WO2021042906A1

WO2021042906A1 - Vibration detection method and related apparatus

Info

Publication number: WO2021042906A1
Application number: PCT/CN2020/104816
Authority: WO
Inventors: 高风波
Original assignee: 深圳市豪视智能科技有限公司
Priority date: 2019-04-26
Filing date: 2020-07-27
Publication date: 2021-03-11
Also published as: CN110617973A; CN110617973B

Abstract

A vibration detection method, applied to an electronic device (101). The electronic device (101) comprises a camera apparatus. The method comprises: an electronic device (101) displaying a vibration detection entrance by means of a main interface of a vibration detection device (S201); acquiring vibration detection type information for the vibration detection entrance inputted by a user, and generating vibration operation prompt information according to the vibration detection type information, wherein the vibration operation prompt information is used to instruct the user to perform a pre-configured operation on a vehicle under detection (S202); acquiring a vibration video of a vehicle exhaust manifold, and performing motion amplification processing on the vibration video according to a pre-configured policy so as to acquire a target video (S203); acquiring vibration data of the vehicle exhaust manifold according to the target video (S204); determining, according to the target video and/or the vibration data, whether a vibration status of the vehicle exhaust manifold is abnormal (S205); and if so, outputting pre-configured alarm information (S206). A vibration detection apparatus, an electronic device, and a computer-readable storage medium are also disclosed. The invention facilitates vibration detection performed on the vehicle exhaust manifold.

Description

振动检测方法及相关装置Vibration detection method and related device

技术领域Technical field

本申请涉及振动检测技术领域，具体涉及一种振动检测方法及相关装置。This application relates to the technical field of vibration detection, and in particular to a vibration detection method and related devices.

背景技术Background technique

车辆中的排气歧管在发动机工作的状态下往往会产生各种各样的振动，其中，存在一些振动反应部件的异常运动状况，为了维护车辆中的排气歧管，针对排气歧管振动检测不可忽视，现有振动检测技术，通常采用加速计设备，但是加速度计需要长的准备和安装时间，在测试时，需要和被测排气歧管直接接触，进而影响排气歧管部件的振动响应，并且仅能测试很有限的离散点。Exhaust manifolds in vehicles often produce various vibrations when the engine is working. Among them, there are some abnormal motions of vibration response components. In order to maintain the exhaust manifolds in the vehicle, the exhaust manifold Vibration detection cannot be ignored. Existing vibration detection technology usually uses accelerometer equipment, but accelerometers require long preparation and installation time. During testing, they need to be in direct contact with the exhaust manifold under test, which affects the exhaust manifold components. Vibration response, and only a limited number of discrete points can be tested.

发明内容Summary of the invention

本申请实施例提供了一种振动检测方法及相关装置，以期振动检测的稳定性。The embodiments of the present application provide a vibration detection method and related devices, in order to ensure the stability of vibration detection.

第一方面，本申请实施例提供了一种振动检测方法，其特征在于，应用于电子设备，所述电子设备连接摄像装置，所述方法包括：In the first aspect, an embodiment of the present application provides a vibration detection method, which is characterized in that it is applied to an electronic device, and the electronic device is connected to a camera device, and the method includes:

通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管；Displaying a vibration detection entrance through the main interface of the vibration detection device, the vibration detection entrance provides a vibration detection type option, and the vibration detection type option includes an automobile exhaust manifold;

获取用户输入的振动检测类型信息，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作；Acquiring vibration detection type information input by the user, and generating vibration operation prompt information according to the vibration detection type information, where the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested;

通过振动装置获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；Obtain the vibration video of the exhaust manifold of the automobile through a vibration device, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, where the motion amplification effect refers to the exhaust manifold of the automobile The target video has been enlarged and processed;

根据所述目标视频获取所述汽车排气歧管的振动数据；Acquiring vibration data of the exhaust manifold of the automobile according to the target video;

根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常；Determine whether the vibration state of the exhaust manifold of the automobile is abnormal according to the target video and/or the vibration data;

若是，则输出预设报警信息。If yes, output preset alarm information.

第二方面，本申请实施例提供了一种振动检测装置，其特征在于，应用于电子设备，所述电子设备连接摄像装置，所述电子设备包括处理单元和通信单元，其中，In a second aspect, an embodiment of the present application provides a vibration detection device, which is characterized in that it is applied to an electronic device, the electronic device is connected to a camera device, and the electronic device includes a processing unit and a communication unit, wherein:

所述处理单元，用于通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管；以及用于获取用户输入的振动检测类型信息，通过所述通信单元传递所述信息信号，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作；以及用于通过振动装置获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；以及用于根据所述目标视频获取所述汽车排气歧管的振动数据；以及用于根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常；若是，则输出预设报警信息。The processing unit is configured to display a vibration detection entrance through the main interface of the vibration detection device, the vibration detection entrance provides a vibration detection type option, the vibration detection type option includes an automobile exhaust manifold; and is used to obtain user input The vibration detection type information, the information signal is transmitted through the communication unit, and vibration operation prompt information is generated according to the vibration detection type information, the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested; and It is used to obtain the vibration video of the automobile exhaust manifold through a vibration device, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect. The motion amplification effect refers to the vehicle exhaust The manifold is amplified in the target video; and used to obtain the vibration data of the automobile exhaust manifold according to the target video; and used to determine according to the target video and/or the vibration data Whether the vibration state of the automobile exhaust manifold is abnormal; if so, output a preset alarm message.

第三方面，本申请实施例提供了一种电子设备，包括处理器、存储器、通信接口，以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行本申请实施例第一方面任一方法中的步骤的指令。In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured by The processor executes, and the program includes instructions for executing the steps in any method in the first aspect of the embodiments of the present application.

第四方面，本申请实施例提供了一种计算机可读存储介质，其中，上述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，上述计算机程序使得计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute In one aspect, part or all of the steps described in any method.

第五方面，本申请实施例提供了一种计算机程序产品，其中，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。In a fifth aspect, the embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute as implemented in this application. For example, part or all of the steps described in any method of the first aspect. The computer program product may be a software installation package.

可以看出，本申请实施例中，电子设备首先通过振动检测设备主界面显示振动检测入口，振动检测入口提供振动检测类型选项，振动检测类型选项包括汽车排气歧管，接着，获取用户输入的振动检测类型信息，并根据振动检测类型信息生成振动操作提示信息，振动操作提示信息用于指示用户对待测车辆进行预设操作，之后，获取汽车排气歧管的振动视频，根据预设策略对振动视频进行处理，得到具有运动放大效果的目标视频，运动放大效果是指汽车排气歧管在目标视频中是经过放大处理的，然后，根据目标视频获取汽车排气歧管的振动数据，而后，根据目标视频和/或振动数据确定汽车排气歧管的振动状态是否异常，若是，则输出预设报警信息。可见，本申请实施例通过处理汽车排气歧管的振动视频，得到汽车排气歧管的振动信息，确定待测汽车排气歧管的振动状态，提高电子设备对振动检测的便捷性。It can be seen that in the embodiment of the present application, the electronic device first displays the vibration detection entrance through the main interface of the vibration detection device, and the vibration detection entrance provides vibration detection type options. The vibration detection type options include automobile exhaust manifolds, and then obtain the user input Vibration detection type information, and generate vibration operation prompt information based on the vibration detection type information. The vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested. After that, obtain the vibration video of the automobile exhaust manifold and perform the control according to the preset strategy. The vibration video is processed to obtain a target video with a motion amplification effect. The motion amplification effect means that the car exhaust manifold is amplified in the target video. Then, the vibration data of the car exhaust manifold is obtained according to the target video, and then , According to the target video and/or vibration data, determine whether the vibration state of the automobile exhaust manifold is abnormal, and if so, output a preset alarm message. It can be seen that the embodiment of the application obtains the vibration information of the exhaust manifold of the automobile by processing the vibration video of the exhaust manifold of the automobile, determines the vibration state of the exhaust manifold of the automobile to be tested, and improves the convenience of electronic equipment for vibration detection.

附图说明Description of the drawings

为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

图1是本申请实施例提供的一种振动检测的***架构示意图；FIG. 1 is a schematic diagram of a system architecture for vibration detection according to an embodiment of the present application;

图2A是本申请实施例提供的一种振动检测方法的流程示意图；2A is a schematic flowchart of a vibration detection method provided by an embodiment of the present application;

图2B为本申请实施例提供的一种振动检测入口的界面示意图；2B is a schematic diagram of an interface of a vibration detection portal provided by an embodiment of the application;

图2C为本申请实施例提供的一种汽车排气歧管分区的示意图；2C is a schematic diagram of an automobile exhaust manifold partition provided by an embodiment of the application;

图3是本申请实施例提供的一种电子设备的结构示意图；FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

图4是本申请实施例提供的一种振动检测装置的功能单元组成框图。Fig. 4 is a block diagram of functional units of a vibration detection device provided by an embodiment of the present application.

