Method and device for detecting spilled objects on expressway surface, electronic equipment and medium

Abstract

The invention relates to a method and device for detecting spilled objects on an expressway surface, electronic equipment and a medium, and belongs to the technical field of traffic detection.The method comprises the steps that vibration signals of all measuring points on the expressway surface can be obtained based on a grating array vibration sensor, and then the vibration signals of all the measuring points can be monitored in real time; the timeliness of detecting the thrown objects on the expressway is improved; furthermore, peak value extraction can be carried out according to the vibration signal, a peak value point corresponding to each measuring point is determined, and all the peak value points are judged and fitted to obtain a vibration characteristic line set; when the vibration characteristic line set meets a preset condition, it is determined that an object throwing event exists at the current moment; the preset condition is that a plurality of initial characteristic lines meeting the characteristics of the throwing object exist; according to the plurality of initial feature lines, the drop point position of the thrown object in the thrown object event can be obtained, and the positioning precision of the highway thrown object is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic detection, and in particular to a method, device, electronic equipment and medium for detecting objects spilled on a high-speed road surface. Background Art

[0002] As the mileage of highways at home and abroad increases year by year, the number of incidents of spilled objects on highways is also on the rise. Spilled objects are one of the important causes of traffic accidents and congestion. Due to the high speed and large traffic volume of vehicles on highways, spilled objects not only pose a hidden danger to the driving safety of highways, but also may reduce the efficiency of highway traffic and cause traffic congestion. The handling of spilled objects is difficult to detect in time, difficult to clean up quickly, and difficult to warn and prevent. How to detect and clean up spilled objects in time is an important problem in current highway management.

[0003] At present, there are two main methods for detecting spilled objects on highways: manual inspection and automatic detection. Manual inspection mainly relies on regular inspections by highway inspectors along the highway. This method is inefficient, cannot detect spilled objects in time, and is dangerous. Automatic detection methods are divided into direct methods and indirect methods. The direct method mainly uses surveillance cameras along the highway to take real-time photos of the road surface and use some image recognition methods to detect road surface obstacles. The indirect method mainly infers the spilled objects by judging whether the traffic flow parameters obtained by the detector are abnormal. Since the direct method relies on taking photos with cameras along the road, it can only detect spilled objects on local roads, and the algorithm detection accuracy is affected by environmental factors, such as the recognition rate is low in the absence of lighting at night and in rainy, snowy and foggy days. The indirect method makes judgments based on traffic flow parameters, and has the disadvantages of poor recognition timeliness and low positioning accuracy.

[0004] Therefore, it is urgent to propose a method, device, electronic equipment and medium for detecting spilled objects on highways to solve the technical problems of poor timeliness and low positioning accuracy in the camera image recognition method for highway spilled objects and the indirect recognition method for traffic flow in the prior art. Summary of the invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and medium for detecting spilled objects on highways, so as to solve the technical problems of poor timeliness and low positioning accuracy in the camera image recognition method of highway spilled objects and the indirect recognition method of traffic flow in the prior art.

[0006] In order to solve the above problems, the present invention provides a method for detecting spilled objects on a high-speed road, comprising: Acquire vibration signals of all measuring points on the highway road surface based on grating array vibration sensors; Extracting peak values ​​according to the vibration signal, determining the peak point corresponding to each measuring point, and judging and fitting all the peak points to obtain a set of vibration characteristic lines; When the vibration characteristic line set meets a preset condition, it is determined that there is a spilled object event at the current moment; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; According to the multiple initial characteristic lines, the landing point position of the scattered object in the scattered object event is obtained.

[0007] In a possible implementation, performing peak extraction according to the vibration signal to determine a peak point corresponding to each measuring point includes: Preprocessing the vibration signal to obtain a preprocessed vibration signal of each measuring point; Performing absolute value calculation on the preprocessed vibration signal to obtain an absolute value signal of each measuring point; Performing signal extraction on the absolute value signal based on a filter to obtain a low-frequency vibration signal of each measuring point; The peak value of the low-frequency vibration signal is extracted based on the peak point identification method to obtain the peak point of each measuring point.

[0008] In a possible implementation, the peak point identification method is used to extract the peak value of the low-frequency vibration signal to obtain the peak point of each measuring point, including: Calculate the local extreme value of the low-frequency vibration signal at any measuring point to obtain the corresponding extreme value; the extreme value includes an initial peak point and a valley point; Calculating the initial peak point and the valley point to obtain a ratio; Determining whether the ratio is greater than a preset threshold; If so, the initial peak point is determined to be the peak point of the corresponding measurement point.

