Vehicle collision detection method and device, vehicle, storage medium and program product

Abstract

The invention provides a vehicle collision detection method and device, a vehicle, a storage medium and a program product, and relates to the technical field of vehicles, the method comprises the following steps: obtaining audio information inside and outside the vehicle, and obtaining first collision information according to the audio information; then acquiring external environment information of the vehicle, and acquiring second collision information according to the external environment information; and according to the first rubbing information and the second rubbing information, rubbing analysis is carried out, and a rubbing detection result is obtained. According to the method and the device, two different data of the audio information and the external environment information are fused, and the first rubbing information and the second rubbing information are integrated for rubbing detection, so that rubbing can be evaluated more comprehensively, and the accuracy of rubbing detection is improved. Besides, the audio information and the external environment information can also be acquired under the condition of slight collision, so that the method and the device are not influenced by the degree of collision, the slight collision can be detected, and the collision condition of the vehicle can be reported in time.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vehicles, and in particular, to a vehicle collision detection method, apparatus, vehicle, storage medium, and program product. Background Art

[0002] A driverless vehicle relies on various sensors to perceive the surrounding environment and road information, and can automatically plan a route and drive autonomously without manual operation. Currently, during the process of a driverless vehicle driving on the road, a collision detection and airbag system is usually used to detect collision events. However, the airbag needs a relatively severe collision to pop out. Therefore, it is difficult to sense relatively minor collisions. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a vehicle collision detection method, apparatus, vehicle, storage medium, and program product.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a vehicle collision detection method, the method including: obtaining audio information inside and / or outside the vehicle, and obtaining audio feature information according to the audio information, where the audio feature information includes a decibel value and / or a sound attenuation degree; determining audio information to be detected according to the audio feature information; obtaining first collision information according to the audio information to be detected; obtaining external environment information of the vehicle, and obtaining second collision information according to the external environment information; and obtaining a collision detection result according to the first collision information and the second collision information.

[0005] Optionally, the audio feature information includes a decibel value, and determining the audio information to be detected according to the audio information includes: determining the audio information to be the audio information to be detected according to the audio information if the decibel value is greater than a preset decibel value.

[0006] Optionally, the audio feature information includes a decibel value, and determining the audio information to be detected according to the audio information includes: determining an ascending gradient of the decibel value; and determining the audio information to be the audio information to be detected if the ascending gradient is greater than a preset gradient.

[0007] Optionally, the audio feature information includes a sound attenuation degree, the audio information includes first audio information collected from inside the vehicle and second audio information collected from outside the vehicle, and determining the audio information to be detected according to the audio information includes: obtaining a first attenuation degree of the sound in the first audio information and obtaining a second attenuation degree of the sound in the second audio information; and determining the first audio information and / or the second audio information to be the audio information to be detected if the first attenuation degree is consistent with the second attenuation degree.

[0008] Optionally, obtaining the first collision information according to the audio information to be detected includes: comparing the audio information to be detected with preset audio information to obtain a similarity, where the preset audio information is audio information collected in the case of a vehicle collision; and obtaining the first collision information according to the similarity.

[0009] Optionally, the external environment information includes an external environment image, and obtaining the second collision information according to the external environment information includes: obtaining the distance between the vehicle and a target object outside the vehicle according to the external environment image; and determining the distance as the second collision information.

[0010] Optionally, the first collision information is a collision prediction probability, and the second collision information is the distance between the vehicle and a target object outside the vehicle. Obtaining a collision detection result according to the first collision information and the second collision information includes: determining a target threshold interval where the collision prediction probability is located from a plurality of threshold intervals; determining a target preset distance corresponding to the target threshold interval according to the corresponding relationship between the threshold interval and the preset distance; and if the distance between the vehicle and the target object is less than the target preset distance, obtaining a collision detection result indicating a collision with the target object.

[0011] Optionally, obtaining the external environment information of the vehicle includes: determining a direction to be detected according to the audio information; and obtaining the external environment image collected by a target camera located in the direction to be detected.

[0012] According to a second aspect of the embodiments of the present disclosure, there is provided a vehicle collision detection device, including: a collection module configured to obtain audio information inside and / or outside the vehicle and obtain audio feature information according to the audio information, where the audio feature information includes a decibel value and / or the attenuation degree of the sound; a determination module configured to determine audio information to be detected according to the audio feature information; a first acquisition module configured to obtain the first collision information according to the audio information to be detected; a second acquisition module configured to obtain the external environment information of the vehicle and obtain the second collision information according to the external environment information; and a detection module configured to obtain a collision detection result according to the first collision information and the second collision information.

