Living object expelling method, device and equipment and storage medium

Abstract

The invention provides a living object expelling method and device, equipment and a storage medium. The method is applied to a controller in a repelling system in a vehicle, and the controller is in communication connection with an image processing system in a cloud server. The method comprises the following steps: acquiring image data in a first preset range around a vehicle body of a vehicle, wherein the image data comprises a living object in the first preset range; sending the image data to an image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage expelling strategy for the living object according to the type of the living object; receiving a voltage expelling strategy sent by the image processing system; and repelling the living object according to the voltage repelling strategy. The purpose of expelling is achieved by providing pulse voltage stimulation for the living objects around the vehicle, the living objects can be prevented from getting close to the vehicle, damage or pollution caused by the living objects to the vehicle is avoided, and meanwhile the problem of noise pollution or light pollution is avoided.

Description

Technical Field

[0001] The present application relates to the automotive field, and in particular to a method, device, equipment and storage medium for driving away a living object. Background Art

[0002] In some scenarios, animals around the vehicle may cause pollution or damage to the vehicle (for example, when there are many birds on the vehicle, it will cause serious pollution to the vehicle), so it is necessary to drive away the animals in such scenarios. Traditional animal removal solutions mainly rely on a series of non-contact technical means, including simulating the sound effects of natural enemies, emitting sound waves of specific frequencies, and using light signals, aiming to achieve the purpose of removal by stimulating the natural defense mechanisms of animals. However, these technical means will cause noise pollution or light pollution problems in practical applications. Summary of the invention

[0003] The present application provides a method, device, equipment and storage medium for driving away living objects, which aims to achieve the purpose of driving away living objects by providing voltage stimulation to living objects around a vehicle, thereby preventing living objects from approaching the vehicle and causing damage or pollution to the vehicle, while avoiding the noise pollution or light pollution problems existing in traditional driving away solutions.

[0004] In a first aspect, the present application provides a method for driving away a living object, which is applied to a controller in a driving away system in a vehicle, wherein the controller is communicatively connected to an image processing system in a cloud server; the method comprises:

[0005] Acquire image data within a first preset range around a body of the vehicle, wherein the image data includes a living object within the first preset range;

[0006] Sending the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage drive-away strategy for the living object according to the type of the living object;

[0007] receiving the voltage drive-off strategy sent by the image processing system;

[0008] The living object is driven away according to the voltage drive-away strategy.

[0009] Optionally, the expulsion system further includes a voltage module, and the controller is in communication connection with the voltage module; and the expulsion of the living object according to the voltage expulsion strategy includes:

[0010] When the living object is located within a second preset range around the vehicle body, the voltage module is controlled to generate a pulse voltage according to the voltage driving-away strategy to drive the living object away, and the second preset range is smaller than the first preset range.

[0011] Optionally, the expulsion system further includes an interference module, and the controller is in communication with the interference module; after the living object is expelled according to the voltage expulsion strategy, the method further includes:

[0012] When the living object is located within a third preset range around the vehicle body, gas is filled into the interference module to make the interference module present a preset shape to drive away the living object, and the third preset range is smaller than the second preset range.

[0013] Optionally, the driving away system further includes an image acquisition unit and a sensor trigger unit, and the sensor trigger unit is communicatively connected to the image acquisition unit and the controller respectively; and the acquiring of image data within a first preset range around the body of the vehicle includes:

[0014] When it is determined that there is a living object within the first preset range, an image acquisition signal is sent to the sensor trigger unit, so that the sensor trigger unit responds to the image acquisition signal and controls the image acquisition unit to acquire image data within the first preset range.

[0015] Optionally, the expulsion system further includes an infrared detection module, and the controller is in communication connection with the infrared detection module; and determining that there is a living object within the first preset range includes:

[0016] Collecting infrared signals of objects within the first preset range through the infrared detection module;

[0017] If the feature of the infrared signal is consistent with the feature characterizing the living object, it is determined that there is a living object within the first preset range.

[0018] In a second aspect, the present application provides a method for driving away a living object, which is applied to a processing module in an image processing system, wherein the processing module is communicatively connected to a driving away system in a vehicle, and the image processing system is located in a cloud server; the method comprises:

[0019] receiving image data within a first preset range around the vehicle body sent by the driving-away system, wherein the image data includes living objects within the first preset range;

[0020] Processing the image data to obtain the type of the living object;

[0021] generating a voltage drive-away strategy for the living object according to the type of the living object;

[0022] The voltage drive-away strategy is sent to the drive-away system, so that the drive-away system drives away the living object according to the voltage drive-away strategy.

[0023] Optionally, the processing the image data to obtain the type of the living object includes:

[0024] The image data is input into a preset liveness recognition model, and the type of the living object is determined according to an output result of the liveness recognition model, where the liveness recognition model is a pre-trained model for recognizing a variety of different types of living objects.