[0009] In a possible implementation, the judging and fitting of all peak points to obtain a set of vibration characteristic lines includes: Determine the range of the wave packet where the peak point of each measuring point is located; Determine whether the ranges of wave packets where the peak points of adjacent measuring points are located overlap in time; If yes, the peak points of the adjacent measuring points are connected to obtain the characteristic lines generated by the same vibration at each measuring point; The characteristic lines are subjected to piecewise linear fitting to obtain a set of vibration characteristic lines.

[0010] In a possible implementation, determining the range of the wave packet where the peak point of each measuring point is located includes: Taking the peak of the peak point as the center, intercept signal segments whose values ​​are greater than the signal mean of multiples of a preset multiple value on both sides of the peak, and determine the signal segments as the range of the wave packet where the peak point is located.

[0011] In a possible implementation, performing piecewise linear fitting on the characteristic lines to obtain a set of vibration characteristic lines includes: According to the characteristic line, determining the minimum time point as the vertex; The characteristic line is divided into left and right parts with the vertex as the boundary, and linear fitting is performed on each part to obtain a sprinkler characteristic line, and a vibration characteristic line set is obtained based on all sprinkler characteristic lines.

[0012] In a possible implementation, obtaining the landing point of the scattered object in the scattered object event according to the multiple initial characteristic lines includes: Comparing the multiple initial feature lines to obtain a target feature line with a minimum vertex; The coordinate positions of points on the target characteristic line and the corresponding amplitude values ​​are calculated based on the centroid positioning to obtain the landing point position of the scattered object in the scattered object event.

[0013] On the other hand, the present invention also provides a high-speed road spill detection device, comprising: A signal acquisition module, used to acquire vibration signals of all measuring points on the highway road surface based on a grating array vibration sensor; A peak extraction module is used to extract the peak value according to the vibration signal, determine the peak point corresponding to each measuring point, and judge and fit all the peak points to obtain a set of vibration characteristic lines; A characteristic line judgment module is used to determine that there is a spilled object event at the current moment when the vibration characteristic line set meets a preset condition; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; The position determination module is used to obtain the landing point position of the scattered object in the scattered object event according to multiple initial characteristic lines.

[0014] On the other hand, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, each step of the above-mentioned embodiment of the method for detecting spilled objects on a high-speed road surface is implemented.

[0015] On the other hand, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various steps of the above-mentioned embodiment of the method for detecting spilled objects on a high-speed road are implemented.

[0016] The beneficial effects of the present invention are as follows: the vibration signals of all measuring points on the highway surface can be acquired based on the grating array vibration sensor, and then the vibration signals of all measuring points can be monitored in real time, thereby improving the timeliness of detection of spilled objects on the highway; further, peak value extraction can be performed based on the vibration signal to determine the peak point corresponding to each measuring point, and all peak points can be judged and fitted to obtain a set of vibration characteristic lines; when the set of vibration characteristic lines meets the preset conditions, it is determined that there is a spilled object event at the current moment; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; based on the multiple initial characteristic lines, the landing point position of the spilled object in the spilled object event can be obtained, thereby improving the positioning accuracy of spilled objects on the highway. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for detecting spilled objects on a highway provided by the present invention; Figure 2 A schematic diagram of the structure of an embodiment of the fiber grating array sensing detection system provided by the present invention; Figure 3 A schematic diagram of the structure of an embodiment of the fiber grating vibration sensor provided by the present invention installed along a road; Figure 4 A schematic diagram of the structure of an embodiment of a waterfall diagram of vibration signals of all measuring points provided by the present invention; Figure 5 For the present invention Figure 1 A schematic flow chart of an embodiment of step S102; Figure 6 A schematic diagram of the structure of an embodiment of a filtered spilled object signal provided by the present invention; Figure 7 A schematic diagram of the structure of an embodiment of the comparison of the smoothed signal, the residual signal and the signal absolute value provided by the present invention; Figure 8 A schematic diagram of the structure of an embodiment of the results of smoothing all the measurement point signals provided by the present invention; Fig. 9 A schematic diagram of the structure of an embodiment of all peak points of all measuring points provided by the present invention; Fig.10 A schematic diagram of the structure of an embodiment of the characteristic line fitting of the scattered object provided by the present invention; Fig.11 A schematic diagram of the structure of an embodiment of a device for detecting spilled objects on a highway provided by the present invention; Fig.12 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0019] like Figure 1 As shown, a specific embodiment of the present invention discloses a method for detecting spilled objects on a high-speed road surface, comprising: S101, acquiring vibration signals of all measuring points on the highway road surface based on a grating array vibration sensor; S102, extracting peak values ​​according to the vibration signal, determining the peak point corresponding to each measuring point, and judging and fitting all the peak points to obtain a set of vibration characteristic lines; S103, when the set of vibration characteristic lines meets a preset condition, determining that there is a spilled object event at the current moment; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; S104. Obtaining a landing point position of the spilled object in the spilled object event according to the multiple initial characteristic lines.

