Method, device and equipment for detecting falling during vehicle traveling and storage medium

Abstract

The invention discloses a method, a device and equipment for detecting falling during vehicle traveling and a storage medium. Comprising the steps that when a vehicle enters a disaster early warning road section, acceleration data and GPS track data of the vehicle are extracted based on a preset time interval; whether falling conditions are met or not is judged based on the acceleration data change characteristics, and when the falling conditions are met, falling starting time and falling ending time are determined based on the acceleration change time; and in a time period from the falling starting time to the falling ending time, judging that the vehicle falls on the basis of stopping updating of the GPS track data or the vehicle speed is zero. According to the method, the vehicle falling behavior can still be quickly found under the severe weather condition or in the environment with poor light, and the problem of road condition sensing blind areas caused by video detection failure and portal flow feedback delay is solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method, device, equipment and storage medium for detecting a vehicle falling while moving. Background Art

[0002] Extreme scenarios such as natural disasters severely restrict the safe operation of highways, and bring huge challenges to infrastructure and traffic operation management. In recent years, with the frequent occurrence of disasters such as road subgrade collapse and bridge overturning caused by large-scale precipitation, the safety of life and property of the traveling public has been seriously damaged. In particular, the traffic volume on highways is large and the speed is fast. When disasters such as road subgrade collapse and bridge overturning occur, if the visibility is poor at night or in bad weather, it is difficult for drivers to detect dangers in time and deal with them decisively, and vicious traffic accidents such as vehicle falls and mass deaths and injuries are inevitable. Therefore, if vehicle falls and other events can be discovered in time and warnings can be issued to upstream vehicles, it is an effective means to avoid the deterioration of disasters and reduce casualties and the impact on traffic operations.

[0003] At present, highways have built a relatively complete rapid event discovery mechanism based on video, gantry traffic and other sensing methods. However, at night or in bad weather, video monitoring is affected by visibility and cannot effectively detect vehicle fall events. Although the road operation interruption and traffic drop caused by the vehicle fall can be reflected on the gantry flow sensor, the detection result will have a large delay due to the low density of the gantry flow sensor. In the era of mobile Internet, location service apps such as navigation maps can be used as high-precision location sensors, and crowdsourced location data after desensitization is also widely used in new business forms such as dynamic road condition calculation, navigation route planning and guidance, and electronic map updates. Based on crowdsourced location data, the "three emergencies and one speed" behavior detection of vehicles during driving, such as sudden acceleration, sudden lane change, sudden braking and speeding, is also widely used for safety warning of following vehicles, playing a significant role in improving driving safety. However, the "three emergencies and one speed" behavior is very common on highways, and it can only be used as a sufficient but not necessary condition for the detection of vehicle fall events. Therefore, it is necessary to find more accurate detection methods and means for vehicle falls during driving. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for detecting a vehicle falling while moving, so as to at least solve the technical problem in the related art that it is difficult to quickly and accurately detect a vehicle falling while moving.

[0005] According to one aspect of an embodiment of the present application, a method for detecting a vehicle falling while moving is provided, comprising:

[0006] When a vehicle enters a disaster warning section, the acceleration data and GPS trajectory data of the vehicle are extracted based on a preset time interval;

[0007] Determine whether the falling condition is met based on the acceleration data change characteristics, and if the falling condition is met, determine the falling start time and the falling end time based on the acceleration change time;

[0008] During the time period from the start time of the fall to the end time of the fall, based on the GPS trajectory data stopping updating or the vehicle speed being zero, it is determined that the vehicle has fallen;

[0009] Based on the fact that the number of trajectories downstream of the falling position is zero, or multiple vehicles fall at the same location, it is determined that the road section at the falling position is damaged.

