A method and device for detecting abnormal parts of unmanned vehicles

Abstract

The embodiment of the present application provides a method and device for detecting abnormal parts of unmanned vehicles, which relates to the field of data processing technology. The method is specifically: receiving an abnormal detection instruction for an unmanned vehicle, and in response to the abnormal detection instruction for the unmanned vehicle, triggering an X-ray transmitter to emit X-rays to the part of the vehicle to be tested; based on the X-ray image information generated after the X-ray penetrates the part of the vehicle to be tested, to generate a target X-ray image corresponding to the part of the vehicle to be tested; extracting image features in the target X-ray image and performing image recognition to obtain an image recognition result; based on the image recognition result, when it is determined that there is an abnormal part in the target X-ray image, the abnormal type corresponding to the abnormal part is obtained. The present application can improve the detection accuracy and reliability of abnormal parts of unmanned vehicles, which has become an urgent problem to be solved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device for detecting abnormal parts of an unmanned vehicle. Background Art

[0002] With the rapid development of driverless technology, the safety of driverless vehicles and other transportation vehicles has become the focus of industry attention. Abnormalities in the mechanical parts of driverless vehicles often require regular manual inspections and maintenance, and also require building a shed outside the vehicle or removing auto parts for inspection.

[0003] Therefore, traditional manual inspection methods are not only time-consuming and laborious, but also difficult to achieve comprehensive and detailed inspection of the complex internal structure of unmanned vehicles. In addition, potential problems such as tiny cracks in mechanical parts and material fatigue are often difficult to detect in time with the naked eye or conventional inspection methods. Once these problems are exposed during driving, they will seriously threaten the safety of passengers.

[0004] Furthermore, how to improve the detection accuracy and reliability of component anomalies in unmanned vehicles has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method and device for detecting abnormal components of unmanned vehicles, which can improve the accuracy and reliability of detecting abnormal components of unmanned vehicles, which has become an urgent problem to be solved.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting abnormal components of an unmanned vehicle, comprising:

[0007] receiving an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, triggering an X-ray transmitter to emit X-rays to a part of the vehicle to be tested; the X-ray transmitter is arranged at a preset position of the unmanned vehicle to be tested;

[0008] Based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested, a target X-ray image corresponding to the vehicle part to be tested is generated; the detector is arranged at a position corresponding to the X-ray emitter;

[0009] Extracting image features from the target X-ray image and performing image recognition to obtain an image recognition result;

[0010] When it is determined based on the image recognition result that an abnormal component exists in the target X-ray image, the abnormality type corresponding to the abnormal component is obtained.

[0011] As an optional implementation of the embodiment of the present application, the X-ray image information generated after the X-ray penetrates the vehicle part to be tested to generate a target X-ray image corresponding to the vehicle part to be tested includes:

[0012] The X-ray image information generated after the X-ray penetrates the part of the vehicle to be tested is collected from the detector to generate the target X-ray image; the detector is used to receive the X-ray after penetrating the part of the vehicle to be tested and generate the X-ray image information.

[0013] As an optional implementation of the embodiment of the present application, the collecting of X-ray image information generated after the X-ray penetrates the vehicle part to be tested from the detector to generate the target X-ray image includes:

[0014] collecting, from the detector, X-ray image information generated after the X-ray penetrates the vehicle part to be tested, and generating an initial X-ray image based on the X-ray image information;

[0015] The initial X-ray image is preprocessed to obtain the target X-ray image.

[0016] As an optional implementation of the embodiment of the present application, the extracting image features in the target X-ray image and performing image recognition to obtain an image recognition result includes:

[0017] Extracting image features of the target X-ray image based on a deep learning algorithm;

[0018] The image recognition result is obtained by comparing the image features of the target X-ray image with the historical image features; the historical image features are the image features obtained under normal conditions for each component of the unmanned vehicle.

