Animal repelling method, program product, electronic device and storage medium

Abstract

The invention relates to the technical field of vehicles, and particularly provides an animal repelling method, a program product, electronic equipment and a storage medium. The animal driving method comprises the following steps: determining a first animal detection result based on image acquisition data; determining a second animal detection result based on the radar scanning data; combining the first and second animal detection results to obtain a comprehensive detection result; determining a driving mode corresponding to the comprehensive detection result; and controlling the sound wave generator to emit a sound wave signal of the driving sound wave frequency corresponding to the driving mode. According to the animal driving method, the first animal detection result determined based on the image acquisition data and the second animal detection result determined based on the radar scanning data are synthesized, and the accuracy of the obtained comprehensive detection result is improved; and then sound wave signals with corresponding driving sound wave frequencies are sent based on the comprehensive detection result, so that accurate driving of animal types appearing around the vehicle is realized, and the driving efficiency of the animal types appearing around the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an animal driving method, a program product, an electronic device and a storage medium. Background Art

[0002] When vehicles are driving on the road, they often encounter some animals blocking the road. Usually, fences or signs are set up to prevent animals from crossing the road, or the driver is required to honk the horn to drive them away or get off the car to drive them away. However, fences or signs have low coverage and cannot play a road isolation effect for smaller animals; if the driver does not see the animal or sees the animal too late, the effect of honking the horn to drive away the animal may be poor or even hit the animal; and getting off the car to drive away the animal is unsafe and not suitable for most road conditions, and may cause safety hazards due to parking, affecting the user experience. Summary of the invention

[0003] In view of this, the purpose of the embodiments of the present application is to provide an animal repelling method, a program product, an electronic device and a storage medium to solve the technical problems of poor repelling effect and user experience of existing animal repelling methods.

[0004] In a first aspect, an embodiment of the present application provides an animal driving method, the method comprising:

[0005] Determine a first animal detection result based on the image acquisition data around the vehicle;

[0006] determining a second animal detection result based on the radar scanning data around the vehicle;

[0007] combining the first animal detection result and the second animal detection result to obtain a comprehensive detection result; wherein the comprehensive detection result includes at least one animal species;

[0008] Determining a driving-out mode corresponding to the comprehensive detection result; wherein the driving-out mode includes a driving-out sound wave frequency;

[0009] The sound wave generator is controlled to emit a sound wave signal of the driving sound wave frequency.

[0010] In the above implementation process, the animal repelling method determines the first animal detection result based on the image acquisition data around the vehicle; determines the second animal detection result based on the radar scanning data around the vehicle; combines the first animal detection result and the second animal detection result to obtain a comprehensive detection result; determines the repelling mode corresponding to the comprehensive detection result; wherein the repelling mode includes the repelling sound wave frequency; controls the sound wave generator to emit a sound wave signal of the repelling sound wave frequency. The animal repelling method combines the first animal detection result determined based on the image acquisition data and the second animal detection result determined based on the radar scanning data, thereby improving the accuracy of the obtained comprehensive detection result; and then controls the sound wave generator to emit a sound wave signal of the repelling sound wave frequency corresponding to the animal species in the comprehensive detection result, thereby realizing the precise repelling of the animal species appearing around the vehicle, and improving the repelling efficiency of the animal species appearing around the vehicle. Based on the animal repelling method provided by the present application, better animal repelling effect and user experience can be obtained, which solves the technical problems of poor repelling effect and user experience of the existing animal repelling method.

[0011] Optionally, in an embodiment of the present application, the first animal detection result includes multiple first animal species and the confidence level of each first animal species; determining the first animal detection result based on the image acquisition data around the vehicle includes: performing feature extraction on the image acquisition data to obtain feature extraction data; and using a classifier to classify the feature extraction data to determine the multiple first animal species and the confidence level of each first animal species.