[0010] In one embodiment, judging whether a falling condition is met based on a change feature of acceleration data, and determining a falling start time and a falling end time based on an acceleration change time when the falling condition is met, includes:

[0011] Calculating a combined acceleration modulus based on the acceleration data;

[0012] Determining whether the vehicle is in a weightless state based on the combined acceleration model;

[0013] When the vehicle is in a weightless state, determining whether the rate of change of the combined acceleration modulus after the first weightlessness occurs is greater than a preset threshold;

[0014] If it is greater than a preset threshold, and the combined acceleration modulus has a fluctuating change characteristic of falling and rebounding, it is determined that the vehicle meets the falling condition;

[0015] The start time of weightlessness is recorded as the start time of falling, and the end time of the combined acceleration mode fluctuation is recorded as the end time of falling.

[0016] In one embodiment, after determining that the vehicle has fallen, the method further includes:

[0017] The vehicle terminal or user handheld terminal of the fallen vehicle pops up a one-key alarm interface;

[0018] The vehicle-mounted terminal of the fallen vehicle or the user's handheld terminal sends out a voice prompt message or obtains the user's voice alarm help message based on the voice interaction module.

[0019] In one embodiment, after determining that the vehicle has fallen, the method further includes:

[0020] Determine the falling position of the vehicle and obtain the number of vehicle tracks downstream of the falling position;

[0021] When the number of tracks downstream of the vehicle falling position is zero, or multiple vehicles fall at the same location, it is determined that the road section at the falling position is damaged.

[0022] In one embodiment, when the number of trajectories downstream of the vehicle falling position is zero, or multiple vehicles fall at the same location, determining that the road section at the falling position is damaged includes:

[0023] Obtain all vehicles that pass the falling position after the falling start time, and count the number of vehicles that have fallen among the passing vehicles;

[0024] Counting the number of first vehicles that pass the falling position and arrive at the road section downstream of the falling position after the falling start time;

[0025] Counting the number of second vehicles on the upstream section of the falling position;

[0026] When the number of fallen vehicles is greater than a preset threshold, or the second number of vehicles is greater than 0 and the first number of vehicles is equal to 0, it is determined that the road section where the fall location is located is damaged.

[0027] In one embodiment, after determining that the falling position section is damaged, the method further includes:

[0028] Generate accident information based on the fall start time, number of fallen vehicles, and damaged road section information;

[0029] The accident information is sent to the traffic control department service end.

[0030] In one embodiment, before the vehicle enters the disaster warning section, the method further includes:

[0031] Determine whether the vehicle enters the target detection geo-fence;

[0032] Based on the weather conditions within the target detection geo-fence and the vehicle entry time, determining whether it is a target detection period;

[0033] When the vehicle enters the target detection geographic fence and falls within the target detection period, it is determined that the vehicle enters the disaster warning section.

[0034] According to another aspect of the embodiment of the present application, there is provided a device for detecting a vehicle falling while moving, comprising:

[0035] A data acquisition module, used to extract the acceleration data and GPS trajectory data of the vehicle based on a preset time interval when the vehicle enters a disaster warning section;

[0036] A first judgment module, used to judge whether a falling condition is met based on the acceleration data change characteristics, and if the falling condition is met, determine the falling start time and the falling end time based on the acceleration change time;

[0037] The second judgment module is used to determine that the vehicle has fallen within the time period from the start time of the fall to the end time of the fall based on the fact that the GPS trajectory data stops updating or the vehicle speed is zero.

[0038] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the method for detecting a vehicle falling while moving through the computer program.

[0039] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for detecting a vehicle falling while moving when running.

[0040] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0041] For the detection of a vehicle falling while moving, the embodiment of the present application first adopts the first condition: judging whether a vehicle has fallen based on the acceleration change characteristics. Then the second condition is used: eliminating the possibility of misjudging the vehicle falling based on whether the trajectory data stops updating. When the first condition and the second condition are met at the same time, it is possible to accurately judge that a vehicle has fallen. Its advantage is that whether in bad weather conditions or in a poorly lit environment, this method can still quickly detect the falling behavior of a moving vehicle, filling the problem of blind spots in road condition perception caused by video detection failure and gantry flow feedback delay. It is also more targeted than the "three emergencies and one speed" behavior detection, and it gains rapid response time for safe highway passage and emergency handling of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 is a flow chart of an optional method for detecting a vehicle falling while moving according to an embodiment of the present application;