[0019] As an optional implementation of the embodiment of the present application, before receiving the unmanned vehicle abnormality detection instruction and triggering the X-ray transmitter to emit X-rays to the vehicle part to be detected in response to the unmanned vehicle abnormality detection instruction, the method further includes:

[0020] Periodically detecting whether there are signs of life inside and around the unmanned vehicle;

[0021] If not, the unmanned vehicle abnormality detection instruction is generated.

[0022] As an optional implementation of the embodiment of the present application, the method further includes:

[0023] The X-ray emitters and corresponding detectors are arranged at multiple locations on the unmanned vehicle.

[0024] As an optional implementation of the embodiment of the present application, when it is determined based on the image recognition result that there is an abnormal component in the target X-ray image, after obtaining the abnormal type corresponding to the abnormal component, the method further includes:

[0025] Generate warning information according to the abnormal type corresponding to the abnormal component;

[0026] The warning information is sent to the central control of the unmanned vehicle to inform the user of the unmanned vehicle; the warning information includes abnormal parts of the unmanned vehicle and the degree of abnormality.

[0027] In a second aspect, an embodiment of the present application provides a method and device for detecting abnormal parts of an unmanned vehicle, including:

[0028] A trigger unit, used to receive an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, trigger an X-ray transmitter to emit X-rays to a part of the vehicle to be tested; the X-ray transmitter is arranged at a preset position of the unmanned vehicle to be tested;

[0029] A generating unit, configured to generate a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested; the detector is arranged at a position corresponding to the X-ray emitter;

[0030] An extraction unit, used to extract image features from the target X-ray image and perform image recognition to obtain an image recognition result;

[0031] A determination unit is used to determine, based on the image recognition result, that there is an abnormal component in the target X-ray image, and then obtain the abnormal type corresponding to the abnormal component.

[0032] As an optional implementation of the embodiment of the present application, the generating unit is specifically used to collect X-ray image information generated after the X-ray penetrates the part of the vehicle to be tested from the detector to generate the target X-ray image; the detector is used to receive the X-ray after penetrating the part of the vehicle to be tested, and generate the X-ray image information.

[0033] As an optional implementation of the embodiment of the present application, the generation unit is specifically used to collect X-ray image information generated after the X-rays penetrate the vehicle part to be tested from the detector, generate an initial X-ray image based on the X-ray image information; pre-process the initial X-ray image to obtain the target X-ray image.

[0034] As an optional implementation of an embodiment of the present application, the generation unit is specifically used to extract image features of the target X-ray image based on a deep learning algorithm; compare the image features of the target X-ray image with historical image features to obtain the image recognition result; the historical image features are image features obtained under normal circumstances for each component of the unmanned vehicle.

[0035] As an optional implementation of the embodiment of the present application, the trigger unit is also used to periodically detect whether there are signs of life inside and around the unmanned vehicle; if not, an abnormality detection instruction for the unmanned vehicle is generated.

[0036] As an optional implementation of the embodiment of the present application, the abnormal component detection method device for an unmanned vehicle also includes a setting unit, which is specifically used to set the X-ray emitter and the corresponding detector at multiple positions on the unmanned vehicle.

[0037] As an optional implementation of an embodiment of the present application, the abnormal component detection method device for an unmanned vehicle also includes a sending unit, which is specifically used to generate warning information according to the abnormal type corresponding to the abnormal component; send the warning information to the unmanned vehicle central control to inform the user of the unmanned vehicle; the warning information includes the abnormal component of the unmanned vehicle and the degree of abnormality.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the abnormal component detection method for an unmanned vehicle described in any of the above embodiments when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computing device, the computing device implements the abnormal component detection method for an unmanned vehicle as described in any of the above embodiments.

