CN113246894B - Vehicle collision detection method and device - Google Patents
Vehicle collision detection method and device Download PDFInfo
- Publication number
- CN113246894B CN113246894B CN202010089934.2A CN202010089934A CN113246894B CN 113246894 B CN113246894 B CN 113246894B CN 202010089934 A CN202010089934 A CN 202010089934A CN 113246894 B CN113246894 B CN 113246894B
- Authority
- CN
- China
- Prior art keywords
- information
- sound
- target vehicle
- audio information
- collision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
- B60R21/0136—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over responsive to actual contact with an obstacle, e.g. to vehicle deformation, bumper displacement or bumper velocity relative to the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
- B60R2021/01302—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over monitoring vehicle body vibrations or noise
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W2030/082—Vehicle operation after collision
Abstract
The invention relates to a vehicle collision detection method and a vehicle collision detection device, wherein the method comprises the following steps: acquiring audio information of a target vehicle in a running process in real time; analyzing and processing the audio information to obtain sound characteristic information of the audio information; acquiring current state information and running environment information of the target vehicle; judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the driving environment information; when the target vehicle collides, generating collision event information according to the sound characteristic information; and sending the collision event information to an automatic driving module so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information. The invention can accurately detect the slight collision between the vehicle and the short-distance barrier by analyzing the audio information collected by the sound sensor arranged on the vehicle frame, the state information of the vehicle and the environmental information.
Description
Technical Field
The invention relates to the technical field of automobile safety, in particular to a vehicle collision detection method and device.
Background
Automatic driving becomes an important direction for the technical development of the modern automobile industry and the electronic and electrical industry, and the combination of automatic driving and new energy in the future can reduce environmental pollution and improve road traffic capacity, so that the technology for automatic driving becomes a key research field of the current high and new technology.
During automatic driving, the vehicle may have a slight traffic accident such as scraping with other traffic participants such as road facilities and non-motor vehicles, and also may have a situation in which a small obstacle scrapes with the vehicle chassis when passing over a small target on the ground. When the situation occurs, safety management personnel at the background need to be informed in time to judge the damage situations of other traffic participants and vehicles and take corresponding measures; meanwhile, events need to be recorded in time for research and development personnel to analyze and avoid.
But the sensors of current autonomous vehicles are mainly cameras, millimeter wave radars, laser radars, ultrasonic radars, etc. Due to the detection principle of the sensor, the existing sensor has a detection blind area in a short distance, so that the existing sensor cannot sense that the vehicle slightly scrapes an obstacle in the short distance; due to the fact that the sensors detect angles and tolerate the ground obstacles, the existing sensors may miss detection of targets with low ground, so that the existing sensors cannot detect scraping events of vehicles and the small ground obstacles.
In addition, the collision detection method of the prior art generally detects the collision of the vehicle by detecting the acceleration of the vehicle, but this method can only detect the collision with a large influence on the acceleration and cannot detect the scratch event with a small influence on the acceleration.
Disclosure of Invention
In view of the above problems of the prior art, an object of the present invention is to provide a vehicle collision detection method and apparatus that can accurately detect a light collision between a vehicle and a short-distance obstacle in a timely manner.
In order to solve the above problem, the present invention provides a vehicle collision detection method including:
acquiring audio information of a target vehicle in a running process in real time;
analyzing and processing the audio information to obtain sound characteristic information of the audio information;
acquiring current state information and running environment information of the target vehicle;
judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the driving environment information;
when the target vehicle collides, generating collision event information according to the sound characteristic information;
and sending the collision event information to an automatic driving module so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information.
Further, the real-time acquisition of the audio information of the target vehicle in the driving process includes:
acquiring first audio information sent by a first sound sensor, wherein the first sound sensor is arranged on a frame of the target vehicle and is used for acquiring sound of a vehicle body of the target vehicle;
and acquiring second audio information sent by a second sound sensor, wherein the second sound sensor is used for acquiring the environmental sound in the running process of the target vehicle.