[0044] Figure 2 is a flow chart of another optional method for detecting a vehicle falling while moving according to an embodiment of the present application;

[0045] Figure 3 is a flow chart of another optional method for detecting a vehicle falling while moving according to an embodiment of the present application;

[0046] Figure 4 This is a schematic diagram of a vehicle falling while driving according to an embodiment of the present application;

[0047] Figure 5 is a schematic diagram of the change of the combined acceleration during a vehicle falling process according to an embodiment of the present application;

[0048] Figure 6 is a schematic diagram of traffic flow changes on a disaster-affected road section according to an embodiment of the present application;

[0049] Figure 7 is a schematic diagram of a device for detecting a vehicle falling while moving according to an embodiment of the present application;

[0050] Figure 8 Schematic diagram of another vehicle falling detection device according to an embodiment of the present application

[0051] Fig. 9 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] With the popularity of GPS, gyroscopes, accelerometers and other sensor devices on mobile phones, when a vehicle uses location services such as navigation software while driving, it is possible to establish a detailed description of the vehicle's behavior during the vehicle's driving. When the vehicle has abnormal behaviors such as falling, detectable signals appear on the GPS, gyroscope, accelerometer and other sensor data. This application integrates the use of multi-source sensors such as GPS to build a behavior detection model for vehicle falls, solving the problem of rapid discovery and early warning of extreme disasters such as road subgrade collapse and bridge overturning.

[0055] The following is combined with Figure 1 The method for detecting a vehicle falling while moving according to an embodiment of the present application is described in detail. Figure 1 As shown, the method mainly includes the following steps:

[0056] S101 extracts acceleration data and GPS trajectory data of the vehicle based on a preset time interval when the vehicle enters a disaster warning section.

[0057] In one implementation scenario, considering issues such as privacy protection and balancing power consumption, the fall detection service is only enabled on disaster warning sections.

[0058] First, determine whether the vehicle has entered a disaster warning section.

[0059] Specifically, it is determined whether the vehicle has entered the target detection geofence, which refers to the spatial range where the vehicle is prone to fall, including roadbeds that are prone to collapse, bridges that are prone to overturning, etc. Based on the weather conditions within the target detection geofence and the time the vehicle entered, it is determined whether it is within the target detection period, which refers to the period when the visibility of the vehicle is less than the set threshold. For example, at night, during precipitation, in fog, etc., visibility will be reduced. When the vehicle enters the target detection geofence and is within the target detection period, it is determined that the vehicle has entered the disaster warning section.

[0060] Furthermore, when a vehicle enters a disaster warning section, a fall detection service is triggered, and the acceleration data and GPS trajectory data of the vehicle are extracted based on a preset time interval. Among them, the specific time interval can be set according to the actual situation, and the embodiment of the present application is not limited. For example, the sensor acceleration data and GPS data are collected every 10S. Among them, the GPS data includes information such as vehicle ID, vehicle location, time, speed, etc. The acceleration and GPS data involved can be obtained through the mobile phone terminal APP of the person in the car or the APP of the car terminal, and the terminal APP can send the accident alarm information to the server. S102 determines whether the fall condition is met based on the change characteristics of the acceleration data. If the fall condition is met, the fall start time and the fall end time are determined based on the acceleration change time.

[0061] Optionally, the combined acceleration modulus is calculated based on the acceleration data. In one embodiment, the combined acceleration modulus of the vehicle is calculated based on the acceleration data, including: calculating the acceleration of the vehicle in the X-axis, Y-axis, and Z-axis directions respectively; and obtaining the combined acceleration modulus based on the square root of the sum of the squares of the acceleration of the vehicle in the X-axis, Y-axis, and Z-axis directions.

