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

Abstract

The present disclosure 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: acquiring 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 obtaining second collision information according to the external environment information; and then performing collision analysis according to the first collision information and the second collision information to obtain a collision detection result. The present disclosure combines two different data, i.e., audio information and external environment information, and comprehensively performs collision detection on the first collision information and the second collision information, so that the collision can be more comprehensively evaluated, and the accuracy of the collision detection is improved. In addition, the audio information and the external environment information can also be collected in the case of slight collision, and the present disclosure is not affected by the degree of collision, so that the slight collision can be detected, and the collision condition of the vehicle can be timely reported.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of vehicles, and particularly relates to a vehicle bump detection method and device, a vehicle, a storage medium and a program product. BACKGROUND

[0002] An unmanned vehicle relies on various sensors to perceive the surrounding environment and road information, and can automatically plan a route and autonomously drive without manual operation. At present, in the process of driving on the road, the unmanned vehicle usually detects a collision event by means of a collision detection and a safety airbag system. However, the safety airbag needs a relatively serious collision to pop out, and thus it is difficult to perceive a relatively slight bump. SUMMARY

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

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

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

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

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

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

[0009] Optionally, the external environment information comprises an external environment image, and the obtaining the second collision information according to the external environment information comprises: obtaining a 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, the second collision information is a distance between the vehicle and a target object outside the vehicle, and the obtaining the collision detection result according to the first collision information and the second collision information comprises: determining a target threshold interval in which 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 a corresponding relationship between a threshold interval and a preset distance; and obtaining a collision detection result representing a collision with the target object if the distance between the vehicle and the target object is less than the target preset distance.

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

[0012] According to a second aspect of the embodiments of the present disclosure, a vehicle collision detection device is provided, which comprises: a collection module configured to obtain audio information inside and / or outside a vehicle, and obtain audio feature information according to the audio information, wherein the audio feature information comprises a decibel value and / or a sound attenuation degree; a determination module configured to determine audio information to be detected according to the audio feature information; a first obtaining module configured to obtain first collision information according to the audio information to be detected; a second obtaining module configured to obtain external environment information of the vehicle, and obtain 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 embodiments of the present disclosure, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: acquire audio information of an inside and / or outside of the vehicle, and obtain audio feature information according to the audio information, wherein the audio feature information comprises a decibel value and / or a degree of attenuation of sound; determine to-be-detected audio information according to the audio feature information; obtain the first scratch information according to the to-be-detected audio information; acquire an outside environment image of the vehicle, and obtain second scratch information according to the outside environment image; and obtain a scratch detection result according to the first scratch information and the second scratch information.

[0014] According to a fourth aspect of embodiments of the present disclosure, a computer-readable storage medium is provided, having stored thereon computer program instructions, which, when executed by a processor, implement the steps of the method according to the first aspect of the present disclosure.

[0015] According to a fifth aspect of embodiments of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the method according to the first aspect of the present disclosure.

[0016] The technical solutions provided by the embodiments of the present disclosure can include the following beneficial effects: The embodiments of the present disclosure fuse two different data of audio information and outside environment information, and comprehensively detect scratches by combining the first scratch information and the second scratch information, so that the scratches can be more comprehensively evaluated, and the accuracy of scratch detection is improved. In addition, the audio information and the outside environment information can also be collected in the case of slight scratches, so that the present disclosure is not affected by the degree of scratches, and can detect slight scratches, which facilitates timely reporting of the scratch situation of the unmanned vehicle.

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

[0018] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

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

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

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

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

[0023] Figure 5 is a flowchart of a vehicle bump detection method according to an example embodiment.

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

[0025] Figure 7 is a block diagram of a vehicle bump detection apparatus according to an example embodiment.