[0013] According to a third aspect of the embodiments of the present disclosure, a vehicle is provided, including: a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to: obtain audio information inside and / or outside the vehicle, and obtain audio feature information according to the audio information, wherein the audio feature information includes a decibel value and / or the degree of attenuation of the sound; determine the audio information to be detected according to the audio feature information; obtain the first collision information according to the audio information to be detected; obtain an external environment image of the vehicle, and obtain second collision information according to the external environment image; obtain a collision detection result according to the first collision information and the second collision information.

[0014] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0015] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0016] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: The embodiments of the present disclosure integrate two different types of data, audio information and external environment information, and perform collision detection by comprehensively considering the first collision information and the second collision information, which can more comprehensively evaluate collisions and improve the accuracy of collision detection. In addition, audio information and external environment information can be collected even in the case of minor collisions, so that the present disclosure is not affected by the severity of the collision, can detect minor collisions, and is convenient for timely reporting the collision situation of driverless vehicles.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0019] Figure 1 is a schematic diagram of vehicle collision.

[0020] Figure 2 is a flowchart of a vehicle collision detection method shown according to an exemplary embodiment.

[0021] Figure 3 is Figure 2 a flowchart of the sub-steps of step S110 in

[0022] Figure 4Yes Figure 2 It is a flowchart of the sub - steps of step S130.

[0023] Figure 5 It is a flowchart of a vehicle collision detection method shown according to an exemplary embodiment.

[0024] Figure 6 It is a schematic diagram of a vehicle collision detection system.

[0025] Figure 7 It is a block diagram of a vehicle collision detection device shown according to an exemplary embodiment.

[0026] Figure 8 It is a block diagram of a vehicle shown according to an exemplary embodiment. Detailed implementation mode

[0027] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0028] A driverless vehicle relies on various sensors to perceive the surrounding environment and road information, and can automatically plan routes and drive autonomously without manual operation. Currently, when a driverless vehicle is driving on the road, it usually relies on a collision detection and airbag system to detect collision events. As Figure 1 shown, when the vehicle 1 detects a collision with the other vehicle 2 through the above - mentioned method, the collision event is reported to the cloud background for subsequent processing and repair. However, the airbag will only pop up under a relatively serious collision. Therefore, it is difficult to perceive relatively minor collisions. There may be hit - and - run situations, and the aforementioned minor collisions cannot be reported and processed in a timely manner.

[0029] To solve the above problems, the present disclosure provides a vehicle collision detection method. Please refer to Figure 2 , the vehicle collision detection method can be applied to Figure 6 the vehicle collision detection system shown in Figure 7 the vehicle collision detection device 200 shown in Figure 8 the vehicle 600 shown in Figure 2 , computer program products, and computer - readable storage media. In this embodiment, it is taken as an example of being applied to a vehicle. The following will elaborate in detail on the process shown in Step S110: Obtain the audio information inside and / or outside the vehicle, and obtain the first collision information based on the audio information.

[0030] Obtain the audio information inside and / or outside the vehicle. In one implementation, a microphone is installed on the vehicle, and the audio information is collected through the microphone on the vehicle. If the sound source is outside the vehicle, the audio information is the audio information outside the vehicle. If the sound source is inside the vehicle, the audio information is the audio information inside the vehicle. If the sound source is both inside and outside the vehicle, the audio information is the audio information mixed with that inside and outside the vehicle. Among them, the number of microphones can be multiple, and a microphone array is formed by multiple microphones. The audio information is collected simultaneously by multiple microphones, and multiple pieces of audio information are collected.

[0031] Optionally, the above microphone can be the microphone in the vehicle-mounted voice control system, which is used to capture the driver's voice commands to achieve voice interaction and thus realize vehicle control. In this embodiment, the microphone in the vehicle-mounted voice control system is reused to collect the audio information. The above microphone can also be a microphone specially installed for vehicle collision tests, which can be arranged inside and outside the vehicle, and the audio information is collected jointly by the microphones inside and outside the vehicle.

[0032] In another implementation, an audio collection device bound to the vehicle is installed or placed on the vehicle, and the audio information inside and / or outside the vehicle is collected through the audio collection device. A microphone is installed on the audio collection device, and the audio collection device can be a smart phone, a tablet computer, a smart wearable device, etc. bound to the vehicle.