[0062] The combined acceleration modulus collected by the acceleration sensor is calculated at fixed intervals. The combined acceleration modulus is calculated as follows:

[0063]

[0064] In the formula, a total represents the combined acceleration modulus, a x 、a y 、a z are the accelerations in the X, Y, and Z axis directions respectively.

[0065] Furthermore, it is determined whether the vehicle is in a weightless state based on the combined acceleration modulus. When the vehicle is in a weightless state, it is determined whether the change rate of the combined acceleration modulus after the first weightlessness is greater than a preset threshold; if it is greater than the preset threshold, and the combined acceleration modulus has a fluctuation change characteristic of falling and rebounding, it is determined that the vehicle meets the falling condition; wherein, the weightlessness start time is recorded as the falling start time; and the combined acceleration modulus fluctuation end time is recorded as the falling end time.

[0066] Among them, the combined acceleration model is used to determine whether the vehicle is in a weightless state, that is, the vehicle has fallen into the air. When the vehicle is driving on the road at a constant speed and in a straight line, the built-in accelerometer will have an initial value, which is the vertical upward acceleration, and its value is equal to the acceleration of gravity g≈9.8m / s 2 The normal driving acceleration is -9.8m / s 2 .

[0067] The vehicle is in a weightless state when falling on the collapsed road section. If the air resistance is not taken into account in an ideal situation, the total acceleration modulus of the accelerometer in the weightless state should be 0. The acceleration of the falling vehicle due to air resistance can be obtained from Newton's second law.

[0068]

[0069] Where F is air resistance, and the calculation formula is:

[0070]

[0071] Where ρ is the air density, v is the vehicle speed, C is the vehicle drag coefficient, and A is the front projection area of ​​the vehicle. Substituting this into Newton's second law, we can get the acceleration caused by air resistance;

[0072]

[0073] Take an ordinary family car with a speed of 100 km / h (27.78 m / s) as an example, assuming that the mass of the car is m = 1500 kg and the air density is ρ = 1.225 kg / m 3 , drag coefficient C = 0.3, vehicle projection area A = 2.5m 2 , then the acceleration given to the vehicle by air resistance can be calculated as:

[0074]

[0075] The acceleration caused by air resistance is calculated to be less than 1m / s 2 When a vehicle is traveling at a constant speed on a smooth road, the total acceleration is only the vertical acceleration g, so air resistance does not affect the judgment of weightlessness. Therefore, the effect of air resistance can be ignored, and the total acceleration modulus of the vehicle in a weightless state is approximately zero.

[0076] When the vehicle is in a weightless state, it is determined whether the rate of change of the combined acceleration modulus after the first weightlessness occurs is greater than a preset threshold.

[0077] When a vehicle is hit hard after weightlessness, it will generate a large combined acceleration. Therefore, after weightlessness is detected, the change rate of the combined acceleration modulus obtained in two adjacent time intervals is calculated. By analyzing whether the change rate of the combined acceleration modulus of the vehicle after weightlessness reaches the set threshold, it is determined whether the vehicle is actually falling.

[0078] The threshold can be determined by a variety of methods, such as the "3 times standard deviation principle". That is, design multiple sets of different drop scene tests and manual shaking phone scene tests, compare the results by drawing a graph and bring them into the formula to verify the threshold θ. The 3σ principle formula is:

[0079] θ=μ 手动 +k·σ 手动

[0080] Among them, μ 手动 is the mean value of the acceleration modulus in the experiment results of manually shaking the mobile phone; σ 手动 is the standard deviation of the acceleration modulus in the experiment of manually shaking the mobile phone; k is a constant, usually 3 to ensure a higher confidence level.

[0081] Furthermore, if it is greater than a preset threshold and the combined acceleration modulus has a fluctuating change characteristic of falling and rebounding, it is determined that the vehicle meets the falling condition.

[0082] Falling is often accompanied by rebounding behavior. At this stage, the mobile phone will reverse irregularly because the force direction is uncertain. The gyroscope shows irregular angular velocity changes in the X, Y, and Z axes. During the rebound landing process, the combined acceleration value will still show multiple alternating changes of weightlessness and large acceleration. After a period of time, the combined acceleration model tends to be stable or fluctuates slightly.