[0026] Figure 8 is a block diagram of a vehicle according to an example embodiment. DETAILED DESCRIPTION

[0027] The example embodiments will be described in detail herein with reference to the accompanying drawings. In the following description, unless otherwise indicated, like numbers in the different drawings represent similar or analogous elements. The following description of example embodiments is not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0028] An unmanned vehicle relies on various sensors to perceive the surrounding environment and road information, and can automatically plan a route and autonomously drive without human operation. At present, in the process of driving on the road, the unmanned vehicle usually detects the collision event by means of the collision detection and airbag system. As shown in Figure 1 , when the host vehicle 1 detects a collision between itself and the other vehicle 2 by the above-mentioned method, the collision event is reported to the cloud background for subsequent processing and repair. However, the airbag needs to be ejected under a relatively serious collision, so it is difficult to perceive a relatively slight bump. The situation of hit-and-run may occur, and the aforementioned slight collision cannot be timely reported and handled.

[0029] To solve the above-mentioned problems, the present disclosure provides a vehicle bump detection method, please refer to Figure 2 , the vehicle bump detection method can be applied to Figure 6 the vehicle bump detection system shown in Figure 7 the vehicle bump detection apparatus 200 shown in Figure 8 the vehicle 600, the computer program product and the computer readable storage medium. In this embodiment, the vehicle is taken as an example. The following will be described in detail with reference to Figure 2 the flowchart shown in

[0030] Step S110, audio information inside and / or outside the vehicle is acquired, and first collision information is obtained according to the audio information.

[0031] The audio information inside and / or outside the vehicle is acquired. In an embodiment, a microphone is installed on the vehicle, and the audio information is collected by the microphone on the vehicle. If the sound comes from outside the vehicle, the audio information is the audio information outside the vehicle. If the sound comes from inside the vehicle, the audio information is the audio information inside the vehicle. If the sound comes from inside and outside the vehicle, the audio information is the audio information mixed inside and outside the vehicle. The number of microphones can be multiple, and a microphone array is formed by the multiple microphones. The audio information is collected by the multiple microphones at the same time, and the collected audio information is multiple.

[0032] Optionally, the microphone can be a microphone in a vehicle voice control system, used to capture the voice instructions of the driver, realize voice interaction, and thus realize vehicle control. In this embodiment, the microphone in the vehicle voice control system is multiplexed to collect the audio information. The microphone can also be a microphone specially installed for vehicle collision test, which can be arranged inside and outside the vehicle, and the audio information inside and outside the vehicle is collected by the microphones.

[0033] In another embodiment, 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 by the audio collection device. The audio collection device is installed with a microphone, and the audio collection device can be a smart phone, a tablet computer, a smart wearable device, etc. bound to the vehicle.

[0034] In another embodiment, audio feature information is obtained according to the audio information, wherein the audio feature information includes a decibel value and / or a sound attenuation degree. The decibel value is used to represent the intensity of the sound, and the sound attenuation degree is used to reflect the gradual attenuation of the energy of the sound in the propagation process. The sound attenuation degree is related to the propagation distance, the characteristics of the propagation medium, reflection, absorption, etc. The to-be-detected audio information is determined according to the audio feature information.

[0035] The collected audio information is analyzed to obtain first collision information, wherein the first collision information can be a collision prediction probability, for example, a collision prediction probability of 50%, 80%, etc. The first collision information can represent that a collision has occurred based on the analysis of the audio information, or that no collision has occurred based on the analysis of the audio information.

[0036] Step S120, the external environment information of the vehicle is acquired, and second collision information is obtained according to the external environment information.

[0037] In an embodiment, for a vehicle utilizing V2X (Vehicle-to-Everything) technology, the vehicle can communicate with other devices such as vehicles, roadside units, traffic lights, and the like, which are interconnected with the vehicle. The vehicle utilizing the V2X technology can receive device information sent by the other devices. Taking other vehicles as an example, the vehicle and the other vehicles exchange driving information between the two vehicles, such as speed, position, brake state, and the like, through the V2X technology. The vehicle determines the received driving information sent by the other vehicles as external environment information.

[0038] The object colliding with the vehicle is an object outside the vehicle. In another embodiment, the external environment information can be an external environment image. As one way, a camera is installed on an unmanned vehicle to perceive the surrounding environment, objects, road conditions, and the like of the vehicle. The camera on the vehicle is reused to collect an external environment image of the vehicle, and the external environment image is determined as the external environment information.