具体实施方式detailed description

为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。In order to enable those skilled in the art to better understand the solutions of the application, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

下面对本申请实施例进行详细介绍。The following describes the embodiments of the present application in detail.

排气歧管振动检测技术是指能够实现检测排气歧管的的技术。电子设备在设置振动检测装置后，通过振动检测装置获取被测排气歧管的振动视频，并对振动视频进行处理分析，以确定被测排气歧管的振动状态是否异常。示例性的，如图1所示，振动检测***中，电子设备101为具备排气歧管振动检测功能的设备，摄像装置102为视频录取装置，电子设备101与摄像装置102建立控制连接后，用户通过电子设备101向摄像装置102发送相关指令来获取车辆103发生运动的区域的振动视频。Exhaust manifold vibration detection technology refers to a technology that can detect exhaust manifolds. After the electronic equipment is equipped with a vibration detection device, it obtains the vibration video of the tested exhaust manifold through the vibration detection device, and processes and analyzes the vibration video to determine whether the vibration state of the tested exhaust manifold is abnormal. Exemplarily, as shown in FIG. 1, in the vibration detection system, the electronic device 101 is a device with the exhaust manifold vibration detection function, and the camera device 102 is a video recording device. After the electronic device 101 and the camera device 102 establish a control connection, The user sends related instructions to the camera 102 through the electronic device 101 to obtain a vibration video of the area where the vehicle 103 is moving.

本申请实施例所涉及到的电子设备可以是具备振动检测功能的电子设备，该电子设备可以包括各种具有振动检测功能的计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的电子设备(terminaldevice)等等。The electronic device involved in the embodiments of the present application may be an electronic device with a vibration detection function. The electronic device may include various computing devices with a vibration detection function or other processing devices connected to a wireless modem, as well as various forms of electronic equipment. Equipment (terminaldevice) and so on.

为了维护车辆中的排气歧管，针对排气歧管振动检测不可忽视，现有振动检测技术，通常采用加速计设备，但是加速度计需要长的准备和安装时间，在测试时，需要和被测排气歧管直接接触，进而影响排气歧管部件的振动响应，并且仅能测试很有限的离散点。In order to maintain the exhaust manifold in the vehicle, the vibration detection of the exhaust manifold cannot be ignored. The existing vibration detection technology usually uses accelerometer equipment, but the accelerometer requires a long preparation and installation time. The direct contact of the exhaust manifold will affect the vibration response of the exhaust manifold components, and only a limited number of discrete points can be tested.

基于上述问题，本申请实施例提出一种振动检测方法，以期提升车辆中排气歧管振动检测的便捷性。下面结合附图对本申请实施例进行详细介绍。Based on the foregoing problems, embodiments of the present application propose a vibration detection method, in order to improve the convenience of vibration detection of the exhaust manifold in a vehicle. The embodiments of the present application will be described in detail below in conjunction with the drawings.

请参阅图2A，图2A是本申请实施例提供了一种振动检测方法的流程示意图，应用于电子设备，如图2A所示，本振动检测方法包括：Please refer to FIG. 2A. FIG. 2A is a schematic flowchart of a vibration detection method provided by an embodiment of the present application, which is applied to an electronic device. As shown in FIG. 2A, the vibration detection method includes:

S201，电子设备通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管。S201: The electronic device displays a vibration detection portal through the main interface of the vibration detection device, the vibration detection portal provides a vibration detection type option, and the vibration detection type option includes an automobile exhaust manifold.

其中，所述振动检测类型选项可以包括振动检测区域选项以及振动检测区域选项对应的“开始振动检测”操作，振动检测区域可以是车辆的排气歧管、轮胎、悬架、发动机，不作具体限定。Wherein, the vibration detection type options may include the vibration detection area option and the "start vibration detection" operation corresponding to the vibration detection area option. The vibration detection area may be the exhaust manifold, tires, suspension, and engine of the vehicle, and is not specifically limited. .

举例来说，如图2B所示，图2B为本申请实施例提供的一种振动检测入口的界面示意图，包括排气歧管、轮胎、悬架、发动机，在用户界面为用户提供振动检测区域选项以及振动检测区域选项对应的“开始振动检测”虚拟按钮，当用户选择排气歧管对应的“开始振动检测”后，电子设备会针对排气歧管进行振动检测。For example, as shown in FIG. 2B, FIG. 2B is a schematic diagram of an interface of a vibration detection entrance provided by an embodiment of the application, including exhaust manifolds, tires, suspensions, and engines. The user interface provides a vibration detection area for the user. The "Start Vibration Detection" virtual button corresponding to the option and the vibration detection area option, when the user selects the "Start Vibration Detection" corresponding to the exhaust manifold, the electronic device will perform vibration detection for the exhaust manifold.

可见，本实施例中，电子设备能够为用户提供振动检测的人机交互界面，通过界面提供给用户点击相应的振动检测类型选项，提升电子设备振动检测的智能性。It can be seen that, in this embodiment, the electronic device can provide the user with a human-computer interaction interface for vibration detection, and the user can click the corresponding vibration detection type option through the interface, thereby improving the intelligence of the vibration detection of the electronic device.

S202，所述电子设备获取用户输入的振动检测类型信息，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作。S202: The electronic device obtains the vibration detection type information input by the user, and generates vibration operation prompt information according to the vibration detection type information, where the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested.

其中，所述预设操作用于使汽车的排气歧管处于工作振动状态。所述预设操作可以将车辆吊起，开启发动机，将摄像装置安放于合适的位置以准备拍摄振动视频，所述预设操作也可以是对车辆进行空挡踩油门操作，将摄像装置安放于合适的位置以准备拍摄振动视频。Wherein, the preset operation is used to make the exhaust manifold of the automobile work and vibrate. The preset operation can hoist the vehicle, turn on the engine, and place the camera device in a suitable position to prepare to shoot the vibration video. The preset operation can also be the operation of stepping on the accelerator pedal in neutral gear and placing the camera device in a suitable position. Position to prepare for shooting vibration video.

可见，电子设备能够提示用户对车辆进行预设操作，以使得汽车排气歧管处于工作振动状态，提升振动检测的便捷性。It can be seen that the electronic device can prompt the user to perform preset operations on the vehicle, so that the exhaust manifold of the vehicle is in a working vibration state, which improves the convenience of vibration detection.

S203，所述电子设备通过振动装置获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的。S203: The electronic device obtains the vibration video of the exhaust manifold of the automobile through a vibration device, and processes the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, where the motion amplification effect refers to all The automobile exhaust manifold is enlarged in the target video.

所述电子设备根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频的实现方式可以是：所述电子设备对所述振动视频进行分帧，得到序列帧；所述电子设备转换所述序列帧的颜色空间，得到所述序列帧的亮度信息；所述电子设备对所述亮度信息进行快速傅氏变换FFT，得到所述序列帧的相位信息；所述电子设备根据所述相位信息对所述序列帧进行运动放大处理得到放大后的序列帧，并将所述放大后的序列帧合成目标视频。The electronic device processes the vibration video according to a preset strategy to obtain a target video with a motion amplification effect. The implementation manner may be: the electronic device divides the vibration video into frames to obtain sequence frames; The device converts the color space of the sequence frame to obtain the brightness information of the sequence frame; the electronic device performs fast Fourier transform FFT on the brightness information to obtain the phase information of the sequence frame; The phase information performs motion amplification processing on the sequence frame to obtain an amplified sequence frame, and synthesizes the amplified sequence frame into a target video.

其中，所述电子设备转换所述序列帧的颜色空间，得到所述序列帧的亮度信息的实现方式可以是：转换所述序列帧的RGB颜色空间到YIQ颜色空间；根据所述序列帧YIQ颜色空间得到所诉序列帧的亮度信息；所述RGB颜色空间和YIQ颜色空间的转换关系为：Y＝0.299*R+0.587*G+0.114*B；I＝0.596*R–0.275*G–0.321*B；Q＝0.212*R-0.523*G+0.311*B。Wherein, the electronic device converts the color space of the sequence frame to obtain the brightness information of the sequence frame may be realized by: converting the RGB color space of the sequence frame to the YIQ color space; according to the YIQ color space of the sequence frame Space to obtain the brightness information of the sequence frame in question; the conversion relationship between the RGB color space and the YIQ color space is: Y=0.299*R+0.587*G+0.114*B; I=0.596*R–0.275*G–0.321* B; Q=0.212*R-0.523*G+0.311*B.

其中，所述电子设备根据所述相位信息对所述序列帧进行运动放大处理得到放大后的序列帧，并将所述放大后的序列帧合成目标视频可以是：所述电子设备识别所述序列帧中所述目标部件的多个特征点；所述电子设备分别对所述多个特征点的振动轨迹进行匹配、聚类、光流场插值，得到所述多个特征点对应的不同的动作层；所述电子设备根据所述动作层合成所述目标视频。Wherein, the electronic device performs motion amplification processing on the sequence frame according to the phase information to obtain an amplified sequence frame, and synthesizing the amplified sequence frame into a target video may be: the electronic device recognizes the sequence Multiple feature points of the target component in the frame; the electronic device respectively performs matching, clustering, and optical flow field interpolation on the vibration trajectories of the multiple feature points to obtain different actions corresponding to the multiple feature points Layer; the electronic device synthesizes the target video according to the action layer.

