Road asset identification and evaluation system based on unmanned aerial vehicle image

Abstract

The invention provides a road asset identification and evaluation system based on an unmanned aerial vehicle image, and relates to the field of road assets, and the system comprises a first information obtaining module which is used for obtaining the image information of a target road according to an image obtaining device carried by an unmanned aerial vehicle; the second information acquisition module is used for acquiring feature information of each road asset target included in the target road; the classification module is used for obtaining a plurality of road asset types; the first result acquisition module is used for obtaining an assessment result corresponding to each road asset type according to the feature information of each road asset target, each road asset type and the asset assessment model corresponding to each road asset type; and the second result acquisition module is used for obtaining an evaluation result of the target road according to the evaluation result of each road asset type. According to the invention, dynamic and preventive maintenance of road asset management is ensured, the management level and the service quality are integrally improved, and smooth road traffic is ensured.

Description

Background Art

[0002] With the continuous expansion of highway construction and the increase in highway operation years, highway asset management has become a vital task in the transportation field. There are many types of highway assets, including pavements, bridges, tunnels, traffic signs, guardrails, etc. Traditional highway asset management methods face many challenges and limitations.

[0003] Traditional highway asset surveys and assessments rely mainly on manual inspections. Manual inspections are not only inefficient, but also cost a lot of manpower, material resources, and time. Inspectors need to inspect each section of the highway. For some sections with complex terrain or heavy traffic, inspections are difficult and may even pose safety risks. For example, on high-altitude highways in mountainous areas or on highways with heavy traffic, manual inspections are difficult to conduct a comprehensive and detailed inspection of highway assets, and are prone to missing some diseases or asset damage.

[0004] At the same time, manual assessment is highly subjective, and different inspectors have different experiences and judgment standards, which makes it difficult to ensure the accuracy and consistency of the assessment results. For example, different people may come to different conclusions about the width of road cracks and the severity of the disease, which brings uncertainty to highway maintenance and repair decisions.

[0005] In recent years, with the rapid development of information technology, some digital technologies have begun to be applied to the field of highway asset management. For example, highway monitoring technology based on satellite remote sensing images can cover a large range of highway areas, but the resolution of satellite images is limited, and it is difficult to clearly identify some small highway assets (such as small traffic signs, local road surface diseases, etc.), which cannot meet the needs of refined highway asset management.

[0006] In addition, vehicle-mounted mobile measurement systems are also used for highway data collection, but they are restricted by road conditions and cannot detect highway assets in some areas that are not open to traffic or have traffic control. The system cost is high, and the equipment installation and maintenance are relatively complicated. Summary of the invention

[0007] In response to the above technical problems, the present application provides a highway asset identification and assessment system based on drone images, which at least partially solves the problems existing in the prior art.

[0008] In a first aspect of the present application, a highway asset identification and assessment system based on drone images is provided, the system comprising:

[0009] A first information acquisition module is used to acquire image information of a target road according to an image acquisition device carried by the UAV; wherein the image information is video information corresponding to the target road;

[0010] A second information acquisition module is used to acquire characteristic information of each road asset target included in the target road according to the image information;

[0011] A classification module, used for classifying each highway asset target according to the characteristic information of each highway asset target to obtain a number of highway asset types; wherein each highway asset type has a corresponding asset evaluation model;

[0012] A first result acquisition module is used to obtain an evaluation result corresponding to each highway asset type according to the characteristic information of each highway asset target, each highway asset type and the asset evaluation model corresponding to each highway asset type;

[0013] The second result acquisition module is used to obtain the evaluation result of the target highway according to the evaluation result of each highway asset type.

[0014] This application has at least the following beneficial effects:

[0015] The highway asset identification and assessment system based on drone images provided in this application uses drones to collect highway image information. It has strong mobility, is not limited by terrain, can quickly cover various road sections, and the collected video information contains richer temporal and spatial content, which effectively improves data acquisition efficiency and lays a solid foundation for subsequent work; it can accurately extract highway asset target feature information, accurately distinguish various types of assets with the help of classification algorithms, avoid subjective misjudgment and omissions in manual identification, achieve refined classification, and facilitate the formulation of targeted maintenance strategies; construct corresponding models for different asset types, and conduct quantitative assessment by comprehensively considering the characteristics of each asset. The results obtained are scientific and accurate, which can help highway management departments grasp the current status and potential risks of assets, rationally plan resources and maintenance plans, ensure highway operation safety and reduce costs; the system realizes highly intelligent and automated operation, reduces manual dependence and reduces labor costs, and can also automatically and continuously monitor, regularly evaluate and issue timely warnings to ensure dynamic highway asset management and preventive maintenance, improve the overall management level and service quality, and ensure smooth highway traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A structural block diagram of a highway asset identification and assessment system based on drone images provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0021] Please refer to Figure 1 As shown, the embodiment of the present application provides a highway asset identification and assessment system 100 based on drone images, the system comprising: a first information acquisition module 110, a second information acquisition module 120, a classification module 130, a first result acquisition module 140 and a second result acquisition module 150; wherein,

[0022] The first information acquisition module 110 is used to acquire image information of the target road according to the image acquisition device carried by the UAV; wherein the image information is video information corresponding to the target road.