[0039] As another way, an image collection device bound to the vehicle is installed or placed on the vehicle to collect an external environment image of the vehicle. The image collection device is provided with a camera, and the image collection device can be a smart phone, a tablet computer, a smart wearable device, or the like bound to the vehicle.

[0040] The vehicle is provided with a plurality of microphones, and the plurality of microphones respectively collect audio information, so that a plurality of audio information can be collected. The vehicle is also provided with a plurality of cameras, and the plurality of cameras are respectively arranged at various positions of the vehicle. Based on this, in another embodiment, a to-be-detected direction is determined according to the audio information. For example, a collision sound is usually represented as a wave crest in an audio signal, the positions of the wave crests in the same period in the plurality of audio information are respectively determined, a plurality of wave crests are determined, the sound intensities of the plurality of wave crests are compared, a microphone corresponding to a wave crest with a strong sound intensity is determined, and a direction where the microphone is located is the direction of a sound source, so that the direction is determined as the to-be-detected direction. For another example, the positions of the wave crests in the same period in the plurality of audio information are respectively determined, the time corresponding to the wave crest positions is further determined, the time instants are compared, a microphone collecting a wave crest at the earliest time instant is closest to the sound source, a direction where the microphone is located is determined as the to-be-detected direction. An external environment image collected by a target camera located at the to-be-detected direction is further obtained. It can be understood that the cameras at a plurality of directions on the vehicle all collect images, but only some of the cameras can collect a target object colliding with the vehicle. If all the images collected by the cameras are processed and analyzed, the processing resources can be wasted. Therefore, the external environment image collected by the target camera located at the to-be-detected direction is obtained. It can be understood that the external environment image in this embodiment is an image at a sound source.

[0041] The second collision information is obtained by analyzing the collected external environment image. In an embodiment, the second collision information can be obtained by obtaining the distance between the vehicle and an external target according to the external environment image, wherein the target can be a remaining vehicle, an obstacle during driving, etc. The distance is determined as the second collision information. For example, the distance is taken as the second collision information.

[0042] It should be noted that the execution order of steps S110 and S120 is not limited, and step S110 can be executed first, and then step S120 can be executed. Step S120 can also be executed first, and then step S110 can be executed. Step S110 and step S120 can also be executed simultaneously.

[0043] Step S130, obtaining a collision detection result according to the first collision information and the second collision information.

[0044] According to the first collision information and the second collision information, a collision prediction result is obtained, wherein the collision prediction result can represent that the vehicle has a collision, or represent that the vehicle has no collision.

[0045] When the collision detection result represents that the vehicle has a collision, the collision time and the collision detection result can be reported to a cloud server, so as to facilitate subsequent maintenance and processing.

[0046] The vehicle collision detection method provided in the embodiment obtains audio information inside and outside the vehicle, and obtains first collision information according to the audio information. Then, external environment information of the vehicle is obtained, and second collision information is obtained according to the external environment information. Then, collision analysis is performed according to the first collision information and the second collision information, and a collision detection result is obtained. If the collision is detected only by the audio information, the detection result may be disturbed by the horn sound and other collision sounds in the environment in which the vehicle is located. If the collision is detected only by the external environment information, for example, the external environment information includes an external environment image, the weather and the shooting angle may affect the shooting effect of the image, so that the collision detection according to the image may be inaccurate. The embodiment fuses two different data of the audio information and the external environment information, and comprehensively detects the collision according to the first collision information and the second collision information, so that the collision can be more comprehensively evaluated, and the accuracy of the collision detection is improved. In addition, the audio information and the external environment image can also be collected in the case of slight collision, and the disclosed embodiment is not affected by the degree of collision, and can detect slight collision, so as to timely report the collision of the unmanned vehicle.

[0047] In an embodiment, in step S110, the first collision information is obtained according to the audio information in the following manner: comparing the audio information with preset audio information to obtain a similarity between the two. The preset audio information is audio information collected by a vehicle in a collision situation. Here, the vehicle can refer to the ego vehicle, i.e., the preset audio information can be audio information collected when the ego vehicle has a collision in the past. The vehicle can be another vehicle, and the preset audio information can also be audio information collected when the other vehicle has a collision. Then, the first collision information is obtained according to the similarity.