Further, the analyzing the audio information to obtain the sound characteristic information of the audio information includes:
comparing and analyzing the first audio information and the second audio information, and removing environmental noise in the first audio information to obtain target audio information;
and performing content identification processing on the target audio information to obtain sound characteristic information of the audio information.
Further, the determining whether the target vehicle collides according to the sound feature information, the current state information, and the driving environment information includes:
determining collision sound characteristic information according to the current state information and the driving environment information;
calculating the matching degree of the sound characteristic information and the collision sound characteristic information;
and when the matching degree of the sound characteristic information and the collision sound characteristic information is greater than a preset threshold value, judging that the target vehicle collides.
Further, before determining whether the target vehicle collides according to the sound feature information, the current state information, and the driving environment information, the method further includes:
matching the sound characteristic information with sound characteristic data in a sound database;
if the matching is successful, determining that the target vehicle is not collided;
and if the matching fails, executing the step of judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the running environment information.
Further, the generating collision event information according to the sound characteristic information when the target vehicle collides comprises:
when the target vehicle collides, determining the type of the collision event according to the sound characteristic information;
and generating collision event information according to the event type and the sound characteristic information.
Further, the method further comprises:
and sending the collision event information to an automatic driving control center so that the automatic driving control center judges whether emergency stop is needed or not according to the collision event information, and sending an emergency stop instruction to an automatic driving module so that the automatic driving module controls the target vehicle to stop emergently when emergency stop is needed.
Further, the method further comprises:
sending the collision event information to an automatic driving control center;
and acquiring a sound database sent by the automatic driving control center, wherein the sound database is generated by the automatic driving control center according to the collision event information.
Another aspect of the present invention protects a vehicle collision detection apparatus, including:
the acquisition unit is used for acquiring audio information in the running process of the target vehicle in real time;
the processing unit is used for analyzing and processing the audio information to obtain sound characteristic information of the audio information;
an acquisition unit configured to acquire current state information and driving environment information of the target vehicle;
a judging unit, configured to judge whether the target vehicle collides or not according to the sound feature information, the current state information, and the driving environment information;
a generating unit configured to generate collision event information according to the sound feature information when the target vehicle collides;
and the sending unit is used for sending the collision event information to an automatic driving module so that the automatic driving module adjusts the automatic driving decision of the target vehicle according to the collision event information.
Further, the acquisition unit comprises a first sound sensor and a second sound sensor;
the first sound sensor is arranged on a frame of the target vehicle and used for collecting sound of a vehicle body of the target vehicle;
the second sound sensor is arranged near the first sound sensor and used for collecting the environmental sound in the running process of the target vehicle.
Due to the technical scheme, the invention has the following beneficial effects:
(1) According to the vehicle collision detection method and device, the audio information in the vehicle driving process is collected and analyzed, whether abnormal sounds such as scraping and collision occur in the vehicle driving process is determined, whether scraping and collision events occur in the vehicle is further judged, and when the scraping and collision events occur, the automatic driving module and the automatic driving control center are timely informed to take appropriate countermeasures, so that the safety in the vehicle driving process can be improved.
(2) According to the vehicle collision detection method and device, the sound of the vehicle body transmitted through the structure and the environmental noise transmitted through the air are respectively collected and compared and analyzed, so that the environmental noise can be effectively filtered, the reliability of signal collection is improved, and the accuracy of collision detection is further improved.
(3) According to the vehicle collision detection method and device, the collected audio information is matched with the normal sound characteristic data in the sound database in advance, and the judgment standard of the collision sound in the current state is determined by combining the current state information and the driving environment information of the vehicle, so that the accuracy of collision detection can be further improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description of the embodiment or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a flow chart of a vehicle collision detection method provided by one embodiment of the present invention;
FIG. 2 is a flow chart of a vehicle collision detection method provided by another embodiment of the present invention;
FIG. 3 is a flow chart of a vehicle collision detection method provided by another embodiment of the present invention;
fig. 4 is a schematic structural diagram of a vehicle collision detection apparatus provided in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to the description, fig. 1 shows a flow of a vehicle collision detection method according to an embodiment of the present invention. The method can be applied to a vehicle collision detection device for detecting micro collision events such as scraping and the like with road facilities, non-motor vehicles, low and small ground obstacles and the like in the driving process of the vehicle. As shown in fig. 1, the method may include:
s110: and acquiring audio information of the target vehicle in the running process in real time.