[0012] In the above implementation process, the first animal detection result corresponding to the image acquisition data can be determined simply and efficiently based on the classifier. And because the first animal detection result includes multiple first animal species and the confidence of each first animal species, when the highest confidence of the first animal species meets the preset confidence condition, the animal species appearing around the vehicle can be accurately determined based on the first animal detection result, so as to realize efficient expulsion of the appearing animal species.

[0013] Optionally, in an embodiment of the present application, the first animal detection result and the second animal detection result are combined to obtain a comprehensive detection result, including: when the highest confidence of the first animal species is greater than or equal to a confidence threshold, determining the comprehensive detection result based on the first animal species whose confidence is greater than the confidence threshold; when the confidence of each of the first animal species is less than the confidence threshold, fusing the first animal detection result and the second animal detection result to obtain the comprehensive detection result.

[0014] In the above implementation process, when the highest confidence of the first animal species is greater than or equal to the confidence threshold, it means that the accuracy of the first animal detection result is high, and the animal species appearing around the vehicle can be accurately determined based on the first animal detection result, that is, the comprehensive detection result. When the confidence of each first animal species is less than the confidence threshold, it means that the accuracy of the first animal detection result is low, and the first animal detection result and the second animal detection result are fused to improve the accuracy of the obtained comprehensive detection result; based on the comprehensive detection result, the animal species that appear can be efficiently driven away, and a better animal driving effect can be obtained.

[0015] Optionally, in an embodiment of the present application, the driving mode further includes driving sound wave intensity and sound wave duration; the determining the driving mode corresponding to the comprehensive detection result includes: determining the driving mode corresponding to the comprehensive detection result based on a trained pattern matching model; wherein the comprehensive detection result further includes at least one of the detection position, detection movement route, detection movement speed and surrounding road conditions of each animal species;

[0016] Before determining the driving pattern corresponding to the comprehensive detection result based on the trained pattern matching model, the method also includes: obtaining driving data of multiple animals corresponding to different driving patterns; wherein the driving data includes animal position, driving route, driving movement speed and road conditions; preprocessing the driving data to obtain preprocessed data; extracting features from the preprocessed data to obtain driving training feature data; obtaining effective training feature data from the driving training feature data based on principal component analysis; inputting the effective training feature data into the pattern matching model to be trained to obtain the training matching pattern output by the pattern matching model to be trained; optimizing the internal parameters of the pattern matching model to be trained based on the effective driving pattern corresponding to the driving data and the training matching pattern to obtain the trained pattern matching model.

[0017] In the above implementation process, through the trained pattern matching model, the driving away mode corresponding to the comprehensive detection results can be more accurately determined according to the detection position, detection movement route, detection movement speed and / or surrounding road conditions of each animal species, so as to obtain better animal driving away effect.

[0018] Optionally, in an embodiment of the present application, the comprehensive detection result also includes the animal's position; before the control sound wave generator emits the sound wave signal of the driving sound wave frequency, the method also includes: adjusting the emission angle of the sound wave generator according to the vehicle's driving direction and the animal's position.

[0019] In the above implementation process, by adjusting the emission angle of the sound wave generator according to the vehicle's driving direction and the animal's position, the effective range of the sound wave signal emitted by the sound wave generator can be increased. When the coverage angle of the sound wave signal is constant, a better animal repelling effect can be obtained.

[0020] Optionally, in an embodiment of the present application, the comprehensive detection result also includes the animal's movement trajectory; the controlling the sound wave generator to emit the sound wave signal of the driving sound wave frequency includes: determining whether the animal is in the vehicle's driving area based on the vehicle's navigation path and the animal's movement trajectory; and when the animal is in the vehicle's driving area, controlling the sound wave generator to emit the sound wave signal of the driving sound wave frequency.

[0021] In the above implementation process, when animals are in the vehicle driving area, the sound wave generator is controlled to emit a sound wave signal with a repelling sound wave frequency, which can ensure the animal repelling effect while reducing the impact on surrounding animals and the natural ecological environment.