[0020] In a specific embodiment of the present invention, it can be applied to a fiber grating array sensing detection system, wherein the fiber grating array sensing detection system is as follows: Figure 2 As shown, it may include a fiber grating array vibration sensor, a vibration sensor demodulation instrument, a big data storage center, a data analysis and processing system, and road surface spillage identification, and the data analysis and processing system may process the data detected by the fiber grating array sensor through the process of vibration sensing data, filtering processing, peak point extraction, characteristic line calculation, and spillage judgment; as shown Figure 3 As shown in the figure, the fiber Bragg grating vibration sensor is laid under the asphalt layer along the highway. A fiber Bragg grating vibration sensing cable is laid in each lane and is laid in the middle of each lane. The fiber Bragg grating vibration sensing cable of each lane is connected to the fiber optic splicing box and connected to the grating array vibration demodulation instrument through the transmission cable. The data collected by the demodulation instrument is processed by the data analysis and processing system to obtain the location and time of the spilled object. The fiber Bragg grating vibration sensor can collect the vibration signals of all measuring points in real time. The waterfall diagram of the vibration signals of all measuring points is shown in the figure below. Figure 4 As shown in the figure, the vehicle trajectory signal and the dovetail signal generated by the spilled object falling on the lane are shown. Peak extraction can be performed based on the vibration signal to determine the peak point corresponding to each measuring point, and all peak points can be judged and fitted to obtain a set of vibration characteristic lines; then the characteristic lines in the vibration characteristic line set can be judged, and when the vibration characteristic line set meets the preset conditions, it can be determined that there is a spilled object event at the current moment; wherein the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; then based on the multiple initial characteristic lines, the location of the spilled object landing point in the spilled object event is obtained.

[0021] Compared with the prior art, the present embodiment provides a method for acquiring vibration signals of all measuring points on the highway surface based on a grating array vibration sensor, and then real-time monitoring of the vibration signals of all measuring points can be performed, thereby improving the timeliness of detection of spilled objects on the highway; further, peak value extraction can be performed based on the vibration signal to determine the peak point corresponding to each measuring point, and all peak points can be judged and fitted to obtain a set of vibration characteristic lines; when the set of vibration characteristic lines meets the preset conditions, it is determined that there is a spillage event at the current moment; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spillage; based on the multiple initial characteristic lines, the landing point of the spillage event can be obtained, thereby improving the positioning accuracy of spilled objects on the highway.

[0022] In some embodiments of the present invention, Figure 5 As shown, step S102 includes: S501, preprocessing the vibration signal to obtain a preprocessed vibration signal of each measuring point; S502, performing absolute value calculation on the preprocessed vibration signal to obtain an absolute value signal of each measuring point; S503, extracting the absolute value signal based on the filter to obtain a low-frequency vibration signal of each measuring point; S504: extract the peak value of the low-frequency vibration signal based on the peak point recognition method to obtain the peak point of each measuring point.

[0023] In a specific embodiment of the present invention, the vibration signal can be preprocessed, and the preprocessing can be high-pass filtering. Specifically, high-pass filtering can be applied to all measuring points, and the filter cutoff frequency can be 150Hz. After filtering, the vehicle signal is greatly weakened, while the spilled object signal is well preserved. Figure 6 As shown, the pre-processed vibration signal of each measuring point can be obtained. Then, the absolute value of the pre-processed vibration signal of each measuring point can be calculated, so that the absolute value signal of each measuring point can be obtained. Then, the absolute value signal can be smoothed by using a Savitzky-Golay filter to obtain the low-frequency vibration signal of each measuring point, where the filter window size can be 41 and the order can be 25. The specific values ​​can be set according to the actual situation. The Savitzkey-Golay filter can be described as shown in formula (1): (1) In the formula, Indicates k The original value of the sampling points; Indicates k The smoothed value of the sampling points is the low-frequency vibration signal. w is the semi-smoothing window width, his the smoothing coefficient. Figure 7 As shown, Figure 7 The absolute value of the single-point signal is obtained and then smoothed using the Savitzky-Golay filter, as well as the residual signal. Figure 8 As shown, Figure 8 The smoothed results of all the measuring point signals are given, and the clear signal of the spilled objects can be seen in the figure. Then, the peak point of each measuring point can be obtained by extracting the peak value of the low-frequency vibration signal based on the peak point recognition method.