[0048] In another embodiment, a vehicle collision is a random event, and therefore, most of the audio information collected inside and outside the vehicle does not contain audio information when the vehicle has a collision. If all the audio information is subjected to collision detection, it can result in waste of vehicle processing resources. Therefore, the audio information can be pre-judged. If the audio information is suspected to be audio information when the vehicle has a collision, the audio information is taken as the audio information to be detected, and further subjected to collision detection. For example, in step S110, the first collision information is obtained according to the audio information in the following manner: Figure 3

[0049] In step S111, the audio information to be detected is determined according to the audio information.

[0050] The microphone on the vehicle can start collecting audio information after the vehicle is started, and a collision is a random event. If all the audio information collected at all times is subjected to judgment, it can result in waste of processing resources. Therefore, the audio information to be detected is determined according to the audio information for subsequent collision detection. It can be understood that the audio information to be detected is audio information suspected to be generated when a collision occurs.

[0051] In this step, audio feature information is obtained according to the audio information, wherein the audio feature information includes a decibel value and / or a sound attenuation degree. The audio information to be detected is determined according to the audio feature information.

[0052] As a manner, the sound generated when a collision occurs is usually large, and therefore, the audio information to be detected can be screened according to the decibel value of the sound. When the audio feature information includes a decibel value, if the decibel value is greater than a preset decibel value, the audio information is determined to be the audio information to be detected. If the decibel value is not greater than the preset decibel value, it indicates that no large sound is generated during the driving of the autonomous vehicle, and no collision occurs. The audio information obtained is not used for subsequent collision detection.

[0053] ​As another way, when the audio feature information comprises a decibel value, an ascending gradient of the decibel value is determined, for example, by the decibel values of the sound collected in two adjacent time periods, the difference between the two decibel values is calculated to determine the ascending gradient; if the ascending gradient is greater than a preset gradient, it is indicated that the decibel of the sound may suddenly become large due to a sudden collision, and it is determined that the audio information is the to-be-detected audio information. If the ascending gradient is less than or equal to the preset gradient, it is indicated that the autonomous vehicle does not collect a suddenly large sound during driving, and a collision may not occur, and the acquired audio information is not used for subsequent collision detection.

[0054] Sound gradually attenuates during propagation, and the degree of attenuation is affected by factors such as the propagation medium. If the collision does not occur on the vehicle, the sound propagates through the air and is collected by the microphones inside and outside the vehicle. If the collision occurs on the vehicle, the sound not only propagates through the air but also propagates through the frame structure of the vehicle and is collected by the microphones inside and outside the vehicle. Since the attenuation of the sound inside the vehicle is affected by the materials and structure inside the vehicle, if it only propagates through the air, the attenuation speed of the sound signal collected inside the vehicle is faster than that of the sound signal collected outside the vehicle. If the vehicle has a collision, the sound generated during the collision also propagates through the vehicle itself, and the difference between the attenuation speeds of the sound signals collected by the microphones inside and outside the vehicle is less than a preset value, which means that the degrees of attenuation of the two are consistent. If the difference is greater than or equal to the preset value, it means that the degrees of attenuation of the two are inconsistent. Based on this, as another way, the audio feature information comprises the degree of attenuation of the sound, the audio information comprises first audio information collected from inside the vehicle, for example, the first audio information is collected by the microphone installed inside the vehicle, and second audio information collected from outside the vehicle, for example, the second audio information is collected by the microphone installed outside the vehicle. The first degree of attenuation of the sound in the first audio information is obtained, and the second degree of attenuation of the sound in the second audio information is obtained. Optionally, the degree of attenuation of the sound can be obtained by reverberation time measurement, acoustic emission attenuation characteristic measurement, reverse integration method, acoustic velocity transmission method, etc. If the first degree of attenuation is consistent with the second degree of attenuation, it is indicated that the first audio information and the second audio information are collected when the vehicle has a collision, and at least one of them is used for subsequent collision detection, that is, it is determined that the first audio information and / or the second audio information is the to-be-detected audio information. Conversely, if the first degree of attenuation is inconsistent with the second degree of attenuation, it is indicated that the first audio information and the second audio information may not be collected when the vehicle has a collision, and the first audio information and the second audio information are not used for collision analysis.