[0022] Optionally, in an embodiment of the present application, the sound wave generator is installed in the front bumper area of ​​the vehicle; the expulsion mode also includes expulsion lights; after determining the expulsion mode corresponding to the comprehensive detection result, the method also includes: controlling the vehicle lighting system to emit the expulsion lights.

[0023] In the above implementation process, the animal's repelling response can be enhanced by using sound wave signals and repelling lights, thereby obtaining a better animal repelling effect.

[0024] In a second aspect, an embodiment of the present application provides a computer program product, which, when executed by a processor, implements the animal driving method as described in any one of the first aspects above.

[0025] In a third aspect, an embodiment of the present application further provides an electronic device; the electronic device includes:

[0026] Memory;

[0027] processor;

[0028] The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the animal driving method as described in any one of the first aspects above is performed.

[0029] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the animal repelling method as described in any one of the above-mentioned first aspects is executed.

[0030] In a fifth aspect, an embodiment of the present application also provides an animal repelling device, which includes: an image detection unit, used to determine a first animal detection result based on image acquisition data around a vehicle; a radar detection unit, used to determine a second animal detection result based on radar scanning data around the vehicle; a comprehensive detection result determination unit, used to combine the first animal detection result and the second animal detection result to obtain a comprehensive detection result; wherein the comprehensive detection result includes at least one animal species; a repelling mode determination unit, used to determine a repelling mode corresponding to the comprehensive detection result; wherein the repelling mode includes a repelling sound wave frequency; a sound wave repelling unit, used to control a sound wave generator to emit a sound wave signal of the repelling sound wave frequency.

[0031] The beneficial effects of the present application include at least: the animal repelling method combines the first animal detection result determined based on the image acquisition data and the second animal detection result determined based on the radar scanning data, thereby improving the accuracy of the comprehensive detection result obtained; and then controlling the sound wave generator to emit a sound wave signal of a repelling sound wave frequency corresponding to the animal species in the comprehensive detection result, thereby achieving accurate repelling of the animal species appearing around the vehicle, thereby improving the efficiency of repelling the animal species appearing around the vehicle. The animal repelling method provided by the present application can obtain better animal repelling effect and user experience, solving the technical problems of poor repelling effect and user experience of the existing animal repelling methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic diagram of a process of an animal driving method provided in an embodiment of the present application;

[0034] Figure 2 A flowchart of a method for determining a comprehensive detection result provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following embodiments of the technical solution of the present application will be described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0038] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0039] See also Figure 1 The flowchart of an animal driving method provided by an embodiment of the present application is shown. The animal driving method may include the following steps:

[0040] S101. Determine a first animal detection result based on image acquisition data around a vehicle.

[0041] S102: Determine a second animal detection result based on the radar scanning data around the vehicle.

[0042] S103. Combining the first animal detection result and the second animal detection result to obtain a comprehensive detection result; wherein the comprehensive detection result includes at least one animal species.

[0043] S104, determining a driving-away mode corresponding to the comprehensive detection result; wherein the driving-away mode includes a driving-away sound wave frequency.

[0044] S105, controlling the sound wave generator to emit a sound wave signal of the driving sound wave frequency.

[0045] Wherein, in step 101, a high-definition camera or a camera with high resolution and low light sensitivity (for example, a low-light camera) can be used to collect image acquisition data around the vehicle. Based on the low-light camera, it can be ensured that the image data in front of the vehicle can be clearly captured both during the day and at night. The image acquisition data can be processed by an image processing algorithm (including image denoising, image transformation, image analysis, image compression, image enhancement, and image blur processing, etc.) to determine the first animal detection result; the image acquisition data can also be identified by training a corresponding image recognition model to determine the first animal detection result. Exemplarily, the acquired image acquisition data can be input into a pre-trained first recognition model to obtain a first recognition result corresponding to the image to be identified (based on the first recognition result, it can be determined whether there is an animal in the image to be identified); when it is determined that there is an animal in the image to be identified, the image acquisition data is input into a pre-trained second recognition model to obtain a second recognition result corresponding to the image to be identified; wherein the second recognition result includes the identified animal species; and then the first animal detection result is determined based on the first recognition result and the second recognition result. The first animal detection result may include no animal identified, may include at least one first animal species, and may also include a confidence level corresponding to the first animal species. The first animal detection result may also include animal image processing data after image denoising, image enhancement and / or image blurring.