[0040] The abnormal component detection method for unmanned vehicles provided in the embodiment of the present application is specifically as follows: receiving an abnormal component detection instruction for an unmanned vehicle, and in response to the abnormal component detection instruction for the unmanned vehicle, triggering an X-ray transmitter to emit X-rays to the vehicle part to be tested; based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested, a target X-ray image corresponding to the vehicle part to be tested is generated; image features in the target X-ray image are extracted and image recognition is performed to obtain an image recognition result; based on the image recognition result, when it is determined that there is an abnormal component in the target X-ray image, the abnormal type corresponding to the abnormal component is obtained. The present application is provided with an X-ray transmitter and a corresponding detector in the unmanned vehicle, and then transmits X-rays to the vehicle part to be tested through the X-ray transmitter, and then generates a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-rays penetrate the vehicle part to be tested, and then obtains an image recognition result corresponding to the target X-ray image, and then when it is determined through the image recognition result that there are abnormal components in the target X-ray image, the abnormal type corresponding to the abnormal component is obtained in time; therefore, the present application can detect the status of key components in real time, and discover and warn of potential faults in time. Compared with traditional manual detection, the present application can greatly shorten the detection time, thereby improving maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 One of the step flow charts of the abnormal component detection method for an unmanned vehicle provided in an embodiment of the present application;

[0044] Figure 2 A second flowchart of the abnormal component detection method for an unmanned vehicle provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of an unmanned vehicle in a method for detecting abnormal components of an unmanned vehicle provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the system architecture of an abnormal component detection method for an unmanned vehicle provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a method and device for detecting abnormal parts of an unmanned vehicle provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0051] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. In addition, in the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more.

[0052] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0053] The present application embodiment provides a method for detecting abnormal components of an unmanned vehicle, referring to Figure 1 As shown, the abnormal component detection method for an unmanned vehicle includes the following steps S101-S104:

[0054] S101, receiving an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, triggering an X-ray transmitter to emit X-rays to a part of the vehicle to be detected.

[0055] Specifically, the X-ray emitter emits X-rays to the components of the unmanned vehicle, which utilizes the high energy penetration of X-rays, which can penetrate various materials, such as metals, plastics, ceramics, etc., and form a perspective image on the detector. This perspective image can display the internal structure of the object and detect defects inside the object, such as cracks, pores, inclusions, etc., without destroying the object itself. Furthermore, in an embodiment of the present application, an X-ray emitter is used to emit X-rays to the vehicle components of the unmanned vehicle to be tested. When the X-rays penetrate the vehicle components and irradiate the detector, a corresponding X-ray image is generated, and the X-ray image can be used to determine whether the vehicle components are abnormal.

[0056] Furthermore, the X-ray emitter is equipped with an X-ray tube for generating X-rays. There are cathodes and anodes inside the X-ray tube. When high voltage current passes through the cathode, electrons are released. These electrons collide with the anode material during the acceleration process, thereby generating X-rays. Different anode materials and voltage conditions will generate X-rays of different energies, which can be adjusted and controlled as needed.

[0057] In the embodiment of the present application, the X-ray emitter may be a low-dose, high-penetration X-ray source to ensure detection effect while reducing radiation risk.

[0058] S102: Generate a target X-ray image corresponding to the vehicle part to be tested based on X-ray image information generated after the X-ray penetrates the vehicle part to be tested.

[0059] Specifically, after the X-rays penetrate the component to be tested, the corresponding detector will be used to collect the X-rays that penetrate the component to be tested to obtain the X-ray image information; therefore, in the present application, the specific implementation method of generating the target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-rays penetrate the vehicle part to be tested can refer to the following steps:

[0060] X-ray image information generated after the X-rays penetrate the vehicle part to be tested is collected from the detector to generate the target X-ray image.

[0061] The detector is used to receive the X-rays after penetrating the vehicle part to be tested and generate the X-ray image information.