[0055] Optionally, the attenuation degree can be characterized by an attenuation speed of the sound, i.e., the first attenuation degree is a first attenuation speed, and the second attenuation degree is a second attenuation speed. If a 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. Otherwise, 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.

[0056] In step S112, the first collision information is obtained according to the to-be-detected audio information.

[0057] As a manner, the to-be-detected audio information is compared with preset audio information to obtain a similarity, wherein the preset audio information is audio information collected in a vehicle collision case; and the first collision information is obtained according to the similarity. Optionally, the similarity can be directly taken as the first collision information.

[0058] In an embodiment, the first collision information is a collision prediction probability, and the second collision information is a distance between the vehicle and a target outside the vehicle. Step S130 can be as follows:

[0059] In step S131, a target threshold interval in which the collision prediction probability is located is determined from a plurality of threshold intervals.

[0060] The plurality of threshold intervals are preset, for example, the plurality of threshold intervals can be 60%-70%, 70%-80%, 80%-90%, and 90%-100% respectively. A threshold interval in which the collision prediction probability is located is determined as the target threshold interval, for example, the collision prediction probability is 83%, the threshold interval in which the collision prediction probability 83% is located is 80%-90%, and the threshold interval 80%-90% is determined as the target threshold interval. If the collision prediction probability does not belong to any of the plurality of preset threshold intervals, it is determined that a collision detection result that the vehicle does not collide is obtained.

[0061] In step S132, a target preset distance corresponding to the target threshold interval is determined according to a corresponding relationship between the threshold interval and the preset distance.

[0062] The preset threshold interval and the preset distance are associated, and optionally, the preset threshold interval value is inversely related to the preset distance. It can be understood that the greater the collision prediction probability, the looser the requirement for the distance between the vehicle and the target object, and the larger the preset distance can be set. Conversely, the smaller the collision prediction probability, the stricter the requirement for the distance between the vehicle and the target object, and the smaller the preset distance can be set. For example, the threshold interval 70%~80% corresponds to a preset distance of 10 cm, the threshold interval 80%~90% corresponds to a preset distance of 15 cm, and the threshold interval 90%~100% corresponds to a preset distance of 20 cm. In combination with the above example, based on the above association, the target preset distance corresponding to the target threshold interval 80%~90% is 15 cm.

[0063] In step S133, if the distance between the vehicle and the target object is less than the target preset distance, a collision detection result representing a collision with the target object is obtained.

[0064] 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 close, and a collision detection result representing 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 far, and a collision detection result representing no collision with the target object is obtained. In combination with the above example, the target preset distance is 15 cm, when the distance between the vehicle and the target object is 10 cm, which is less than the target preset distance 15 cm, a collision detection result representing a collision with the target object is obtained. When the distance between the vehicle and the target object is 20 cm, which is greater than the target preset distance 15 cm, a collision detection result representing no collision with the target object is obtained.

[0065] In this embodiment, the preset distance is flexibly selected according to the collision prediction probability, which improves the accuracy of the collision detection result detection under different conditions.

[0066] This embodiment provides a vehicle collision detection method, please refer to Figure 5 , the method comprises the following steps:

[0067] In step a, the vehicle-mounted microphone array receives the surrounding audio.

[0068] The 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 vehicle.

[0069] In step b, the near-field audio is subjected to audio feature recognition.

[0070] The audio feature is identified to determine the audio information to be detected.

[0071] In step c, the camera surrounding vehicle is identified.

[0072] A camera is deployed on a vehicle to capture images of the surrounding external environment or record videos of the external environment, for identifying target objects such as vehicles.

[0073] Step d, fusion of audio and video judgment results.

[0074] In combination with audio and video, audio and images are fused to jointly perform vehicle collision detection and obtain collision detection results.

[0075] Step e, post-event processing.

[0076] If the collision detection result indicates that a collision event occurs to the vehicle, the post-event processing can include reporting the collision detection result to a cloud server. Alternatively, if the target object identified to have collided is a pedestrian, the processing includes automatically parking the vehicle on the roadside. If the target object identified to have collided is a stone, the driving path is re-planned for continuing driving.

