Detection method and detection system for abnormal objects on road surface

Abstract

The present application provides a method for detecting abnormal objects on a road surface, a detection system, and a computer-readable storage medium, wherein the method for detecting abnormal objects on a road surface comprises: obtaining image data of a road surface to be detected; detecting the image data to determine whether a target object exists on the road surface to be detected; if a target object exists on the road surface to be detected, tracking the target object; determining whether the degree of change of the target object during the tracking process meets preset requirements; if the preset requirements are met, determining that the target object is an abnormal object on the road surface. The technical solution provided by the present application is conducive to improving the accuracy of detecting abnormal objects on the road surface and reducing the false detection rate.

Description

Technical Field

[0001] The present application relates to the technical field of road surface detection, and in particular to a method and system for detecting abnormal objects on a road surface, and a computer-readable storage medium. Background Art

[0002] Engineering vehicles (such as muck trucks, mixer trucks, gravel trucks, and oil trucks) on the road are prone to leaking or spilling muck, mud, gravel, or oil, which not only pollutes the road surface, but also increases road safety hazards. In related technologies, real-time road monitoring images are generally obtained, and image recognition technology is used to determine whether there are abnormal objects on the road surface that pollute the road or increase road safety hazards, but the false detection rate is usually high. Summary of the invention

[0003] The present application provides a method, a detection system and a computer-readable storage medium for detecting abnormal objects on a road surface, which improve the accuracy of detecting abnormal objects on a road surface and reduce the false detection rate.

[0004] The first technical solution adopted in the present application is: to provide a method for detecting abnormal objects on a road surface, including: obtaining image data of a road surface to be tested; detecting the image data to determine whether a target object exists on the road surface to be tested; if a target object exists on the road surface to be tested, tracking the target object; determining whether the degree of change of the target object during the tracking process meets preset requirements; if the preset requirements are met, determining that the target object is an abnormal object on the road surface.

[0005] Optionally, determining whether the degree of change of the target object during the tracking process meets preset requirements includes: determining the similarity of a first tracking image and a second tracking image, the first tracking image and the second tracking image being image regions corresponding to the target object in different images collected during the tracking process, respectively; and in response to the similarity being greater than or equal to a preset threshold, determining that the degree of change of the target object during the tracking process meets the preset requirements.

[0006] Optionally, determining the similarity between the first tracking image and the second tracking image includes: extracting apparent features of the first tracking image and the second tracking image; calculating initial similarity between the first tracking image and the second tracking image using the apparent features of the first tracking image and the second tracking image; and correcting the initial similarity using a time correlation function to obtain the similarity between the first tracking image and the second tracking image.

[0007] Optionally, the image data is detected to determine whether there is a target object on the road surface to be tested, including: using a first detection model to detect the image data to determine whether there is a target object on the road surface to be tested, wherein the first detection model is obtained by training multiple target objects and multiple interference objects.

[0008] Optionally, the image data is detected to determine whether there is a target object on the road to be tested, including: if there is a target object on the road to be tested, obtaining the category information and position information of the target object from the image data; after obtaining the image data of the road to be tested, it also includes: detecting the image data to determine whether there is a construction vehicle passing by the road to be tested; if there is a construction vehicle passing by, obtaining the category information and position information of the construction vehicle from the image data.

[0009] Optionally, if a construction vehicle passes by, if preset requirements are met, after determining that the target object is an abnormal road surface object, the method further includes: determining whether there is an engineering vehicle associated with the target object based on the location information of the target object and the location information of the engineering vehicle, and the engineering vehicle associated with the target object last passed through the area where the target object is located within a preset time period before the target object was detected; if so, determining whether the type of the engineering vehicle associated with the target object matches the type of the target object; if they match, determining that the target object is an abnormal road surface object.

[0010] Optionally, judging whether there is a construction vehicle associated with the target object based on the position information of the target object and the position information of the construction vehicle includes: determining the motion trajectory of the construction vehicle using the position information of the construction vehicle, and determining whether there is a construction vehicle associated with the target object based on the motion trajectory of the construction vehicle and the position information of the target object.