其中，所述电子设备根据所述相位信息对所述序列帧进行运动放大处理得到放大后的序列帧，并将所述放大后的序列帧合成目标视频的实现方式可以是：将所述FFT变换后的Y通道图像进行复数可操纵金子塔空域分解得到第一图像；对所述第一图像进行时域带通滤波、放大时域带通滤波、复数可操纵金字塔重建，得到放大后的Y通道图像；根据所述放大后的Y通道图像合成目标视频。Wherein, the electronic device performs motion amplification processing on the sequence frame according to the phase information to obtain the amplified sequence frame, and the implementation manner of synthesizing the amplified sequence frame into the target video may be: transforming the FFT The latter Y channel image is subjected to spatial decomposition of the complex steerable gold tower to obtain the first image; the first image is subjected to time domain band pass filtering, amplified time domain band pass filtering, and complex steerable pyramid reconstruction to obtain the amplified Y channel Image; synthesize the target video according to the enlarged Y-channel image.

可见，本示例中，电子设备能够通过颜色空间转换、FFT得到具有运动放大效果的目标视频，提升了振动检测的智能性。It can be seen that in this example, the electronic device can obtain a target video with a motion amplification effect through color space conversion and FFT, which improves the intelligence of vibration detection.

S204，所述电子设备根据所述目标视频获取所述汽车排气歧管的振动数据。S204: The electronic device obtains vibration data of the exhaust manifold of the automobile according to the target video.

其中，所述电子设备根据所述目标视频获取所述的发生运动的区域的振动数据的实现方式可以是：对合成后的目标视频进行相位计算、插值滤波，以得到所述的发生运动的区域的振动数据，其中，振动数据可以是振动幅度、振动频率、振动相位中的至少一种。其中，所述振动频率是指单位时间内发生运动的区域进行振动的部分完成的全振动的次数，所述振动幅度是发生运动的区域进行振动时离开平衡位置最大位移的绝对值，振幅在数值上等于最大位移的大小，描述了物体振动幅度的大小和振动的强弱。Wherein, the implementation manner of the electronic device acquiring the vibration data of the moving area according to the target video may be: performing phase calculation and interpolation filtering on the synthesized target video to obtain the moving area Vibration data of, where the vibration data can be at least one of vibration amplitude, vibration frequency, and vibration phase. Wherein, the vibration frequency refers to the number of complete vibrations that are partially completed in the area where the movement occurs per unit time, and the vibration amplitude is the absolute value of the maximum displacement from the equilibrium position when the area where the movement occurs vibrates, and the amplitude is in the numerical value. The upper is equal to the magnitude of the maximum displacement, which describes the magnitude of the object's vibration amplitude and the strength of the vibration.

可见，本示例中，电子设备通过对目标视频的处理，得到发生运动的区域的振动数据。It can be seen that, in this example, the electronic device obtains the vibration data of the area where the movement occurs by processing the target video.

S205，所述电子设备根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常。S205: The electronic device determines whether the vibration state of the exhaust manifold of the automobile is abnormal according to the target video and/or the vibration data.

可选的，所述电子设备根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常，包括：所述电子设备获取参考振动数据，所述振动参考数据为所述汽车排气歧管在正常情况下所对应的振动数据；所述电子设备当确定所述振动数据大于所述参考振动数据时，确定所述汽车排气歧管的振动状态为异常状态。Optionally, the electronic device determines whether the vibration state of the automobile exhaust manifold is abnormal according to the target video and/or the vibration data, including: the electronic device obtains reference vibration data, and the vibration reference data is Vibration data corresponding to the automobile exhaust manifold under normal conditions; when the electronic device determines that the vibration data is greater than the reference vibration data, it determines that the vibration state of the automobile exhaust manifold is an abnormal state.

举例来说，所述振动数据可以是振动幅度，所述振动幅度是所述汽车排气歧管的最大振动幅度，将所述汽车排气歧管的最大振动幅度与所述参考振动数据进行比较，若所述汽车排气歧管的最大振动幅度大于所述参考振动数据中的参考振动幅度时，确定所述待测车辆的振动状态为异常状态。For example, the vibration data may be a vibration amplitude, the vibration amplitude is the maximum vibration amplitude of the exhaust manifold of the automobile, and the maximum vibration amplitude of the exhaust manifold of the automobile is compared with the reference vibration data If the maximum vibration amplitude of the exhaust manifold of the automobile is greater than the reference vibration amplitude in the reference vibration data, it is determined that the vibration state of the vehicle under test is an abnormal state.

可见，本示例中，电子设备通过将发生运动的区域的最大振动幅度与参考振动幅度进行比较，确定待测车辆的振动状态为异常状态。It can be seen that, in this example, the electronic device determines that the vibration state of the vehicle to be tested is an abnormal state by comparing the maximum vibration amplitude of the moving area with the reference vibration amplitude.

进一步的，所述电子设备获取参考振动数据，包括：所述电子设备以所述汽车排气歧管的编号为查询标识，查询数据库，得到所述编号对应的配置条件，所述数据库包括汽车排气歧管的编号与配置条件的对应关系，所述配置条件包括所述汽车排气歧管的参考振动数据。Further, obtaining the reference vibration data by the electronic device includes: the electronic device uses the number of the automobile exhaust manifold as a query identifier to query a database to obtain the configuration condition corresponding to the number, and the database includes the automobile exhaust manifold. Correspondence between the number of the gas manifold and the configuration condition, the configuration condition including the reference vibration data of the exhaust manifold of the automobile.

其中，所述排气歧管的编号为所述电子设备存储的所述汽车排气歧管的代号。所述数据库中参考振动数据为经过实验得到的所述汽车排气歧管正常条件下得到的实验数据，包括共振频率。Wherein, the number of the exhaust manifold is the code number of the exhaust manifold of the automobile stored in the electronic device. The reference vibration data in the database is experimental data obtained through experiments under normal conditions of the exhaust manifold of the automobile, including the resonance frequency.

可见，本示例中，电子设备通过汽车排气歧管的编号，进而获取参考振动数据，从而保证对振动检测的可靠It can be seen that in this example, the electronic device obtains the reference vibration data through the number of the exhaust manifold of the car, so as to ensure the reliability of the vibration detection.

S206，若是，则输出预设报警信息。S206: If yes, output preset alarm information.

所述预设报警信息可以是“更换所述排气歧管”。The preset alarm message may be "replace the exhaust manifold".

可见，本示例中，电子设备通过输出报警信息，提升振动检测的可靠性。It can be seen that in this example, the electronic device improves the reliability of vibration detection by outputting alarm information.

在一个可能的示例中，所述电子设备根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，包括：所述电子设备将目标视频的多帧图像组成的帧序列进行空域金字塔分解，得到由多个不同空间分辨率的子图像组成的金字塔形结构；所述电子设备对金字塔型结构中的多个子图像中每个子图像进行时域带通滤波处理，得到目标频带对应的变换信号；所述电子设备对变换信号对应的位移进行A倍放大，获得放大后信号，其中A的取值范围为(2，Amax),其中Amax的值由目标频带和变换信号的位移函数确定；所述电子设备结合放大后信号和金字塔形结构进行金字塔重构，得到放大输出视频。In a possible example, the electronic device processes the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, including: the electronic device performs a frame sequence composed of multiple frames of the target video Spatial pyramid decomposition, to obtain a pyramid structure composed of multiple sub-images with different spatial resolutions; the electronic device performs time-domain band-pass filtering processing on each of the multiple sub-images in the pyramid structure to obtain the target frequency band corresponding The conversion signal of the conversion signal; the electronic device amplifies the displacement corresponding to the conversion signal by A times to obtain the amplified signal, where the value range of A is (2, Amax), where the value of Amax is determined by the displacement function of the target frequency band and the conversion signal Determine; the electronic device combines the amplified signal and the pyramid structure to perform pyramid reconstruction to obtain an amplified output video.

具体地，采用欧拉运动放大对目标视频进行放大，首先需要将目标视频中的像素转换成时间和空间的函数，即通过图像金字塔变换将目标视频的多帧图像组成的帧序列分解成多个不同空间分辨率、不同尺度大小的子图像以构成一个金字塔塔型结构，例如采用高斯金字塔对目标视频的多帧图像进行分解，即由一组在尺寸上逐层减半的图像序列组成金字塔结构，序列中的每一级图像均为其前一级图像低通滤波并隔行隔列采样的结果。Specifically, to use Euler motion amplification to amplify the target video, it is first necessary to convert the pixels in the target video into a function of time and space, that is, through the image pyramid transformation, the frame sequence composed of multiple frames of the target video is decomposed into multiple Sub-images of different spatial resolutions and different scale sizes form a pyramid structure. For example, a Gaussian pyramid is used to decompose the multi-frame image of the target video, that is, a pyramid structure is composed of a set of image sequences that are halved in size. , Each level of image in the sequence is the result of low-pass filtering of the previous level of image and sampling every other row and every column.