[0023] Specifically, choose a drone with a high-resolution camera (such as a professional aerial survey camera), stable flight performance and long endurance. Equipped with a GPS positioning module, an inertial measurement unit (IMU) and a data transmission module, ensure that the image location information and flight attitude information can be accurately obtained, and the data can be transmitted back to the ground control station in real time.

[0024] The second information acquisition module 120 is used to acquire characteristic information of each road asset target included in the target road according to the image information.

[0025] Specifically, the data transmission module of the drone uses wireless communication technology (such as 4G / 5G network or dedicated microwave communication link) to transmit the collected image data and flight parameter information to the ground control station in real time. During the transmission process, the data is encrypted to ensure the security and integrity of the data.

[0026] After receiving the data, the ground control station stores the image data and related parameter information in a high-performance storage server. A distributed storage architecture, such as the Hadoop Distributed File System (HDFS), is used to meet the storage needs of massive data and ensure high reliability and scalability of the data. At the same time, a data indexing mechanism is established to facilitate subsequent data query and retrieval.

[0027] The collected original images are preprocessed, including radiation correction (eliminating the influence of uneven lighting and other factors on the image), geometric correction (correcting the image deformation caused by the flight posture of the drone and the undulating terrain) and denoising (removing noise points in the image to improve the image quality). Professional image processing software libraries (such as OpenCV) are used to implement the above preprocessing operations.

[0028] Use deep learning target detection algorithms (such as Faster R-CNN, YOLO series, etc.) to detect highway asset targets on preprocessed images. First, collect a large number of image samples containing various highway assets and annotate them to create a training data set. Then, use the training data set to train the selected target detection model and adjust the model parameters so that it can accurately identify different types of highway assets, such as pavement diseases (cracks, potholes, etc.), bridge structural components (piers, abutments, bridge decks, etc.), traffic signs (speed limit signs, prohibition signs, etc.) and protective facilities (guardrails, isolation piers, etc.).

[0029] For the detected highway asset targets, further extract their feature information, such as shape, texture, color, etc. Feature extraction algorithms (such as scale-invariant feature transform (SIFT), histogram of oriented gradients (HOG), etc.) are used for feature extraction.

[0030] The classification module 130 is used to classify each highway asset target according to the characteristic information of each highway asset target to obtain a number of highway asset types; wherein each highway asset type has a corresponding asset evaluation model.

[0031] Specifically, the highway assets are classified in combination with machine learning classification algorithms (such as support vector machine (SVM), random forest (RF), etc.) to determine their specific categories and attribute information.

[0032] In one embodiment, each highway asset target is classified by the following method: the extracted feature data (such as SIFT or HOG feature vectors) are combined with the corresponding highway asset category labels to form a data set. For example, if there are categories such as pavement cracks, traffic signs, guardrails, etc., each sample data is the corresponding feature vector and category label. The data set is divided into a training set and a test set according to a certain ratio (such as 70% training set and 30% test set). A random partitioning method can be used to ensure that both the training set and the test set can better represent the distribution of the entire data set. Initialize the SVM classifier, select a suitable kernel function (such as a linear kernel, a polynomial kernel, a radial basis function (RBF) kernel, etc.) and related parameters (such as a penalty parameter, etc.). For the linear kernel function, the penalty parameter is mainly adjusted. The larger the penalty parameter, the greater the penalty for misclassification, and the more the model tends to fit the training data better, but it may cause overfitting; for the RBF kernel function, the kernel coefficient also needs to be adjusted. The kernel coefficient determines the distribution of the data after it is mapped to the new feature space. The feature data and category labels of the training set are input into the SVM classifier for training. The decision function of the SVM is solved by an optimization algorithm (such as the Sequential Minimum Optimization (SMO) algorithm) to determine the parameters of the classification hyperplane so as to maximize the classification interval and minimize the training error. The feature data of the test set is input into the trained SVM classifier, and the score or probability of each test sample belonging to each category is calculated according to the decision function of the classifier. The sample is classified into the category with the highest score or the highest probability to obtain the classification result of the test set.