[0011] Optionally, if no engineering vehicle passes by, then if preset requirements are met, after determining that the target object is an abnormal object on the road surface, the method further includes: identifying the target object as a false detection.

[0012] The second technical solution adopted in the present application is: to provide a detection system for abnormal road objects, including: an image acquisition unit and an image processing unit, wherein the image acquisition unit is configured to obtain image data of the road surface to be tested; the image processing unit is electrically connected to the image acquisition unit, and is configured to detect the image data to determine whether there is a target object on the road surface to be tested; when there is a target object on the road surface to be tested, the target object is tracked; if the degree of change of the target object during the tracking process meets the preset requirements, the target object is identified as an abnormal road surface object.

[0013] The third technical solution adopted in the present application is: providing a computer-readable storage medium on which computer instructions are stored, and when the computer instructions are executed by a processor, any of the above detection methods is implemented.

[0014] Beneficial effects of the present application: The inventor has found through long-term research that common interferences to abnormal objects on the road surface include water stains, water splashes, light and shadows, water surface reflections, etc. These interferences are prone to cause false detections, and these interferences are prone to change over time. The present application tracks the target object after detecting it, and determines whether the target object is an abnormal object on the road surface according to the degree of change of the target object. This can effectively eliminate the interference of interferences such as water stains, water splashes, light and shadows, water surface reflections, etc., thereby reducing the false detection rate and improving the accuracy of abnormal object detection on the road surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 It is a flow chart of an embodiment of a method for detecting abnormal objects on a road surface of the present application;

[0017] Figure 2 yes Figure 1 A schematic diagram of a flow chart of an embodiment of S104;

[0018] Figure 3 yes Figure 2 A schematic diagram of a flow chart of an embodiment of S1041;

[0019] Figure 4 yes Figure 1 A schematic diagram of another embodiment of S104;

[0020] Figure 5 It is a flow chart of another embodiment of the method for detecting abnormal objects on a road surface of the present application;

[0021] Figure 6 It is a structural schematic diagram of an embodiment of a detection system for abnormal road objects of the present application;

[0022] Figure 7 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings and examples. It is particularly noted that the following examples are only used to illustrate the present application, but are not intended to limit the scope of the present application. Similarly, the following examples are only some embodiments of the present application rather than all embodiments, and all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0024] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] It should be noted that the terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. 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 device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0026] See also Figure 1 , Figure 1 It is a flow chart of an embodiment of a method for detecting abnormal objects on a road surface of the present application.

[0027] Specifically, the method for detecting abnormal objects on the road surface includes the following steps:

[0028] S101: Acquire image data of a road surface to be tested.

[0029] Specifically, a plurality of cameras are set up on the road, and a preset distance may be set between two adjacent cameras, so that image data of the road surface to be tested can be obtained in real time through the cameras set up on the road. The image data may include multiple images.

[0030] S102: Detect the image data to determine whether there is a target object on the road surface to be tested.

[0031] In this embodiment, this step may include: using a first detection model to detect the image data to determine whether there is a target object on the road surface to be tested, wherein the first detection model is obtained by training multiple target objects and multiple interference objects.

[0032] For example, the first detection model based on the deep learning framework can be trained by modeling four types of target objects, namely, slag, sand, mud, and oil stains, and four types of interference objects, namely, water stains, water splashes, light and shadows, and water surface reflections. Since the first detection model is obtained by training on a variety of target objects and a variety of interference objects, the first detection model has a deep classification function, which is conducive to reducing the interference of interference objects on the detection results and reducing the false detection rate to a certain extent.

[0033] In this embodiment, the step may further include: if there is a target object on the road to be tested, obtaining the category information and position information of the target object from the image data. For example, the category of the target object may be slag, gravel, mud or oil stain, etc., and the position of the target object may be the specific position of the target object on the road to be tested.

[0034] S103: If there is a target object on the road surface to be tested, the target object is tracked.