进行金字塔分解即对帧序列进行空域滤波，分解得到不同空间频率的频带，并对这些频带分别进行放大。因为处于不同空间频率的频带对应的信噪比不同，空间频率越低，图像噪声越少，信噪比越高，因此每层空间频率的频带可以设置不同的放大系数。例如可以使用一个线性可变的放大倍数来放大不同频率的频带。金字塔结构中，从顶层到底层，放大倍数依次降低。Pyramid decomposition is to perform spatial filtering on the frame sequence, decompose to obtain frequency bands of different spatial frequencies, and amplify these frequency bands respectively. Because frequency bands at different spatial frequencies correspond to different signal-to-noise ratios, the lower the spatial frequency, the less image noise and the higher the signal-to-noise ratio. Therefore, different amplification factors can be set for each layer of spatial frequency bands. For example, a linearly variable magnification factor can be used to amplify frequency bands of different frequencies. In the pyramid structure, from the top to the bottom, the magnifications are sequentially reduced.

通过金字塔处理得到不同空间频率的频带后，还可以对每个频带进行时域的带通滤波处理，以得到感兴趣的变换信号，即目标频带对应的变换信号，并只对目标频带对应的变换信号进行放大处理。在进行带通滤波处理时，可以采用理想带通滤波器，Butterworth带通滤波器，二阶无限脉冲响应滤波器等。After the frequency bands of different spatial frequencies are obtained through pyramid processing, time-domain band-pass filtering can be performed on each frequency band to obtain the transformed signal of interest, that is, the transformed signal corresponding to the target frequency band, and only the transformation corresponding to the target frequency band The signal is amplified. When performing band-pass filtering, ideal band-pass filters, Butterworth band-pass filters, second-order infinite impulse response filters, etc. can be used.

获得目标频带对应的变换信号后，令I(x,t)为点x在时刻t的灰度值，且初始值为f(x)，则：After obtaining the transformed signal corresponding to the target frequency band, let I(x,t) be the gray value of point x at time t, and the initial value is f(x), then:

其中δ(t)表示位移信号。Where δ(t) represents the displacement signal.

对I(x,t)放大α倍，即对位移信号δ(t)进行放大，且放大后的信号为：Amplify I(x,t) by α times, that is, amplify the displacement signal δ(t), and the amplified signal is:

因为微小运动进行放大时，倍数太小是没有意义的，因此A的最小取值大于2。另外，放大倍数与空间频率相关，且满足如下关系：Because it is meaningless for the magnification of small movements to be too small, the minimum value of A is greater than 2. In addition, the magnification is related to the spatial frequency and satisfies the following relationship:

其中，空间频率为ω，目标频带的空间波长为λ，且λ＝2π/ω，则可通过目标频带和变换信号的位移函数确定α的最大值。Amax≤α。Among them, the spatial frequency is ω, the spatial wavelength of the target frequency band is λ, and λ=2π/ω, the maximum value of α can be determined by the displacement function of the target frequency band and the transformed signal. Amax≤α.

获得放大后信号之后，将其重新与原本的频带相结合，再通过金字塔重构，例如拉普拉斯金字塔变换重构，得到放大后的图像，进行得到放大输出视频。After the amplified signal is obtained, it is recombined with the original frequency band, and then pyramid reconstruction, such as Laplace pyramid transform reconstruction, is used to obtain the amplified image, and then proceed to obtain the amplified output video.

可见，在本申请实施例中，电子设备通过对振动视频进行放大处理，进而更清楚的呈现汽车排气歧管的振动情况，提升了振动检测的精确度。It can be seen that, in the embodiment of the present application, the electronic device magnifies the vibration video to more clearly present the vibration of the exhaust manifold of the automobile, thereby improving the accuracy of vibration detection.

在一个可能的示例中，所述电子设备根据所述目标视频获取所述汽车排气歧管的振动数据，包括：所述电子设备获取目标视频中汽车排气歧管的多个图像帧，对所述多个图像帧中的每个图像帧进行图像识别；所述电子设备根据识别结果对所述每个图像帧中的所述汽车排气歧管进行预设区域划分，获得多个区域；所述电子设备确定所述多个区域中每个区域对应的多个目标特征点；所述电子设备对所述多个目标特征点进行跟踪，得到所述多个目标特征点的位置变化信息；所述电子设备根据所述位置信息生成所述多个目标特征点的振动追踪图像；所述电子设备根据所述振动追踪图像，获得所述目标视频对应的振动数据。In a possible example, the electronic device acquiring the vibration data of the automobile exhaust manifold according to the target video includes: the electronic device acquiring multiple image frames of the automobile exhaust manifold in the target video, Performing image recognition on each of the multiple image frames; the electronic device performs a preset area division on the automobile exhaust manifold in each image frame according to the recognition result to obtain multiple areas; The electronic device determines multiple target feature points corresponding to each of the multiple regions; the electronic device tracks the multiple target feature points to obtain position change information of the multiple target feature points; The electronic device generates vibration tracking images of the multiple target feature points according to the position information; the electronic device obtains vibration data corresponding to the target video according to the vibration tracking image.

其中，所述电子设备根据识别结果对所述每个图像帧中的所述汽车排气歧管进行预设区域划分的实现方式可以是：按照排气主管、排气支管、排气法兰的对每个图像帧中的所述汽车排气歧管进行预设区域划分。Wherein, according to the recognition result, the electronic device may implement the preset area division of the automobile exhaust manifold in each image frame as follows: according to the exhaust gas main pipe, exhaust branch pipe, and exhaust flange A preset area is divided into the exhaust manifold of the automobile in each image frame.

举例来说，以4排气支管的汽车排气歧管为例，如图2C所示，图2C为本申请实施例提供的一种汽车排气歧管分区的示意图，如图2C所示，将汽车排气歧管分为第一振动区域201、第二振动区域202、第三振动区域203、第四振动区域204、第五振动区域205以及第六振动区域206，其中，第一振动区域201对应汽车排气歧管的排气主管、第二振动区域202对应汽车排气歧管的第一排气支管、第三振动区域203对应汽车排气歧管的第二排气支管、第四振动区域204对应汽车排气歧管的第三排气支管、第五振动区域205对应汽车排气歧管的第四分排气支管，第六振动区域206对应汽车排气歧管的法兰。For example, take an automobile exhaust manifold with 4 exhaust manifolds as an example, as shown in FIG. 2C, which is a schematic diagram of an automobile exhaust manifold partition provided by an embodiment of the application, as shown in FIG. 2C. The automobile exhaust manifold is divided into a first vibration area 201, a second vibration area 202, a third vibration area 203, a fourth vibration area 204, a fifth vibration area 205, and a sixth vibration area 206. The first vibration area 201 corresponds to the exhaust main pipe of the automobile exhaust manifold, the second vibration zone 202 corresponds to the first exhaust branch of the automobile exhaust manifold, and the third vibration zone 203 corresponds to the second exhaust branch and fourth of the automobile exhaust manifold. The vibration area 204 corresponds to the third exhaust branch of the automobile exhaust manifold, the fifth vibration area 205 corresponds to the fourth sub-exhaust branch of the automobile exhaust manifold, and the sixth vibration area 206 corresponds to the flange of the automobile exhaust manifold.

可见，本示例中，电子设备能够识别汽车排气歧管并根据排气歧管的结构对图像帧中的汽车排气歧管进行预设区域划分，再确定区域每个区域中的目标特征点个数。It can be seen that in this example, the electronic device can identify the car exhaust manifold and divide the car exhaust manifold in the image frame into a preset area according to the structure of the exhaust manifold, and then determine the target feature points in each area of the area Number.