[0083] The combined acceleration model of weightlessness, impact and rebound is as follows: Figure 5 As shown in the figure. In the weightless state, the resultant acceleration will drop to 0. After being hit, a larger resultant acceleration will be generated. When rebounding, the resultant acceleration will fluctuate.

[0084] In one embodiment, the falling start time and the falling end time are determined based on the combined acceleration module change time, including: obtaining the falling start time based on the weightlessness start time; and obtaining the falling end time based on the combined acceleration module fluctuation end time.

[0085] In an optional implementation, the fall can also be determined based on the variation characteristics of the z-axis acceleration, and the determination logic is the same as that of the combined acceleration model.

[0086] S103 determines that the vehicle has fallen based on the fact that the GPS trajectory data stops updating or the vehicle speed is zero during the time period from the fall start time to the fall end time.

[0087] Furthermore, the GPS track information of the vehicle is used to determine whether the vehicle has actually fallen, thereby eliminating misidentification caused by a mobile phone falling in the vehicle.

[0088] Define the moment when the vehicle is airborne as the time when the vehicle falls start The time when the vehicle returns to a stationary state after falling is the end time of the vehicle falling t end Given a set of GPS trajectories of a fallen vehicle It means t start to end All GPS track points of the car within the time, p i Represents the i-th trajectory point, which contains the vehicle's current latitude and longitude, time and speed information.

[0089] Given the GPS trajectory of the vehicle to be verified, the conditions for verifying that it is a fall are: at t start to end During this period, the vehicle track stops updating or the speed drops to 0km / h, that is:

[0090]

[0091] Where, t n Represents a set of trajectories The time corresponding to the nth trajectory point in vn express The velocity corresponding to the nth trajectory point in .

[0092] The fall detection method of this application needs to be enabled and executed with the authorization of the user. Specifically, when a road section within a specific detection geo-fence is in the detection period, the App will enable the fall detection service for vehicles on the road section with the authorization of the user. A vehicle in the detection area is judged to have fallen if it has the following characteristics:

[0093] (1) The vehicle is judged to be experiencing weightlessness through the combined acceleration model, and the start time of weightlessness is recorded as t start , the location is recorded as the incident location pos1;

[0094] (2) The vehicle's combined acceleration modulus change rate after weightlessness exceeds the set threshold θ;

[0095] (3) The combined acceleration modulus after the impact has the characteristics of falling and rebounding, that is, there are multiple alternations of weightlessness and collisions, and finally the combined acceleration modulus tends to be stable or fluctuates slightly. This is defined as the end of the falling state and is recorded as t end ;

[0096] (4) The vehicle's GPS signal is from t start From to end Stop, GPS track information stops updating or the speed drops to 0km / h.

[0097] In one embodiment, after determining that the vehicle has fallen, the method further includes:

[0098] The vehicle terminal or user handheld terminal of the fallen vehicle pops up a one-button alarm interface; in one embodiment, once the vehicle fall is confirmed, the alarm module will immediately send an alarm signal. This may include automatically dialing emergency services through the vehicle's communication system, or sending an alarm signal with vehicle location information to a rescue center. At the same time as the alarm, the background service end can determine the precise location of the vehicle through GPS or other positioning technology and pass this information to rescue personnel. Inside the vehicle, a conspicuous alarm button can be designed so that the driver or passenger can easily trigger the alarm in an emergency.

[0099] Optionally, voice prompt information can be issued or user voice alarm help information can be obtained based on the voice interaction module. Built-in AI voice recognition interaction module receives the user's voice alarm help information. Through voice interaction with the user, information such as event type, number of injured, location, etc. is collected. For example, the voice module can send a voice to ask whether the vehicle has fallen, receive the user's answer, and when the user confirms that the vehicle has fallen, ask whether it is human-caused or a road problem, and ask whether an alarm is needed. When the user is injured and cannot operate the one-button alarm, the user's help information can be quickly obtained through voice interaction. It can respond quickly when the vehicle falls and provide key information to rescue personnel, thereby improving rescue efficiency.