[0033] In another implementation, according to the audio information, obtain audio feature information, where the audio feature information includes the decibel value and / or the attenuation degree of the sound. The decibel value is used to characterize the intensity of the sound, and the attenuation degree of the sound is used to reflect the situation where the energy of the sound gradually attenuates during the propagation process. The attenuation degree of the sound is related to factors such as the propagation distance, the characteristics of the propagation medium, reflection, and absorption. Then, according to the audio feature information, determine the audio information to be detected.

[0034] Analyze the collected audio information to obtain the first collision information. The first collision information can be the collision prediction probability. For example, the collision prediction probability is 50%, 80%, etc. The first collision information can characterize that a collision has occurred based on the analysis of the audio information, or can characterize that no collision has occurred based on the analysis of the audio information.

[0035] Step S120: Obtain the external environment information of the vehicle, and obtain the second collision information based on the external environment information.

[0036] In one embodiment, for a vehicle utilizing V2X (Vehicle-to-Everything) technology, the vehicle can communicate with other devices such as other vehicles, roadside units, traffic lights, etc. that it is interconnected with. The vehicle can receive device information sent by other devices using V2X technology. Taking other vehicles as an example of other devices, the vehicle exchanges driving information between the two vehicles, such as speed, position, braking state, etc., with other vehicles through V2X technology. The vehicle determines the driving information sent by other vehicles that it receives as external environment information.

[0037] The object that collides with the vehicle is an object outside the vehicle. In another embodiment, the external environment information can be an external environment image. As a way, cameras are installed on a driverless vehicle to sense the surrounding environment, objects, road conditions, etc. of the vehicle. Reusing the cameras on the vehicle, the external environment image of the vehicle is collected through the cameras, and the external environment image is determined as the external environment information.

[0038] As another way, an image acquisition device bound to the vehicle is installed or placed on the vehicle, and the external environment image of the vehicle is collected through the image acquisition device. A camera is installed on the image acquisition device, and the image acquisition device can be a smartphone, a tablet computer, a smart wearable device, etc. bound to the vehicle.

[0039] Multiple microphones are provided on the vehicle, and each of the multiple microphones collects audio information, so that multiple audio information can be collected. Multiple cameras are also provided on the vehicle, and the multiple cameras are respectively arranged at various positions of the vehicle. Based on this, in another embodiment, the position to be detected is determined according to the audio information. For example, the collision sound usually appears as a peak in the audio signal. The positions of the peaks in the same time period in the multiple audio information are respectively determined to determine multiple peaks; the sound intensities of the multiple peaks are compared, and the microphone corresponding to the one with the stronger sound is determined, and the orientation where the microphone is located is the orientation of the sound source, and thus this orientation can be determined as the position to be detected. For another example, the positions of the peaks in the same time period in the multiple audio information are respectively determined; then the moments corresponding to the peak positions are determined, and the multiple moments are compared. The microphone of the audio information that first captures the peak is the closest to the sound source, and the orientation where the microphone is located is determined as the position to be detected. Then the external environment image collected by the target camera located at the position to be detected is obtained. It can be understood that cameras at multiple orientations on the vehicle all collect images, but perhaps only some cameras can capture the target object that collides with the vehicle. If the images collected by all cameras are processed and analyzed, it may lead to a waste of processing resources. Therefore, the external environment image collected by the target camera located at the position to be detected is obtained. It can be understood that the external environment image in this embodiment is the image at the sound source.

[0040] Analyze the collected external environment images to obtain second collision information. In one implementation, the second collision information can be obtained in the following manner. According to the external environment images, obtain the distance between the vehicle and an object outside the vehicle, where the object can be another vehicle, an obstacle during driving, etc. Then determine the distance as the second collision information. For example, use the distance as the second collision information.

[0041] It should be noted that the execution order of step S110 and step S120 is not limited. Step S110 can be executed first, and then step S120. It is also possible to execute step S120 first and then step S110. It is also possible to execute step S110 and step S120 simultaneously.

[0042] Step S130: Obtain a collision detection result according to the first collision information and the second collision information.

[0043] Obtain a collision prediction result according to the first collision information and the second collision information, where the collision prediction result can indicate that a collision has occurred to the vehicle or that no collision has occurred to the vehicle.