[0025] In a third aspect, the present application provides a living object expulsion device, which is applied to a controller in an expulsion system in a vehicle, wherein the controller is communicatively connected to an image processing system in a cloud server; the device comprises:

[0026] An acquisition module, configured to acquire image data within a first preset range around a body of the vehicle, wherein the image data includes living objects within the first preset range;

[0027] a first sending module, configured to send the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage driving away strategy for the living object according to the type of the living object;

[0028] A first receiving module, configured to receive the voltage drive-off strategy sent by the image processing system;

[0029] The first driving away module is used to drive away the living object according to the voltage driving away strategy.

[0030] Optionally, the driving-away system further includes a voltage module, the controller is in communication connection with the voltage module, and the first driving-away module includes:

[0031] The first control submodule is used to control the voltage module to generate a pulse voltage to drive away the living object according to the voltage drive-away strategy when the living object is located within a second preset range around the body of the vehicle, and the second preset range is smaller than the first preset range.

[0032] Optionally, the expulsion system further includes an interference module, the controller is communicatively connected with the interference module, and the device includes:

[0033] The second driving-away module is used to fill gas into the interference module so that the interference module presents a preset shape to drive away the living object when the living object is located within a third preset range around the body of the vehicle, and the third preset range is smaller than the second preset range.

[0034] Optionally, the expulsion system further includes an image acquisition unit and a sensor trigger unit, and the sensor trigger unit is communicatively connected to the image acquisition unit and the controller respectively; the acquisition module includes:

[0035] The second control submodule is used to send an image acquisition signal to the sensor trigger unit when it is determined that there is a living object within the first preset range, so that the sensor trigger unit responds to the image acquisition signal and controls the image acquisition unit to acquire image data within the first preset range.

[0036] Optionally, the second control submodule includes:

[0037] A collection submodule, used for collecting infrared signals of objects within the first preset range through the infrared detection module;

[0038] The first determination submodule is configured to determine that a living object exists within the first preset range if the feature of the infrared signal is consistent with the feature characterizing the living object.

[0039] In a fourth aspect, the present application provides a living object driving away device, which is applied to a processing module in an image processing system, wherein the processing module is communicatively connected with the driving away system in a vehicle, and the image processing system is located in a cloud server; the device comprises:

[0040] A second receiving module, configured to receive image data within a first preset range around the vehicle body sent by the driving away system, wherein the image data includes living objects within the first preset range;

[0041] A processing module, used for processing the image data to obtain the type of the living object;

[0042] A generating module, configured to generate a voltage driving-away strategy for the living object according to the type of the living object;

[0043] The second sending module is used to send the voltage driving away strategy to the driving away system, so that the driving away system drives away the living object according to the voltage driving away strategy.

[0044] Optionally, the processing module includes:

[0045] The second determination submodule is used to input the image data into a preset liveness recognition model, and determine the type of the living object according to the output result of the liveness recognition model, wherein the liveness recognition model is a pre-trained model for identifying a variety of different types of living objects.

[0046] In a fifth aspect, the present application provides an electronic device, including:

[0047] processor;

[0048] a memory for storing instructions executable by the processor;

[0049] The processor is configured to execute to implement the method for driving away a living object as described in the first aspect of the present application, or to implement the method for driving away a living object as described in the second aspect of the present application.

[0050] In a sixth aspect, the present application provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for expelling living objects as described in the first aspect of the present application, or to implement the method for expelling living objects as described in the second aspect of the present application.

[0051] In implementing the living object expulsion method of the present application, the controller in the expulsion system in the vehicle first obtains image data within a first preset range around the vehicle body, and the image data includes living objects within the first preset range. Then, the image data is sent to the image processing system located in the cloud server, so that the image processing system determines the type of the living object based on the image data, and generates a voltage expulsion strategy for the living object based on the type of the living object. Then, the controller receives the voltage expulsion strategy sent by the image processing system, and drives away the living object according to the voltage expulsion strategy. In the present application, the expulsion system on the vehicle side and the image processing system in the cloud server work together, aiming to achieve the expulsion purpose by providing voltage stimulation to the living objects around the vehicle, which can prevent the living objects from approaching the vehicle and avoid the living objects from causing damage or pollution to the vehicle, while avoiding the noise pollution or light pollution problems existing in traditional expulsion schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 is a flow chart of a method for driving away a living object shown in one embodiment of the present application;

[0054] Figure 2 is a system architecture diagram of a method for driving away a living object shown in an embodiment of the present application;

[0055] Figure 3 It is a structural block diagram of a living object driving away device shown in one embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] The living object expulsion method in the present application is applied to a controller in an expulsion system. The expulsion system is arranged on a vehicle, and the controller is communicatively connected with an image processing system in a cloud server. Figure 1 1 is a flow chart of a method for driving away a living object according to an embodiment of the present application. Figure 1 The living object expulsion method of the present application specifically includes the following steps:

[0058] Step S11: acquiring image data within a first preset range around a vehicle body, wherein the image data includes living objects within the first preset range.

[0059] In this embodiment, the first preset range can be set according to actual needs, for example, it can be set to a circular area with the vehicle body as the center and a radius of 4 meters.