[0077] Based on the same inventive concept, the disclosure also provides a vehicle collision detection system, please refer to Figure 6 The vehicle collision detection system includes:

[0078] An audio processing system and a microphone array inside and outside the vehicle, the audio processing system being configured to process audio received by the microphone array, i.e., to extract audio information.

[0079] An audio feature recognition system configured to learn audio features of vehicle collisions and compare the audio from the audio processing system to evaluate the matching degree and give a preliminary judgment of the event status.

[0080] An intelligent driving system configured to identify surrounding vehicles and other target objects through a camera on the vehicle, as well as the relative position and distance between the vehicle and the target objects. The intelligent driving system is also configured to perform corresponding event processing actions when the logic control unit evaluates that an event has occurred.

[0081] A logic control unit configured to control the logic of the entire function and complete the fusion judgment of the audio and video evaluation of the event.

[0082] A network system configured to report collision events and related audio and video evidence to a cloud backend.

[0083] Based on the same inventive concept, the disclosure also provides a vehicle collision detection device, please refer to Figure 7 The vehicle collision detection device 200 includes a collection module 210, a determination module 220, a first acquisition module 230, a second acquisition module 240, and a detection module 250.

[0084] The collection module 210 is configured to acquire 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 a sound attenuation degree.

[0085] The determination module 220 is configured to determine to-be-detected audio information according to the audio feature information.

[0086] The first acquisition module 230 is configured to obtain the first bump information according to the to-be-detected audio information.

[0087] The second acquisition module 240 is configured to acquire external environment information of the vehicle, and obtain second bump information according to the external environment information.

[0088] The detection module 250 is configured to obtain a bump detection result according to the first bump information and the second bump information.

[0089] Optionally, the audio feature information includes a decibel value, and the determination module 220 includes:

[0090] The first determination module is configured to determine that the audio information is the to-be-detected audio information if the decibel value is greater than a preset decibel value.

[0091] Optionally, the audio feature information includes a decibel value, and the determination module 220 includes:

[0092] The rising gradient acquisition module is configured to determine a rising gradient of the decibel value.

[0093] The second determination module is configured to determine that the audio information is the to-be-detected audio information if the rising gradient is greater than a preset gradient.

[0094] 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 the determination module 220 includes:

[0095] The attenuation degree acquisition module is configured to acquire a first attenuation degree of sound in the first audio information, and acquire a second attenuation degree of sound in the second audio information.

[0096] The third determination module is configured to determine that the first audio information and / or the second audio information is the to-be-detected audio information if the first attenuation degree is consistent with the second attenuation degree.

[0097] Optionally, the first bump information acquisition module includes:

[0098] The similarity obtaining module is configured to compare the to-be-detected audio information with preset audio information to obtain a similarity, wherein the preset audio information is audio information collected in a vehicle collision situation.

[0099] The obtaining module is configured to obtain the first collision information according to the similarity.

[0100] Optionally, the external environment information includes an external environment image, and the second obtaining module 220 includes:

[0101] The distance obtaining module is configured to obtain a distance between the vehicle and a target object outside the vehicle according to the external environment image.

[0102] The distance predicting module is configured to determine the distance as the second collision information.

[0103] Optionally, the first collision information is a collision prediction probability, and the second collision information is a distance between the vehicle and a target object outside the vehicle, and the detecting module 230 includes:

[0104] The target threshold interval determining module is configured to determine a target threshold interval in which the collision prediction probability is located from a plurality of threshold intervals.

[0105] The target preset distance determining module is configured to determine a target preset distance corresponding to the target threshold interval according to a corresponding relationship between a threshold interval and a preset distance.

[0106] The collision detection result obtaining module is configured to obtain a collision detection result representing a collision with the target object if the distance between the vehicle and the target object is less than the target preset distance.

[0107] Optionally, the second obtaining module 240 includes:

[0108] The to-be-detected direction determining module is configured to determine a to-be-detected direction according to the audio information.