[0062] In some embodiments, after X-rays penetrate the component to be tested, they will fall on the corresponding detector to form an image. Specifically, the detector is usually composed of a pixel array composed of many pixels. The X-ray intensities received at different pixel positions are different, and the number of photoelectrons and charge signal intensities generated are also different. For example, in X-ray imaging, after X-rays penetrate an object, the area with high density of the object absorbs more X-rays, and the X-ray intensity received by the corresponding detector pixels is low, and the photoelectrons generated are small and the signal intensity is weak; while the area with low density of the object is the opposite. These signals of different intensities are converted into digital signals after analog-to-digital conversion (ADC), and each digital signal corresponds to the X-ray intensity information of a pixel position. By arranging these digital signals according to the pixel position by computer software, these digital signals can be understood as the X-ray image information, and the X-ray image can be reconstructed according to the X-ray image information, that is, the target X-ray image corresponding to the part to be tested is generated.

[0063] It should be noted that the detector can be a modern digital detector, which can convert X-ray images into digital signals, and process and analyze them through a computer, so as to achieve high-resolution and high-precision detection. In the present application, the detector adopts a digital detector made of a high-resolution CMOS sensor, or a digital detector made of a high-resolution CCD sensor, wherein high-resolution CMOS and CCD detectors have their own advantages in different application scenarios. If there are high requirements for cost, speed, power consumption, integration, etc., or if a large amount of image data needs to be processed quickly, a high-resolution CMOS detector is a better choice; if you pursue extreme image quality, high sensitivity and large dynamic range, and are not particularly sensitive to cost and power consumption, then a high-resolution CCD detector may be more suitable.

[0064] Specifically, the X-ray emitter and the corresponding detector are set at multiple positions of the unmanned vehicle to be tested, so as to more comprehensively identify and detect the components at multiple positions of the unmanned vehicle to be tested; it should be noted that the abnormal component detection method for unmanned vehicles provided in the present application can not only be used to detect the components of unmanned vehicles, but also can be used for other unmanned vehicles and aircraft, and the present application does not impose any specific restrictions.

[0065] S103, extracting image features from the target X-ray image and performing image recognition to obtain an image recognition result.

[0066] In some embodiments, after emitting X-rays to the component to be tested and generating a target X-ray image of the component to be tested, it is necessary to analyze and identify the target X-ray image, and determine the current state of the component to be tested from the target X-ray image. Specifically, the target X-ray image can be sent to a corresponding image processor, and a deep learning algorithm module will be integrated in the graphics processor to perform feature extraction on the target X-ray image to further realize image recognition, automatically identify abnormal conditions such as cracks, corrosion, material fatigue, etc. of mechanical parts, and then generate the image recognition result.

[0067] S104. When it is determined based on the image recognition result that an abnormal component exists in the target X-ray image, an abnormality type corresponding to the abnormal component is obtained.

[0068] Exemplarily, the image recognition result may be that a slight crack appears on the left front wheel hub of the vehicle to be tested; then, based on the image recognition result, it is determined that the abnormal component of the current vehicle to be tested is the left front wheel hub, and the abnormal type is a crack. Then, after obtaining the abnormal type corresponding to the abnormal component, it is necessary to immediately inform the relevant personnel of the current abnormal situation. Therefore, the abnormal component detection method for unmanned vehicles provided in the embodiment of the present application also includes the following steps 1 and 2:

[0069] Step 1: Generate warning information according to the abnormal type corresponding to the abnormal component.

[0070] Exemplarily, the warning information generated according to the abnormal type corresponding to the abnormal component may be: a slight crack appears in the left front wheel hub of the current vehicle, and immediate repair is required.

[0071] Step 2: Send the warning information to the central control of the unmanned vehicle to inform the user of the unmanned vehicle.

[0072] The warning information includes abnormal parts of the unmanned vehicle and the degree of abnormality.

[0073] After the warning information is generated, it is immediately sent to the central control of the unmanned vehicle to ensure that the central control personnel can receive the warning information and take corresponding maintenance measures in time to avoid vehicle accidents.