[0024] In some embodiments of the present invention, the peak point identification method may include: Calculate the local extreme value of the low-frequency vibration signal of any measuring point to obtain the corresponding extreme value; the extreme value includes the initial peak point and the valley point; Calculate the initial peak point and valley point to obtain the ratio; Determine whether the ratio is greater than a preset threshold; If so, the initial peak point is determined to be the peak point of the corresponding measurement point.

[0025] In a specific embodiment of the present invention, the local extreme value of the low-frequency vibration signal of any measuring point is calculated to obtain the corresponding extreme value; wherein the extreme value may include an initial peak point and a valley point. Specifically, the initial peak point may be obtained by formula (2), and formula (2) is as follows: (2) In the formula, f(t) Indicates time t The vibration signal, is a small value; then determine the initial peak point Maximum search range on both sides w1 and w2 , which can be described as formula (3) and formula (4): (3) (4) In the formula, is a constant; the initial peak point t p Centered on both sides w 1 and w Search for valley points within 2 t v1 and t v2 , which can be described as formula (5) and formula (6): (5) (6) Then the initial peak point and valley point can be calculated to get the ratio, and then the ratio can be judged to determine whether it is greater than the preset threshold. c , where the preset threshold can be 2.5, as shown in formula (7): (7) If yes, the initial peak point can be determined is the peak point of the corresponding measuring point .After the peak extraction of all measuring points is completed, the peak points corresponding to all measuring points can be obtained.

[0026] In some embodiments of the present invention, step S102 includes: Determine the range of the wave packet where the peak point of each measuring point is located; Determine whether the ranges of wave packets where the peak points of adjacent measuring points are located overlap in time; If so, connect the peak points of adjacent measuring points to obtain the characteristic lines generated by the same vibration at each measuring point; Perform piecewise linear fitting on the characteristic lines to obtain a set of vibration characteristic lines.

[0027] In some embodiments of the present invention, determining the range of the wave packet where the peak point of each measuring point is located includes: Taking the peak of the peak point as the center, intercept the signal segment whose value is greater than the multiple of the preset multiple value on both sides of the peak, and determine the signal segment as the range of the wave packet where the peak point is located, such as Fig. 9 As shown, Fig. 9 The coordinate system above shows all the peak points of all the measurement points. Fig. 9 The following diagram shows the wave packet range.

[0028] In a specific embodiment of the present invention, after obtaining the peak point corresponding to each measuring point, a preset multiple value n can be selected with the peak of the peak point as the center, and signal segments with values ​​greater than n times the signal mean can be intercepted on both sides of the peak as the range of the wave packet where the peak point of each measuring point is located.

[0029] Furthermore, all the peaks of the peak point of each measuring point are traversed to determine the wave packet of the peak point of each measuring point, and the wave packet range of a certain peak is compared with the range of the wave packet of the peak of the adjacent measuring point. If the two ranges overlap in time, the two peaks are marked as peaks caused by the same vibration. All the peaks of the measuring points are traversed and marked, and then the peaks with the same mark are connected to obtain the characteristic lines generated by the same vibration at each measuring point.

[0030] In some embodiments of the present invention, piecewise linear fitting is performed on the characteristic lines to obtain a set of vibration characteristic lines, including: According to the characteristic line, the minimum time point is determined as the vertex; The characteristic line is divided into two parts, left and right, with the vertex as the boundary, and linear fitting is performed on each part to obtain the characteristic line of the spilled object, and a set of vibration characteristic lines is obtained based on all the characteristic lines of the spilled object.

[0031] In a specific embodiment of the present invention, the least square method can be used to perform piecewise linear fitting on the characteristic line. First, find the time minimum point of the characteristic line (i.e., the vertex), and divide the characteristic line into two parts, left and right, with the vertex as the boundary, and perform linear fitting on each part. The piecewise linear fitting can be shown as formula (7): (8) In the formula, and For straight line The coefficient of x 0 ，y 0) is the node of the piecewise straight line, w is the weight coefficient of the fitting point. Fig.10 It is the characteristic line of the spill obtained by piecewise linear fitting, and the characteristic line is dovetail-shaped.