[0060] Among them, living objects may include humans and animals.

[0061] In this embodiment, the driving away system further includes an image acquisition unit, which is responsible for acquiring image data within the first preset range and sending the image data to the controller.

[0062] Step S12: sending the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage driving strategy for the living object according to the type of the living object.

[0063] In this embodiment, the expulsion system further includes a first communication module, which is respectively connected to the controller and the image processing system for communication. After acquiring the image data, the controller can send the image data to the image processing system through the first communication module.

[0064] In a specific implementation, after the image acquisition unit acquires the image data within the first preset range, it can also directly send the acquired image data to the image processing system through the first communication module. In other words, after the image acquisition unit acquires the image data, it can directly send the image data to the image processing system through the first communication module, or send the image data to the image processing system through the controller and the first communication module in sequence. The specific method can be set according to actual needs, and this embodiment does not impose specific restrictions on this.

[0065] The image processing system is responsible for analyzing the image data, identifying the type of living objects in the image data, and generating a voltage drive-away strategy based on the type of living objects. In this embodiment, different types of living objects correspond to different voltage drive-away strategies. The voltage drive-away strategy is used to provide pulse voltage stimulation to the living objects, thereby achieving the purpose of drive-away. In this embodiment, the voltage drive-away strategy is generated only when the type of the living object belongs to the animal type. That is, the voltage drive-away strategy is mainly used to drive away animals, and the types of animals that can be driven away can be set according to actual needs, for example, mice, birds, etc.

[0066] After generating the voltage drive-off strategy, the image processing system sends the voltage drive-off strategy to the controller.

[0067] Step S13: receiving the voltage drive-off strategy sent by the image processing system.

[0068] Step S14: driving away the living object according to the voltage driving away strategy.

[0069] In this embodiment, after receiving the voltage drive-off strategy, the controller generates a pulse voltage according to the voltage drive-off strategy, thereby providing a pulse voltage stimulation to the living object, thereby achieving voltage drive-off of the living object.

[0070] In this embodiment, the expulsion system on the vehicle side collects image data (including living objects) around the vehicle body, and the image processing system in the cloud server analyzes the image data to obtain an expulsion strategy and sends the expulsion strategy to the expulsion system. The two work together to achieve the expulsion purpose. This application can prevent living objects from approaching the vehicle and avoid damage or pollution to the vehicle by living objects, while avoiding noise pollution or light pollution problems caused by traditional expulsion solutions. In addition, since the cloud server has powerful data analysis and processing performance, the image processing system can use advanced image processing technology for image processing, thereby improving the accuracy of the type recognition results of living objects and the accuracy of the final expulsion strategy, significantly improving the expulsion effect of living objects.

[0071] In combination with the above embodiments, in one implementation, the expulsion system further includes a voltage module, and the controller is in communication connection with the voltage module. On this basis, in step S14, the living object is expelled according to the voltage expulsion strategy, which specifically includes:

[0072] When the living object is located within a second preset range around the vehicle body, the voltage module is controlled to generate a pulse voltage to drive the living object away according to the voltage driving-away strategy, and the second preset range is smaller than the first preset range.

[0073] In this embodiment, after the controller receives the voltage drive-away strategy, it does not necessarily execute the voltage drive-away strategy immediately, but detects whether the living object is located within the second preset range around the vehicle body. If the living object is located within the second preset range, it means that the living object is close to the vehicle and the probability of causing damage to the vehicle or vehicle pollution is high. At this time, it is necessary to drive the living object away. Therefore, the present application can execute the drive-away strategy after determining that the living object is located within the second preset range, and stop executing the drive-away strategy until the living object is no longer within the second preset range.

[0074] In specific implementation, the distance between the living object and the vehicle can be determined by a radar device (such as a laser radar, a millimeter wave radar, etc.) installed on the vehicle, and then whether the living object is within the second preset range can be determined based on the distance. For example, when the second preset range is a circular area with the vehicle body as the center and a radius of 1 meter, if the distance value between the living object and the vehicle is 0.5 meters, it means that the living object is within the second preset range around the vehicle body.

[0075] In actual implementation, the distance between the living object and the vehicle may also be detected by other methods. This embodiment does not specifically limit the method for detecting the distance between the living object and the vehicle.

[0076] The voltage drive-off strategy includes voltage parameter information, and the voltage parameter information may include the magnitude of the output pulse voltage, the frequency of the output pulse voltage, etc. The specific voltage parameter information may be set according to actual needs.

[0077] In this embodiment, different types of living objects correspond to different voltage parameter information. The correspondence between the type of living object and the voltage parameter information can be pre-recorded in the drive-away information table. In this way, when generating a voltage drive-away strategy, the magnitude of the pulse voltage, the frequency of the output pulse voltage, and other information can be directly determined according to the drive-away information table.

[0078] In one implementation, if the voltage drive-off strategy includes the magnitude of the pulse voltage and the frequency of the output pulse voltage, then, according to the voltage drive-off strategy, controlling the voltage module to generate the pulse voltage may include:

[0079] According to the frequency of the output pulse voltage, the voltage control module outputs a pulse voltage that matches the magnitude of the pulse voltage.