[0044] When the collision detection result indicates that a collision has occurred to the vehicle, the collision time, the collision detection result, etc. can be reported to the cloud server for subsequent maintenance and processing.

[0045] The vehicle collision detection method provided in this embodiment obtains the audio information inside and outside the vehicle and obtains the first collision information according to the audio information; then obtains the external environment information of the vehicle and obtains the second collision information according to the external environment information; and then performs collision analysis according to the first collision information and the second collision information to obtain a collision detection result. Imagine that if only the audio information is used to detect collisions, the honking of horns and other collision sounds in the environment where the vehicle is located may interfere with the detection result; if only the external environment information is used to detect collisions, for example, the external environment information includes external environment images, factors such as weather and shooting angle may affect the shooting effect of the images, which may lead to inaccurate collision detection based on the images. This embodiment combines two different types of data, audio information and external environment information, and comprehensively performs collision detection according to the first collision information and the second collision information, which can more comprehensively evaluate collisions and improve the accuracy of collision detection. In addition, audio information and external environment images can also be collected in the case of minor collisions. The embodiments of the present disclosure are not affected by the severity of the collision and can detect minor collisions, facilitating the timely reporting of the collision situation of driverless vehicles.

[0046] In one embodiment, in step S110, obtaining the first collision information from the audio information may be achieved in the following manner: comparing the audio information with preset audio information to obtain the similarity between the two. Here, the preset audio information is the audio information collected when the vehicle is in a collision situation. The vehicle here may refer to the vehicle itself, that is, the preset audio information may be the audio information collected when the vehicle itself has had a collision in the past. The vehicle may also be other vehicles, and the preset audio information may also be the audio information collected when other vehicles are in a collision situation. Then, based on the similarity, the first collision information is obtained.

[0047] In another embodiment, vehicle collisions are accidental events. Therefore, among the audio information collected inside and outside the vehicle, most of the audio information does not contain the audio during vehicle collisions. If collision recognition is performed on all audio, it may lead to a waste of vehicle processing resources. Therefore, the audio information can be pre-judged. If the audio information is suspected to be the audio during vehicle collision, then the audio information is used as the audio to be detected and further collision detection is performed. Exemplarily, please refer to Figure 3 , in step S110, obtaining the first collision information from the audio information may be achieved in the following manner: Step S111: Determine the audio information to be detected according to the audio information.

[0048] The microphone on the vehicle may start collecting audio information after the vehicle starts. Collision is an accidental event. If all the audio information collected at all times is judged, it will lead to a waste of processing resources. Therefore, determining the audio information to be detected according to the audio information for subsequent collision detection, it can be understood that the audio information to be detected is the audio information suspected to be generated during a collision.

[0049] In this step, according to the audio information, audio feature information is obtained, where the audio feature information includes the decibel value and / or the degree of sound attenuation; according to the audio feature information, the audio information to be detected is determined.

[0050] As a method, the sound generated during a collision is usually relatively loud. Therefore, the audio information to be detected can be screened according to the decibel value of the sound. When the audio feature information includes the decibel value, if the decibel value is greater than the preset decibel value, it is determined that the audio information is the audio information to be detected. If the decibel value is not greater than the preset decibel value, it means that no relatively loud sound is generated during the driving of the driverless vehicle, and there may be no collision, and the obtained audio information is not used for subsequent collision detection.

[0051] As another approach, when the audio feature information includes decibel values, determine the rising gradient of the decibel values. For example, calculate the difference between two decibel values of sounds collected in two adjacent time periods to determine the rising gradient. If the rising gradient is greater than a preset gradient, it indicates that a sudden collision may have caused the decibel of the sound to suddenly increase, and determine that the audio information is the audio information to be detected. If the rising gradient is less than or equal to the preset gradient, it means that no suddenly increased sound is collected during the driving of the driverless vehicle, and a collision may not have occurred, and the obtained audio information is not used for subsequent collision detection.