[0035] To further reduce the false detection rate, after the first detection model detects the existence of the target object on the road to be tested, the target object can be tracked to obtain the degree of change of the target object during the tracking process. Since road abnormal objects such as slag, mud, gravel, or oil stains are relatively stable and have a small degree of change during the tracking process, if the target object changes greatly during the tracking process, it means that the target object is an interference object such as water stains, water splashes, light and shadow, water surface reflection, etc., and is not a real road abnormal object; if the target object changes little during the tracking process, it means that the target object is a real road abnormal object.

[0036] S104: Determine whether the change degree of the target object during the tracking process meets the preset requirements.

[0037] See also Figure 2 , Figure 2 yes Figure 1 S104 is a flow chart of an embodiment. In this embodiment, this step may include:

[0038] S1041: Determine the similarity between a first tracking image and a second tracking image, where the first tracking image and the second tracking image are image regions corresponding to the target object in different images collected during the tracking process.

[0039] For example, the first tracking image may be captured from an image in which the target object is detected, and the second tracking image may be captured from another image acquired in real time after the target object is detected, and a preset time period may be provided between the two images. The specific length of the preset time period is not limited in this application, and those skilled in the art may select it according to actual needs.

[0040] In some embodiments, the first tracking image may also be captured from an image acquired in real time after the target object is detected. The present application does not impose any restrictions on this. The first tracking image and the second tracking image may be taken from two images acquired at intervals of a preset time period. Technical personnel in this field may make a choice based on actual needs.

[0041] Specifically, determining the similarity between the first tracking image and the second tracking image may include: Figure 3 The following steps are shown in :

[0042] S10411: Extracting appearance features of the first tracking image and the second tracking image.

[0043] Specifically, the deep learning neural network can be used to extract the appearance features of the first tracking image and the second tracking image. The appearance features can refer to color features, texture features, or both color features and texture features. This application does not limit this, and those skilled in the art can choose according to actual needs.

[0044] S10412: Calculate initial similarity between the first tracking image and the second tracking image using the appearance features of the first tracking image and the second tracking image.

[0045] For example, the initial similarity between the second tracking image and the first tracking image may be calculated using a histogram similarity algorithm, a cosine similarity algorithm, or a Bhattacharyya coefficient. This application does not limit the specific algorithm, and those skilled in the art may select it according to actual needs.

[0046] S10413: Correct the initial similarity using the time correlation function to obtain the similarity between the first tracking image and the second tracking image.

[0047] Since there is a preset time period between the first tracking image and the second tracking image, the passage of time may cause changes in the environment (for example, the passage of time may cause changes in light), thereby affecting the similarity between the first tracking image and the second tracking image. This embodiment introduces a time correlation function to correct the initial similarity calculated in S10422, which is conducive to eliminating the influence of the passage of time on the similarity between the first tracking image and the second tracking image.

[0048] S1042: In response to the similarity being greater than or equal to a preset threshold, determining that a degree of change of the target object during the tracking process meets a preset requirement.

[0049] The present application does not limit the specific value of the preset threshold, and those skilled in the art can select it according to actual needs. Specifically, if the similarity between the second tracking image and the first tracking image is greater than or equal to the preset threshold, the change degree of the target object during the tracking process is small, and the preset requirement is met; if the similarity between the second tracking image and the first tracking image is less than the preset threshold, the change degree of the target object during the tracking process is large, the tracking is interrupted, and the preset requirement is not met.