[0080] It is understandable that when a living object approaches a vehicle and is stimulated by a pulse voltage, it will actively move away from the vehicle, so the present application can achieve the purpose of driving away living animals that are close to the vehicle.

[0081] It is particularly noted here that the pulse voltage released to the living animal objects in this application complies with various laws and regulations and will not cause harm to the living objects.

[0082] Through this embodiment, living objects approaching the vehicle can be effectively driven away to prevent the living objects from causing damage or pollution to the vehicle.

[0083] In combination with the above embodiments, in one implementation, in step S14, the living object is driven away according to the voltage driving away strategy, which may specifically include:

[0084] When the living object is located within a second preset range around the vehicle body and the living object stays within the second preset range for longer than a preset time, the voltage module is controlled to generate a pulse voltage according to the voltage drive-away strategy to drive the living object away, and the second preset range is smaller than the first preset range.

[0085] In some scenarios, some living objects may just be passing vehicles, and there is no need to drive them away. Therefore, in order to avoid mistakenly driving away living objects when passing vehicles, the present application can detect whether the length of time that the living object stays in the second preset range exceeds the preset time. If it does not exceed the preset time, it will not be driven away. On the contrary, if it exceeds the preset time, it will be driven away.

[0086] Through this embodiment, the scene where the living object needs to be driven away can be accurately identified, the accuracy of the operation of driving away the living object is improved, and the driving away effect is improved.

[0087] In combination with the above embodiments, in one implementation, the expulsion system further includes an interference module, and the controller is in communication connection with the interference module. On this basis, after the living object is expelled according to the expulsion strategy, the method of the present application may further include:

[0088] When the living object is within a third preset range around the vehicle body, gas is filled into the interference module to make the interference module present a preset shape to drive away the living object, and the third preset range is smaller than the second preset range.

[0089] The gas filled in may be nitrogen or other types of safe gas.

[0090] The interference module includes an inflatable interference strip and an inflation module. The interference strip can be installed near the four wheels of the vehicle body, or the front grille, or the rear tail throat, and the position of the interference strip can be set according to actual needs. When a living object enters the third preset range around the vehicle body, the inflation module is controlled to quickly fill nitrogen into the interference strip, thereby achieving the effect of driving away the living object.

[0091] The nitrogen in the present application can be obtained by air separation technology, for example, using an air separation device to separate oxygen, nitrogen and other gases in the air, and the separated nitrogen can be compressed and stored in a storage tank. As for liquid nitrogen, due to its smaller volume and higher density, it can be stored in a dedicated low-temperature liquid nitrogen tank for long-term storage and transportation.

[0092] When nitrogen needs to be quickly charged, the valve of the storage tank can be opened through the charging module, and then the nitrogen is delivered to the interference strip through the pressure reducer. The function of the pressure reducer is to reduce the pressure of nitrogen so that it can adapt to different application scenarios. If it is liquid nitrogen, it can be quickly converted into gaseous nitrogen and released through the gasification process. The gasification process can be achieved by heating the liquid nitrogen or exposing it to room temperature.

[0093] Through this embodiment, the living object can be driven away when the living object gets closer to the vehicle, thereby preventing the living object from getting close to the vehicle, avoiding the living object from causing damage or pollution to the vehicle, and improving the driving effect.

[0094] In combination with the above embodiments, in one implementation, the driving away system further includes an image acquisition unit and a sensor trigger unit, and the sensor trigger unit is respectively connected to the image acquisition unit and the controller for communication. On this basis, the image data within the first preset range around the vehicle body is obtained in step S11, which may specifically include:

[0095] When it is determined that there is a living object within the first preset range, an image acquisition signal is sent to the sensor trigger unit, so that the sensor trigger unit responds to the image acquisition signal and controls the image acquisition unit to acquire image data within the first preset range.

[0096] In this embodiment, the image data within the first preset range is collected by the image acquisition unit. In order to avoid the situation where the driving system is overloaded and the power consumption is high when the image acquisition unit works in real time, the sensor trigger unit controls whether the image acquisition unit works in this embodiment.

[0097] Specifically, if the sensor trigger unit receives an image acquisition signal sent by the controller, it controls the image acquisition unit to start working and acquire image data within a first preset range; if the sensor trigger unit does not receive the image acquisition signal sent by the controller, it controls the image acquisition unit to be in a closed state.

[0098] In actual implementation, the controller first determines whether there is a living object within the first preset range, and generates an image acquisition signal only when there is a living object.

[0099] In this embodiment, any method can be used to detect whether there is a living object within the first preset range.

[0100] The image acquisition unit includes multiple different types of cameras, which can be installed in different locations on the vehicle. For example, a forward-looking camera (used to capture road conditions ahead) can be installed in the middle of the roof, and a surround-view camera (also called a fisheye camera, used to provide a 360-degree panoramic view around the vehicle to enhance the vehicle's environmental perception capabilities) can be installed below the left and right rearview mirrors of the vehicle.