[0046] Among them, in step 102, a radar detection device can be used to collect radar scanning data around the vehicle; specifically, a millimeter wave radar with good penetration in different weather conditions can be used to collect radar scanning data around the vehicle to improve the accuracy of the acquired radar scanning data. It is also possible to set a fan-shaped or cone-shaped scanning mode to ensure that the radar detection device can fully detect the radar scanning data around the vehicle to improve the accuracy of the second animal detection result determined based on the radar scanning data. The second animal detection result may include at least one second animal species, and may also include a confidence level corresponding to the second animal species. The second animal detection result may also include animal radar processing data processed by digital signal processing technology (e.g., filtering, denoising and / or target tracking).

[0047] Wherein, in step 103, when the first animal detection result includes at least one first animal species and a confidence level corresponding to the first animal species, and the second animal detection result includes at least one second animal species and a confidence level corresponding to the second animal species, at least one animal species can be determined based on the confidence level corresponding to the first animal species and the confidence level corresponding to the second animal species, and used as a comprehensive detection result. When the first animal detection result includes animal image processing data after image denoising, image enhancement and / or image blurring, and the second animal detection result includes animal radar processing data after filtering, denoising and / or target tracking, the animal image processing data and the animal radar processing data can be fused based on a fusion algorithm, and a comprehensive detection result can be determined through a multi-sensor data fusion algorithm. Exemplarily, the animal image processing data and the animal radar processing data can be fused based on a weighted average algorithm or a Kalman filter algorithm to determine a comprehensive detection result. Taking the weighted average algorithm as an example, the method can be used to (Among them, Y 1 represents animal image processing data, Y 2 represents the animal radar processing data, a represents the confidence of the first animal species corresponding to the animal image processing data, and b represents the confidence of the second animal species corresponding to the animal radar processing data) to determine the comprehensive detection data Y z , and based on deep learning algorithms, etc., the comprehensive detection data is analyzed to obtain the corresponding comprehensive detection results; wherein, when the first animal detection result includes multiple first animal species and corresponding confidences, a can represent the sum of multiple first animal species and corresponding confidences, or it can be the maximum confidence value among multiple first animal species and corresponding confidences; when the second animal detection result includes multiple second animal species and corresponding confidences, b can represent the sum of multiple second animal species and corresponding confidences, or it can be the maximum confidence value among multiple second animal species and corresponding confidences. Optionally, the audio data emitted by the surrounding animals can also be collected, the audio data can be extracted, and the comprehensive detection results can be comprehensively determined by combining the extracted audio features such as audio frequency, amplitude, duration, etc.

[0048] Wherein, in step 104, the driving mode corresponding to the comprehensive detection result can be determined according to the preset optimal sound wave frequency range corresponding to a plurality of animal species. The driving mode corresponding to the comprehensive detection result can also be determined according to the correspondence between the preset different animal species and the preset driving mode. The driving mode corresponding to the different comprehensive detection results can also be preset, and then the most suitable driving mode can be determined according to at least one animal species included in the comprehensive detection result. Field experiments can be first conducted in a highway environment or a natural area similar to a highway environment, using sound waves of different frequencies to drive the corresponding animals, observe and record the escape reaction of the animals, and determine the driving effect of sound waves of different frequencies on the corresponding animals according to the data such as the escape speed, escape distance, residence time and escape route of the animals. The optimal sound wave frequency range corresponding to different animal species can be determined by analyzing the experimental data. Exemplarily, animal species may include mice (corresponding to an optimal sound wave frequency range of 20khz-50khz), dogs (corresponding to an optimal sound wave frequency range of 20khz-40khz), deer (corresponding to an optimal sound wave frequency range of 20khz-30khz), cats (corresponding to an optimal sound wave frequency range of 25khz-40khz) and rabbits (corresponding to an optimal sound wave frequency range of 25khz-60khz), etc. When the comprehensive detection results include mice and dogs, a driving mode with a driving sound wave frequency within the range of 20khz-40khz may be selected; when the comprehensive detection results include deer and cats, a driving mode with a driving sound wave frequency within the range of 25khz-30khz may be selected.