[0074] The abnormal component detection method for unmanned vehicles provided in the embodiment of the present application is specifically as follows: receiving an abnormal component detection instruction for an unmanned vehicle, and in response to the abnormal component detection instruction for the unmanned vehicle, triggering an X-ray transmitter to emit X-rays to the vehicle part to be tested; based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested, a target X-ray image corresponding to the vehicle part to be tested is generated; image features in the target X-ray image are extracted and image recognition is performed to obtain an image recognition result; based on the image recognition result, when it is determined that there is an abnormal component in the target X-ray image, the abnormal type corresponding to the abnormal component is obtained. The present application is provided with an X-ray transmitter and a corresponding detector in the unmanned vehicle, and then transmits X-rays to the vehicle part to be tested through the X-ray transmitter, and then generates a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-rays penetrate the vehicle part to be tested, and then obtains an image recognition result corresponding to the target X-ray image, and then when it is determined through the image recognition result that there are abnormal components in the target X-ray image, the abnormal type corresponding to the abnormal component is obtained in time; therefore, the present application can detect the status of key components in real time, and discover and warn of potential faults in time. Compared with traditional manual detection, the present application can greatly shorten the detection time, thereby improving maintenance efficiency.

[0075] As an extension and refinement of the above embodiment, refer to Figure 2 As shown, the abnormal component detection method for unmanned vehicles provided in the present application also includes the following steps S201-S205:

[0076] S201, receiving an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, triggering an X-ray transmitter to emit X-rays to a part of the vehicle to be detected.

[0077] Wherein, the X-ray emitter is arranged at a preset position of the unmanned vehicle to be tested.

[0078] In some embodiments, before receiving the unmanned vehicle abnormality detection instruction, it is necessary to generate the unmanned vehicle abnormality detection instruction. In the embodiment of the present application, the specific steps of generating the unmanned vehicle abnormality detection instruction include the following steps 1 and 2:

[0079] Step 1: Periodically detect whether there are any signs of life inside and around the unmanned vehicle.

[0080] During the X-ray detection process, the unmanned vehicle can periodically detect whether there are people inside and around the vehicle, so as to generate the unmanned vehicle abnormality detection instruction in a safe environment without people, so as to trigger the detection process. This can prevent the radiation effect of X-rays on people.

[0081] Step 2: If not, generate the unmanned vehicle abnormality detection instruction.

[0082] In some embodiments, when it is determined that there is no one inside or outside the unmanned vehicle, an abnormal detection instruction for the unmanned vehicle is generated to avoid triggering the X-ray transmitter to emit X-rays in the presence of people, which may cause damage to the human body.

[0083] It should be noted that in order to further reduce the radiation damage caused by X-rays to the surrounding environment and operators, a radiation protection layer can be set inside and outside the unmanned vehicle to be tested to ensure that no radiation damage is caused to the surrounding environment and operators during the detection process.

[0084] S202: Collect X-ray image information generated after the X-ray penetrates the vehicle part to be tested from the detector to generate the target X-ray image.

[0085] The detector is used to receive the X-rays after penetrating the vehicle part to be tested and generate the X-ray image information.

[0086] In some embodiments, the detailed steps of the above S202 (collecting X-ray image information generated after the X-ray penetrates the vehicle part to be tested from the detector to generate the target X-ray image) refer to the following S2021 and S2022:

[0087] S2021. Collect from the detector the X-ray image information generated after the X-ray penetrates the vehicle part to be tested, and generate an initial X-ray image based on the X-ray image information.

[0088] In some embodiments, the target X-ray image in step S202 is obtained after preprocessing the initial X-ray image, because when generating the X-ray image based on the X-ray image information, some errors may occur, or the generated X-ray image may be poor due to interference factors, affecting the accuracy of subsequent image recognition; in order to improve the accuracy of subsequent image recognition, the initial X-ray image obtained based on the X-ray image information will be preprocessed in this application to improve the quality of the X-ray image.

[0089] S2022. Preprocess the initial X-ray image to obtain the target X-ray image.