[0050] exist Figure 2 In the embodiment shown, two tracking images are obtained by one tracking to determine whether the degree of change of the target object meets the preset requirements. Figure 4 As shown, Figure 4 yes Figure 1 In the schematic diagram of another embodiment of S104, N+1 tracking images can be obtained through N tracking times to determine whether the change degree of the target object meets the preset requirements. If the similarity between the N+1 tracking image and the first tracking image is greater than or equal to a preset threshold, it means that the target object is relatively stable and is a real abnormal road surface object. If the similarity between the N+1 tracking image and the first tracking image is less than the preset threshold, it means that the tracking of the target object is interrupted, the target object is unstable, and is not a real abnormal road surface object. The value of N can be any positive integer, which is not limited by this application, and can be selected by those skilled in the art according to actual needs. For example, N can be 2, that is, three tracking images are obtained through two trackings to determine whether the change degree of the target object meets the preset requirements; or N can be 3, four tracking images are obtained through three trackings to determine whether the change degree of the target object meets the preset requirements; or N can be 4, five tracking images are obtained through four trackings to determine whether the change degree of the target object meets the preset requirements; of course, it can also be more times of tracking, which is not limited by this application, and can be selected by those skilled in the art according to actual needs.

[0051] S105: If the preset requirements are met, the target object is determined to be an abnormal road surface object.

[0052] Specifically, if the degree of change of the target object during the tracking process meets the preset requirements, it means that the degree of change of the target object is small and it is a real abnormal object on the road surface; if the degree of change of the target object during the tracking process does not meet the preset requirements, it means that the degree of change of the target object is large, the tracking is interrupted, and the target object is a false detection and is not a real abnormal object on the road surface.

[0053] The present application tracks the target object after detecting it, and determines whether the target object is an abnormal object on the road surface based on the degree of change of the target object. It can effectively eliminate interference from interference objects such as water stains, water splashes, light and shadows, and water surface reflections, thereby reducing the false detection rate and improving the accuracy of abnormal object detection on the road surface.

[0054] In some embodiments, it is also possible to further eliminate false detections and improve the accuracy of abnormal road object detection by determining whether an engineering vehicle has passed the target object area within a preset time period before the target object is detected. Figure 5 , Figure 5 This is a flow chart of another embodiment of the method for detecting abnormal objects on a road surface of the present application, which may further include the following steps after S101:

[0055] S106: Detect the image data to determine whether there is an engineering vehicle passing by the road to be tested.

[0056] In this embodiment, this step may include: using a second detection model to detect the image data to determine whether an engineering vehicle has passed by the road to be tested, wherein the second detection model is obtained by training a variety of engineering vehicles.

[0057] For example, the second detection model based on the deep learning framework can be trained by modeling five types of engineering vehicles, namely, muck trucks (corresponding to muck), gravel trucks (corresponding to gravel), mixer trucks (corresponding to mud), oil tankers (corresponding to oil stains), and water trucks (corresponding to interference objects). Since the second detection model is obtained by training on a variety of engineering vehicles, the second detection model has a deep classification function.

[0058] S107: If a construction vehicle passes by, obtain the type information and location information of the construction vehicle from the image data.

[0059] If a construction vehicle passes by the road to be tested, it means that a construction vehicle may have passed by the target object area within the preset time period before the target object is detected, and the target object may be a real abnormal object on the road. If no construction vehicle passes by the road to be tested, it means that no construction vehicle passes by the target object area within the preset time period before the target object is detected, that is, the target object is a false detection and is not a real abnormal object on the road. For example, the type of construction vehicle can be a muck truck, sand truck, mixer truck, oil tanker, sprinkler truck, etc., and the location of the construction vehicle can be the specific location of the construction vehicle on the road to be tested.

[0060] Please continue reading Figure 5 In this embodiment, if an engineering vehicle passes by the road to be tested, the following steps may be further included after S105:

[0061] S108: Determine whether there is an engineering vehicle associated with the target object according to the location information of the target object and the location information of the engineering vehicle, and the engineering vehicle associated with the target object last passed the area where the target object is located within a preset time period before the target object is detected.

[0062] The specific length of the preset time period is not limited in this application, and those skilled in the art may select it according to actual needs. Specifically, this step may include: determining the motion trajectory of the engineering vehicle using the location information of the engineering vehicle, and determining whether there is an engineering vehicle associated with the target object according to the motion trajectory of the engineering vehicle and the location information of the target object.