[0049] Among them, in step 105, by controlling the sound wave generator to emit a sound wave signal of a driving-away sound wave frequency, the detected animal species can be driven away to reduce the safety hazard caused by the appearance of animals in the middle of the road.

[0050] It can be seen that the animal repelling method provided in the embodiment of the present application combines the first animal detection result determined based on the image acquisition data and the second animal detection result determined based on the radar scanning data, thereby improving the accuracy of the obtained comprehensive detection result; and then by controlling the sound wave generator to emit a sound wave signal of a repelling sound wave frequency corresponding to the animal species in the comprehensive detection result, the animal species appearing around the vehicle can be accurately repelled, thereby improving the efficiency of repelling the animal species appearing around the vehicle. Based on the animal repelling method provided by the present application, better animal repelling effect and user experience can be obtained, solving the technical problems of poor repelling effect and user experience of the existing animal repelling methods.

[0051] In some optional embodiments, the first animal detection result includes multiple first animal species and the confidence level of each first animal species; S101, determining the first animal detection result based on image acquisition data around the vehicle, including: performing feature extraction on the image acquisition data to obtain feature extraction data; using a classifier to classify the feature extraction data to determine the multiple first animal species and the confidence level of each first animal species.

[0052] Among them, feature extraction methods such as principal component analysis, feature importance assessment or scale-invariant feature transformation can be used to extract features from image acquisition data to obtain feature extraction data (specifically, feature data such as the shape, size, texture, and movement pattern of the animal). Taking principal component analysis as an example, the mean of each feature in the image acquisition data can be calculated first; the image acquisition data can be decentralized according to the mean (the feature value minus the mean of the corresponding feature) to obtain the decentralized feature value X c ;based on Calculate and decentralize the eigenvalue X c The corresponding covariance matrix σ; where m refers to the number of image acquisition data, Represents the decentralized characteristic value X c The transposed matrix of the covariance matrix is ​​obtained by performing eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​and corresponding eigenvectors; and the eigenvectors corresponding to the first K eigenvalues ​​are selected as feature extraction data; wherein the specific value of K may be 3, 5 or other reasonable values. The classifier may be implemented by a support vector machine SVM or a decision tree, etc., and the feature extraction data is classified and processed by the classifier to determine multiple first animal species and the confidence level of each first animal species. When the confidence level is high, the animal species appearing around the vehicle may be directly determined based on the first animal detection result; when the confidence level is low, a comprehensive judgment may be made in combination with the radar scanning data, so as to realize the accurate expulsion of the animal species appearing around the vehicle based on the comprehensive detection results, thereby improving the efficiency of expelling the animal species appearing around the vehicle.

[0053] Please refer to Figure 2 , Figure 2 A flowchart of a method for determining a comprehensive detection result provided in an embodiment of the present application.

[0054] In some optional embodiments, the combination of the first animal detection result and the second animal detection result to obtain a comprehensive detection result includes: S201, when the highest confidence of the first animal species is greater than or equal to the confidence threshold, determining the comprehensive detection result based on the first animal species whose confidence is greater than the confidence threshold; S202, when the confidence of each of the first animal species is less than the confidence threshold, fusing the first animal detection result and the second animal detection result to obtain the comprehensive detection result.