[0100] For the detection of a vehicle falling while moving, the first condition is first used: judging whether a vehicle has fallen based on the acceleration change characteristics. Then the second condition is used: judging whether the trajectory data stops updating to exclude the possibility of a vehicle falling by mistake. When the first and second conditions are met at the same time, it is possible to accurately judge that a vehicle has fallen.

[0101] However, it is not certain whether the cause of the fall was caused by road collapse or other reasons (such as the vehicle ran out of control and fell off the road). Therefore, a third condition is added: whether it is a group of vehicles falling to verify whether the road surface is damaged.

[0102] like Figure 2 As shown, in some embodiments, after determining that the vehicle has fallen, in order to confirm whether the vehicle has fallen due to road damage, the following steps S104 are also included, which are as follows:

[0103] S104: Based on the fact that the number of tracks downstream of the falling position is zero, or multiple vehicles fall at the same location, it is determined that the road section at the falling position is damaged.

[0104] Obtain all vehicles that pass the fall location after the fall start time, and count the number of vehicles that have fallen among the passing vehicles. Count the number of first vehicles that pass the fall location and reach the downstream section of the fall location after the fall start time; count the number of second vehicles in the upstream section of the fall location; if the number of vehicles that have fallen is greater than a preset threshold, or the number of second vehicles is greater than 0 and the number of first vehicles is equal to 0, determine that the section of the fall location is damaged.

[0105] like Figure 4 and Figure 6 As shown, if the road is damaged and interrupted, the number of vehicles downstream of the fall location will drop sharply, and the number of vehicles reaching the downstream through the fall location will be 0.

[0106] In one embodiment, multiple vehicle drop verifications are performed:

[0107] Extract trajectory collection The position of the first point in pos1 is taken as the location of the incident, and the road section where it is located is extracted as the disaster-affected road section to be verified link aff Get t start All vehicles that have passed the event location pos1 since the time Use the first and second conditions to verify whether the n vehicles are fallen vehicles one by one. Let the number of vehicles determined to be fallen vehicles be n. d (n d ≤n).

[0108] Given a threshold n aff , if n d ≥n aff , then determine the road segmentlink aff Affected by the disaster.

[0109] Perform multiple GPS track anomaly verification:

[0110] Due to the interception effect of the disaster-affected road section on traffic flow, the traffic passing through the disaster-affected road section cannot reach the downstream after the disaster. Figure 6 As shown in the figure, the traffic volume on the affected road section quickly returned to zero after the disaster. Therefore, the GPS trajectory statistical method can be used for verification:

[0111] Given link aff The downstream segment is link next Statistics start After the time, pass the disaster-affected road link aff , reaching the downstream link next The number of trajectories n pass Statistics start After the time, pass the disaster-affected road link aff The number of trajectories n all When both satisfy n all >0 and n pass = 0, you can verify the current time segment link aff The disaster-affected road section.

[0112] In one embodiment, after determining that the road section at the falling position is damaged, the method further includes: generating accident information based on the falling start time, the number of fallen vehicles, and the damaged road section information; and sending the accident information to the traffic control department service end, so that the traffic control department can promptly carry out accident rescue and road repair, and promptly transmit the road damage information to the vehicles upstream of the falling position to avoid more vehicles being damaged.

[0113] In order to facilitate understanding of the method provided in the embodiment of the present application, Figure 3 Further description. Figure 3 As shown, including:

[0114] Determine the specific detection geographic fence and specific detection period to obtain the disaster warning section. Determine whether the vehicle has entered the disaster warning section. If so, start the detection service and extract acceleration and GPS data. Determine whether the vehicle has fallen based on the acceleration data. If so, determine whether the vehicle has stopped based on the GPS trajectory information. If so, a one-key alarm interface pops up on the mobile phone, or the alarm number is directly dialed through voice commands. The backend server parses the alarm information sent by the vehicle computer to obtain the information of the affected vehicle.