[0090] In some embodiments, the method for preprocessing the initial X-ray image may include: grayscale correction, noise removal, and geometric correction methods, wherein grayscale correction can effectively stretch or compress the grayscale range, improve the contrast of the image, make the grayscale distribution of the image more uniform, and enhance the contrast of the image, especially for those X-ray images with a relatively concentrated grayscale distribution.

[0091] In X-ray images, common noises include quantum noise, electronic noise and scattering noise. Electronic noise is generated by the electronic components of the detector, such as thermal noise and readout noise of the detector. Scattering noise is generated when X-rays are scattered inside the object and then received by the detector. It will blur the image and reduce the contrast and resolution of the image; therefore, it is necessary to remove noise to improve the accuracy of X-ray images.

[0092] X-ray images may be geometrically deformed due to factors such as geometric distortion of the imaging device, incorrect placement of the object, or inaccurate relative position of the detector and the X-ray source. This geometric deformation will affect the accurate judgment of the shape, size and position of the object in the image; the X-ray image can then be corrected through geometric correction.

[0093] S203. Extracting image features of the target X-ray image based on a deep learning algorithm.

[0094] In some embodiments, the extraction of image features of the target X-ray image based on a deep learning algorithm can be implemented through some deep learning models, for example, a Convolutional Neural Network (CNN) model, which is a classic deep learning model architecture for processing image data, and can be used to extract features of X-ray images. It automatically learns local and global features in images through components such as convolutional layers, pooling layers, and fully connected layers. In addition to the traditional CNN architecture, some CNN-based variants or fusion architectures can also be considered. For example, DenseNet establishes dense connections so that each layer in the network can directly receive feature information from all previous layers, further enhancing feature propagation and reuse, which may help to extract X-ray image features more comprehensively.

[0095] S204: Compare the image features of the target X-ray image with the historical image features to obtain the image recognition result.

[0096] The historical image features are image features obtained under normal circumstances for each component of the unmanned vehicle.

[0097] In an embodiment of the present application, after obtaining the image features of the target X-ray image, it is possible to compare them with historical image features, that is, compare them with normal image features, and then determine whether the image features of the current target X-ray image are abnormal, and further determine which vehicle component the abnormal image features belong to, and what type of abnormality the component has. Specifically, the abnormality types may include pores, slag inclusions, cracks, etc.

[0098] It should be noted that the image features of the target X-ray image can also be input into a classifier for defect identification. For machine learning methods, classifiers such as support vector machines and decision trees can be used to classify images into defective or non-defective categories based on feature vectors, and further determine the defect type. For deep learning methods, the trained CNN model itself can be used as a classifier to directly output defect categories and location information. In the classification process, the differences between the features are used to distinguish different types of defects, such as pores, slag inclusions, and cracks, as well as to distinguish defects of different degrees (such as small cracks and larger cracks).

[0099] S205. When it is determined based on the image recognition result that an abnormal component exists in the target X-ray image, an abnormality type corresponding to the abnormal component is obtained.

[0100] In an embodiment of the present application, the image features of the target X-ray image are extracted based on a deep learning algorithm, and then the image features of the target X-ray image are compared with the historical image features to obtain the image recognition result; thereby, tiny defects can be identified through the deep learning algorithm, thereby improving the accuracy and reliability of detection and extending the service life of the vehicle.

[0101] As an extension and refinement of the above-mentioned embodiment, the embodiment of the present application also provides a framework diagram of an abnormal component detection system for an unmanned vehicle corresponding to an abnormal component detection method for an unmanned vehicle. In the framework 300, it includes: an X-ray emitter 31, a detector 32 and an image processor 33; wherein the X-ray emitter 31 is used to emit X-rays to the vehicle part to be tested after receiving an abnormal detection instruction for an unmanned vehicle; the detector 32 is used to collect the X-ray image information generated after the X-ray penetrates the vehicle part to be tested; the image processor 33 is used to generate a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested; and extract the image features in the target X-ray image and perform image recognition to obtain an image recognition result. Then, based on the image recognition result, when it is determined that there is an abnormal component in the target X-ray image, the abnormal type corresponding to the abnormal component is obtained.