[0109] The external environment image shooting module is configured to obtain the external environment image collected by a target camera located at the to-be-detected direction.

[0110] As to the vehicle collision detection device 200 in the above embodiments, the specific manners in which the modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0111] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, the program instructions being executed by a processor to implement the steps of the vehicle collision detection method provided by the present disclosure.

[0112] Figure 8 is a block diagram of a vehicle 600 according to an example embodiment. The vehicle 600 can be a hybrid vehicle, for example, or a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other type of vehicle. The vehicle 600 can be an autonomous vehicle or a semi-autonomous vehicle.

[0113] Referring to Figure 8 , the vehicle 600 can include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 can include more or fewer subsystems, and each subsystem can include multiple components. In addition, each subsystem and each component of the vehicle 600 can be interconnected by wired or wireless means.

[0114] In some embodiments, the infotainment system 610 can include a communication system, an entertainment system, a navigation system, and the like.

[0115] The perception system 620 can include a number of sensors for sensing information of the environment surrounding the vehicle 600. For example, the perception system 620 can include a global positioning system (which can be a GPS system, a Beidou system, or other positioning system), an inertial measurement unit (IMU), a lidar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0116] The decision control system 630 can include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0117] The drive system 640 can include components that provide motive power for the vehicle 600. In one embodiment, the drive system 640 can include an engine, an energy source, a transmission system, and wheels. The engine can be one or a combination of an internal combustion engine, an electric motor, an air compression engine, or the like. The engine can convert energy provided by the energy source into mechanical energy.

[0118] Some or all functions of the vehicle 600 are controlled by the computing platform 650. The computing platform 650 can include at least one processor 651 and a memory 652, and the processor 651 can execute instructions 653 stored in the memory 652.

[0119] The processor 651 can be any conventional processor, such as a commercial available CPU. The processor can also include a graphics processing unit (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0120] The memory 652 can be implemented by any type of volatile or nonvolatile storage devices 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 storage, flash memory, magnetic or optical disk.

[0121] In addition to the instructions 653, the memory 652 can also store data, such as road maps, route information, the position, direction, speed of the vehicle, and the like. The data stored in the memory 652 can be used by the computing platform 650.

[0122] In the embodiments of the present disclosure, the processor 651 can execute the instructions 653 to complete all or part of the steps of the methods described above.

[0123] In another exemplary embodiment, a computer program product is also provided, which includes a computer program capable of being executed by a programmable device, and the computer program has code portions for executing the methods described above when executed by the programmable device.

[0124] In another exemplary embodiment, a computer readable storage medium is also provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the methods described above.

[0125] 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 thereof. Whether the functions are implemented by hardware or software depends on the specific application and design requirements of the whole system. Those skilled in the art can implement the functions described above in various ways for each specific application, but such implementation should not be understood as beyond the scope of the embodiments of the present application.

[0126] Furthermore, the word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs. Rather, use of the word exemplary is intended to present concepts in a concrete manner. As used in this application, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise, or clear from context, "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied under any of the foregoing instances. In addition, the articles "a" and "an" as used in this application and the appended claims should generally be construed to mean "one or more" unless specified otherwise or clear from context to be directed to a singular form. Thus, use of the articles in this application and the following claims is not limiting.

[0127] Also, although the disclosure has been described with respect to one or more implementations, those skilled in the art will readily appreciate that other alternatives can be used. It is contemplated that the disclosure can be carried out in alternate embodiments that do not depart from the spirit and scope of the present disclosure. Accordingly, other than in the instances where the exercise of the present disclosure's inherent right to exempt, alter, and / or adapt all equivalents, adaptations are in the spirit and scope of the present disclosure, as set forth in the following claims.

[0128] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features of the disclosure disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0129] It is to be understood that the disclosure is not limited to the precise construction described and as shown in the drawings, and that changes can be made in various modifications and equivalents without departing from the scope of the disclosure. The scope of the disclosure is limited only by the claims appended hereto.