[0052] Sound gradually attenuates during propagation, and the attenuation degree is affected by factors such as the propagation medium. If the collision does not occur on the vehicle itself, then the sound is transmitted through the air and collected by microphones inside and outside the vehicle. If the collision occurs on the vehicle itself, then the sound is transmitted not only through the air but also through the vehicle's frame structure and collected by microphones inside and outside the vehicle. Since the attenuation of the sound inside the vehicle is affected by the materials and structures inside the vehicle, if it is only transmitted through the air, the attenuation rate of the sound signal collected inside the vehicle is faster than that of the sound signal collected outside the vehicle. If a collision occurs on the vehicle, the sound generated during the collision is also transmitted through the vehicle itself. Then, if the difference between the attenuation rates of the sound signals collected by the microphones inside and outside the vehicle is less than a preset value, it can be considered that the attenuation degrees of the two are the same. If the difference is greater than or equal to the preset value, it can be considered that the attenuation degrees of the two are different. Based on this, as another approach, the audio feature information includes the attenuation degree of the sound, and the audio information includes the first audio information collected from inside the vehicle. For example, the first audio information is collected by a microphone installed inside the vehicle; and the second audio information collected from outside the vehicle, for example, the second audio information is collected by a microphone installed outside the vehicle. Obtain the first attenuation degree of the sound in the first audio information and the second attenuation degree of the sound in the second audio information. Optionally, the attenuation degree of the sound can be obtained by methods such as the reverberation time measurement method, the acoustic emission attenuation characteristic measurement method, the reverse integration method, and the sound velocity transmission method. If the first attenuation degree is the same as the second attenuation degree, it indicates that the first audio information and the second audio information are collected when a collision occurs on the vehicle, and at least one of them is used for subsequent collision detection, that is, determine the first audio information and / or the second audio information as the audio information to be detected. On the contrary, if the first attenuation degree is different from the second attenuation degree, it indicates that the first audio information and the second audio information may not be collected when a collision occurs on the vehicle itself, and the first audio information and the second audio information are not used for collision analysis.

[0053] Optionally, the attenuation degree can be characterized by the attenuation speed of the sound, that is, the first attenuation degree is the first attenuation speed, and the second attenuation degree is the second attenuation speed. If the difference between the first attenuation speed and the second attenuation speed is less than a preset value, it is determined that the first attenuation degree is consistent with the second attenuation degree. On the contrary, if the difference between the first attenuation speed and the second attenuation speed is greater than or equal to the preset value, it is determined that the first attenuation degree is inconsistent with the second attenuation degree.

[0054] Step S112: Obtain the first rubbing information according to the audio information to be detected.

[0055] As a method, compare the audio information to be detected with preset audio information to obtain a similarity, where the preset audio information is audio information collected under the condition of vehicle rubbing; obtain the first rubbing information according to the similarity. Optionally, the similarity can be directly used as the first rubbing information.

[0056] In an implementation manner, the first rubbing information is a rubbing prediction probability, the second rubbing information is the distance between the vehicle and an object outside the vehicle, and step S130 can be as follows: Step S131: Determine the target threshold interval where the rubbing prediction probability is located from multiple threshold intervals.

[0057] Multiple threshold intervals are set in advance. For example, the multiple threshold intervals can be 60% - 70%, 70% - 80%, 80% - 90%, 90% - 100% respectively. Determine the threshold interval where the rubbing prediction probability is located as the target threshold interval. For example, if the rubbing prediction probability is 83%, and the threshold interval where the rubbing prediction probability of 83% is located is 80% - 90%, then determine the threshold interval 80% - 90% as the target threshold interval. If the rubbing prediction probability does not belong to any of the preset multiple threshold intervals, it is determined that the rubbing detection result of the vehicle not having a rub is obtained.

[0058] Step S132: Determine the target preset distance corresponding to the target threshold interval according to the correspondence between the threshold interval and the preset distance.

[0059] Pre-set the correspondence between the threshold interval and the preset distance. Optionally, the magnitude of the value of the preset threshold interval is inversely correlated with the preset distance. It can be understood that the greater the probability of collision prediction, the looser the requirement for the distance between the vehicle and the target object, and the preset distance can be set larger. Conversely, the smaller the probability of collision prediction, the stricter the requirement for the distance between the vehicle and the target object, and the preset distance can be set smaller. For example, the preset distance corresponding to the threshold interval of 70% - 80% is 10 cm, the preset distance corresponding to the threshold interval of 80% - 90% is 15 cm, and the preset distance corresponding to the threshold interval of 90% - 100% is 20 cm. Combining the above example, based on the above correspondence, the target preset distance corresponding to the target threshold interval of 80% - 90% is 15 cm.

[0060] Step S133: If the distance between the vehicle and the target object is less than the target preset distance, obtain a collision detection result indicating a collision with the target object.