[0102] For example, refer to Figure 4 As shown, taking unmanned vehicles as an example, Figure 4 A schematic diagram showing the locations of multiple X-ray emitters and detectors on an unmanned vehicle. Figure 4Eight X-ray emitters are integrated and placed in the corners and the middle of the vehicle. The placement and number of X-ray emitters can also be set according to the actual situation of the vehicle. An X-ray detector and an image processor are built in from the rear of the engine to the front of the cab to collect and process X-ray images. Another X-ray detector and an image processor are built in between the trunk and the backup seat to collect and process X-ray images. The X-ray detector can be a narrow-sided rectangular parallelepiped. X-ray images can be collected on both the front and back sides. The X-ray detector and the image processor can be integrated together or separately.

[0103] For different vehicle models, or other means of transportation such as airplanes or ships, manufacturers can flexibly choose the number of X-ray emitters and their corresponding number of X-ray detectors, and select appropriate placement locations based on actual architecture and application requirements.

[0104] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present application also provides an abnormal component detection method device for unmanned vehicles. This embodiment corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that an abnormal component detection method device for unmanned vehicles in this embodiment can correspond to the implementation of all the contents in the aforementioned method embodiment.

[0105] The present application provides a method and device for detecting abnormal parts of an unmanned vehicle. Figure 4 FIG. 1 is a schematic diagram of the structure of the abnormal component detection method device for unmanned vehicles, as shown in FIG. Figure 5 As shown, the abnormal component detection method and device 500 for an unmanned vehicle includes:

[0106] The trigger unit 501 is used to receive an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, trigger an X-ray transmitter to emit X-rays to a part of the vehicle to be tested; the X-ray transmitter is set at a preset position of the unmanned vehicle to be tested;

[0107] A generating unit 502 is used to generate a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested; the detector is set at a position corresponding to the X-ray emitter;

[0108] An extraction unit 503 is used to extract image features from the target X-ray image and perform image recognition to obtain an image recognition result;

[0109] The determination unit 504, when determining that there is an abnormal component in the target X-ray image based on the image recognition result, obtains the abnormality type corresponding to the abnormal component.

[0110] As an optional implementation of the embodiment of the present application, the generation unit 502 is specifically used to collect X-ray image information generated after the X-ray penetrates the part of the vehicle to be tested from the detector to generate the target X-ray image; the detector is used to receive the X-ray after penetrating the part of the vehicle to be tested, and generate the X-ray image information.

[0111] As an optional implementation of the embodiment of the present application, the generation unit 502 is specifically used to collect X-ray image information generated after the X-rays penetrate the vehicle part to be tested from the detector, generate an initial X-ray image based on the X-ray image information; pre-process the initial X-ray image to obtain the target X-ray image.

[0112] As an optional implementation of an embodiment of the present application, the generation unit 502 is specifically used to extract image features of the target X-ray image based on a deep learning algorithm; compare the image features of the target X-ray image with historical image features to obtain the image recognition result; the historical image features are image features obtained under normal circumstances for each component of the unmanned vehicle.

[0113] As an optional implementation of the embodiment of the present application, the trigger unit 501 is also used to periodically detect whether there are signs of life inside and around the unmanned vehicle; if not, an abnormality detection instruction for the unmanned vehicle is generated.

[0114] As an optional implementation of the embodiment of the present application, the abnormal component detection method device for an unmanned vehicle also includes a setting unit, which is specifically used to set the X-ray emitter and the corresponding detector at multiple positions on the unmanned vehicle.

[0115] As an optional implementation of an embodiment of the present application, the abnormal component detection method device for an unmanned vehicle also includes a sending unit, which is specifically used to generate warning information according to the abnormal type corresponding to the abnormal component; send the warning information to the unmanned vehicle central control to inform the user of the unmanned vehicle; the warning information includes the abnormal component of the unmanned vehicle and the degree of abnormality.