[0055] Among them, the confidence threshold can be 80%, or 85% or other reasonable values. When the highest confidence of the first animal species is greater than or equal to the confidence threshold, it means that the accuracy of the first animal detection result is high, and the animal species appearing around the vehicle can be accurately determined based on the first animal detection result, that is, the comprehensive detection result. When the confidence of each first animal species is less than the confidence threshold, it means that the accuracy of the first animal detection result is low. The first animal detection result and the second animal detection result are fused to improve the accuracy of the obtained comprehensive detection result; based on the comprehensive detection result, efficient expulsion of the animal species that appear can be achieved, and better animal expulsion effect can be obtained.

[0056] In some optional embodiments, the expulsion mode further includes expulsion sound wave intensity and sound wave duration; S104, determining the expulsion mode corresponding to the comprehensive detection result, including: determining the expulsion mode corresponding to the comprehensive detection result based on the trained pattern matching model;

[0057] Wherein, the comprehensive detection result also includes at least one of the detected position, detected moving route, detected moving speed and surrounding road conditions of each animal species; before determining the driving mode corresponding to the comprehensive detection result based on the trained pattern matching model, the method also includes: obtaining driving data of multiple animals corresponding to different driving modes; wherein the driving data includes animal position, driving route, driving moving speed and road conditions; preprocessing the driving data to obtain preprocessed data; extracting features from the preprocessed data to obtain driving training feature data; obtaining effective training feature data from the driving training feature data based on principal component analysis; inputting the effective training feature data into the pattern matching model to be trained to obtain the training matching mode output by the pattern matching model to be trained; optimizing the internal parameters of the pattern matching model to be trained based on the effective driving mode corresponding to the driving data and the training matching mode to obtain the trained pattern matching model.

[0058] Wherein, a plurality of different sound wave frequency ranges can be pre-set according to the optimal sound wave frequency range corresponding to different animal species. The sound wave frequencies, sound wave intensities or sound wave durations included in different driving modes are different. The parameters such as the sound wave emission power or the sound wave emission interval can be changed to switch different sound wave intensities for driving away. Since the comprehensive detection result also includes at least one of the detection position, detection moving route, detection moving speed and surrounding road conditions of each animal species, the comprehensive detection result can be input into the trained pattern matching model, and then the corresponding driving mode can be determined more accurately based on the trained pattern matching model, so as to realize the accurate driving away of the animal species appearing around the vehicle. Through field experiments, in the natural area of ​​the highway environment or the highway-like environment, the sound waves with different frequencies, intensities or durations can be used to drive away the corresponding animals, observe and record the escape reaction of the animals, and determine the driving data of the various animals corresponding to the different driving modes according to the data such as the escape speed, escape distance, residence time and escape route of the animals. The expulsion data can be pre-processed by data cleaning (to delete or correct invalid or abnormal data points), data denoising (can be achieved by filtering algorithms, such as Gaussian filtering and median filtering), and normalization processing, and then feature extraction is performed on the pre-processed data to obtain expulsion training feature data. The expulsion training feature data may include at least one of the training animal species and the training position, training moving route, training moving speed, or training road conditions corresponding to the training animal species. Through the trained pattern matching model, the expulsion mode corresponding to the comprehensive detection result can be more accurately determined based on the data such as the detection position, detection moving route, detection moving speed, and / or surrounding road conditions of each animal species, so as to obtain a better animal expulsion effect.

[0059] The preprocessed data may also be divided into a training set, a validation set, and a test set. The training set is used to train the pattern matching model to be trained, the validation set is used to optimize the internal parameters of the pattern matching model to be trained, and a trained pattern matching model is obtained, and then the performance of the trained pattern matching model is tested through the test set.

[0060] Optionally, the internal parameters of the pattern matching model to be trained can be optimized by cross-validation. The training set, validation set and test set obtained by the above division can be used in turn as a test set for "testing the performance of the trained pattern matching model", and the remaining two sets can be used as a training set for "training the pattern matching model to be trained" and a validation set for "optimizing the internal parameters of the pattern matching model to be trained", and the training and optimization process of the model can be repeated many times to obtain a pattern matching model with better performance.