[0061] If the distance between the vehicle and the target object is less than the preset target distance, it indicates that the distance between the vehicle and the target object is relatively close, and a collision detection result indicating a collision with the target object is obtained. If the distance between the vehicle and the target object is greater than or equal to the preset target distance, it indicates that the distance between the vehicle and the target object is relatively far, and a collision detection result indicating no collision with the target object is obtained. Continuing with the above example, the target preset distance is 15 cm. When the distance between the vehicle and the target object is 10 cm, this distance is less than the target preset distance of 15 cm, and a collision detection result indicating a collision with the target object is obtained. When the distance between the vehicle and the target object is 20 cm, this distance is greater than the target preset distance of 15 cm, and a collision detection result indicating no collision with the target object is obtained.

[0062] In this embodiment, by flexibly selecting the preset distance according to the change of the collision prediction probability, the accuracy of the collision detection result detection in different situations is improved.

[0063] This embodiment provides a vehicle collision detection method. Please refer to Figure 5 , and this method includes the following steps: Step a: The in-vehicle microphone array receives the surrounding audio.

[0064] A microphone array is deployed on the vehicle, and the surrounding audio is received through the microphone array. The surrounding audio includes the audio information inside and / or outside the aforementioned vehicle.

[0065] Step b: Perform audio feature recognition on the near-field audio.

[0066] Perform audio feature recognition to determine the audio information to be detected.

[0067] Step c: Identify the vehicles around the camera.

[0068] A camera is deployed on the vehicle to collect external environment images around the vehicle or record videos of the external environment images for identifying targets such as vehicles.

[0069] Step d: Fuse the audio and video judgment results.

[0070] Combine the audio and video, fuse the audio and images, and jointly perform vehicle collision detection to obtain the collision detection result.

[0071] Step e: Processing after the event occurs.

[0072] If the collision detection result indicates that a vehicle collision event has occurred, the processing after the event can include reporting the collision detection result to the cloud server. Or, if the target identified as being involved in the collision is a pedestrian, then the processing includes automatically parking the vehicle on the side of the road. If the target identified as being involved in the collision is a rock, then re-plan the driving route and continue driving.

[0073] Based on the same inventive concept, the present disclosure also provides a vehicle collision detection system. Please refer to Figure 6 , the vehicle collision detection system includes: An audio processing system and a microphone array inside and outside the vehicle. The audio processing system is used to process the audio received by the microphone array, that is, to extract audio information.

[0074] An audio feature recognition system, which is used to learn the audio features during vehicle collision and compare them with the audio transmitted by the audio processing system, evaluate the matching degree, and give a preliminary judgment on the event status.

[0075] An intelligent driving system, which is used to sense and identify surrounding vehicles and other targets through the cameras on the vehicle, as well as the relative positions and distances between the vehicle and the targets. It is also used to perform corresponding event processing actions when the logic control unit evaluates that an event has occurred.

[0076] A logic control unit, which is used to control the logic of the entire function and complete the fusion judgment of the audio and video for event evaluation.

[0077] A networking system, which is used to report the collision event and related audio and video evidence to the cloud background.

[0078] Based on the same inventive concept, the present disclosure also provides a vehicle collision detection device. Please refer to Figure 7 , the vehicle collision detection device 200 includes: an acquisition module 210, a determination module 220, a first acquisition module 230, a second acquisition module 240, and a detection module 250; The acquisition module 210 is configured to obtain audio information inside and / or outside the vehicle, and obtain audio feature information according to the audio information, where the audio feature information includes a decibel value and / or the attenuation degree of the sound; The determination module 220 is configured to determine the audio information to be detected according to the audio feature information; The first acquisition module 230 is configured to obtain the first rubbing information according to the audio information to be detected; The second acquisition module 240 is configured to obtain the external environment information of the vehicle, and obtain the second rubbing information according to the external environment information; The detection module 250 is configured to obtain a rubbing detection result according to the first rubbing information and the second rubbing information.

[0079] Optionally, the audio feature information includes a decibel value, and the determination module 220 includes: The first determination module is configured to determine that the audio information is the audio information to be detected if the decibel value is greater than a preset decibel value.

[0080] Optionally, the audio feature information includes a decibel value, and the determination module 220 includes: The rising gradient acquisition module is configured to determine the rising gradient of the decibel value; The second determination module is configured to determine that the audio information is the audio information to be detected if the rising gradient is greater than a preset gradient.