在一个可能的示例中，所述电子设备确定所述多个区域中每个区域对应的多个目标特征点，包括：所述电子设备根据所述多个区域中每个区域对应的预设类型的特征点作为初始特征点，所述预设类型的特征点包括以下至少一种：角点、边缘点、暗区的亮点以及亮区的暗点；所述电子设备基于最小差值平方和SSD匹配，计算所述多个初始特征点的流向量；所述电子设备根据所述多个初始特征点对应的流向量计算所述多个初始特征点的偏移距离；所述电子设备分别对所述多个初始特征点对应的多个偏移距离进行聚类，采用K-means聚类算法对所述多个偏移距离进行聚类，其中，设置k值为5，获得5个聚类类簇；所述电子设备对所述5个聚类类簇求平均值，并获得第一类簇平均值，第二类簇平均值、第三类簇平均值、第四类簇平均值和第五类簇平均值，其中，第一类簇平均值<第二类簇平均值<第三类簇平均值<第四类簇平均值<第五类簇平均值；所述电子设备确定所述第三类簇平均值中的偏移距离对应的初始特征点作为所述多个目标特征点。In a possible example, the electronic device determining the multiple target feature points corresponding to each of the multiple regions includes: the electronic device according to the preset type corresponding to each of the multiple regions As the initial feature points, the preset types of feature points include at least one of the following: corner points, edge points, bright points in dark areas, and dark points in bright areas; the electronic device is based on the minimum difference square sum SSD Matching, calculating the flow vectors of the multiple initial feature points; the electronic device calculates the offset distances of the multiple initial feature points according to the flow vectors corresponding to the multiple initial feature points; The multiple offset distances corresponding to the multiple initial feature points are clustered, and the multiple offset distances are clustered using the K-means clustering algorithm, wherein the k value is set to 5 to obtain 5 clustering classes Cluster; the electronic device averages the 5 clusters, and obtains the average of the first type of cluster, the average of the second type of cluster, the average of the third type of cluster, the average of the fourth type of cluster, and the first Five types of cluster average values, where the first type cluster average value<the second type cluster average value<the third type cluster average value<the fourth type cluster average value<the fifth type cluster average value; the electronic device determines the The initial feature points corresponding to the offset distance in the average value of the third cluster are used as the multiple target feature points.

具体地，角点是轮廓之间的交点，对于同一场景，即使视角发生变化，角点通常具备稳定性质的特征，并且该点附近区域的像素点无论在梯度方向上还是其梯度幅值上有着较大变化。边缘点为振动物体与背景图像之间的交点，亮区的暗点和暗区的亮点与其他像素点之间的对比度高，都可以作为初始特征点，以便更好地进行运动特征点观测。选择初始特征点后，采用最小差值平方和(Sum of Squared Differences,SSD)匹配，计算初始特征点的流向量。SSD的值越小，说明特征点之间的相似度越大，根据这一原则可以确定初始特征点的运动轨迹，进而获得初始特征点的流向量。再根据流向量计算初始特征点的偏移距离，例如对

求模，获得

即为初始特征点从点A到点B的偏移距离。 Specifically, the corner point is the intersection between the contours. For the same scene, even if the viewing angle changes, the corner point usually has the characteristics of stability, and the pixels in the area near the point have both the gradient direction and the gradient magnitude. Big change. The edge point is the intersection between the vibrating object and the background image. The dark point in the bright area and the bright point in the dark area have high contrast with other pixels, and can be used as the initial feature point for better observation of the motion feature point. After selecting the initial feature points, the Sum of Squared Differences (SSD) matching is used to calculate the flow vector of the initial feature points. The smaller the value of SSD, the greater the similarity between the feature points. According to this principle, the motion trajectory of the initial feature point can be determined, and then the flow vector of the initial feature point can be obtained. Then calculate the offset distance of the initial feature point according to the flow vector, for example,

Find the modulus, get

It is the offset distance of the initial feature point from point A to point B.

获得多个初始特征点的偏移距离后，对这些值进行聚类，采用K-means聚类算法对所述多个偏移距离进行聚类，设置k值为5，获得5个聚类类簇；所述电子设备对所述5个聚类类簇求平均值，并获得第一类簇平均值，第二类簇平均值、第三类簇平均值、第四类簇平均值和第五类簇平均值，其中，第一类簇平均值<第二类簇平均值<第三类簇平均值<第四类簇平均值<第五类簇平均值。其中，第一聚类平均值和第二聚类平均值的类簇对应的初始特征点即可确定为静止点(背景点)，第四聚类平均值和第五聚类平均值的类簇对应的初始特征点即可确定为剧烈运动的点，第三聚类平均值的类簇对应的初始特征点确定为目标特征点。After obtaining the offset distances of multiple initial feature points, cluster these values, cluster the multiple offset distances using the K-means clustering algorithm, set the k value to 5, and obtain 5 cluster classes Cluster; the electronic device averages the 5 clusters, and obtains the average of the first type of cluster, the average of the second type of cluster, the average of the third type of cluster, the average of the fourth type of cluster, and the first Five cluster averages, among which, the average of the first cluster <the average of the second cluster <the average of the third cluster <the average of the fourth cluster <the average of the fifth cluster. Among them, the initial feature points corresponding to the clusters of the first cluster average and the second cluster average can be determined as stationary points (background points), and the clusters of the fourth cluster average and the fifth cluster average The corresponding initial feature point can be determined as the point of violent movement, and the initial feature point corresponding to the cluster of the third cluster average is determined as the target feature point.

其中，所述电子设备确定所述多个区域中每个区域对应的多个初始特征点的实现方式可以是：在所述多个区域中每个区域选取特定个数的初始特征点，其中，特定个数可以大于10的任意个数，其中，所述多个区域中每个区域选取特定个数可以相同，也可以不同。Wherein, the implementation manner for the electronic device to determine the multiple initial feature points corresponding to each of the multiple regions may be: selecting a specific number of initial feature points in each of the multiple regions, wherein: The specific number can be any number greater than 10, and the specific number selected for each of the multiple regions can be the same or different.

可见，本示例中，电子设备能够从多个初始特征点中确定出多个目标特征点，提升振动检测的有效性。It can be seen that in this example, the electronic device can determine multiple target feature points from multiple initial feature points, which improves the effectiveness of vibration detection.

在一个可能的示例中，所述电子设备根据所述位置信息生成所述多个目标特征点的振动追踪图像，包括：所述电子设备以时间为横坐标，以所述多个目标特征点中每个目标特征点的相对位移为纵坐标构建直角坐标系；所述电子设备根据所述位置信息在所述直角坐标系画出多个目标特征点的振动追踪图像。In a possible example, the electronic device generating vibration tracking images of the multiple target feature points according to the position information includes: the electronic device uses time as the abscissa, and takes the multiple target feature points as the The relative displacement of each target feature point is the ordinate to construct a rectangular coordinate system; the electronic device draws vibration tracking images of multiple target feature points in the rectangular coordinate system according to the position information.

其中，所述每个目标特征点的相对位移对应所述每个目标特征点的振幅。Wherein, the relative displacement of each target feature point corresponds to the amplitude of each target feature point.

可见，本示例中，电子设备能够通过构建目标特征点的振动追踪图像，能够清楚的展示目标特征点的振幅等振动数据。It can be seen that, in this example, the electronic device can construct a vibration tracking image of the target feature point, and can clearly display the vibration data such as the amplitude of the target feature point.

与上述图2A所示的实施例一致的，请参阅图3，图3是本申请实施例提供的一种电子设备300的结构示意图，如图所示，所述电子设备300包括应用处理器310、存储器320、通信接口330以及一个或多个程序321，其中，所述一个或多个程序321被存储在上述存储器320中，并且被配置由上述应用处理器310执行，所述一个或多个程序321包括用于执行以下步骤的指令；Consistent with the embodiment shown in FIG. 2A, please refer to FIG. 3. FIG. 3 is a schematic structural diagram of an electronic device 300 according to an embodiment of the present application. As shown in the figure, the electronic device 300 includes an application processor 310 , A memory 320, a communication interface 330, and one or more programs 321, wherein the one or more programs 321 are stored in the above-mentioned memory 320 and are configured to be executed by the above-mentioned application processor 310, and the one or more The program 321 includes instructions for performing the following steps;

获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；Acquire the vibration video of the automobile exhaust manifold, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect. The motion amplification effect means that the vehicle exhaust manifold is in the The target video is magnified;

若是，则输出预设报警信息。If yes, output preset alarm information.

在一个可能的示例中，在所述根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频方面，所述一个或多个程序321的指令具体用于：将目标视频的多帧图像组成的帧序列进行空域金字塔分解，得到由多个不同空间分辨率的子图像组成的金字塔形结构；对金字塔型结构中的多个子图像中每个子图像进行时域带通滤波处理，得到目标频带对应的变换信号；对变换信号对应的位移进行A倍放大，获得放大后信号，其中A的取值范围为(2，Amax),其中Amax的值由目标频带和变换信号的位移函数确定；结合放大后信号和金字塔形结构进行金字塔重构，得到放大输出视频。In a possible example, in terms of processing the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, the instructions of the one or more programs 321 are specifically used to: The frame sequence composed of multi-frame images is subjected to spatial pyramid decomposition to obtain a pyramid structure composed of multiple sub-images with different spatial resolutions; each sub-image in the multiple sub-images in the pyramid structure is subjected to time-domain band-pass filtering. Obtain the transformed signal corresponding to the target frequency band; amplify the displacement corresponding to the transformed signal by A times to obtain the amplified signal, where the value range of A is (2, Amax), where the value of Amax is determined by the displacement function of the target frequency band and the transformed signal Confirm; combine the amplified signal and pyramid structure to reconstruct the pyramid to get the amplified output video.