[0101] In actual implementation, the type and quantity of cameras and the installation position of each camera can be determined according to actual needs, and this embodiment does not impose any specific restrictions on this.

[0102] In this embodiment, the image acquisition unit acquires image data within the first preset range, thereby avoiding the situation where the drive system is overloaded and the power consumption is high when the image acquisition unit works in real time.

[0103] In combination with the above embodiments, in one implementation, the expulsion system further includes an infrared detection module, and the controller is in communication connection with the infrared detection module; determining whether there is a living object within the first preset range includes:

[0104] Collecting infrared signals of objects within a first preset range through an infrared detection module;

[0105] If the feature of the infrared signal is consistent with the feature characterizing the living object, it is determined that there is a living object within the first preset range.

[0106] In this embodiment, the infrared detection module includes an infrared sensor and a signal processing module. The infrared sensor can receive and respond to infrared radiation and convert the received infrared radiation into an electrical signal for output. The signal processing module is used to amplify, filter and process the electrical signal output by the infrared sensor. This application does not limit the type of infrared sensor, including but not limited to thermopile infrared sensor, pyroelectric infrared sensor, etc.

[0107] When detecting whether there is a living object in the first preset range, the infrared sensor is aligned with the first preset range and receives infrared radiation from various objects in the first preset range. If there are living objects (people, animals, etc.) in the first preset range, the infrared radiation emitted by these living objects will be received by the infrared sensor and converted into electrical signals. Then, the signal processing module analyzes and judges the electrical signal to determine whether there is a living object. If the signal characteristics match the infrared radiation characteristics of a known living object, it can be determined that there is a living object in the first preset range.

[0108] In actual implementation, it is also possible to determine whether there is a living object within the first preset range by other means. For example, a monitoring system with a liveness detection function can be installed on the vehicle. The monitoring system collects monitoring videos within the first preset range and determines whether there is a living object within the first preset range based on the built-in liveness detection function. For another example, a common monitoring system can be installed on the vehicle. The monitoring system collects monitoring videos within the first preset range and sends them to the controller. The controller analyzes the monitoring videos to determine whether there is a living object within the first preset range. The present application does not specifically limit the method for determining whether there is a living object within the first preset range.

[0109] Through this embodiment, it is possible to accurately detect whether there is a living object within the first preset range, and to ensure smooth implementation of the subsequent living object driving away method.

[0110] The following is a detailed description of the living object expulsion method of the present application from the image processing system side. The present application also provides another living object expulsion method, which is applied to a processing module in an image processing system, the processing module is communicatively connected to the expulsion system in the vehicle, and the image processing system is located in a cloud server. The method specifically includes the following steps:

[0111] Step S21: receiving image data within a first preset range around the vehicle body sent by the driving away system, wherein the image data includes living objects within the first preset range.

[0112] In this embodiment, the driving away system collects image data within the first preset range and sends the image data to the image processing system. The detailed description of the driving away system and the image data within the first preset range can be found in the above text, and this embodiment will not be repeated here.

[0113] Step S22: Process the image data to obtain the type of the living object.

[0114] In this embodiment, the image processing system can analyze the image data based on any existing image processing technology to obtain the type of the living object.

[0115] Step S23: generating a voltage drive-away strategy for the living object according to the type of the living object.

[0116] In this embodiment, according to the type of the living object, the voltage parameter information corresponding to the type is queried in the drive-away information table, and finally the voltage drive-away strategy is generated according to the voltage parameter information.

[0117] The image processing system is provided with a feature recognition module, a storage module and an analysis module, and the processing module generates a voltage drive-off strategy through the feature recognition module, the storage module and the analysis module.

[0118] Among them, the feature recognition module is used to determine the type of living objects according to the image data, the storage module is used to store the expulsion information table, the living object feature library, etc. The living object feature library is used to store the features corresponding to various different types of living objects. The feature recognition module uses the living object feature library when determining the type of living objects (matching the extracted features of the living objects with each feature in the living object feature library, and determining the type corresponding to the successfully matched features as the type of the living object to be identified), and the analysis module is used to generate a voltage expulsion strategy according to the type of the living object and the expulsion information table.

[0119] Step S24: sending the voltage drive-away strategy to the drive-away system, so that the drive-away system drives away the living object according to the voltage drive-away strategy.

[0120] In this embodiment, the image processing system further includes a second communication module. After obtaining the voltage drive-away strategy, the processing module sends the voltage drive-away strategy to the drive-away system through the second communication module. The drive-away system includes a controller and a drive-away module. After receiving the voltage drive-away strategy, the controller controls the drive-away module to execute the voltage drive-away strategy to drive away the living object. In one implementation, the image processing system can also directly send the voltage drive-away strategy to the drive-away module, and the drive-away module implements the voltage drive-away strategy.

[0121] The drive-away module may include a voltage module and an interference module. For the description of the voltage module and the interference module, please refer to the above text, which will not be described in detail in this embodiment.