[0061] In some optional embodiments, the comprehensive detection result also includes the animal's position; before S105, controlling the sound wave generator to emit the sound wave signal of the driving sound wave frequency, the method also includes: adjusting the emission angle of the sound wave generator according to the vehicle's driving direction and the animal's position.

[0062] Among them, the animal orientation may include orientation data between the animal and the current position of the vehicle. Specifically, the sound wave emission deflection angle (the angle between the animal orientation and the vehicle's driving direction) can be determined according to the vehicle's driving direction and the animal's orientation, and the emission angle of the sound wave generator can be adjusted according to the sound wave emission deflection angle. Exemplarily, when the vehicle's driving direction and the animal's orientation are consistent, the emission angle of the sound wave generator can be adjusted within [-5°, +5°]; wherein, the direction of the sound wave signal emitted by the emission angle of 0° is consistent with the vehicle's driving direction; when the angle between the animal's orientation and the vehicle's driving direction is -30°, the emission angle of the sound wave generator can be adjusted to [-35°, -25°]. By adjusting the emission angle of the sound wave generator according to the vehicle's driving direction and the animal's orientation, the effective range of the sound wave signal emitted by the sound wave generator can be increased, and when the sound wave signal has a certain coverage angle, a better animal repelling effect can be obtained. In addition, by limiting the sound wave emission angle range of the sound wave generator to within 10°, the impact of the emitted sound wave signal on surrounding animals and the natural ecological environment can be reduced; it is also possible to increase the effective distance of the emitted sound wave signal while keeping the total sound wave emission power constant, thereby further obtaining a better animal repelling effect.

[0063] In some optional embodiments, the comprehensive detection result also includes the animal's movement trajectory; S105, controlling the sound wave generator to emit the sound wave signal of the driving sound wave frequency, including: determining whether the animal is in the vehicle's driving area based on the vehicle's navigation path and the animal's movement trajectory; when the animal is in the vehicle's driving area, controlling the sound wave generator to emit the sound wave signal of the driving sound wave frequency.

[0064] The vehicle navigation path can be the current navigation path of the navigation software bound to the vehicle, or the current navigation path on the vehicle's onboard system; the vehicle navigation path can also be determined according to the specified driving direction of the current road section. It can be determined whether the animal is in the vehicle's driving area based on the vehicle navigation path and the animal's movement trajectory; if the animal is in the vehicle's driving area, the sound wave generator is controlled to emit a sound wave signal of a repelling sound wave frequency, which can ensure the animal repelling effect while reducing the impact on the surrounding animals and the natural ecological environment.

[0065] In some optional embodiments, the sound wave generator is installed in the front bumper area of ​​the vehicle; the expulsion mode also includes expulsion lights; after S104, determining the expulsion mode corresponding to the comprehensive detection result, the method also includes: controlling the vehicle lighting system to emit the expulsion lights.

[0066] Among them, the animal's repelling reaction can be enhanced by sound wave signals and repelling lights, and the synergistic effect of the two can achieve a better animal repelling effect. By installing the sound wave generator in the front bumper area of ​​the vehicle, it is ensured that the sound waves emitted can cover the area in front of the vehicle; and then during the driving process of the vehicle, the sound waves are used to repel animals that appear in front of the vehicle, reducing the safety hazards caused by animals appearing in the middle of the road.

[0067] In some optional embodiments, a driving mode indicator light may be provided on the vehicle, so that the driver can understand the current driving mode through the driving mode indicator light and manually adjust the driving mode according to the current driving mode and the actual driving situation, thereby improving the practicality of the animal driving method.

[0068] Please refer to Figure 3 , Figure 3 The electronic device 300 is a schematic diagram of a structure of an electronic device 300 provided in an embodiment of the present application. The electronic device 300 comprises: a memory 302 and a processor 301; the memory 302 stores a computer program executable by the processor 301, and when the computer program is executed by the processor 301, the animal repelling method described in any one of the first aspects is executed.