[0033] Then, the RF classifier is trained and classified: First, training is performed: determine the number of decision trees in the random forest (generally determined by experiments, such as 100-500 trees). For each decision tree: a certain proportion of samples are randomly selected from the training set with replacement as the training data of the tree, that is, bootstrap sampling; at each node, a subset is randomly selected from all features, the information gain or other splitting criteria of these features are calculated, the best features are selected for splitting, and a decision tree is constructed. Repeat this process until the decision tree reaches a predetermined depth or other stopping condition (such as the number of samples in the node is less than a certain threshold). Secondly, classification is performed: for each sample in the test set, its feature data is input into each decision tree in the random forest, and each tree will give a classification result. Using the voting method, the classification results of all decision trees are counted, and the samples are classified into the category with the most votes to obtain the classification result of the test set.

[0034] Finally, performance evaluation and optimization are performed: First, the performance indicators of the classifier are calculated, such as accuracy, recall, F1 value, etc. Accuracy refers to the ratio of correctly classified samples to the total number of samples; recall refers to the ratio of correctly classified positive samples to the actual number of positive samples; F1 value is an indicator that comprehensively considers accuracy and recall. According to the performance evaluation results, if the classification performance is not ideal, for the SVM classifier, the kernel function type and parameters can be adjusted, such as increasing the amount of training data, using cross-validation methods to find the best parameters, etc.; for the RF classifier, the number of decision trees, the depth of the tree, the size of the feature subset and other parameters can be adjusted, or the diversity of the training data can be increased, and the classifier can be retrained until satisfactory classification performance is achieved.

[0035] Each highway asset target is classified using the trained classifier to obtain several highway asset types.

[0036] The first result acquisition module 140 is used to obtain the evaluation result corresponding to each highway asset type according to the characteristic information of each highway asset target, each highway asset type and the asset evaluation model corresponding to each highway asset type.

[0037] Specifically, according to the evaluation results of all highway asset targets included in each highway asset type, the evaluation result corresponding to each highway asset type is obtained by weighted summation. Among them, the weight of each highway asset target included in each highway asset type is determined according to the importance of each highway asset target to the corresponding highway asset type. Those skilled in the art can use any weight determination method suitable for this solution, which will not be repeated here.

[0038] The second result acquisition module 150 is used to obtain the evaluation result of the target highway according to the evaluation result of each highway asset type.

[0039] Specifically, the evaluation results of each highway asset type are weighted and summed to obtain the evaluation result of the target highway. The weight corresponding to each highway asset type is determined according to the importance of each highway asset type to the evaluation result of the target highway. Those skilled in the art can use any weight determination method suitable for this solution, which will not be described in detail here.

[0040] It should be noted that the data format of each of the above evaluation results can be a score or a ratio.

[0041] It is understandable that when obtaining the evaluation result of the target highway, the target highway can be obtained in sections, that is, the target highway can be divided into several preset sections, and all highway asset targets included in each preset section are obtained, thereby obtaining all highway asset targets included in the target highway.

[0042] This embodiment uses drones to collect highway image information. The drones have strong mobility, are not limited by terrain, can quickly cover all road sections, and the collected video information contains richer temporal and spatial content, effectively improving data acquisition efficiency and laying a solid foundation for subsequent work. The drones can accurately extract highway asset target feature information, accurately distinguish various types of assets with the help of classification algorithms, avoid subjective misjudgments and missed judgments in manual identification, achieve refined classification, and facilitate the formulation of targeted maintenance strategies. Corresponding models are constructed for different asset types, and quantitative evaluation is carried out by comprehensively considering the characteristics of each asset. The results are scientific and accurate, which can help highway management departments grasp the current status of assets and potential risks, rationally plan resources and maintenance plans, ensure highway operation safety and reduce costs. The system realizes highly intelligent and automated operation, reduces manual dependence and labor costs, and can also automatically and continuously monitor, regularly evaluate and issue timely warnings to ensure dynamic highway asset management and preventive maintenance, improve the overall management level and service quality, and ensure smooth highway traffic.