In the embodiment of the invention, the audio information in the running process of the target vehicle can be collected in real time through the sound sensor, and the sound sensor can comprise a Micro Electro Mechanical System (MEMS) microphone, a vibration sensor and the like.
In one possible embodiment, the information of audio frequency, vibration and the like of abnormal sound propagated through the vehicle body structure in the running process of the target vehicle can be collected in real time through a sound sensor arranged on the frame of the target vehicle, and the information is distinguished from 'air propagation'. Environmental noises such as wind noise, a loudspeaker and the like can be effectively filtered through 'structural propagation', and the signal-to-noise ratio of the collected signals is improved.
In one possible embodiment, the real-time collecting of the audio information during the driving process of the target vehicle may include:
acquiring first audio information sent by a first sound sensor, wherein the first sound sensor is arranged on a frame of the target vehicle and is used for acquiring sound of a vehicle body of the target vehicle;
and acquiring second audio information sent by a second sound sensor, wherein the second sound sensor is used for acquiring the environmental sound in the running process of the target vehicle.
Specifically, the first sound sensor may be mounted on the vehicle frame, and directly pick up information such as audio, vibration, and the like of abnormal sounds of the vehicle, which are propagated through the "structure" of the vehicle body, as distinguished from "air propagation". Can be through near first sound sensor sets up the second sound sensor for gather the vehicle ambient noise of in-process of traveling, through right first audio information with the analysis of comparison can further increase the interference killing feature, improve collision detection's accuracy.
S120: and analyzing and processing the audio information to obtain the sound characteristic information of the audio information.
In the embodiment of the present invention, the sound characteristic information may include information such as sound intensity, sound source, voiceprint characteristics, and power spectrum. The audio information may be analyzed and processed by a Processing Unit such as a Central Processing Unit (CPU), a Digital Signal Processor (DSP), and a Field-Programmable Gate Array (FPGA).
In a possible embodiment, the analyzing the audio information to obtain the sound characteristic information of the audio information may include:
comparing and analyzing the first audio information and the second audio information, and removing environmental noise in the first audio information to obtain target audio information;
and performing content identification processing on the target audio information to obtain sound characteristic information of the audio information.
In the embodiment of the present invention, the first audio information and the second audio information may be compared and analyzed to determine whether the first audio information is ambient noise or abnormal collision sound, and when the first audio information is abnormal collision sound, the ambient noise in the first audio information may be removed before detailed analysis is performed to obtain the target audio information. In addition, the content identification processing of the target audio information may include: firstly, preprocessing the target audio information, wherein the preprocessing may include conditioning, hardware noise reduction, analog-to-Digital (AD) conversion, and the like, on the target audio information to convert the target audio information into a signal that can be digitally analyzed; and then, carrying out digital noise reduction processing, spectrum analysis, wavelet signal analysis, voiceprint analysis, power spectrum analysis and the like on the preprocessed target audio information, and also carrying out digital operation analysis such as voiceprint recognition, voiceprint matching and the like on the preprocessed target audio information based on an artificial intelligence algorithm so as to obtain the sound characteristic information of the audio information.
It should be noted that multiple methods may be used to perform content identification processing on the target audio information to obtain the sound characteristic information of the audio information, or only one method may be used to perform content identification processing on the target audio information to obtain the sound characteristic information of the audio information, which is not limited in the present invention.
S130: and acquiring the current state information and the running environment information of the target vehicle.
In the embodiment of the invention, the current state information of the target vehicle can comprise information such as current vehicle speed information and engine output power, and the current state information of the target vehicle can be obtained through an automatic driving module; the driving environment information may include high-precision maps, ground information such as vehicle-mounted sensor (including camera, radar, etc.) data, and external environment information such as weather information.