[0122] In combination with the above embodiments, in one implementation, the image data is processed to obtain the type of the living object, including:

[0123] The image data is input into a preset liveness recognition model, and the type of the liveness object is determined according to the output result of the liveness recognition model. The liveness recognition model is a pre-trained model for recognizing a variety of different types of liveness objects.

[0124] The living body recognition model may be located in the feature recognition module.

[0125] The liveness recognition model in this embodiment can identify whether the live object is a person or an animal. If it is an animal, it can also identify the specific animal type. The liveness recognition model can adopt a variety of deep learning architectures, including but not limited to the following:

[0126] (1) Convolutional Neural Network (CNN): CNN is one of the most commonly used models in animal detection. Through structures such as convolutional layers, pooling layers, and fully connected layers, CNN can automatically extract features from images and perform classification. CNN has high accuracy and strong generalization ability in animal detection.

[0127] (2) Regional Convolutional Neural Network (R-CNN) and its improved versions: such as Fast R-CNN, Faster R-CNN, etc. These models introduce the Candidate Region Propagation Network (RPN) based on CNN, which can more accurately locate the animal area in the image and classify it, and are widely used in large-scale animal detection tasks.

[0128] (3) YOLO (You Only Look Once) series models: The YOLO model treats animal detection as a regression problem and obtains the location and category information of the animal through a single forward propagation. It has a fast detection speed and high accuracy and is suitable for real-time animal detection tasks.

[0129] (4) SSD (Single Shot MultiBox Detector) model: The SSD model combines the regression idea of ​​YOLO and the anchor mechanism of Faster R-CNN. It can make predictions on feature maps of different scales, thereby improving the accuracy and recall rate of animal detection.

[0130] In specific implementation, the liveness recognition model can be constructed by using any type of the above-mentioned architecture, or by using other architectures in the field of image recognition to construct a liveness recognition model.

[0131] The steps of training a liveness recognition model in this application generally include:

[0132] Step 1: Data collection. Collect a large amount of image data containing different animal categories. This data covers various scenes, angles, and lighting conditions to ensure the generalization ability of the trained model. At the same time, annotate the image data, that is, mark the location and category information of the animals in the image data.

[0133] Step 2: Data preprocessing. The collected image data is preprocessed, including image scaling, cropping, normalization and other steps to improve the training efficiency and accuracy of the model.

[0134] Step 3: Model construction. Select a suitable deep learning framework and algorithm to build a liveness recognition model. According to the task requirements and data characteristics, select a suitable model architecture and parameter settings. The model architecture can adopt any of the four model architectures mentioned above.

[0135] Step 4: Model training. The preprocessed image data is input into the model for training. During the training process, the parameters and weights of the model are adjusted so that the model can accurately identify the categories of different animals. Various optimization algorithms and regularization techniques in existing technologies can also be used during the training process to improve the performance and generalization ability of the model.

[0136] Step 5: Model evaluation. Use the test data set to evaluate the trained model. Evaluation indicators may include accuracy, recall, etc. Based on the evaluation results, the model can be further optimized and adjusted.

[0137] Step 6: Model deployment: Deploy the trained model to the image processing system of this application.

[0138] In the above training process, the following techniques can also be used:

[0139] (1) Data enhancement: Rotating, flipping, scaling, and other operations on the original image can generate more training samples and improve the generalization ability of the model.

[0140] (2) Transfer learning: Using a pre-trained deep learning model (such as a model trained on a large dataset such as ImageNet) as the initial model, and then fine-tuning it to accelerate the training process and improve the accuracy of the model.

[0141] (3) Multi-scale feature fusion: By fusing feature maps of different scales, the model’s ability to detect animals of different scales is improved.

[0142] (4) Difficult example mining: During the training process, focus on samples that are difficult to classify, and improve the model's ability to recognize these samples by increasing the weight of these samples or repeating the training.

[0143] In addition, other technologies besides the above four technologies may be used in the training process, and this embodiment does not impose any specific limitation on this.

[0144] Figure 2 This is a system architecture diagram of a method for driving away a living object according to an embodiment of the present application. Figure 2 , a complete embodiment is used to describe the living object expulsion method of the present application in detail.

[0145] exist Figure 2In the embodiment, a driving-away system is deployed on the vehicle, and an image processing system is deployed on the cloud server. The driving-away system includes a first communication module, a controller, an image acquisition unit, an infrared detection module, a sensor trigger unit, and a driving-away module. The image processing system includes a second communication module, a processing module, a feature recognition module, a storage module, and an analysis module. The second communication module is respectively connected to the first communication module and the driving-away module. The controller is respectively connected to the first communication module, the image acquisition unit, the sensor trigger unit, the infrared detection module, and the driving-away module. The processing module is respectively connected to the second communication module, the feature recognition module, the storage module, and the analysis module. The driving-away module includes a voltage module and an interference module.