[0069] The memory 302 and the processor 301 can be interconnected and communicate with each other via a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301, and when the computer program is executed by the processor 301, the animal driving method described in the first aspect above is executed.

[0070] The embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by the processor 301, the animal driving method described in the first aspect above is executed.

[0071] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0072] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device / system and method can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0073] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0074] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. A method for driving away animals, characterized in that: The method comprises: Determine a first animal detection result based on the image acquisition data around the vehicle; determining a second animal detection result based on the radar scanning data around the vehicle; combining the first animal detection result and the second animal detection result to obtain a comprehensive detection result; wherein the comprehensive detection result includes at least one animal species; Determining a driving mode corresponding to the comprehensive detection result; wherein the driving mode includes a driving sound wave frequency; The sound wave generator is controlled to emit a sound wave signal of the driving sound wave frequency.

2. The method according to claim 1, characterized in that in, The first animal detection result includes a plurality of first animal types and a confidence level of each first animal type; The step of determining a first animal detection result based on image acquisition data around the vehicle includes: Performing feature extraction on the image acquisition data to obtain feature extraction data; A classifier is used to classify the feature extraction data to determine the plurality of first animal species and the confidence level of each of the first animal species.

3. The method according to claim 2, characterized in that in, The combining the first animal detection result and the second animal detection result to obtain a comprehensive detection result includes: In a case where the highest confidence of the first animal species is greater than or equal to a confidence threshold, determining the comprehensive detection result based on the first animal species having a confidence greater than the confidence threshold; In the case where the confidence level of each of the first animal species is less than the confidence level threshold, the first animal detection result and the second animal detection result are fused to obtain the comprehensive detection result.

4. The method according to claim 1, characterized in that: in, The expulsion mode also includes the expulsion sound wave intensity and the sound wave duration; The step of determining the driving mode corresponding to the comprehensive detection result includes: Based on the trained pattern matching model, determining a driving pattern corresponding to the comprehensive detection result; The comprehensive detection result further includes at least one of the detected position, detected movement route, detected movement speed and surrounding road conditions of each of the animal species; Before determining the expulsion pattern corresponding to the comprehensive detection result based on the trained pattern matching model, the method further includes: Acquire driving data of multiple animals corresponding to different driving modes; wherein the driving data includes animal location, driving route, driving movement speed and road conditions; Preprocessing the expulsion data to obtain preprocessed data; Extracting features from the preprocessed data to obtain driving training feature data; Acquire effective training feature data from the driving training feature data based on principal component analysis; Inputting the effective training feature data into the pattern matching model to be trained, and obtaining the training matching pattern output by the pattern matching model to be trained; Based on the effective expulsion pattern corresponding to the expulsion data and the training matching pattern, the internal parameters of the pattern matching model to be trained are optimized to obtain the trained pattern matching model.

5. The method according to claim 1, characterized in that in, The comprehensive detection result also includes the animal's position; Before the control sound wave generator emits the sound wave signal of the driving sound wave frequency, the method further includes: The emission angle of the sound wave generator is adjusted according to the driving direction of the vehicle and the orientation of the animal.

6. The method according to claim 1, characterized in that in, The comprehensive detection results also include animal movement tracks; The controlling sound wave generator to emit the sound wave signal of the driving sound wave frequency comprises: Determining whether the animal is within the vehicle's travel area based on the vehicle's navigation path and the animal's movement trajectory; When an animal is in the vehicle driving area, the sound wave generator is controlled to emit a sound wave signal of the driving sound wave frequency.

7. The method according to any one of claims 1 to 6, characterized in that: in, The sound wave generator is installed in the front bumper area of ​​the vehicle; the driving mode also includes driving lights; After determining the driving mode corresponding to the comprehensive detection result, the method further includes: The vehicle lighting system is controlled to emit the driving-away light.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

9. An electronic device, characterized in that: The electronic device comprises: Memory; processor; The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images