[0043] In an exemplary embodiment of the present application, the first information acquisition module 110 includes:

[0044] The curve acquisition unit is used to acquire the historical evaluation result change curve of each highway asset target contained in each preset section of the target highway within the first target time window, so as to obtain the historical evaluation result change curve list set L=(L 1 , L 2 , …, L i , …, L n );i=1,2,…,n;wherein n is the number of preset sections included in the target highway; L i is a list of historical evaluation result change curves of the i-th preset road section included in the target highway; i =(L i，1 , L i，2 , …, L i，a, …, L i，f(i) ); a = 1, 2, ..., f(i); f(i) is the number of highway asset targets included in the i-th preset road section included in the target highway; L i，a It is a historical evaluation result variation curve of the a-th highway asset target of the i-th preset road section included in the target highway; each highway asset target has a corresponding standard evaluation result.

[0045] Specifically, the end time of the first target time window is the evaluation time closest to the current time. The historical evaluation result change curve of each highway asset target included in each preset section of the target highway within the first target time window represents the evaluation result change of the highway asset target in the preset section within the first target time window.

[0046] The duration acquisition unit is used to obtain a comprehensive historical abnormal duration list Y=(Y 1 , Y 2 , …, Y i , …, Y n ), where Y i It is the comprehensive historical abnormal duration of the i-th preset road section included in the target highway.

[0047] Specifically, Y i Meet the following characteristics:

[0048] Y i =Σ f(i) a＝1 Y i，a

[0049] Among them, Y i，a It is the historical abnormal duration of the a-th highway asset target of the i-th preset road section included in the target highway.

[0050] Y i，a Meet the following characteristics:

[0051] If Y i，a If the historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is less than the corresponding standard evaluation result, then Y i，a The length of time during which the historical evaluation result is less than the standard evaluation result in the second time window;

[0052] If Y i，a If the historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is equal to or greater than the corresponding standard evaluation result, then Y i，a =0.

[0053] Among them, the end time of the second time window is the same as that of the first time window. The time length of the second time window is less than that of the first time window.

[0054] Specifically, in this embodiment, if Y i，a The historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is less than the corresponding standard evaluation result, which indicates that Y i，a When the corresponding highway asset target is at the evaluation time closest to the current time, the evaluation result is low, that is, the asset condition of the highway asset target is poor, and the possible damage degree is high. Furthermore, if the time length during which the historical evaluation result is less than the standard evaluation result within the second time window is long, it indicates that within the recent period, Y i，a The asset condition of the corresponding highway asset target continues to be poor. On the contrary, if Y i，a The historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is equal to or greater than the corresponding standard evaluation result. Regardless of the previous historical evaluation results, it indicates that the current asset condition of the highway asset target is good. If the previous asset condition of the highway asset target was poor, it may have been repaired or replaced.

[0055] Furthermore, the historical abnormal durations of all highway asset targets in each preset road section are summed up to obtain the comprehensive historical abnormal duration of each preset road section.

[0056] The speed acquisition unit is used to obtain the target flight speed list F=(F 1 , F 2 , …, F i , …, F n ) according to Y; where F i is the target flight speed of the i-th preset road section included in the target highway.

[0057] Specifically, the speed acquisition unit includes:

[0058] The ratio determination sub-unit is used to obtain the abnormal ratio list B=(B 1 , B 2 , …, B i , …, B n ) according to L and Y; where B i is the abnormal ratio of the i-th preset road section included in the target highway; B i =Y i / N i ; N i is the time length of the first time window;

[0059] The speed determination subunit is used to obtain the target flight speed list F=(F 1 , F 2 , …, F i , …, F n ); wherein the preset mapping table includes each abnormal ratio and the flight speed corresponding to each abnormal ratio.

[0060] In this embodiment, different target flight speeds are provided for different abnormality ratios. It should be noted that if the abnormality ratio of a preset road section is larger, it means that the asset condition of the preset road section has been poor in the recent period. At this time, a slower flight speed is set for the preset road section to obtain a clearer image, that is, the specific situation of each highway asset target in the preset road section can be obtained. Conversely, if the abnormality ratio of a preset road section is smaller, it means that the asset condition of the preset road section has been good in the recent period. At this time, a faster flight speed is set for the preset road section to save the overall flight time.

[0061] The image information acquisition unit is used to acquire the image information of the target road according to F.

[0062] In an exemplary embodiment of the present application, a method for identifying and evaluating highway assets based on drone images is also provided, the method comprising:

[0063] The image information of the target road is obtained according to the image acquisition device carried by the UAV; wherein the image information is the video information corresponding to the target road.

[0064] According to the image information, characteristic information of each road asset target included in the target road is obtained.

[0065] Each highway asset target is classified according to the characteristic information of each highway asset target to obtain a number of highway asset types; wherein each highway asset type has a corresponding asset evaluation model.