[0116] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as Figure 6As shown, the electronic device provided in this embodiment includes: a memory 601 and a processor 602, wherein the memory 601 is used to store a computer program; and the processor 602 is used to execute the audio data processing method provided in the above embodiment when executing the computer program.

[0117] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computing device implements the abnormal component detection method for unmanned vehicles provided in the above embodiment.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media that include computer-usable program code.

[0119] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0120] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0121] Computer readable media include permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting abnormal parts of an unmanned vehicle, characterized in that: include: receiving an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, triggering an X-ray transmitter to emit X-rays to a part of the vehicle to be detected; Based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested, a target X-ray image corresponding to the vehicle part to be tested is generated; Extracting image features from the target X-ray image and performing image recognition to obtain an image recognition result; When it is determined based on the image recognition result that an abnormal component exists in the target X-ray image, the abnormality type corresponding to the abnormal component is obtained.

2. The method according to claim 1, characterized in that The method of generating a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested comprises: The X-ray image information generated after the X-ray penetrates the part of the vehicle to be tested is collected from the detector to generate the target X-ray image; the detector is used to receive the X-ray after penetrating the part of the vehicle to be tested and generate the X-ray image information.

3. The method according to claim 2, characterized in that The step of collecting X-ray image information generated after the X-ray penetrates the vehicle part to be tested from the detector to generate the target X-ray image includes: collecting, from the detector, X-ray image information generated after the X-ray penetrates the vehicle part to be tested, and generating an initial X-ray image based on the X-ray image information; The initial X-ray image is preprocessed to obtain the target X-ray image.

4. The method according to claim 1, characterized in that The extracting image features from the target X-ray image and performing image recognition to obtain an image recognition result includes: Extracting image features of the target X-ray image based on a deep learning algorithm; The image recognition result is obtained by comparing the image features of the target X-ray image with the historical image features; the historical image features are the image features obtained under normal conditions for each component of the unmanned vehicle.

5. The method according to claim 1, characterized in that Before receiving the unmanned vehicle abnormality detection instruction and triggering the X-ray transmitter to emit X-rays to the vehicle part to be detected in response to the unmanned vehicle abnormality detection instruction, the method further includes: Periodically detecting whether there are signs of life inside and around the unmanned vehicle; If not, the unmanned vehicle abnormality detection instruction is generated.

6. The method according to claim 1, characterized in that The method further comprises: The X-ray emitters and corresponding detectors are arranged at multiple locations on the unmanned vehicle.

7. The method according to claim 1, characterized in that When it is determined based on the image recognition result that there is an abnormal component in the target X-ray image, after obtaining the abnormal type corresponding to the abnormal component, the method further includes: Generate warning information according to the abnormal type corresponding to the abnormal component; The warning information is sent to the central control of the unmanned vehicle to inform the user of the unmanned vehicle; the warning information includes abnormal parts of the unmanned vehicle and the degree of abnormality.

8. A method and device for detecting abnormal parts of an unmanned vehicle, characterized in that: include: A trigger unit, configured to receive an unmanned vehicle abnormality detection instruction, and in response to the unmanned vehicle abnormality detection instruction, trigger an X-ray transmitter to emit X-rays to a part of the vehicle to be detected; A generating unit, configured to generate a target X-ray image corresponding to the vehicle part to be tested based on the X-ray image information generated after the X-ray penetrates the vehicle part to be tested; An extraction unit, used to extract image features from the target X-ray image and perform image recognition to obtain an image recognition result; A determination unit is used to determine, based on the image recognition result, that there is an abnormal component in the target X-ray image, and then obtain the abnormal type corresponding to the abnormal component.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the abnormal component detection method for an unmanned vehicle as described in any one of claims 1 to 7 when executing the computer program.

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 computing device, the computing device implements the abnormal component detection method for an unmanned vehicle as described in any one of claims 1-7.

Images