[0115] Furthermore, it is determined whether there are multiple vehicles that have fallen at the same location, and whether the number of GPS tracks downstream of the accident site is 0. If multiple vehicles have fallen, or the number of GPS tracks downstream of the accident site is 0, it is determined that the road has been damaged. The information of the affected vehicles and the affected road sections is obtained, and an early warning signal is sent to the traffic control department, and information such as road conditions and the location of the fall is integrated to assist in control and rescue work.

[0116] Through the above multi-condition judgment, we can get basic information such as the number of fallen vehicles, the falling location, and the time of the incident. This information can be used to send early warning information to the vehicles behind, brake in time to avoid more accidents; it can also send disaster alerts to the company of the road section to which it belongs based on the location information, and the traffic management department can take measures such as closing roads and information board prompts as soon as possible to reduce the impact of the affected roads on the operation of the road network; at the same time, the relevant rescue units can also obtain the type of disaster as soon as possible to launch targeted rescue and reduce the loss of life and property of the masses.

[0117] According to another aspect of the embodiments of the present application, a vehicle falling detection device for implementing the above-mentioned vehicle falling detection method is also provided. Figure 7 As shown, the device comprises:

[0118] The data acquisition module 601 is used to extract the acceleration data and GPS trajectory data of the vehicle based on a preset time interval when the vehicle enters a disaster warning section;

[0119] A first judgment module 602 is used to judge whether a falling condition is met based on the acceleration data change characteristics, and if the falling condition is met, determine the falling start time and the falling end time based on the acceleration change time;

[0120] The second judgment module 603 is used to determine that the vehicle has fallen if the GPS trajectory data stops updating or the vehicle speed is zero during the period from the fall start time to the fall end time.

[0121] In one embodiment, the device further includes a third determination module 604, such as Figure 8 Shown

[0122] The third judgment module 604 is used to determine that the road section at the falling location is damaged based on the number of tracks downstream of the falling location being zero, or multiple vehicles falling at the same location.

[0123] It should be noted that the device for detecting a vehicle falling while in motion provided in the above-mentioned embodiment only uses the division of the above-mentioned functional modules as an example when executing the method for detecting a vehicle falling while in motion. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for detecting a vehicle falling while in motion provided in the above-mentioned embodiment and the method for detecting a vehicle falling while in motion belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0124] According to another aspect of an embodiment of the present application, an electronic device corresponding to the method for detecting a vehicle falling while moving provided in the aforementioned embodiment is also provided to execute the aforementioned method for detecting a vehicle falling while moving.

[0125] Please refer to Fig. 9 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Fig. 9 As shown, the electronic device includes: a processor 700, a memory 701, a bus 702 and a communication interface 703, and the processor 700, the communication interface 703 and the memory 701 are connected via the bus 702; the memory 701 stores a computer program that can be run on the processor 700, and when the processor 700 runs the computer program, it executes the method for detecting a vehicle falling while moving provided in any of the aforementioned embodiments of the present application.

[0126] The memory 701 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 703 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0127] The bus 702 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 701 is used to store programs, and the processor 700 executes the programs after receiving the execution instructions. The vehicle falling detection method disclosed in any implementation of the above-mentioned embodiment of the present application may be applied to the processor 700, or implemented by the processor 700.

[0128] The processor 700 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 700. The above processor 700 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 701, and the processor 700 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0129] The electronic device provided in the embodiment of the present application and the method for detecting a vehicle falling while moving provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0130] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium corresponding to the method for detecting a vehicle falling while moving provided in the aforementioned embodiments, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the method for detecting a vehicle falling while moving provided in any of the aforementioned embodiments.