[0146] Step 1: The infrared detection module performs real-time infrared detection of the environment around the vehicle body and determines whether there is a living object within a first preset range around the vehicle body. Once it is determined that there is a living object within the first preset range, a message is sent to the controller to inform the controller that there is a living object within the first preset range.

[0147] Step 2: The controller sends an image acquisition signal to the sensor trigger unit. After receiving the image acquisition signal, the sensor trigger unit controls the first image acquisition unit to acquire image data within a first preset range.

[0148] Step 3: After the first image acquisition unit acquires image data within the first preset range, the image data is sent to the controller, and then the controller sends the image data to the second communication module through the first communication module.

[0149] Step 4: The processing module obtains image data within the first preset range through the second communication module, inputs the image data into the living body recognition model in the feature recognition module, and determines the type of the living object through the living body recognition model.

[0150] Step 5: The analysis module generates a voltage drive-away strategy for the living object according to the type of the living object and the drive-away information table in the storage module.

[0151] Step 6: The processing module sends the voltage drive-away strategy obtained by the analysis module to the first communication module or the drive-away module through the second communication module, and the controller controls the drive-away module to execute the voltage drive-away strategy, or the drive-away module executes the voltage drive-away strategy.

[0152] Step 7: When the living object is located within a second preset range around the vehicle body, the controller controls the voltage module to generate a pulse voltage to drive away the living object according to the voltage drive-away strategy, and the second preset range is smaller than the first preset range. The drive-away strategy is not stopped until the living object leaves the second preset range.

[0153] Step 8: If a living object is detected entering a third preset range around the vehicle body, under the control of the controller, gas is filled into the interference module to make the interference module present a preset shape to drive away the living object, and the third preset range is smaller than the second preset range.

[0154] In the above steps, the distance between the living object and the vehicle body can be detected in any way to determine whether the living object is located in the second preset range or the third preset range. This embodiment does not impose specific restrictions on this. In the present application, the expulsion system on the vehicle side collects image data (including living objects) around the vehicle body, and the image processing system in the cloud server analyzes the image data to obtain an expulsion strategy and sends the expulsion strategy to the expulsion system. The two work together to achieve the expulsion purpose. The present application can prevent the living object from approaching the vehicle and avoid the living object from causing damage or pollution to the vehicle, while avoiding the noise pollution or light pollution problems caused by the traditional expulsion scheme. In addition, since the cloud server has powerful data analysis and processing performance, the image processing system can use advanced image processing technology for image processing, thereby improving the accuracy of the type recognition results of the living object and the accuracy of the final expulsion strategy, and significantly improving the expulsion effect of the living object.

[0155] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0156] Based on the same inventive concept, an embodiment of the present application provides a living object driving away device 300, which is applied to a controller in a driving away system in a vehicle, and the controller is connected to the image processing system in the cloud server for communication. Figure 3 , Figure 3 1 is a structural block diagram of a living object driving device according to an embodiment of the present application. Figure 3 As shown, the device 300 includes:

[0157] An acquisition module 301 is used to acquire image data within a first preset range around the body of the vehicle, wherein the image data includes living objects within the first preset range;

[0158] A first sending module 302, configured to send the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage drive-away strategy for the living object according to the type of the living object;

[0159] A first receiving module 303, configured to receive the voltage drive-off strategy sent by the image processing system;

[0160] The first driving away module 304 is configured to drive away the living object according to the voltage driving away strategy.

[0161] Optionally, the driving-away system further includes a voltage module, the controller is in communication connection with the voltage module, and the first driving-away module 304 includes:

[0162] The first control submodule is used to control the voltage module to generate a pulse voltage to drive away the living object according to the voltage drive-away strategy when the living object is located within a second preset range around the body of the vehicle, and the second preset range is smaller than the first preset range.

[0163] Optionally, the expulsion system further includes an interference module, the controller is communicatively connected with the interference module, and the device 300 includes:

[0164] The second driving-away module is used to fill gas into the interference module so that the interference module presents a preset shape to drive away the living object when the living object is located within a third preset range around the body of the vehicle, and the third preset range is smaller than the second preset range.

[0165] Optionally, the expulsion system further includes an image acquisition unit and a sensor trigger unit, and the sensor trigger unit is communicatively connected to the image acquisition unit and the controller respectively; the acquisition module 301 includes:

[0166] The second control submodule is used to send an image acquisition signal to the sensor trigger unit when it is determined that there is a living object within the first preset range, so that the sensor trigger unit responds to the image acquisition signal and controls the image acquisition unit to acquire image data within the first preset range.

[0167] Optionally, the second control submodule includes:

[0168] A collection submodule, used for collecting infrared signals of objects within the first preset range through the infrared detection module;

[0169] The first determination submodule is configured to determine that a living object exists within the first preset range if the feature of the infrared signal is consistent with the feature characterizing the living object.