[0032] Furthermore, if the characteristic line obtained by segmented fitting is a "swallowtail type", it is judged that the characteristic line has the characteristics of spilled objects. If there are two or more "swallowtail type" initial characteristic lines within a certain time window and a certain measuring point range, a spilled object event occurs at the current moment.

[0033] In some embodiments of the present invention, step S104 includes: Compare multiple initial feature lines to obtain a target feature line with the minimum vertex; Based on the centroid positioning, the coordinate position of the point on the target characteristic line and the corresponding amplitude value are calculated to obtain the landing point position of the spilled object in the spilled object event.

[0034] In a specific embodiment of the present invention, all the initial characteristic lines of the "swallowtail" of the spilled object event are compared to find the target characteristic line with the smallest vertex, and the coordinate position of the point on the target characteristic line and the corresponding amplitude value are used to determine the position of the spilled object by centroid positioning. , the centroid formula (9) is as follows: (9) In the formula, x i represents the coordinates of points on the feature line, f ( x i ) represents the peak value at that position, N Indicates the number of points on the feature line.

[0035] The embodiment of the present invention is based on the detection of spilled objects on the high-speed road surface using fiber grating array sensors, wherein the vibration-sensing optical cable has the advantages of convenient installation and construction, low cost, high temperature resistance, and resistance to electromagnetic interference. The present invention solves the problem that the current traditional highway spilled object identification method is difficult to achieve full-domain timely automatic alarm. By real-time acquisition of road vibration sensor signals and using digital signal processing methods to extract the signal characteristics of the spilled objects for identification, the location of the spilled objects and the time when the spilling event occurred can be located in real time. The method has the advantages of fast response speed, full-domain road detection, no influence of light vision, and little interference from the environment.

[0036] In order to better implement the high-speed road spilled object detection method in the embodiment of the present invention, based on the high-speed road spilled object detection method, the embodiment of the present invention also provides a high-speed road spilled object detection device, such as Fig.11 As shown, the high-speed road spilled object detection device 1100 includes: A signal acquisition module 1101 is used to acquire vibration signals of all measuring points on the highway road surface based on a grating array vibration sensor; The peak extraction module 1102 is used to extract the peak value according to the vibration signal, determine the peak point corresponding to each measuring point, and judge and fit all the peak points to obtain a set of vibration characteristic lines; The characteristic line judgment module 1103 is used to determine that there is a spilled object event at the current moment when the vibration characteristic line set meets the preset condition; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; The position determination module 1104 is used to obtain the landing point position of the scattered object in the scattered object event according to multiple initial characteristic lines.

[0037] The highway road spilled object detection device 1100 provided in the above embodiment can implement the technical solution described in the above embodiment of the highway road spilled object detection method. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the highway road spilled object detection method, which will not be repeated here.

[0038] like Fig.12 As shown, the present invention also provides an electronic device 1200. The electronic device 1200 includes a processor 1201, a memory 1202 and a display 1203. Fig.12 Only some components of the electronic device 1200 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0039] In some embodiments, the memory 1202 may be an internal storage unit of the electronic device 1200, such as a hard disk or memory of the electronic device 1200. In other embodiments, the memory 1202 may also be an external storage device of the electronic device 1200, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1200.

[0040] Furthermore, the memory 1202 may include both an internal storage unit of the electronic device 1200 and an external storage device. The memory 1202 is used to store application software installed in the electronic device 1200 and various data.

[0041] In some embodiments, the processor 1201 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 1202, such as the high-speed road spill detection method of the present invention.

[0042] In some embodiments, the display 1203 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1203 is used to display information of the electronic device 1200 and to display a visual user interface. The components 1201-1203 of the electronic device 1200 communicate with each other via a system bus.

[0043] In some embodiments of the present invention, when the processor 1201 executes the high-speed road spill detection program in the memory 1202, the following steps may be implemented: Acquire vibration signals of all measuring points on the highway road surface based on grating array vibration sensors; Peak value extraction is performed based on the vibration signal to determine the peak point corresponding to each measuring point, and all peak points are judged and fitted to obtain a set of vibration characteristic lines; When the set of vibration characteristic lines meets the preset conditions, it is determined that there is a spill event at the current moment; the preset conditions are that there are multiple initial characteristic lines that meet the characteristics of the spill; According to the multiple initial characteristic lines, the landing point position of the scattered object in the scattered object event is obtained.