[0063] As mentioned above, the image data in S101 includes multiple images. The movement trajectory of the construction vehicle can be obtained by integrating the position information of the construction vehicle in the multiple images. From the movement trajectory of the construction vehicle, it can be determined whether the construction vehicle passes through the area where the target object is located within a preset time period before the target object is detected.

[0064] S109: If yes, determine whether the type of the engineering vehicle associated with the target object matches the type of the target object.

[0065] Some abnormal objects on the road are close to interference objects, and there may still be a probability of false detection after the above steps, such as oil stains and water stains. Therefore, if there is an engineering vehicle associated with the target object, it is possible to further determine whether the category of the engineering vehicle associated with the target object matches the category of the target object, so as to further reduce the false detection rate and improve the accuracy of abnormal object detection on the road.

[0066] S110: If they match, the target object is determined to be an abnormal object on the road surface.

[0067] Specifically, if the category of the engineering vehicle associated with the target object matches the category of the target object, for example, the category of the target object is mud, and the category of the engineering vehicle associated with the target object is a mixer truck, then it means that the target object is a real abnormal object on the road surface. If the category of the engineering vehicle associated with the target object does not match the category of the target object, for example, the category of the target object is oil stains, and the category of the engineering vehicle associated with the target object is a sprinkler truck, then it means that the target object is a false detection and is not a real abnormal object on the road surface.

[0068] In this embodiment, if no engineering vehicle passes by the road to be tested, then after S105 , the following step may further include: identifying the target object as a false detection.

[0069] Specifically, if no engineering vehicle passes by the road to be tested, it means that there must be no abnormal road object on the road to be tested, and the target object is a false detection.

[0070] After the false detection rate is reduced by associating the engineering vehicle with the target object, the remaining detected events are real events of abnormal objects on the road surface. In some embodiments, the relevant information of the abnormal objects on the road surface and the relevant information of the engineering vehicles associated with them can be further sorted to obtain complete event results and issue an alarm.

[0071] See also Figure 6 , Figure 6 It is a structural schematic diagram of an embodiment of a detection system for abnormal road objects of the present application. The detection system 100 for abnormal road objects may include an image acquisition unit 10 and an image processing unit 20. Among them, the image acquisition unit 10 is configured to obtain image data of the road surface to be tested. The image processing unit 20 is electrically connected to the image acquisition unit 10, and is configured to detect the image data memory to determine whether there is a target object on the road surface to be tested; when there is a target object on the road surface to be tested, the area where the target object is located is tracked; if the degree of change of the target object during the tracking process meets the preset requirements, the target object is identified as an abnormal road surface object.

[0072] For example, the image acquisition unit 10 may be a camera installed on the road. The image processing unit 20 may further include a processor and a memory coupled to each other. The memory may store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the above-mentioned method for detecting abnormal objects on the road surface.

[0073] The processor may also be referred to as a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0074] The memory may include random access memory (RAM), read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, CD-ROMs, and the like. The memory may store program data, which may include, for example, a single instruction or many instructions, and may be distributed over several different code segments, distributed between different programs, and distributed across multiple memories. The memory may be coupled to a processor so that the processor can read and write information from / to the memory. Of course, the memory may be integrated into the processor, which is not limited in the present application, and those skilled in the art may select according to actual needs.

[0075] See also Figure 7 , Figure 7 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 200 stores a computer program, and when the computer program is executed, the steps of the method for detecting abnormal objects on the road surface as described above are implemented.

[0076] The technical solution of the present application, in essence, 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, which is stored in a storage device and includes a number of instructions (program data) to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various implementation methods of the present invention. The aforementioned storage device includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and electronic devices such as computers, mobile phones, laptops, tablet computers, cameras, etc. having the above storage media.