在一个可能的示例中，在所述根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常方面，所述一个或多个程序321的指令具体用于：获取参考振动数据，所述振动参考数据为所述汽车排气歧管在正常情况下所对应的振动数据；当确定所述振动数据大于所述参考振动数据时，确定所述汽车排气歧管的振动状态为异常状态。In a possible example, in terms of determining whether the vibration state of the automobile exhaust manifold is abnormal according to the target video and/or the vibration data, the instructions of the one or more programs 321 are specifically used to: obtain Reference vibration data, the vibration reference data is the vibration data corresponding to the automobile exhaust manifold under normal conditions; when it is determined that the vibration data is greater than the reference vibration data, the vibration data of the automobile exhaust manifold is determined The vibration state is abnormal.

在一个可能的示例中，所述获取参考振动数据方面，所述一个或多个程序321的指令具体用于：以所述汽车排气歧管的编号为查询标识，查询数据库，得到所述编号对应的配置条件，所述数据库包括汽车排气歧管的编号与配置条件的对应关系，所述配置条件包括所述汽车排气歧管的参考振动数据。In a possible example, in terms of obtaining reference vibration data, the instructions of the one or more programs 321 are specifically used to: use the number of the exhaust manifold of the automobile as a query identifier, query the database, and obtain the number Corresponding configuration conditions, the database includes the corresponding relationship between the number of the exhaust manifold of the automobile and the configuration conditions, and the configuration condition includes reference vibration data of the exhaust manifold of the automobile.

在一个可能的示例中，在所述根据所述目标视频获取所述汽车排气歧管的振动数据方面，所述一个或多个程序321的指令具体用于：获取目标视频中汽车排气歧管的多个图像帧，对所述多个图像帧中的每个图像帧进行图像识别；根据识别结果对所述每个图像帧中的所述汽车排气歧管进行预设区域划分，获得多个区域；确定所述多个区域中每个区域对应的多个目标特征点；对所述多个目标特征点进行跟踪，得到所述多个目标特征点的位置变化信息；根据所述位置信息生成所述多个目标特征点的振动追踪图像；根据所述振动追踪图像，获得所述目标视频对应的振动数据。In a possible example, in terms of obtaining the vibration data of the exhaust manifold of the automobile according to the target video, the instructions of the one or more programs 321 are specifically used to: obtain the exhaust manifold of the automobile in the target video. Perform image recognition on each of the multiple image frames of the tube; perform a preset area division on the automobile exhaust manifold in each image frame according to the recognition result to obtain Multiple regions; determine multiple target feature points corresponding to each of the multiple regions; track the multiple target feature points to obtain position change information of the multiple target feature points; according to the position The information generates vibration tracking images of the multiple target feature points; according to the vibration tracking image, the vibration data corresponding to the target video is obtained.

在一个可能的示例中，在所述确定所述多个区域中每个区域对应的多个目标特征点方面，所述一个或多个程序321的指令具体用于：根据所述多个区域中每个区域对应的预设类型的特征点作为初始特征点，所述预设类型的特征点包括以下至少一种：角点、边缘点、暗区的亮点以及亮区的暗点；基于最小差值平方和SSD匹配，计算所述多个初始特征点的流向量；所述电子设备根据所述多个初始特征点对应的流向量计算所述多个初始特征点的偏移距离；所述电子设备分别对所述多个初始特征点对应的多个偏移距离进行聚类，采用K-means聚类算法对所述多个偏移距离进行聚类，其中，设置k值为3，获得3个聚类类簇；对所述3个聚类类簇求平均值，并获得第一类簇平均值，第二类簇平均值、第三类簇平均值、第四类簇平均值和第五类簇平均值，其中，第一类簇平均值<第二类簇平均值<第三类簇平均值<第四类簇平均值<第五类簇平均值；所述电子设备确定所述第三类簇平均值中的偏移距离对应的初始特征点作为所述多个目标特征点。In a possible example, in the aspect of determining the multiple target feature points corresponding to each of the multiple regions, the instructions of the one or more programs 321 are specifically used to: The feature points of the preset type corresponding to each area are used as the initial feature points, and the feature points of the preset type include at least one of the following: corner points, edge points, bright spots in dark areas, and dark points in bright areas; based on the minimum difference The value square is matched with the SSD, and the flow vectors of the multiple initial feature points are calculated; the electronic device calculates the offset distances of the multiple initial feature points according to the flow vectors corresponding to the multiple initial feature points; The device clusters the multiple offset distances corresponding to the multiple initial feature points, and uses the K-means clustering algorithm to cluster the multiple offset distances, where the k value is set to 3, and 3 is obtained. Clusters; average the three clusters, and obtain the average of the first cluster, the average of the second cluster, the average of the third cluster, the average of the fourth cluster, and the fourth Five cluster averages, where the first cluster average<the second cluster average<the third cluster average<the fourth cluster average<the fifth cluster average; the electronic device determines the The initial feature points corresponding to the offset distance in the average value of the third type of clusters are used as the multiple target feature points.

在一个可能的示例中，在所述根据所述位置信息生成所述多个目标特征点的振动追踪图像方面，所述一个或多个程序321的指令具体用于：以时间为横坐标，以所述多个目标特征点中每个目标特征点的相对位移为纵坐标构建直角坐标系；根据所述位置信息在所述直角坐标系画出多个目标特征点的振动追踪图像。In a possible example, in terms of generating the vibration tracking images of the multiple target feature points according to the position information, the instructions of the one or more programs 321 are specifically used to: take time as the abscissa, and The relative displacement of each target feature point in the multiple target feature points is the ordinate to construct a rectangular coordinate system; and the vibration tracking images of the multiple target feature points are drawn in the rectangular coordinate system according to the position information.

上述主要从方法侧执行过程的角度对本申请实施例的方案进行了介绍。可以理解的是，电子设备为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件单元。本领域技术人员应该很容易意识到，结合本文中所提供的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。The foregoing mainly introduces the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that, in order to implement the above-mentioned functions, an electronic device includes hardware structures and/or software units corresponding to each function. Those skilled in the art should easily realize that in combination with the units and algorithm steps of the examples described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

本申请实施例可以根据上述方法示例对电子设备进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个处理单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。需要说明的是，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。The embodiment of the present application may divide the electronic device into functional units according to the foregoing method examples. For example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.

图4是本申请实施例中所涉及的振动检测装置400的功能单元组成框图。该振动检测装置400应用于电子设备，包括处理单元401和通信单元402，其中，FIG. 4 is a block diagram of functional units of the vibration detection device 400 involved in an embodiment of the present application. The vibration detection device 400 is applied to electronic equipment, and includes a processing unit 401 and a communication unit 402, wherein,

所述处理单元401，用于通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管；以及用于获取用户输入的振动检测类型信息，通过所述通信单元402传递所述信息信号，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作；以及用于通过振动装置获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；以及用于根据所述目标视频获取所述汽车排气歧管的振动数据；以及用于根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常；若是，则输出预设报警信息。The processing unit 401 is configured to display a vibration detection portal through the main interface of the vibration detection device, the vibration detection portal provides vibration detection type options, and the vibration detection type options include automobile exhaust manifolds; and for obtaining users The input vibration detection type information transmits the information signal through the communication unit 402, and generates vibration operation prompt information according to the vibration detection type information, and the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested And used to obtain the vibration video of the automobile exhaust manifold through a vibration device, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, the motion amplification effect refers to the car The exhaust manifold is amplified in the target video; and used to obtain vibration data of the automobile exhaust manifold according to the target video; and used to obtain vibration data according to the target video and/or the vibration The data determines whether the vibration state of the automobile exhaust manifold is abnormal; if it is, the preset alarm information is output.

其中，所述控制装置400还可以包括存储单元403，用于存储电子设备的程序代码和数据。所述处理单元401可以是处理器，所述通信单元402可以是触控显示屏或者收发器，存储单元403可以是存储器。Wherein, the control device 400 may further include a storage unit 403 for storing program codes and data of the electronic device. The processing unit 401 may be a processor, the communication unit 402 may be a touch screen or a transceiver, and the storage unit 403 may be a memory.

在一个可能的示例中，在所述根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频方面，所述处理单元401具体用于：将目标视频的多帧图像组成的帧序列进行空域金字塔分解，得到由多个不同空间分辨率的子图像组成的金字塔形结构；对金字塔型结构中的多个子图像中每个子图像进行时域带通滤波处理，得到目标频带对应的变换信号；对变换信号对应的位移进行A倍放大，获得放大后信号，其中A的取值范围为(2，Amax),其中Amax的值由目标频带和变换信号的位移函数确定；结合放大后信号和金字塔形结构进行金字塔重构，得到放大输出视频。In a possible example, in terms of processing the vibration video according to a preset strategy to obtain a target video with a motion amplification effect, the processing unit 401 is specifically configured to: compose multiple frames of the target video The frame sequence is subjected to spatial pyramid decomposition to obtain a pyramid-shaped structure composed of multiple sub-images with different spatial resolutions; each sub-image in the multiple sub-images in the pyramid-shaped structure is subjected to time-domain band-pass filtering to obtain the corresponding target frequency band Transform the signal; Amplify the displacement corresponding to the transformed signal by A times to obtain the amplified signal, where the value range of A is (2, Amax), where the value of Amax is determined by the target frequency band and the displacement function of the transformed signal; combined with the amplification Pyramid reconstruction is performed on the signal and pyramid structure to obtain an amplified output video.