[0131] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0132] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for detecting a vehicle falling while moving provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0133] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for detecting a vehicle falling while moving, characterized in that: include: When a vehicle enters a disaster warning section, the acceleration data and GPS trajectory data of the vehicle are extracted based on a preset time interval; Determine whether the falling condition is met based on the acceleration data change characteristics, and if the falling condition is met, determine the falling start time and the falling end time based on the acceleration change time; During the time period from the start time of the fall to the end time of the fall, it is determined that the vehicle has fallen based on the fact that the GPS trajectory data stops updating or the vehicle speed is zero.

2. The method according to claim 1, characterized in that Judging whether a falling condition is met based on the change characteristics of the acceleration data, and determining the falling start time and the falling end time based on the acceleration change time when the falling condition is met, including: Calculating a combined acceleration modulus based on the acceleration data; Determining whether the vehicle is in a weightless state based on the combined acceleration model; When the vehicle is in a weightless state, determining whether the rate of change of the combined acceleration modulus after the first weightlessness occurs is greater than a preset threshold; If it is greater than a preset threshold, and the combined acceleration modulus has a fluctuating change characteristic of falling and rebounding, it is determined that the vehicle meets the falling condition; The start time of weightlessness is recorded as the start time of falling, and the end time of the combined acceleration mode fluctuation is recorded as the end time of falling.

3. The method according to claim 1, characterized in that: After determining that the vehicle has fallen, it also includes: The vehicle terminal or user handheld terminal of the fallen vehicle pops up a one-key alarm interface; The vehicle-mounted terminal of the fallen vehicle or the user's handheld terminal sends out a voice prompt message or obtains the user's voice alarm help message based on the voice interaction module.

4. The method according to claim 1, characterized in that: After determining that the vehicle has fallen, the method further includes: Determine the falling position of the vehicle and obtain the number of vehicle tracks downstream of the falling position; When the number of tracks downstream of the vehicle falling position is zero, or multiple vehicles fall at the same location, it is determined that the road section at the falling position is damaged.

5. The method according to claim 4, characterized in that When the number of tracks downstream of the vehicle falling position is zero, or multiple vehicles fall at the same location, it is determined that the road section at the falling position is damaged, including: Obtain all vehicles that pass the falling position after the falling start time, and count the number of vehicles that have fallen among the passing vehicles; Counting the number of first vehicles that pass the falling position and arrive at the road section downstream of the falling position after the falling start time; Counting the number of second vehicles on the upstream section of the falling position; When the number of fallen vehicles is greater than a preset threshold, or the second number of vehicles is greater than 0 and the first number of vehicles is equal to 0, it is determined that the road section where the fall location is located is damaged.

6. The method according to claim 1 or 4, characterized in that: After determining that the falling position section is damaged, the method further includes: Generate accident information based on the fall start time, number of fallen vehicles, and damaged road section information; The accident information is sent to the traffic control department service end.

7. The method according to claim 1, characterized in that Before a vehicle enters a disaster warning section, it also includes: Determine whether the vehicle enters the target detection geo-fence; Based on the weather conditions within the target detection geo-fence and the vehicle entry time, determining whether it is a target detection period; When the vehicle enters the target detection geographic fence and falls within the target detection period, it is determined that the vehicle enters the disaster warning section.

8. A device for detecting a vehicle falling while moving, characterized in that: include: A data acquisition module, used to extract the acceleration data and GPS trajectory data of the vehicle based on a preset time interval when the vehicle enters a disaster warning section; A first judgment module, used to judge whether a falling condition is met based on the acceleration data change characteristics, and if the falling condition is met, determine the falling start time and the falling end time based on the acceleration change time; The second judgment module is used to determine that the vehicle has fallen within the time period from the start time of the fall to the end time of the fall based on the fact that the GPS trajectory data stops updating or the vehicle speed is zero.

9. An electronic device, characterized in that: The invention comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the method for detecting a vehicle falling while moving as claimed in any one of claims 1 to 7 when executing the program instructions.

10. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a method for detecting a vehicle falling while moving as described in any one of claims 1 to 7.

Images