[0081] Optionally, the audio feature information includes the attenuation degree of the sound, the audio information includes first audio information collected from inside the vehicle and second audio information collected from outside the vehicle, and the determination module 220 includes: The attenuation degree acquisition module is configured to obtain a first attenuation degree of the sound in the first audio information and a second attenuation degree of the sound in the second audio information; The third determination module is configured to determine that the first audio information and / or the second audio information is the audio information to be detected if the first attenuation degree is consistent with the second attenuation degree.

[0082] Optionally, the first rubbing information acquisition module includes: The similarity acquisition module is configured to compare the audio information to be detected with preset audio information to obtain a similarity, where the preset audio information is audio information collected in the case of vehicle rubbing; The acquisition module is configured to obtain the first rubbing information according to the similarity.

[0083] Optionally, the external environment information includes an external environment image, and the second acquisition module 220 includes: a distance acquisition module, configured to acquire a distance between the vehicle and an object outside the vehicle according to the external environment image; a distance prediction module, configured to determine the distance as the second collision information.

[0084] Optionally, the first collision information is a collision prediction probability, and the second collision information is a distance between the vehicle and an object outside the vehicle. The detection module 230 includes: a target threshold interval determination module, configured to determine a target threshold interval in which the collision prediction probability is located from a plurality of threshold intervals; a target preset distance determination module, configured to determine a target preset distance corresponding to the target threshold interval according to a correspondence between the threshold interval and the preset distance; a collision detection result acquisition module, configured to obtain a collision detection result indicating a collision with the object if the distance between the vehicle and the object is less than the target preset distance.

[0085] Optionally, the second acquisition module 240 includes: a to-be-detected orientation determination module, configured to determine a to-be-detected orientation according to the audio information; an external environment image capturing module, configured to acquire the external environment image captured by a target camera located at the to-be-detected orientation.

[0086] Regarding the vehicle collision detection device 200 in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0087] The present disclosure further provides a computer-readable storage medium, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the vehicle collision detection method provided by the present disclosure are implemented.

[0088] Figure 8 is a block diagram of a vehicle 600 shown according to an exemplary embodiment. For example, the vehicle 600 may be a hybrid vehicle, or may also be a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 600 may be an autonomous vehicle or a semi-autonomous vehicle.

[0089] Please refer to Figure 8, Vehicle 600 may include various subsystems. For example, an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. Among them, Vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of Vehicle 600 may be interconnected by wired or wireless means.

[0090] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, a navigation system, and the like.

[0091] The perception system 620 may include several sensors for sensing information about the environment around Vehicle 600. For example, the perception system 620 may include a global positioning system (the global positioning system may be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0092] The decision control system 630 may include a computing system, a vehicle controller, a steering system, an accelerator, and a braking system.

[0093] The drive system 640 may include components that provide motive power for Vehicle 600. In one embodiment, the drive system 640 may include an engine, an energy source, a powertrain, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, and an air compression engine. The engine can convert the energy provided by the energy source into mechanical energy.

[0094] Some or all functions of Vehicle 600 are controlled by the computing platform 650. The computing platform 650 may include at least one processor 651 and a memory 652. The processor 651 may execute instructions 653 stored in the memory 652.

[0095] The processor 651 may be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0096] The memory 652 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 read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0097] In addition to the instructions 653, the memory 652 can also store data, such as road maps, route information, data on the position, direction, speed, etc. of the vehicle. The data stored in the memory 652 can be used by the computing platform 650.

[0098] In an embodiment of the present disclosure, the processor 651 can execute the instructions 653 to complete all or part of the steps of the above method.

[0099] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above method when executed by the programmable device.

[0100] In another exemplary embodiment, a computer-readable storage medium is also provided. A computer program is stored thereon. When the computer program is executed by a processor, the steps of the above method are implemented.

[0101] Those skilled in the art can also understand that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of both. Whether such a function is implemented by hardware or software depends on the specific application and the design requirements of the entire system. For each specific application, those skilled in the art can use various methods to implement the described function, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present application.

[0102] In addition, as used herein, the word "exemplary" is used to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as advantageous over other aspects or designs. Rather, the word exemplary is intended to present concepts in a concrete fashion. As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified, or clear from the context, "X applies A or B" is intended to mean any of the natural inclusive permutations. That is, if X applies A; X applies B; or X applies both A and B, then "X applies A or B" is satisfied under any one of the foregoing instances. Additionally, unless otherwise specified or clear from the context that points to the singular form, the articles "a" and "an" as used in this application and the appended claims are generally understood to mean "one or more".