[0044] It should be understood that: when the processor 1201 executes the high-speed road spilled object detection program in the memory 1202, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0045] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 1200 mentioned, and the electronic device 1200 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1200 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0046] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the high-speed road spilled object detection method provided by the above-mentioned method embodiments can be implemented.

[0047] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0048] The above is a detailed introduction to the high-speed road spilled object detection method, device, electronic device and medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting spilled objects on a highway, characterized in that: include: Acquire vibration signals of all measuring points on the highway road surface based on grating array vibration sensors; Extracting the peak value of the vibration signal, determining the peak point corresponding to each measuring point, and judging and fitting all the peak points to obtain a set of vibration characteristic lines; When the vibration characteristic line set meets a preset condition, it is determined that there is a spilled object event at the current moment; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; According to the multiple initial characteristic lines, the landing point position of the scattered object in the scattered object event is obtained.

2. The method for detecting spilled objects on a highway according to claim 1, characterized in that: The step of extracting the peak value according to the vibration signal and determining the peak point corresponding to each measuring point includes: Preprocessing the vibration signal to obtain a preprocessed vibration signal of each measuring point; Performing absolute value calculation on the preprocessed vibration signal to obtain an absolute value signal of each measuring point; Performing signal extraction on the absolute value signal based on a filter to obtain a low-frequency vibration signal of each measuring point; The peak value of the low-frequency vibration signal is extracted based on the peak point identification method to obtain the peak point of each measuring point.

3. The method for detecting spilled objects on a highway according to claim 2, characterized in that: The peak point identification method is used to extract the peak value of the low-frequency vibration signal to obtain the peak point of each measuring point, including: Calculate the local extreme value of the low-frequency vibration signal at any measuring point to obtain the corresponding extreme value; the extreme value includes an initial peak point and a valley point; Calculating the initial peak point and the valley point to obtain a ratio; Determining whether the ratio is greater than a preset threshold; If so, the initial peak point is determined to be the peak point of the corresponding measurement point.

4. The method for detecting spilled objects on a highway according to claim 1, characterized in that: The above-mentioned judging and fitting all the peak points to obtain a set of vibration characteristic lines includes: Determine the range of the wave packet where the peak point of each measuring point is located; Determine whether the ranges of wave packets where the peak points of adjacent measuring points are located overlap in time; If yes, the peak points of the adjacent measuring points are connected to obtain the characteristic lines generated by the same vibration at each measuring point; The characteristic lines are subjected to piecewise linear fitting to obtain a set of vibration characteristic lines.

5. The method for detecting spilled objects on a highway according to claim 4, characterized in that: Determining the range of the wave packet where the peak point of each measuring point is located includes: Taking the peak of the peak point as the center, intercept signal segments whose values ​​are greater than the signal mean of multiples of a preset multiple value on both sides of the peak, and determine the signal segments as the range of the wave packet where the peak point is located.

6. The method for detecting spilled objects on a highway according to claim 4, characterized in that: The step of performing piecewise linear fitting on the characteristic lines to obtain a set of vibration characteristic lines includes: According to the characteristic line, determining the minimum time point as the vertex; The characteristic line is divided into left and right parts with the vertex as the boundary, and linear fitting is performed on each part to obtain a sprinkler characteristic line, and a vibration characteristic line set is obtained based on all sprinkler characteristic lines.

7. The method for detecting spilled objects on a highway according to claim 1, characterized in that: The step of obtaining the landing point of the scattered object in the scattered object event according to the plurality of initial characteristic lines comprises: Comparing the multiple initial feature lines to obtain a target feature line with a minimum vertex; The coordinate positions of points on the target characteristic line and the corresponding amplitude values ​​are calculated based on the centroid positioning to obtain the landing point position of the scattered object in the scattered object event.

8. A device for detecting spilled objects on a high-speed road, characterized in that: include: A signal acquisition module, used to acquire vibration signals of all measuring points on the highway road surface based on a grating array vibration sensor; A peak extraction module is used to extract the peak value according to the vibration signal, determine the peak point corresponding to each measuring point, and judge and fit all the peak points to obtain a set of vibration characteristic lines; A characteristic line judgment module is used to determine that there is a spilled object event at the current moment when the vibration characteristic line set meets a preset condition; the preset condition is that there are multiple initial characteristic lines that meet the characteristics of the spilled object; The position determination module is used to obtain the landing point position of the scattered object in the scattered object event according to multiple initial characteristic lines.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the method for detecting spilled objects on a high-speed road surface are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for detecting spilled objects on a high-speed road surface as described in any one of claims 1-7 are implemented.

Images