight factors combined with historical information to obtain the construction type.

[0132] In one embodiment, when the processor 502 implements the step of combining the construction element features to form a multi-channel scene feature vector and fusing the feature weights to obtain a fusion result when the road construction state belongs to the construction state, the processor 502 specifically implements the following steps: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector; the weight of each channel is represented by the segmentation result corresponding to the feature; the feature weights of the multi-channel scene feature vector are fused to obtain a fusion result.

[0133] In one embodiment, when the processor 502 implements the step of fusing the feature weights of the multi-channel scene feature vectors to obtain a fusion result, the processor 502 specifically implements the following steps: The feature weights of the multi-channel scene feature vectors are fused by at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion to obtain a fusion result.

[0134] In one embodiment, when the processor 502 implements the step of calculating the feature influencing factor corresponding to the construction element feature according to the fusion result, the processor 502 specifically implements the following steps: use Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

[0135] In one embodiment, when the processor 502 implements the step of calculating the environmental weight factor corresponding to the construction element feature, the processor 502 specifically implements the following steps: Calculate the relevant parameters of the construction element characteristics; use prior parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain a processing result; and perform Softmax processing on the processing result to obtain an environmental weight factor.

[0136] In one embodiment, when the processor 502 performs the step of performing comprehensive judgment based on the characteristic influencing factor and the environmental weight factor in combination with historical information to obtain the construction type, the processor 502 specifically implements the following steps: The sigmoid function is applied to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result; and the construction type is determined according to the activation result and the environmental weight factor combined with historical information.

[0137] In one embodiment, when the processor 502 implements the step of determining the construction type according to the activation result and the environmental weight factor combined with historical information, the processor 502 specifically implements the following steps: use Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; and is 0.5, It refers to the degree of influence of historical data; Activation result.

[0138] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0139] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0140] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps: Acquire a road image collected by a road traffic vehicle; perform target recognition and segment the road area, construction area, and construction element features based on the road image to obtain a target recognition result; use a multi-target tracking method to track the construction vehicle to determine the movement of the construction vehicle; determine the road construction status based on a set decision tree in combination with the target recognition result and the movement of the construction vehicle; according to the road construction status, fuse the construction element features, and calculate the feature influencing factors and environmental weighting factors corresponding to the construction element features based on the fusion results, and make a judgment based on the comprehensive feature influencing factors, environmental weighting factors, and historical information to determine the construction type.

[0141] Among them, the decision tree includes eight different construction states and non-construction states, among which the construction state includes: with fence; without fence, with construction vehicle, construction vehicle is stationary, with construction personnel; without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, with traffic cones; without fence, without construction vehicle, with construction personnel, with traffic cones; the non-construction state includes: without fence, with construction vehicle, construction vehicle is stationary, without construction personnel, without traffic cones; without fence, with construction vehicle, construction vehicle is moving; without fence, without construction vehicle, with construction personnel, without traffic cones; without fence, without construction vehicle, without construction personnel.

[0142] In one embodiment, when the processor executes the computer program to implement the steps of fusing the construction element features according to the road construction status, calculating the feature influencing factors and the environmental weighting factors corresponding to the construction element features according to the fusion results, and making a judgment based on the feature influencing factors and the environmental weighting factors and historical information to determine the construction type, the following steps are specifically implemented: When the road construction status belongs to the construction status, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features; the feature influence factors corresponding to the construction element features are calculated according to the fusion results; the environmental weight factors corresponding to the construction element features are calculated; and a comprehensive judgment is made based on the feature influence factors and the environmental weight factors combined with historical information to obtain the construction type.

[0143] In one embodiment, when the processor executes the computer program to implement the step of combining the construction element features to form a multi-channel scene feature vector when the road construction state belongs to the construction state, and fusing the feature weights to obtain a fusion result, the processor specifically implements the following steps: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector; the weight of each channel is represented by the segmentation result corresponding to the feature; the feature weights of the multi-channel scene feature vector are fused to obtain a fusion result.

[0144] In one embodiment, when the processor executes the computer program to implement the step of fusing the feature weights of the multi-channel scene feature vectors to obtain a fusion result, the processor specifically implements the following steps: The feature weights of the multi-channel scene feature vectors are fused by at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion to obtain a fusion result.

[0145] In one embodiment, when the processor executes the computer program to implement the step of calculating the feature influencing factor corresponding to the construction element feature according to the fusion result, the processor specifically implements the following steps: use Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

[0146] In one embodiment, when the processor executes the computer program to implement the step of calculating the environmental weight factor corresponding to the construction element feature, the processor specifically implements the following steps: Calculate the relevant parameters of the construction element characteristics; use prior parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain a processing result; and perform Softmax processing on the processing result to obtain an environmental weight factor.

[0147] In one embodiment, when the processor executes the computer program to implement the step of performing a comprehensive judgment based on the characteristic influencing factor and the environmental weight factor in combination with historical information to obtain the construction type, the processor specifically implements the following steps: The sigmoid function is applied to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result; and the construction type is determined according to the activation result and the environmental weight factor combined with historical information.