在一个可能的示例中，在所述根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常方面，所述处理单元401具体用于：获取参考振动数据，所述振动参考数据为所述汽车排气歧管在正常情况下所对应的振动数据；当确定所述振动数据大于所述参考振动数据时，确定所述汽车排气歧管的振动状态为异常状态。In a possible example, in terms of determining whether the vibration state of the automobile exhaust manifold is abnormal according to the target video and/or the vibration data, the processing unit 401 is specifically configured to: obtain reference vibration data, and The vibration reference data is the vibration data corresponding to the exhaust manifold of the automobile under normal conditions; when it is determined that the vibration data is greater than the reference vibration data, it is determined that the vibration state of the exhaust manifold of the automobile is an abnormal state .

在一个可能的示例中，所述获取参考振动数据方面，所述处理单元401具体用于：以所述汽车排气歧管的编号为查询标识，查询数据库，得到所述编号对应的配置条件，所述数据库包括汽车排气歧管的编号与配置条件的对应关系，所述配置条件包括所述汽车排气歧管的参考振动数据。In a possible example, in terms of obtaining reference vibration data, the processing unit 401 is specifically configured to: use the number of the automobile exhaust manifold as a query identifier, query a database, and obtain the configuration conditions corresponding to the number, The database includes the corresponding relationship between the serial number of the automobile exhaust manifold and the configuration condition, and the configuration condition includes the reference vibration data of the automobile exhaust manifold.

在一个可能的示例中，在所述根据所述目标视频获取所述汽车排气歧管的振动数据方面，所述处理单元401具体用于：获取目标视频中汽车排气歧管的多个图像帧，对所述多个图像帧中的每个图像帧进行图像识别；根据识别结果对所述每个图像帧中的所述汽车排气歧管进行预设区域划分，获得多个区域；确定所述多个区域中每个区域对应的多个目标特征点；对所述多个目标特征点进行跟踪，得到所述多个目标特征点的位置变化信息；根据所述位置信息生成所述多个目标特征点的振动追踪图像；根据所述振动追踪图像，获得所述目标视频对应的振动数据。In a possible example, in terms of obtaining vibration data of the exhaust manifold of the automobile according to the target video, the processing unit 401 is specifically configured to: obtain multiple images of the exhaust manifold of the automobile in the target video Frame, performing image recognition on each of the multiple image frames; performing preset area division on the automobile exhaust manifold in each image frame according to the recognition result to obtain multiple areas; determining Multiple target feature points corresponding to each of the multiple regions; tracking the multiple target feature points to obtain position change information of the multiple target feature points; generating the multiple target feature points according to the location information A vibration tracking image of a target feature point; according to the vibration tracking image, the vibration data corresponding to the target video is obtained.

在一个可能的示例中，在所述确定所述多个区域中每个区域对应的多个目标特征点方面，所述处理单元401具体用于：根据所述多个区域中每个区域对应的预设类型的特征点作为初始特征点，所述预设类型的特征点包括以下至少一种：角点、边缘点、暗区的亮点以及亮区的暗点；基于最小差值平方和SSD匹配，计算所述多个初始特征点的流向量；所述电子设备根据所述多个初始特征点对应的流向量计算所述多个初始特征点的偏移距离；所述电子设备分别对所述多个初始特征点对应的多个偏移距离进行聚类，采用K-means聚类算法对所述多个偏移距离进行聚类，其中，设置k值为5，获得5个聚类类簇；对所述5个聚类类簇求平均值，并获得第一类簇平均值，第二类簇平均值、第三类簇平均值、第四类簇平均值和第五类簇平均值，其中，第一类簇平均值<第二类簇平均值<第三类簇平均值<第四类簇平均值<第五类簇平均值；所述电子设备确定所述第三类簇平均值中的偏移距离对应的初始特征点作为所述多个目标特征点。In a possible example, in the aspect of determining the multiple target feature points corresponding to each of the multiple regions, the processing unit 401 is specifically configured to: The feature points of the preset type are used as the initial feature points, and the feature points of the preset type include at least one of the following: corner points, edge points, bright points in dark areas, and dark points in bright areas; based on minimum difference square sum SSD matching Calculate the flow vectors of the multiple initial feature points; the electronic device calculates the offset distances of the multiple initial feature points according to the flow vectors corresponding to the multiple initial feature points; The multiple offset distances corresponding to multiple initial feature points are clustered, and the multiple offset distances are clustered using the K-means clustering algorithm, where the k value is set to 5 to obtain 5 clusters Calculate the average of the 5 clusters, and obtain the average of the first type of cluster, the average of the second type of cluster, the average of the third type of cluster, the average of the fourth type of cluster, and the average of the fifth type of cluster , Wherein the average value of the first type cluster<the average value of the second type cluster<the average value of the third type cluster<the average value of the fourth type cluster<the average value of the fifth type cluster; the electronic device determines the average value of the third type cluster The initial feature points corresponding to the offset distance in the value are used as the multiple target feature points.

在一个可能的示例中，在所述根据所述位置信息生成所述多个目标特征点的振动追踪图像方面，所述处理单元401具体用于：以时间为横坐标，以所述多个目标特征点中每个目标特征点的相对位移为纵坐标构建直角坐标系；根据所述位置信息在所述直角坐标系画出多个目标特征点的振动追踪图像。In a possible example, in the aspect of generating vibration tracking images of the multiple target feature points according to the position information, the processing unit 401 is specifically configured to: take time as the abscissa and take the multiple target The relative displacement of each target feature point in the feature points is the ordinate to construct a rectangular coordinate system; the vibration tracking images of multiple target feature points are drawn in the rectangular coordinate system according to the position information.

本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤，上述计算机包括电子设备。An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method as recorded in the above method embodiment , The above-mentioned computer includes electronic equipment.

本申请实施例还提供一种计算机程序产品，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括电子设备。The embodiments of the present application also provide a computer program product. The above-mentioned computer program product includes a non-transitory computer-readable storage medium storing a computer program. The above-mentioned computer program is operable to cause a computer to execute any of the methods described in the above-mentioned method embodiments. Part or all of the steps of the method. The computer program product may be a software installation package, and the above-mentioned computer includes electronic equipment.

需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和单元并不一定是本申请所必须的。It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited by the described sequence of actions. Because according to this application, some steps can be performed in other order or at the same time. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and units involved are not necessarily required by this application.

在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed device may be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the above-mentioned units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored, or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.

上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described above as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例上述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，RandomAccessMemory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory. A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the foregoing methods of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器(英文：Read-OnlyMemory，简称：ROM)、随机存取器(英文：RandomAccessMemory，简称：RAM)、磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory (English: Read-OnlyMemory, abbreviation: ROM), random access device (English: RandomAccessMemory, abbreviation: RAM), magnetic disk or CD, etc.

以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。The embodiments of the application are described in detail above, and specific examples are used in this article to illustrate the principles and implementation of the application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the application; at the same time, for Those of ordinary skill in the art, based on the ideas of the application, will have changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as limiting the application.

Claims

一种振动检测方法，其特征在于，应用于电子设备，所述方法包括：A vibration detection method, characterized in that it is applied to an electronic device, and the method includes:

通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管；Displaying a vibration detection entrance through the main interface of the vibration detection device, the vibration detection entrance provides a vibration detection type option, and the vibration detection type option includes an automobile exhaust manifold;

获取用户输入的振动检测类型信息，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作；Acquiring vibration detection type information input by the user, and generating vibration operation prompt information according to the vibration detection type information, where the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested;

获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；Acquire the vibration video of the automobile exhaust manifold, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect. The motion amplification effect means that the vehicle exhaust manifold is in the The target video is magnified;

根据所述目标视频获取所述汽车排气歧管的振动数据；Acquiring vibration data of the exhaust manifold of the automobile according to the target video;

根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常；Determine whether the vibration state of the exhaust manifold of the automobile is abnormal according to the target video and/or the vibration data;

若是，则输出预设报警信息。If yes, output preset alarm information.
根据权利要求1所述的方法，其特征在于，所述根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，包括：The method according to claim 1, wherein the processing the vibration video according to a preset strategy to obtain a target video with a motion amplification effect comprises:

将目标视频的多帧图像组成的帧序列进行空域金字塔分解，得到由多个不同空间分辨率的子图像组成的金字塔形结构；Perform spatial pyramid decomposition of the frame sequence composed of multiple frames of the target video to obtain a pyramid structure composed of multiple sub-images with different spatial resolutions;