[0077] In the several embodiments provided in the present application, it should be understood that the disclosed training method of the semantic segmentation network can be implemented in other ways. For example, the electronic device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. 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. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0078] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0079] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0080] The above descriptions are only some embodiments of the present application, and do not limit the protection scope of the present application. Any equivalent device or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting abnormal objects on a road surface, characterized in that: include: Acquire image data of the road surface to be tested; Detecting the image data to determine whether a target object exists on the road surface to be tested and whether an engineering vehicle passes by the road surface to be tested; If the target object exists on the road surface to be tested, the target object is tracked, and category information and position information of the target object are acquired from the image data; If the engineering vehicle passes by, obtaining the type information and location information of the engineering vehicle from the image data; Determining whether the degree of change of the target object during tracking meets preset requirements; If the preset requirement is met, determining that the target object is an abnormal road surface object; If the engineering vehicle passes by, then if the preset requirement is met, after determining that the target object is an abnormal road surface object, the method further includes: Determine whether there is an engineering vehicle associated with the target object according to the location information of the target object and the location information of the engineering vehicle, and the engineering vehicle associated with the target object has most recently passed through the area where the target object is located within a preset time period before the target object is detected; If so, determining whether the type of the engineering vehicle associated with the target object matches the type of the target object; If they match, it is determined that the target object is an abnormal road surface object.

2. The detection method according to claim 1, characterized in that: The determining whether the change degree of the target object during the tracking process meets the preset requirements includes: Determining a similarity between a first tracking image and a second tracking image, wherein the first tracking image and the second tracking image are image regions corresponding to the target object in different images acquired during the tracking process; In response to the similarity being greater than or equal to a preset threshold, it is determined that a degree of change of the target object during the tracking process meets the preset requirement.

3. The detection method according to claim 2, characterized in that: The determining the similarity between the first tracking image and the second tracking image comprises: extracting appearance features of the first tracking image and the second tracking image; Calculating initial similarity between the first tracking image and the second tracking image using the appearance features of the first tracking image and the second tracking image; The initial similarity is corrected using a time correlation function to obtain the similarity between the first tracking image and the second tracking image.

4. The detection method according to claim 1, characterized in that: The detecting the image data to determine whether there is a target object on the road surface to be tested includes: The image data is detected using a first detection model to determine whether the target object exists on the road surface to be tested, wherein the first detection model is obtained by training a plurality of target objects and a plurality of interference objects.

5. The detection method according to claim 1, characterized in that: The determining whether there is the engineering vehicle associated with the target object according to the position information of the target object and the position information of the engineering vehicle comprises: The motion track of the engineering vehicle is determined by using the position information of the engineering vehicle, and whether the engineering vehicle associated with the target object exists is determined according to the motion track of the engineering vehicle and the position information of the target object.

6. The detection method according to claim 1, characterized in that: If the engineering vehicle does not pass by, then if the preset requirement is met, after determining that the target object is an abnormal road surface object, the method further includes: The target object is identified as a false detection.

7. A detection system for abnormal objects on a road surface, characterized in that: include: An image acquisition unit configured to acquire image data of a road surface to be tested; as well as An image processing unit, electrically connected to the image acquisition unit, configured to detect the image data, determine whether there is a target object on the road surface to be tested, and determine whether an engineering vehicle passes by the road surface to be tested; When the target object exists on the road surface to be tested, tracking the target object and acquiring category information and position information of the target object from the image data; When the engineering vehicle passes by, obtaining the category information and location information of the engineering vehicle from the image data; When the degree of change of the target object during the tracking process meets the preset requirements, the target object is identified as an abnormal road surface object; Wherein, the image processing unit is configured as follows: After the engineering vehicle passes by and meets the preset requirements, and the target object is determined to be an abnormal object on the road surface, it is determined whether there is an engineering vehicle associated with the target object according to the position information of the target object and the position information of the engineering vehicle, and the engineering vehicle associated with the target object has passed the area where the target object is located most recently within a preset time period before the target object is detected; When there is the engineering vehicle associated with the target object, determining whether the type of the engineering vehicle associated with the target object matches the type of the target object; When the type of the engineering vehicle associated with the target object matches the type of the target object, the target object is determined to be an abnormal road surface object.

8. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the detection method according to any one of claims 1 to 6 is implemented.

Images