[0066] According to the characteristic information of each highway asset target, each highway asset type and the asset evaluation model corresponding to each highway asset type, the evaluation result corresponding to each highway asset type is obtained.

[0067] Based on the assessment results of each highway asset type, the assessment results of the target highway are obtained.

[0068] In an exemplary embodiment of the present application, an electronic device for implementing the above method is also provided.

[0069] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0070] The electronic device according to this embodiment of the present application is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0071] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0072] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present application.

[0073] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0074] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0075] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0076] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device, and / or communicate with any device (such as routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. This communication can be carried out through an input / output (I / O) interface. In addition, the electronic device can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0077] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0078] In an exemplary embodiment of the present application, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Exemplary Method" section of the present specification.

[0079] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0080] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0082] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0083] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0084] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0085] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A highway asset identification and assessment system based on drone images, characterized in that: The system comprises: A first information acquisition module is used to acquire image information of a target road according to an image acquisition device carried by the UAV; wherein the image information is video information corresponding to the target road; A second information acquisition module is used to acquire characteristic information of each road asset target included in the target road according to the image information; A classification module, used for classifying each highway asset target according to the characteristic information of each highway asset target to obtain a number of highway asset types; wherein each highway asset type has a corresponding asset evaluation model; A first result acquisition module is used to obtain an evaluation result corresponding to each highway asset type according to the characteristic information of each highway asset target, each highway asset type and the asset evaluation model corresponding to each highway asset type; The second result acquisition module is used to obtain the evaluation result of the target highway according to the evaluation result of each highway asset type.

2. The highway asset identification and assessment system based on drone images according to claim 1 is characterized in that: The first information acquisition module includes: The curve acquisition unit is used to acquire the historical evaluation result change curve of each highway asset target contained in each preset section of the target highway within the first target time window to obtain a historical evaluation result change curve list set L = (L1, L2, ..., L i , …, L n );i=1,2,…,n;wherein n is the number of preset sections included in the target highway; L i is a list of historical evaluation result change curves of the i-th preset road section included in the target highway; i =(L i，1 , L i，2 , …, L i，a , …, L i，f(i) ); a = 1, 2, ..., f(i); f(i) is the number of highway asset targets included in the i-th preset road section included in the target highway; L i，a The historical evaluation result change curve of the a-th highway asset target of the i-th preset road section included in the target highway; each highway asset target has a corresponding standard evaluation result; The duration acquisition unit is used to obtain a comprehensive historical abnormal duration list Y=(Y1, Y2, ..., Y i , …, Y n ), where Y i is the comprehensive historical abnormal duration of the i-th preset road section included in the target highway; The speed acquisition unit is used to obtain the target flight speed list F=(F1, F2, ..., F i , …, F n ), where F i is the target flight speed of the i-th preset road section included in the target highway; The image information acquisition unit is used to acquire the image information of the target road according to F.

3. The highway asset identification and assessment system based on drone images according to claim 2 is characterized in that: The end time of the first target time window is the evaluation time closest to the current time.

4. The highway asset identification and assessment system based on drone images according to claim 3 is characterized in that: Y i Meet the following characteristics: AND i =Σ f(i) a＝1 AND i，a Among them, Y i，a It is the historical abnormal duration of the a-th highway asset target of the i-th preset road section included in the target highway.

5. The highway asset identification and assessment system based on drone images according to claim 4 is characterized in that: Y i，a Meet the following characteristics: If Y i，a If the historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is less than the corresponding standard evaluation result, then Y i，a The length of time during which the historical evaluation result is less than the standard evaluation result in the second time window; If Y i，a If the historical evaluation result of the corresponding highway asset target at the evaluation time closest to the current time is equal to or greater than the corresponding standard evaluation result, then Y i，a =0.

6. The highway asset identification and assessment system based on drone images according to claim 5 is characterized in that: The end time of the second time window is the same as the end time of the first time window.

7. The highway asset identification and assessment system based on drone images according to claim 6 is characterized in that: The time length of the second time window is shorter than the time length of the first time window.

8. The highway asset identification and assessment system based on drone images according to claim 2 is characterized in that: The speed acquisition unit comprises: The ratio determination subunit is used to obtain an abnormal ratio list B=(B1, B2, ..., B i , …, B n ), where B i is the abnormal proportion of the i-th preset road section included in the target highway; B i =Y i / N i ; N i is the length of the first time window; The speed determination subunit is used to obtain the target flight speed list F=(F1, F2, ..., F i , …, F n ); wherein the preset mapping table includes each abnormal ratio and the flight speed corresponding to each abnormal ratio.

Images