对金字塔型结构中的多个子图像中每个子图像进行时域带通滤波处理，得到目标频带对应的变换信号；Perform time-domain band-pass filtering on each of the multiple sub-images in the pyramid structure to obtain a transformed signal corresponding to the target frequency band;

对变换信号对应的位移进行A倍放大，获得放大后信号，其中A的取值范围为(2，Amax),其中Amax的值由目标频带和变换信号的位移函数确定；Amplify the displacement corresponding to the transformed signal by A times to obtain the amplified signal, where the value range of A is (2, Amax), and the value of Amax is determined by the target frequency band and the displacement function of the transformed signal;

结合放大后信号和金字塔形结构进行金字塔重构，得到放大输出视频。Pyramid reconstruction is performed by combining the amplified signal and the pyramid structure to obtain the amplified output video.
根据权利要求1所述的方法，其特征在于，所述根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常，包括：The method according to claim 1, wherein the determining whether the vibration state of the exhaust manifold of the automobile is abnormal according to the target video and/or the vibration data comprises:

获取参考振动数据，所述振动参考数据为所述汽车排气歧管在正常情况下所对应的振动数据；Acquiring reference vibration data, where the vibration reference data is vibration data corresponding to the exhaust manifold of the automobile under normal conditions;

当确定所述振动数据大于所述参考振动数据时，确定所述汽车排气歧管的振动状态为异常状态。When it is determined that the vibration data is greater than the reference vibration data, it is determined that the vibration state of the exhaust manifold of the automobile is an abnormal state.
根据权利要求3所述的方法，其特征在于，所述获取参考振动数据，包括：The method according to claim 3, wherein said obtaining reference vibration data comprises:

以所述汽车排气歧管的编号为查询标识，查询数据库，得到所述编号对应的配置条件，所述数据库包括汽车排气歧管的编号与配置条件的对应关系，所述配置条件包括所述汽车排气歧管的参考振动数据。Using the number of the automobile exhaust manifold as a query identifier, query a database to obtain the configuration condition corresponding to the number. The database includes the corresponding relationship between the number of the automobile exhaust manifold and the configuration condition, and the configuration condition includes all the configuration conditions. Describes the reference vibration data of the exhaust manifold of a car.
根据权利要求1-4任一项所述的方法，其特征在于，所述根据所述目标视频获取所述汽车排气歧管的振动数据，包括：The method according to any one of claims 1 to 4, wherein the acquiring vibration data of the exhaust manifold of the automobile according to the target video comprises:

获取目标视频中汽车排气歧管的多个图像帧，对所述多个图像帧中的每个图像帧进行图像识别；Acquiring multiple image frames of the automobile exhaust manifold in the target video, and performing image recognition on each of the multiple image frames;

根据识别结果对所述每个图像帧中的所述汽车排气歧管进行预设区域划分，获得多个区域；Performing preset area division on the automobile exhaust manifold in each image frame according to the recognition result to obtain multiple areas;

确定所述多个区域中每个区域对应的多个目标特征点；Determining a plurality of target feature points corresponding to each of the plurality of regions;

对所述多个目标特征点进行跟踪，得到所述多个目标特征点的位置变化信息；Tracking the multiple target feature points to obtain position change information of the multiple target feature points;

根据所述位置信息生成所述多个目标特征点的振动追踪图像；Generating vibration tracking images of the multiple target feature points according to the position information;

根据所述振动追踪图像，获得所述目标视频对应的振动数据。According to the vibration tracking image, the vibration data corresponding to the target video is obtained.
根据权利要求5所述的方法，其特征在于，所述确定所述多个区域中每个区域对应的多个目标特征点，包括：The method according to claim 5, wherein the determining a plurality of target feature points corresponding to each of the plurality of regions comprises:

根据所述多个区域中每个区域对应的预设类型的特征点作为初始特征点，所述预设类型的特征点包括以下至少一种：角点、边缘点、暗区的亮点以及亮区的暗点；According to the feature points of the preset type corresponding to each of the multiple regions as the initial feature points, the feature points of the preset type include at least one of the following: corner points, edge points, bright spots in dark areas, and bright areas The dark spot

基于最小差值平方和SSD匹配，计算所述多个初始特征点的流向量；所述电子设备根据所述多个初始特征点对应的流向量计算所述多个初始特征点的偏移距离；所述电子设备分别对所述多个初始特征点对应的多个偏移距离进行聚类，采用K-means聚类算法对所述多个偏移距离进行聚类，其中，设置k值为5，获得5个聚类类簇；Calculating the flow vectors of the multiple initial feature points based on the minimum difference square and SSD matching; the electronic device calculates the offset distances of the multiple initial feature points according to the flow vectors corresponding to the multiple initial feature points; The electronic device clusters the multiple offset distances corresponding to the multiple initial feature points, and clusters the multiple offset distances by using a K-means clustering algorithm, wherein the k value is set to 5. , Get 5 clusters;

对所述5个聚类类簇求平均值，并获得第一类簇平均值，第二类簇平均值、第三类簇平均值、第四类簇平均值和第五类簇平均值，其中，第一类簇平均值<第二类簇平均值<第三类簇平均值<第四类簇平均值<第五类簇平均值；所述电子设备确定所述第三类簇平均值中的偏移距离对应的初始特征点作为所述多个目标特征点。Calculate the average of the 5 clusters, and obtain the average of the first type of cluster, the average of the second type of cluster, the average of the third type of cluster, the average of the fourth type of cluster, and the average of the fifth type of cluster, Wherein, the average value of the first type cluster<the average value of the second type cluster<the average value of the third type cluster<the average value of the fourth type cluster<the average value of the fifth type cluster; the electronic device determines the average value of the third type cluster The initial feature point corresponding to the offset distance in is used as the multiple target feature points.
根据权利要求6所述的方法，其特征在于，所述根据所述位置信息生成所述多个目标特征点的振动追踪图像，包括：The method according to claim 6, wherein the generating vibration tracking images of the multiple target feature points according to the position information comprises:

以时间为横坐标，以所述多个目标特征点中每个目标特征点的相对位移为纵坐标构建直角坐标系；Using time as the abscissa, and using the relative displacement of each target feature point in the plurality of target feature points as the ordinate to construct a rectangular coordinate system;

根据所述位置信息在所述直角坐标系画出多个目标特征点的振动追踪图像。Drawing vibration tracking images of multiple target feature points in the rectangular coordinate system according to the position information.
一种振动检测装置，其特征在于，所述电子设备包括处理单元和通信单元，其中，A vibration detection device, characterized in that the electronic equipment includes a processing unit and a communication unit, wherein:

所述处理单元，用于通过所述振动检测设备主界面显示振动检测入口，所述振动检测入口提供振动检测类型选项，所述振动检测类型选项包括汽车排气歧管；以及用于获取用户输入的振动检测类型信息，通过所述通信单元传递所述信息信号，并根据所述振动检测类型信息生成振动操作提示信息，所述振动操作提示信息用于指示用户对待测车辆进行预设操作；以及用于通过振动装置获取所述汽车排气歧管的振动视频，根据预设策略对所述振动视频进行处理，得到具有运动放大效果的目标视频，所述运动放大效果是指所述汽车排气歧管在所述目标视频中是经过放大处理的；以及用于根据所述目标视频获取所述汽车排气歧管的振动数据；以及用于根据所述目标视频和/或所述振动数据确定汽车排气歧管的振动状态是否异常；若是，则输出预设报警信息。The processing unit is configured to display a vibration detection entrance through the main interface of the vibration detection device, the vibration detection entrance provides a vibration detection type option, the vibration detection type option includes an automobile exhaust manifold; and is used to obtain user input The vibration detection type information, the information signal is transmitted through the communication unit, and vibration operation prompt information is generated according to the vibration detection type information, the vibration operation prompt information is used to instruct the user to perform a preset operation on the vehicle to be tested; and It is used to obtain the vibration video of the automobile exhaust manifold through a vibration device, and process the vibration video according to a preset strategy to obtain a target video with a motion amplification effect. The motion amplification effect refers to the vehicle exhaust The manifold is amplified in the target video; and used to obtain the vibration data of the automobile exhaust manifold according to the target video; and used to determine according to the target video and/or the vibration data Whether the vibration state of the automobile exhaust manifold is abnormal; if so, output a preset alarm message.
一种电子设备，其特征在于，包括处理器、存储器、通信接口，以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行如权利要求1-7任一项所述的方法中的步骤的指令。An electronic device, characterized by comprising a processor, a memory, a communication interface, and one or more programs, the one or more programs are stored in the memory and configured to be executed by the processor, The program includes instructions for performing the steps in the method according to any one of claims 1-7.
一种计算机可读存储介质，其特征在于，存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-7任一项所述的方法。A computer-readable storage medium, characterized by storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the method according to any one of claims 1-7.