Claims

1. A vehicle bump detection method characterized by, The method comprises: obtaining audio information inside and / or outside the vehicle, and obtaining audio feature information according to the audio information, wherein the audio feature information comprises a decibel value and / or a sound attenuation degree; determining to-be-detected audio information according to the audio feature information; obtaining first bump information according to the to-be-detected audio information, the first bump information being a bump prediction probability; obtaining external environment information of the vehicle, and obtaining second bump information according to the external environment information, the second bump information being a distance between the vehicle and a target object outside the vehicle; determining a target threshold interval in which the bump prediction probability is located from a plurality of threshold intervals; determining a target preset distance corresponding to the target threshold interval according to a corresponding relationship between a threshold interval and a preset distance; if the distance between the vehicle and the target object is less than the target preset distance, obtaining a collision detection result representing a bump with the target object.

2. The method of claim 1, wherein, The audio feature information comprises a decibel value, and the determining to-be-detected audio information according to the audio information comprises: if the decibel value is greater than a preset decibel value, determining that the audio information is the to-be-detected audio information.

3. The method of claim 1, wherein, The audio feature information comprises a decibel value, and the determining to-be-detected audio information according to the audio information comprises: determining an ascending gradient of the decibel value; if the ascending gradient is greater than a preset gradient, determining that the audio information is the to-be-detected audio information.

4. The method of claim 1, wherein, The audio feature information comprises a sound attenuation degree, the audio information comprises first audio information collected inside the vehicle and second audio information collected outside the vehicle, and the determining to-be-detected audio information according to the audio information comprises: obtaining a first attenuation degree of sound in the first audio information and a second attenuation degree of sound in the second audio information; if the first attenuation degree is consistent with the second attenuation degree, determining that the first audio information and / or the second audio information is the to-be-detected audio information.

5. The method according to any one of claims 1 to 4, characterized in that, The obtaining the first bump information according to the to-be-detected audio information comprises: comparing the to-be-detected audio information with preset audio information to obtain a similarity, wherein the preset audio information is audio information collected in a vehicle bumping case; obtaining the first bump information according to the similarity.

6. The method of claim 1, wherein, The external environment information comprises an external environment image, and the obtaining second bump information according to the external environment information comprises: obtaining a distance between the vehicle and the target object outside the vehicle according to the external environment image; determining the distance as the second bump information.

7. The method of claim 6, wherein, The obtaining external environment information of the vehicle comprises: determining a to-be-detected direction according to the audio information; obtaining the external environment image collected by a target camera located at the to-be-detected direction.

8. A vehicle bump detection apparatus characterized by comprising: The device comprises: a collection module 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 comprises a decibel value and / or a sound attenuation degree; a determination module configured to determine to-be-detected audio information according to the audio feature information; The first obtaining module is configured to obtain first swipe information according to the to-be-detected audio information, the first swipe information being swipe prediction probability. The second obtaining module is configured to obtain external environment information of the vehicle and obtain second swipe information according to the external environment information, the second swipe information being distance between the vehicle and a target object outside the vehicle. The detecting module is configured to determine a target threshold interval in which the swipe prediction probability is located from a plurality of threshold intervals, determine a target preset distance corresponding to the target threshold interval according to a corresponding relationship between threshold intervals and preset distances, and obtain a collision detection result representing swipe with the target object if the distance between the vehicle and the target object is less than the target preset distance.

9. A vehicle characterized by comprising: The method comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: obtain audio information inside and / or outside a vehicle and obtain audio feature information according to the audio information, wherein the audio feature information comprises decibel value and / or sound attenuation degree; determine to-be-detected audio information according to the audio feature information; obtain first swipe information according to the to-be-detected audio information, the first swipe information being swipe prediction probability; obtain external environment information of the vehicle and obtain second swipe information according to the external environment information, the second swipe information being distance between the vehicle and a target object outside the vehicle; determine a target threshold interval in which the swipe prediction probability is located from a plurality of threshold intervals; determine a target preset distance corresponding to the target threshold interval according to a corresponding relationship between threshold intervals and preset distances; obtain a collision detection result representing swipe with the target object if the distance between the vehicle and the target object is less than the target preset distance.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-7.

11. A computer program product, characterised in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-7. The computer program is executed by the processor to implement the steps of the method of any one of claims 1-7.

Images