[0103] Likewise, although the present disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the claims. Specifically with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terms used to describe such components are intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if not structurally equivalent to the disclosed structure. Additionally, although a particular feature of the present disclosure may have been disclosed with respect to only one of several implementations, such a feature may, as may be desired and advantageous for any given or particular application, be combined with one or more other features of other implementations. Further, with respect to the terms "comprising", "having", "including", "containing", or variants thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term "including".

[0104] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

[0105] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes may be made without departing from its scope. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A vehicle collision detection method, characterized in that: The method comprises: Acquire audio information inside and / or outside the vehicle, and obtain audio feature information based on the audio information, wherein the audio feature information includes a decibel value and / or a sound attenuation degree; Determining the audio information to be detected according to the audio feature information; Obtaining first collision information according to the audio information to be detected; Acquiring external environment information of the vehicle, and obtaining second collision information according to the external environment information; A collision detection result is obtained according to the first collision information and the second collision information.

2. The method according to claim 1, characterized in that The audio feature information includes a decibel value, and determining the audio information to be detected according to the audio information includes: If the decibel value is greater than a preset decibel value, the audio information is determined to be the audio information to be detected.

3. The method according to claim 1, characterized in that The audio feature information includes a decibel value, and determining the audio information to be detected according to the audio information includes: determining a rising gradient of the decibel value; If the rising gradient is greater than a preset gradient, it is determined that the audio information is the audio information to be detected.

4. The method according to claim 1, characterized in that The audio feature information includes a sound attenuation degree, the audio information includes first audio information collected from inside the vehicle, and second audio information collected from outside the vehicle, and determining the audio information to be detected based on the audio information includes: Acquire a first attenuation degree of the sound in the first audio information, and acquire a second attenuation degree of the sound in the second audio information; If the first attenuation degree is consistent with the second attenuation degree, the first audio information and / or the second audio information is determined to be the audio information to be detected.

5. The method according to any one of claims 1 to 4, characterized in that: The obtaining the first collision information according to the audio information to be detected includes: Comparing the audio information to be detected with preset audio information to obtain similarity, wherein the preset audio information is audio information collected in the case of a vehicle collision; The first collision information is obtained according to the similarity.

6. The method according to claim 1, characterized in that The external environment information includes an external environment image, and obtaining the second collision information according to the external environment information includes: Acquiring the distance between the vehicle and a target object outside the vehicle according to the external environment image; The distance is determined as the second collision information.

7. The method according to any one of claims 1 to 4, characterized in that: The first collision information is a collision prediction probability, the second collision information is a distance between the vehicle and a target object outside the vehicle, and obtaining a collision detection result according to the first collision information and the second collision information includes: Determine a target threshold interval where the collision prediction probability is located from a plurality of threshold intervals; Determine the target preset distance corresponding to the target threshold interval according to the corresponding relationship between the threshold interval and the preset distance; If the distance between the vehicle and the target object is less than the preset target distance, a collision detection result indicating a collision with the target object is obtained.

8. The method according to claim 6, characterized in that The obtaining of the external environment information of the vehicle includes: Determining a direction to be detected according to the audio information; The external environment image captured by the target camera located at the position to be detected is obtained.

9. A vehicle collision detection device, characterized in that: The device comprises: A collection module is configured to obtain audio information inside and / or outside the vehicle, and obtain audio feature information based on the audio information, wherein the audio feature information includes a decibel value and / or a sound attenuation degree; A determination module, configured to determine the audio information to be detected according to the audio feature information; A first acquisition module is configured to obtain first collision information according to the audio information to be detected; A second acquisition module is configured to acquire external environment information of the vehicle and obtain second collision information according to the external environment information; The detection module is configured to obtain a collision detection result according to the first collision information and the second collision information.

10. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Acquire audio information inside and / or outside the vehicle, and obtain audio feature information based on the audio information, wherein the audio feature information includes a decibel value and / or a sound attenuation degree; Determining the audio information to be detected according to the audio feature information; Obtaining first collision information according to the audio information to be detected; Acquiring external environment information of the vehicle, and obtaining second collision information according to the external environment information; A collision detection result is obtained according to the first collision information and the second collision information.

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

12. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Images