S140: and judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the driving environment information.
In the embodiment of the present invention, whether the target vehicle collides may be determined according to whether the sound feature information of the audio information conforms to the sound feature of the scratch and other minor collisions, for example, it may be determined whether the features such as the sound size and the length exceed a set value, it may be determined whether the power spectrum exceeds a set threshold, and it may be determined whether the voiceprint feature conforms to the voiceprint feature of the scratch and other sounds. The current state information and the driving environment information can be used for compensating a judgment standard of collision, and the judgment accuracy is improved.
In one possible embodiment, as shown in fig. 2, the determining whether the target vehicle has collided with based on the sound characteristic information, the current state information and the running environment information may include:
s141: and determining the characteristic information of the collision sound according to the current state information and the driving environment information.
S142: and calculating the matching degree of the sound characteristic information and the collision sound characteristic information.
S143: and when the matching degree of the sound characteristic information and the collision sound characteristic information is greater than a preset threshold value, judging that the target vehicle collides.
The collision sound characteristic information is a sound characteristic of micro-collision such as scraping generated under the current state and the driving environment of the vehicle, when the current state information is different from the driving environment information, different collision sound characteristic information can be obtained, and when the matching degree of the sound characteristic information and the collision sound characteristic information is larger than a preset threshold value, the sound emitted by the collision can be judged according to the audio information, and then the target vehicle is judged to collide.
In one possible embodiment, before the determining whether the target vehicle collides according to the sound characteristic information, the current state information, and the driving environment information, the method may further include:
matching the sound characteristic information with sound characteristic data in a sound database;
if the matching is successful, judging that the target vehicle is not collided;
and if the matching fails, executing a step of judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the running environment information.
The sound database is normal sound characteristic data of the vehicle under various working conditions, such as characteristic data of light impact sound of small splashed stones and the vehicle frame when the vehicle runs on a road surface full of small broken stones. The sound database can be obtained through theoretical analysis, vehicle experiments and the like of the vehicle before leaving a factory, and can also be obtained through an automatic driving control center, and different vehicle types have different sound database contents. And matching the sound characteristic information with sound characteristic data in a sound database, judging whether the audio information is environmental noise, engine noise or abnormal collision sound, and when the audio information is judged to be the abnormal collision sound, continuing to perform detailed analysis and judgment.
S150: and when the target vehicle collides, generating collision event information according to the sound characteristic information.
In the embodiment of the invention, when the target vehicle is judged not to be collided, the detection is finished, and no treatment can be carried out; when it is determined that the target vehicle collides, it is necessary to take corresponding measures according to the collision situation.
In one possible embodiment, the generating collision event information based on the sound characteristic information when the target vehicle collides may include:
when the target vehicle collides, determining the type of the collision event according to the sound characteristic information;
and generating collision event information according to the event type and the sound characteristic information.
Specifically, the event type may include side scratch, chassis scratch, and the like, and the event type of the collision may be determined by classifying according to the voiceprint features of the audio information, where the collision event information may include information such as an event type, sound intensity, and sound source.
S160: and sending the collision event information to an automatic driving module so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information.
In the embodiment of the invention, the collision event information CAN be sent to the automatic driving module through Controller Area Network (CAN) communication or an asynchronous transmission standard interface (RS 232 interface). Accordingly, after receiving the collision event information, the autopilot module enters an automatic processing program, that is, the autopilot module may determine an operation (including operations such as continuing to travel, decelerating to travel, and processing an emergency stop) to be taken according to the collision event information. Specifically, the automatic driving module may determine the severity of the collision and determine whether emergency stop processing is required according to the crash event information and the comprehensive information such as data of other vehicle-mounted sensors (including a camera, a laser radar, and the like).
In one possible embodiment, as shown in fig. 3, the method may further include:
s170: and sending the collision event information to an automatic driving control center so that the automatic driving control center judges whether emergency stop is needed or not according to the collision event information, and sending an emergency stop instruction to an automatic driving module when the emergency stop is needed so that the automatic driving module controls the target vehicle to stop emergently.