[0148] In one embodiment, when the processor executes the computer program to implement the step of determining the construction type according to the activation result and the environmental weight factor combined with historical information, the processor specifically implements the following steps: use Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; and is 0.5, It refers to the degree of influence of historical data; Activation result.

[0149] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0150] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0151] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0152] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0154] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A road construction status detection method based on dynamic data monitoring, characterized in that: include: Acquire road images collected by road traffic vehicles; Performing target recognition and segmenting road areas, construction areas, and construction element features according to the road image to obtain target recognition results; Tracking the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle; Determine the road construction status according to a set decision tree based on the target recognition result and the movement of the construction vehicle; According to the road construction status, the construction element characteristics are integrated, and the characteristic influencing factors and environmental weight factors corresponding to the construction element characteristics are calculated based on the fusion results. The characteristic influencing factors, environmental weight factors and historical information are comprehensively judged to determine the construction type.

2. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: According to the road construction status, the construction element characteristics are integrated, and the characteristic influencing factors and environmental weighting factors corresponding to the construction element characteristics are calculated according to the integration results. The characteristic influencing factors, environmental weighting factors and historical information are comprehensively judged to determine the construction type, including: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result; wherein the construction element features include fence features, construction vehicle features, construction personnel features, and traffic cone features; Calculate the characteristic influencing factor corresponding to the construction element characteristic according to the fusion result; Calculating the environmental weight factor corresponding to the construction element characteristics; A comprehensive judgment is made based on the characteristic influencing factors and environmental weight factors in combination with historical information to obtain the construction type.

3. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: The decision tree includes eight different construction states and non-construction states, wherein the construction state includes: with fences; without fences, with construction vehicles, the construction vehicles are stationary, and with construction personnel; without fences, with construction vehicles, the construction vehicles are stationary, without construction personnel, and with traffic cones; without fences, without construction vehicles, with construction personnel, and with traffic cones; the non-construction state includes: without fences, with construction vehicles, the construction vehicles are stationary, without construction personnel, and without traffic cones; without fences, with construction vehicles, and with moving construction vehicles; without fences, without construction vehicles, with construction personnel, and without traffic cones; without fences, without construction vehicles, and without construction personnel.

4. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector, and the feature weights are fused to obtain a fusion result, including: When the road construction state belongs to the construction state, the construction element features are combined to form a multi-channel scene feature vector; wherein the weight of each channel is represented by the segmentation result corresponding to the feature; The multi-channel scene feature vectors are fused by feature weights to obtain a fusion result.

5. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: The multi-channel scene feature vectors are fused with feature weights to obtain a fusion result, including: The feature weights of the multi-channel scene feature vectors are fused by at least one of Gaussian fusion, regional mean feature fusion, regional cluster mode feature fusion, regional median feature fusion, and double-layer dynamic feature activation fusion to obtain a fusion result.

6. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: The calculating, according to the fusion result, the characteristic influencing factor corresponding to the construction element characteristic comprises: use Calculate the characteristic influencing factor corresponding to the construction element characteristic, where: It refers to the characteristics of fences, construction vehicles, construction workers, and traffic cones; is the weight coefficient; is the fusion result; is the characteristic influencing factor corresponding to the construction element characteristics.

7. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: The calculating of the environmental weight factor corresponding to the construction element feature includes: Calculating relevant parameters of the construction element characteristics; Using a priori parameters to pre-normalize the relevant parameters of the construction element characteristics to obtain a processing result; The processing result is subjected to Softmax processing to obtain an environment weight factor.

8. The road construction status detection method based on dynamic data monitoring according to claim 1 is characterized in that: The construction type is obtained by making a comprehensive judgment based on the characteristic influencing factors and the environmental weight factors in combination with historical information, including: Applying a sigmoid function to activate the characteristic influencing factors corresponding to the construction element characteristics to obtain an activation result; The construction type is determined according to the activation result and the environmental weight factor combined with historical information.

9. The road construction status detection method based on dynamic data monitoring according to claim 8 is characterized in that: The determining of the construction type according to the activation result and the environmental weight factor combined with historical information includes: use Determine the type of construction, where For construction type; It refers to the importance weight of current and historical data; , , , are the environmental weight factors corresponding to the characteristics of the construction elements; , , , are characteristic influencing factors corresponding to the characteristics of the construction elements respectively; and is 0.5, It refers to the degree of influence of historical data; Activation result.

10. A road construction status detection device based on dynamic data monitoring, characterized in that: include: An image acquisition unit, used to acquire a road image collected by a road traffic vehicle; An identification and segmentation unit, used to perform target identification and segment the road area, construction area, and construction element features according to the road image to obtain a target identification result; A tracking unit, used to track the construction vehicle using a multi-target tracking method to determine the movement of the construction vehicle; A state determination unit, configured to determine the road construction state according to a set decision tree in combination with the target recognition result and the movement of the construction vehicle; The construction type determination unit is used to fuse the construction element characteristics according to the road construction status, and calculate the characteristic influencing factors and environmental weighting factors corresponding to the construction element characteristics according to the fusion results, and make a judgment based on the comprehensive characteristic influencing factors, environmental weighting factors and historical information to determine the construction type.

Images