[0170] Based on the same inventive concept, an embodiment of the present application provides a living object driving away device, which is applied to a processing module in an image processing system, wherein the processing module is communicatively connected with the driving away system in a vehicle, and the image processing system is located in a cloud server. The device includes:

[0171] A second receiving module, configured to receive image data within a first preset range around the vehicle body sent by the driving away system, wherein the image data includes living objects within the first preset range;

[0172] A processing module, used for processing the image data to obtain the type of the living object;

[0173] A generating module, configured to generate a voltage driving-away strategy for the living object according to the type of the living object;

[0174] The second sending module is used to send the voltage driving away strategy to the driving away system, so that the driving away system drives away the living object according to the voltage driving away strategy.

[0175] Optionally, the processing module includes:

[0176] The second determination submodule is used to input the image data into a preset liveness recognition model, and determine the type of the living object according to the output result of the liveness recognition model, wherein the liveness recognition model is a pre-trained model for identifying a variety of different types of living objects.

[0177] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0178] The present application also provides an electronic device, which includes:

[0179] processor;

[0180] a memory for storing instructions executable by the processor;

[0181] The processor is configured to execute to implement a method for driving away a living object as described in an embodiment of the present application.

[0182] The embodiment of the present application also provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute a method for removing a living object described in the embodiment of the present application.

[0183] 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 in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0184] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0185] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0187] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0188] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for driving away a living object, characterized in that: A controller used in a drive-away system, wherein the drive-away system is disposed on a vehicle, and wherein the controller is communicatively connected to an image processing system in a cloud server; the method comprises: Acquire image data within a first preset range around a body of the vehicle, wherein the image data includes a living object within the first preset range; Sending the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage drive-away strategy for the living object according to the type of the living object; receiving the voltage drive-off strategy sent by the image processing system; The living object is driven away according to the voltage drive-away strategy.

2. The method for driving away a living object according to claim 1, characterized in that: The expulsion system further includes a voltage module, and the controller is in communication with the voltage module; and the expulsion of the living object according to the voltage expulsion strategy includes: When the living object is located within a second preset range around the vehicle body, the voltage module is controlled to generate a pulse voltage according to the voltage driving-away strategy to drive the living object away, and the second preset range is smaller than the first preset range.

3. The method for driving away a living object according to claim 2, characterized in that: The expulsion system further includes an interference module, and the controller is communicatively connected with the interference module; After driving away the living object according to the voltage driving away strategy, the method further includes: When the living object is located within a third preset range around the vehicle body, gas is filled into the interference module to make the interference module present a preset shape to drive away the living object, and the third preset range is smaller than the second preset range.

4. The method for driving away a living object according to claim 1, characterized in that: The driving away system further includes an image acquisition unit and a sensor trigger unit, wherein the sensor trigger unit is respectively connected to the image acquisition unit and the controller for communication; the acquiring of image data within a first preset range around the vehicle body includes: When it is determined that there is a living object within the first preset range, an image acquisition signal is sent to the sensor trigger unit, so that the sensor trigger unit responds to the image acquisition signal and controls the image acquisition unit to acquire image data within the first preset range.

5. The method for driving away a living object according to claim 4, characterized in that: The expulsion system further includes an infrared detection module, and the controller is in communication with the infrared detection module; and determining that a living object exists within the first preset range includes: Collecting infrared signals of objects within the first preset range through the infrared detection module; If the feature of the infrared signal is consistent with the feature characterizing the living object, it is determined that there is a living object within the first preset range.

6. A method for driving away a living object, characterized in that: A processing module is applied to an image processing system, the processing module is in communication with a drive-away system in a vehicle, and the image processing system is disposed in a cloud server; the method comprises: receiving image data within a first preset range around the vehicle body sent by the driving-away system, wherein the image data includes living objects within the first preset range; Processing the image data to obtain the type of the living object; generating a voltage drive-away strategy for the living object according to the type of the living object; The voltage drive-away strategy is sent to the drive-away system, so that the drive-away system drives away the living object according to the voltage drive-away strategy.

7. The method for driving away a living object according to claim 6, characterized in that: The processing of the image data to obtain the type of the living object includes: The image data is input into a preset liveness recognition model, and the type of the living object is determined according to an output result of the liveness recognition model, where the liveness recognition model is a pre-trained model for recognizing a variety of different types of living objects.

8. A device for driving away a living object, characterized in that: A controller used in a drive-away system, wherein the drive-away system is disposed on a vehicle, and wherein the controller is communicatively connected to an image processing system in a cloud server; the device comprises: An acquisition module, configured to acquire image data within a first preset range around a body of the vehicle, wherein the image data includes living objects within the first preset range; a first sending module, configured to send the image data to the image processing system, so that the image processing system determines the type of the living object according to the image data, and generates a voltage driving away strategy for the living object according to the type of the living object; A first receiving module, configured to receive the voltage drive-off strategy sent by the image processing system; The first driving away module is used to drive away the living object according to the voltage driving away strategy.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement the living object driving away method according to any one of claims 1 to 5, or to implement the living object driving away method according to any one of claims 6 to 7.

10. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to implement the living object expulsion method as described in any one of claims 1 to 5, or implement the living object expulsion method as described in any one of claims 6 to 7.

Images