Specifically, the collision event information may be sent to an automatic driving control center in a remote communication manner, and the automatic driving control center may determine whether manual intervention is required according to the collision event information. The automatic driving control center can manually call and check the video of the collision event and judge whether the sound intensity and the collision type of the collision are accurate or not. When the collision event is judged to be an effective event, such as a major collision event or a collision event with pedestrians, small animals and the like, the automatic driving vehicle is controlled to decelerate or enter an emergency stop state in a remote control mode. And when the collision event is judged not to be an effective event but a system false alarm, analyzing the reason of the false alarm information.
In one possible embodiment, the method may further include:
sending the collision event information to an automatic driving control center;
and acquiring a sound database sent by the automatic driving control center, wherein the sound database is generated by the automatic driving control center according to the collision event information.
Specifically, when it is determined that the collision event is not an "effective event," but a system false alarm, the sound database corresponding to the target vehicle may be updated according to the false alarm sound feature information, and the updated sound database may be sent to the collision detection device of the target vehicle, so that when the same event is encountered next time, repeated false alarms may be avoided, and the accuracy of collision determination may be improved. The automatic driving control center can also send the updated sound database to a collision detection device of other vehicles with the same type as the target vehicle, so that false alarm of other vehicles to collision is reduced.
In summary, the vehicle collision detection method of the present invention has the following beneficial effects:
(1) According to the vehicle collision detection method, the audio information in the vehicle driving process is collected and analyzed, whether abnormal sounds such as scraping and collision occur in the vehicle driving process is determined, whether scraping and collision events occur in the vehicle is further judged, and when the scraping and collision events occur, the automatic driving module and the automatic driving control center are timely informed to take appropriate countermeasures, so that the safety in the vehicle driving process can be improved.
(2) According to the vehicle collision detection method, the sound of the vehicle body transmitted through the structure and the environmental noise transmitted through the air are respectively collected and compared and analyzed, so that the environmental noise can be effectively filtered, the reliability of signal collection is improved, and the accuracy of collision detection is further improved.
(3) According to the vehicle collision detection method, the collected audio information is matched with the normal sound characteristic data in the sound database in advance, and the judgment standard of the collision sound in the current state is determined by combining the current state information and the driving environment information of the vehicle, so that the accuracy of collision detection can be further improved.
Referring to the description to fig. 4, there is shown a structure of a vehicle collision detecting apparatus 400 according to an embodiment of the present invention. As shown in fig. 4, the apparatus 400 may include:
the acquisition unit 410 is used for acquiring audio information in the running process of the target vehicle in real time;
the processing unit 420 is configured to analyze and process the audio information to obtain sound characteristic information of the audio information;
an obtaining unit 430, configured to obtain current state information and driving environment information of the target vehicle;
a determining unit 440, configured to determine whether the target vehicle collides according to the sound feature information, the current state information, and the driving environment information;
a generating unit 450 for generating collision event information according to the sound characteristic information when the target vehicle collides;
a sending unit 460, configured to send the collision event information to an automatic driving module, so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information.
In one possible embodiment, the acquisition unit 410 may include a first sound sensor and a second sound sensor;
the first sound sensor is arranged on a frame of the target vehicle and used for collecting sound of a vehicle body of the target vehicle;
the second sound sensor is arranged near the first sound sensor and used for collecting the environmental sound in the running process of the target vehicle.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments, which are not described herein again.
The foregoing description has disclosed fully preferred embodiments of the present invention. It should be noted that those skilled in the art can make modifications to the embodiments of the present invention without departing from the scope of the appended claims. Accordingly, the scope of the appended claims is not to be limited to the specific embodiments described above.
Claims (7)
1. A vehicle collision detection method characterized by comprising:
acquiring audio information of a target vehicle in a running process in real time;
analyzing and processing the audio information to obtain sound characteristic information of the audio information;
acquiring current state information and running environment information of the target vehicle;
judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the driving environment information;
when the target vehicle collides, generating collision event information according to the sound characteristic information;
sending the collision event information to an automatic driving module so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information;
wherein, the real-time audio information who gathers the target vehicle in-process that traveles includes:
acquiring first audio information sent by a first sound sensor, wherein the first sound sensor is arranged on a frame of the target vehicle and is used for acquiring sound of a vehicle body of the target vehicle;
acquiring second audio information sent by a second sound sensor, wherein the second sound sensor is used for acquiring environmental sound in the running process of the target vehicle;
the analyzing the audio information to obtain the sound characteristic information of the audio information includes:
comparing and analyzing the first audio information and the second audio information, and removing environmental noise in the first audio information to obtain target audio information;
and performing content identification processing on the target audio information to obtain sound characteristic information of the audio information.
2. The method according to claim 1, wherein the determining whether the target vehicle has collided according to the sound characteristic information, the current state information, and the running environment information includes:
determining collision sound characteristic information according to the current state information and the driving environment information;
calculating the matching degree of the sound characteristic information and the collision sound characteristic information;
and when the matching degree of the sound characteristic information and the collision sound characteristic information is greater than a preset threshold value, judging that the target vehicle collides.
3. The method according to claim 1, wherein before determining whether the target vehicle has collided with based on the sound characteristic information, the current state information, and the running environment information, further comprising:
matching the sound characteristic information with sound characteristic data in a sound database;
if the matching is successful, judging that the target vehicle is not collided;
and if the matching fails, executing the step of judging whether the target vehicle collides or not according to the sound characteristic information, the current state information and the running environment information.
4. The method of claim 1, wherein generating collision event information from the sound feature information when the target vehicle collides comprises:
when the target vehicle collides, determining the type of the collision event according to the sound characteristic information;
and generating collision event information according to the event type and the sound characteristic information.
5. The method of claim 1, further comprising:
and sending the collision event information to an automatic driving control center so that the automatic driving control center judges whether emergency stop is needed or not according to the collision event information, and sending an emergency stop instruction to an automatic driving module when the emergency stop is needed so that the automatic driving module controls the target vehicle to stop emergently.
6. The method according to claim 1 or 5, characterized in that the method further comprises:
sending the collision event information to an automatic driving control center;
and acquiring a sound database sent by the automatic driving control center, wherein the sound database is generated by the automatic driving control center according to the collision event information.
7. A vehicle collision detection apparatus characterized by comprising:
the acquisition unit is used for acquiring audio information in the running process of the target vehicle in real time;
the processing unit is used for analyzing and processing the audio information to obtain sound characteristic information of the audio information;
an acquisition unit configured to acquire current state information and driving environment information of the target vehicle;
a judging unit, configured to judge whether the target vehicle collides or not according to the sound feature information, the current state information, and the driving environment information;
a generating unit configured to generate collision event information according to the sound feature information when the target vehicle collides;
the sending unit is used for sending the collision event information to an automatic driving module so that the automatic driving module adjusts an automatic driving decision of the target vehicle according to the collision event information;
wherein, the acquisition unit is specifically configured to:
acquiring first audio information sent by a first sound sensor, wherein the first sound sensor is arranged on a frame of the target vehicle and is used for acquiring sound of a vehicle body of the target vehicle;
acquiring second audio information sent by a second sound sensor, wherein the second sound sensor is used for acquiring environmental sound in the running process of the target vehicle;
the processing unit is specifically configured to:
comparing and analyzing the first audio information and the second audio information, and removing environmental noise in the first audio information to obtain target audio information;
and performing content identification processing on the target audio information to obtain sound characteristic information of the audio information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089934.2A CN113246894B (en) | 2020-02-13 | 2020-02-13 | Vehicle collision detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089934.2A CN113246894B (en) | 2020-02-13 | 2020-02-13 | Vehicle collision detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113246894A CN113246894A (en) | 2021-08-13 |
| CN113246894B true CN113246894B (en) | 2022-11-22 |
Family
ID=77219770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010089934.2A Active CN113246894B (en) | 2020-02-13 | 2020-02-13 | Vehicle collision detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113246894B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102004043597A1 (en) * | 2004-09-06 | 2006-03-09 | Robert Bosch Gmbh | Device for detecting a collision of a vehicle with an obstacle |
| CN102568153A (en) * | 2010-12-20 | 2012-07-11 | 淄博高新区联创科技服务中心 | Vehicle collision detection device |
| JP5816533B2 (en) * | 2011-11-16 | 2015-11-18 | 株式会社ケーヒン | Vehicle collision determination device |
| KR101526668B1 (en) * | 2013-06-10 | 2015-06-05 | 현대자동차주식회사 | Apparatus for detecting accidental contact of the vehicle and method thereof |
| KR101573744B1 (en) * | 2014-03-13 | 2015-12-14 | 재단법인 다차원 스마트 아이티 융합시스템 연구단 | Apparatus for Recording Video Data based on Input Sound Signal and Method Thereof |
| CN105976450A (en) * | 2016-04-27 | 2016-09-28 | 百度在线网络技术（北京）有限公司 | Unmanned vehicle data processing method and device, and black box system |
| CN106027865B (en) * | 2016-06-14 | 2022-04-26 | 北京钛方科技有限责任公司 | Vehicle collision triggering alarm and recording device and detection method thereof |
| JP2019181989A (en) * | 2018-04-02 | 2019-10-24 | 株式会社デンソー | Collision detection device |
| CN109291872A (en) * | 2018-10-29 | 2019-02-01 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and the storage medium of automatic driving vehicle |
-
2020
- 2020-02-13 CN CN202010089934.2A patent/CN113246894B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113246894A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112885144B (en) | Early warning method and system for vehicle crash event in construction operation area | |
| KR101731050B1 (en) | Automatic incident detection apparatus using composite sensor of acoustic sensor, radar sensor and image sensor, and method for the same | |
| CN109460007B (en) | Abnormal sound diagnosis and driving decision method for hybrid electric vehicle | |
| WO2019185045A1 (en) | Transport device collision detection, alarm, and guard method | |
| CN107464416B (en) | Semi-automatic driving method and system for bus | |
| CN112277936B (en) | Vehicle collision detection processing method and device, vehicle-mounted terminal and storage medium | |
| CN113568002A (en) | Rail transit active obstacle detection device based on laser and image data fusion | |
| CN113096387B (en) | Vehicle-mounted road surface monitoring and early warning method, system, terminal and storage medium | |
| EP1657568B1 (en) | System and method for monitoring the external environment of a motor vehicle | |
| CN113022434A (en) | Automatic door opening anti-collision device and method for vehicle | |
| CN114964330A (en) | Fault monitoring system and method based on optical fiber sensing and multi-parameter fusion | |
| CN113246894B (en) | Vehicle collision detection method and device | |
| CN113246893A (en) | Vehicle collision processing method and system | |
| CN211527320U (en) | Automobile-used laser figure surveys barrier device | |
| CN116704644A (en) | Automobile management and control platform based on cloud data processing and multi-source data analysis | |
| CN113643551B (en) | New energy automobile identification system, filtering system | |
| CN111806432B (en) | Vehicle avoiding method and device, vehicle and storage medium | |
| CN111746451B (en) | Detection method, device, detection system, vehicle and medium | |
| CN110889409B (en) | Method, device, equipment and storage medium for monitoring and optimizing automobile radar | |
| CN210119708U (en) | Omnidirectional railway inspection robot | |
| CN210442657U (en) | Intelligent transportation monitoring system for wind generating set and components | |
| CN211001120U (en) | Vehicle distance testing device based on DSRC and binocular camera | |
| CN111352072B (en) | Blind area detection device and method for vehicle | |
| CN113313654B (en) | Laser point cloud filtering denoising method, system, equipment and storage medium | |
| CN117864075A (en) | Active brake control method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |