Method for detecting and processing traffic accident on basis of electric bicycle helmet, and electric bicycle

By installing a camera in front of the motorcycle helmet, detecting traffic accidents in real time and sending warning instructions, the problems of manual detection lag and inefficiency are solved, and efficient detection and timely handling of traffic accidents are achieved.

WO2024239371A1PCT designated stage expired Publication Date: 2024-11-28HUNAN XIBAODA INFORMATION TECH CO LTD

Patent Information

Application Number
PCT/CN2023/097867
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-23
Filing Date
2023-06-01
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

In the prior art, traffic accident detection relies on manual operations, with obvious lag and low detection efficiency, and the characteristics of shared electric motorcycles themselves are not used for testing.

Method used

By installing a camera in front of the motorcycle helmet, real-time environmental image information is obtained, whether there is a traffic accident, and early warning instructions are sent according to the accident assessment level, real-time detection and record uploading are achieved, and detection efficiency is improved.

Benefits of technology

Realize immediate detection and efficient recording and uploading of traffic accidents, promptly handle serious accidents, and improve detection efficiency and rescue response speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023097867_28112024_PF_FP_ABST
    Figure CN2023097867_28112024_PF_FP_ABST
Patent Text Reader

Abstract

A method for detecting and processing a traffic accident on the basis of an electric bicycle helmet, and an electric bicycle. The method comprises: acquiring real-time state information of an electric bicycle, and determining, according to the real-time state information, whether the electric bicycle is in a turn-on state; when the electric bicycle is in the turn-on state, controlling a camera, which is mounted in the front of an electric bicycle helmet, to enter a snapshot mode, and acquiring, according to a first preset time interval, environmental image information which is snapshot by the camera; determining whether there is a preset traffic accident image in the environmental image information; and when there is the preset traffic accident image in the environmental image information, controlling the camera to enter a first video recording mode, and after a first preset duration elapses, sending, to a first target object, environmental image information which is recorded by the camera within the first duration and / or a first early warning instruction. By means of the method, it is possible to detect whether a traffic accident occurs in an external environment of an electric bicycle and at the electric bicycle itself, and therefore the method has the advantages of high timeliness and high detection efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

A method for detecting and handling traffic accidents based on motorcycle helmets and motorcycle helmets Technical Field

[0001] The present invention relates to the technical field of traffic accident detection, and in particular to a method for detecting and handling traffic accidents based on a motorcycle helmet, and a motorcycle. Background Art

[0002] With the increasing development of road infrastructure and rising living standards, cars and shared electric motorcycles have become important means of transportation for many families and users. With the increasing number of cars and shared vehicles, traffic accidents are also becoming more common. Once a traffic accident occurs, there may be casualties, requiring timely detection and rescue.

[0003] In the existing technology, the detection of traffic accidents is still mainly based on manual operations, that is, relevant staff watch the surveillance video from the monitoring equipment on the traffic section to discover the image information of the traffic accident scene, and then report the relevant video or picture information. Due to factors such as the number of personnel and energy, the manual detection and analysis of traffic accidents has a significant lag, which may delay the best time for rescue on the one hand, and on the other hand, there is a problem of obvious low detection efficiency.

[0004] In addition, shared electric motorcycles themselves have the characteristics of large number, high convenience, and high frequency of use. There is no detection method in the existing technology that can detect traffic accidents by utilizing the characteristics of shared electric motorcycles.

[0005] In view of this, it is necessary to propose a method for detecting and handling traffic accidents based on motorcycle helmets and a motorcycle to solve or at least alleviate the above-mentioned defects.

[0006] Summary of the Invention

[0007] The main purpose of the present invention is to provide a method and motorcycle for detecting and handling traffic accidents based on a motorcycle helmet, so as to solve the problem that the detection of traffic accidents is still mainly based on manual operation, with obvious lag and low detection efficiency.

[0008] To achieve the above objectives, the present invention provides a method for detecting and handling traffic accidents based on motorcycle helmets, comprising the steps of:

[0009] S1, obtaining real-time status information of an electric motorcycle, and determining whether the electric motorcycle is in an on state according to the real-time status information;

[0010] S2, when the motorcycle is in the on-state, controlling the camera mounted on the front of the motorcycle helmet to enter a capture mode, and acquiring environmental image information captured by the camera at a first preset time interval;

[0011] S3, determining whether the environmental image information contains a preset traffic accident image;

[0012] S4, when the environmental image information contains the preset traffic accident image, control the camera to enter the first video recording mode, wait for the first preset time, and then send the environmental image information and / or the first warning instruction recorded by the camera within the first preset time to the first target object.

[0013] Preferably, the step S4 specifically includes the following steps:

[0014] S41, when the preset traffic accident image is included in the environmental image information, determining a traffic accident assessment level corresponding to the preset traffic accident image based on the preset traffic accident image, and determining whether the traffic accident assessment level is greater than a preset severity level; if the traffic accident assessment level is greater than the preset severity level, executing steps S42 to S44; if the traffic accident assessment level is less than or equal to the preset severity level, executing steps S45 to S47;

[0015] S42, controlling the camera to enter the first video recording mode, and obtaining the current running speed of the motorcycle and the distance between the motorcycle and the traffic accident point;

[0016] S43, determining a theoretical calculation time for the motorcycle to travel to the traffic accident point based on the interval distance and the current running speed, and using the theoretical calculation time as the first preset duration;

[0017] S44, after waiting for the first preset time period, sending the environmental information recorded by the camera within the first preset time period, the traffic accident assessment level, and the current position of the motorcycle to the first target object;

[0018] S45: Control the camera to enter the first video recording mode, and record the environmental information video obtained by the camera within a second preset time period after entering the first video recording mode, and determine whether the environmental information node video corresponding to the first time node at the end of the second preset time period contains a preset traffic accident image;

[0019] S46, when the environment information node video corresponding to the first time node at the end of the second preset time period contains a preset traffic accident image, extending the second preset time period by a third preset time period as the first preset time period;

[0020] S47, after waiting for the first preset time period, sending the environmental image information recorded by the camera within the first preset time period, the traffic accident assessment level and the current position of the motorcycle to the first target object.

[0021] Preferably, the step S3 further includes the following steps:

[0022] S51, when the environment image information does not contain a preset traffic accident image, obtaining a real-time running speed of the motorcycle, and determining whether the motorcycle is in a stationary state based on the real-time running speed;

[0023] S52, when the motorcycle is in a stationary state, obtaining vehicle body posture information detected by a vehicle body tilt angle detection device, and obtaining a vertical distance between the camera and the ground; wherein the vehicle body tilt angle detection device is disposed in the body of the motorcycle;

[0024] S53, determining whether the motorcycle is in a tilting state and determining whether the vertical distance is less than a preset threshold according to the vehicle posture information;

[0025] S54, when either the motorcycle is in a tilted state or the vertical distance is less than a preset threshold value, controlling the camera to enter a second video recording mode, acquiring an environmental information video obtained by the camera within a fourth preset time period after entering the second video recording mode, and determining, at a second time point at the end of the fourth preset time period, whether the motorcycle is in a tilted state and whether the vertical distance between the camera and the ground is less than a preset threshold value;

[0026] S55, when any one of the following conditions holds true: the motorcycle is in a tilted state and the vertical distance is less than a preset threshold, sending the environmental image information recorded by the camera within the fourth preset time period and / or the second warning instruction to the selected operation and maintenance personnel;

[0027] S56, when neither of the two conditions, namely, that the motorcycle is in a tilted state and that the vertical distance is less than a preset threshold, is true, the camera is maintained in the capture mode.

[0028] Preferably, the step S54 further includes the following steps:

[0029] S541, when two of the following conditions are met simultaneously: the motorcycle is in a tilted state and the vertical distance is less than a preset threshold, it is determined that the motorcycle is in a serious traffic accident level, and the environmental image information recorded by the camera within the fourth preset time period and the third warning instruction are sent to the second target object.

[0030] Preferably, the step S3 further includes the following steps:

[0031] S301, when the environmental image information does not contain a preset traffic accident image, obtaining an angle change rate of the helmet detected by a helmet tilt angle detection device, and obtaining a speed change rate of the motorcycle body, and determining whether the angle change rate is greater than a first preset threshold within a first set time, and determining whether the speed change rate of the motorcycle is greater than a second preset threshold within a second set time;

[0032] S302, when either the angle change rate is greater than a first preset threshold within a first set time or the speed change rate of the motorcycle is greater than a second preset threshold within a second set time, determining that the motorcycle is in a serious traffic accident level, and sending the environmental image information recorded by the camera within the set time and a third warning instruction to a second target object;

[0033] S303, when both of the angle change rate being greater than the first preset threshold within the first set time and the speed change rate of the motorcycle being greater than the second preset threshold within the second set time are not true, return to step S301.

[0034] Preferably, the step S3 further includes the following steps:

[0035] S31, when the environment image information does not contain a preset traffic accident image, determining whether the environment image information contains a target obstacle;

[0036] S32: When the target obstacle is present in the environmental image information, adjust the first preset time interval to a second preset time interval; wherein the second preset time interval is smaller than the first preset time interval.

[0037] Preferably, the step S32 further includes the following steps:

[0038] S33, determining whether the corresponding environment image information has the target obstacle at a third time point at the end of a fifth preset time period after the target obstacle is first detected;

[0039] S34, when the environmental image information does not have the target obstacle, adjusting the second preset time interval to the first time interval;

[0040] S35 , when the environmental image information contains the target obstacle, maintaining the camera to continue capturing images according to the second preset time interval.

[0041] Preferably, the step S4 further includes the following steps:

[0042] S401, obtaining historical position data of the motorcycle within a sixth preset time period before the current moment and determining a vector motion path of the motorcycle based on the historical position data set;

[0043] S402, determining, based on the current position of the motorcycle and the vector motion path, whether there is a target shared vehicle located behind the current motorcycle and within a preset range from the current position; wherein the target shared vehicle is in communication with the motorcycle;

[0044] S403: When there is a target shared vehicle behind the current motorcycle and within a preset range from the current position, a fourth warning instruction is sent to the target shared vehicle.

[0045] Preferably, the "selected operation and maintenance personnel" in step S55 is obtained through the following steps:

[0046] S551, obtaining the real-time location of the motorcycle, and obtaining, based on the real-time location of the motorcycle, the operation and maintenance task amounts of multiple candidate operation and maintenance personnel within a preset range from the real-time location, as well as the distances between the candidate operation and maintenance personnel and the real-time location;

[0047] S552: Determine, as the selected operation and maintenance personnel, a candidate operation and maintenance personnel whose distance is within a preset range and whose operation and maintenance task load is less than a preset task load among the plurality of candidate operation and maintenance personnel;

[0048] S553: ​​When there are multiple candidate operation and maintenance personnel whose distances are within a preset range and whose operation and maintenance task amounts are less than a preset task amount, randomly select one of the candidate operation and maintenance personnel as the selected operation and maintenance personnel.

[0049] The present invention also provides an electric motorcycle, comprising a body, a helmet, and a control system arranged in the body; wherein, the body is also provided with an inclination sensor device for detecting body posture information, the inclination sensor is connected to the control system, the helmet is provided with a communication module connected to the control system, a camera for acquiring riding environment images is installed in front of the helmet, the control system comprises a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the computer program, the steps of the method for detecting and handling traffic accidents based on an electric motorcycle helmet are implemented as described above.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention provides a method and motorcycle for detecting and handling traffic accidents based on a motorcycle helmet. The method obtains real-time status information of the motorcycle and determines whether the motorcycle is in an on-state based on the real-time status information. When the motorcycle is in an on-state, the method controls a camera mounted on the front of the motorcycle helmet to enter a capture mode, obtains environmental image information captured by the camera at a first preset time interval, determines whether the environmental image information contains a preset traffic accident image, and if the environmental image information contains the preset traffic accident image, controls the camera to enter a first video recording mode. After waiting for a first preset time period, the method sends the environmental image information recorded by the camera within the first preset time period and / or a first warning instruction to a first target object. In this way, the traffic accident image information captured by the camera can be immediately detected, recorded, and uploaded, with high timeliness and detection efficiency.

[0052] In addition, when the preset traffic accident image is included in the environmental image information, the traffic accident assessment level corresponding to the preset traffic accident image is determined based on the preset traffic accident image, and it is judged whether the traffic accident assessment level is greater than the preset severity level, so that the serious traffic accident is urgently dealt with. At the same time, the situation in which a traffic accident occurs on the motorcycle itself is also taken into consideration, and relevant processing is performed when a traffic accident occurs on the motorcycle itself, so as to carry out timely rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0054] FIG1 is a schematic diagram of a process in one embodiment of the present invention;

[0055] FIG2 is a flow chart showing the specific steps of step S4 in one embodiment of the present invention;

[0056] FIG3 is a flow chart showing steps further included after step S3 in one embodiment of the present invention.

[0057] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0060] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0061] In addition, the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0062] 1 to 3 , a method for detecting and handling traffic accidents based on motorcycle helmets according to an embodiment of the present invention includes the following steps:

[0063] S1, obtain the real-time status information of the electric motorcycle, and determine whether the electric motorcycle is in the on state based on the real-time status information; for example, it can be detected by detecting whether the output current of the motor is greater than a preset threshold or by detecting the power-on status of the entire electric motorcycle. The specific technical personnel in this field can set it according to actual needs.

[0064] S2: When the motorcycle is turned on, control the camera mounted on the front of the motorcycle helmet to enter a capture mode, and obtain environmental image information captured by the camera at a first preset time interval. It is understood that the camera can have a capture mode and a video recording mode. The camera in this application is set on the front of the helmet to capture environmental image information during riding. The first preset time interval can be set as needed, for example, set to 2 seconds, that is, one piece of environmental image information is captured every 2 seconds.

[0065] S3, determining whether the environmental image information contains a preset traffic accident image; it is worth noting that there are multiple ways to determine whether the environmental image information contains a preset traffic accident image. For example, an image template matching algorithm can be used to set a preset traffic accident image in advance, for example, obvious image features such as bloodstains, vehicle debris, and vehicle broken creases are set as the preset traffic accident image, and then the image matching algorithm is used to match the current environmental image information with the template. When the matching degree is greater than the preset value, it can be considered that the current environmental image information contains the preset traffic accident image. In another preferred example, whether the environmental image information contains a preset traffic accident image can be detected by deep learning. For example, by pre-collecting a large number of / sufficient image samples, all image samples are divided into training sets and test sets, and each image sample is manually labeled (i.e., corresponding to whether it is a preset traffic accident image) to train it into a neural network model with high accuracy, and then the trained neural network model is used to predict / detect it. This detection method using a neural network is a mature technology in the existing technology and will not be described in detail here.

[0066] S4. When the environmental image information contains the preset traffic accident image, control the camera to enter a first video recording mode. After waiting for a first preset time, send the environmental image information recorded by the camera within the first preset time and / or a first warning instruction to a first target object. The first preset time can be set to 10 seconds, and the first target object can be one or more of the user of the motorcycle, a backend management system, a traffic management department system, a medical system, and shared motorcycle operation and maintenance personnel. The first warning instruction can be sending the environmental image information, the real-time location and time information of the motorcycle to the first target object.

[0067] The technical solution of the present application obtains real-time status information of an electric motorcycle and determines whether the electric motorcycle is in an on-state based on the real-time status information. When the electric motorcycle is in an on-state, the camera mounted on the front of the electric motorcycle helmet is controlled to enter a capture mode, and the environmental image information captured by the camera is obtained at a first preset time interval. It is determined whether the environmental image information contains a preset traffic accident image. If the environmental image information contains the preset traffic accident image, the camera is controlled to enter a first video recording mode. After waiting for a first preset time period, the environmental image information recorded by the camera within the first preset time period and / or a first warning instruction are sent to a first target object. The present invention can detect the external environment of an electric motorcycle and whether a traffic accident has occurred in the motorcycle itself, with high timeliness and detection efficiency.

[0068] As a preferred embodiment of the present invention, step S4 specifically includes the following steps:

[0069] S41, when the preset traffic accident image is included in the environmental image information, the traffic accident assessment level corresponding to the preset traffic accident image is determined according to the preset traffic accident image, and it is judged whether the traffic accident assessment level is greater than the preset severity level; when the traffic accident assessment level is greater than the preset severity level, steps S42 to S44 are executed; when the traffic accident assessment level is less than or equal to the preset severity level, steps S45 to S47 are executed; specifically, the traffic accident assessment level corresponding to the preset traffic accident image is determined by the preset traffic accident image. For example, the traffic accident assessment level corresponding to the preset traffic accident image can be determined by calculating physical evidence that can reflect a serious traffic accident (such as vehicle debris, vehicle broken creases, bloodstains, images of people falling to the ground, etc.), or it can be determined by a neural network algorithm, such as collecting a sufficient number of historical sample images, and manually labeling each image (corresponding accident level), dividing the historical sample images into a training set and a test set, and training to obtain a trained neural network model, through which the current traffic accident image can be detected.

[0070] S42, controlling the camera to enter the first video recording mode, and obtaining the current running speed of the motorcycle and the interval distance between the motorcycle and the traffic accident point; it should be noted that the traffic accident point can select the most serious area in the traffic accident image as the traffic accident point.

[0071] S43, determining the theoretical calculation time for the motorcycle to move to the traffic accident point based on the interval distance and the current running speed, and using the theoretical calculation time as the first preset duration; wherein, the theoretical calculation time is the time required for the motorcycle to move from the current position to the traffic accident point. In other words, the recording duration of the camera is the time from the current moment to the time when the motorcycle moves to the location where the traffic accident occurs. During this period of time, sufficient image information of the traffic accident scene can be collected.

[0072] S44, after waiting for the first preset time period, sends the environmental information recorded by the camera within the first preset time period, the traffic accident assessment level and the current position of the motorcycle to the first target object; by sending the environmental information recorded by the camera within the first preset time period, the traffic accident assessment level and the current position of the motorcycle to the first target object, the traffic accident scene image can be sent to the target object in time for timely recording, tracking and subsequent processing.

[0073] S45, control the camera to enter the first video recording mode, and record the environmental information video obtained by the camera within the second preset time length (30s) after entering the first video recording mode, and determine whether the environmental information node video corresponding to the first time node at the end of the second preset time length has the preset traffic accident image; it should be noted that when the traffic accident assessment level is less than or equal to the preset severity level, it means that the camera may not have detected the traffic accident or the traffic accident is relatively minor. At this time, further detection is required for such situations. That is, the environmental information video obtained by the camera within the second preset time length after entering the first video recording mode is recorded, and the environmental information node video corresponding to the first time node at the end of the second preset time length has the preset traffic accident image. In other words, the recording detection is continuously performed within 30s, and the environmental information node video is intercepted again at the end of 30s, and it is determined whether the environmental information node video has the preset traffic accident image, indicating that the traffic accident still exists within 30s. In order to further determine the severity of the accident, the subsequent steps are performed for detection.

[0074] S46. When the environmental information node video corresponding to the first time node at the end of the second preset time length has a preset traffic accident image, the second preset time length is extended by a third preset time length (1 minute) as the first preset time length; when the environmental information node video corresponding to the first time node at the end of the second preset time length has a preset traffic accident image, it indicates that the traffic accident at this time is more serious and the detection time will be extended.

[0075] S47: After waiting for the first preset time period, the environmental image information recorded by the camera during the first preset time period, the traffic accident assessment level, and the current location of the motorcycle are transmitted to the first target object. In other words, after the delay, the first preset time period becomes one minute and thirty seconds, thereby increasing the detection time and recording more on-site information.

[0076] As a preferred embodiment of the present invention, the step S3 further includes the following steps:

[0077] S51. When the environmental image information does not contain a preset traffic accident image, the real-time running speed of the motorcycle is obtained, and whether the motorcycle is in a stationary state is determined based on the real-time running speed. It is worth noting that when the environmental image information does not contain a preset traffic accident image, there is a possibility that the motorcycle itself may or may not have a traffic accident. In order to accurately determine whether the motorcycle itself has a traffic accident, this embodiment obtains the real-time running speed, and determines whether the motorcycle is in a stationary state based on the real-time running speed. For example, when the real-time running speed is 0, it can be determined that the motorcycle is in a stationary state.

[0078] S52, when the electric motorcycle is in a stationary state, obtains the body posture information detected by the body inclination detection device, and obtains the vertical distance between the camera and the ground; wherein, the body inclination detection device is arranged in the body of the electric motorcycle; it can be understood that the existing shared electric motorcycles are usually equipped with an inclination detection device (such as a gyroscope, etc.), which can detect the body posture information of the electric motorcycle, for example, it can be determined whether the electric motorcycle is in a tilting state; according to the existing mature image processing algorithms, for example, the vertical distance between the camera and the ground can be determined by the Euclidean distance method; it should also be noted that if the environmental image information does not have a ground image, it means that the distance between the camera and the ground is infinite.

[0079] S53, determining whether the motorcycle is in a tilting state and determining whether the vertical distance is less than a preset threshold according to the vehicle posture information;

[0080] S54, when any one of the following conditions is met: the motorcycle is in a tilted state and the vertical distance is less than a preset threshold, that is, the motorcycle is already in a tilted state and the helmet has fallen to the ground, the camera is controlled to enter the second video recording mode, and the environmental information video obtained by the camera within the fourth preset time period (for example, 2 minutes) after entering the second video recording mode is obtained, and at the second time node at the end of the fourth preset time period, it is judged whether the motorcycle is in a tilted state and whether the vertical distance between the camera and the ground is less than the preset threshold; that is, after 2 minutes, the motorcycle is still in a tilted state, or the helmet is still on the ground. At this time, it can be judged that the motorcycle may be in a randomly parked state or a traffic accident has occurred. At this time, subsequent steps need to be performed to further confirm these two states.

[0081] S55, when any one of the following conditions is met: the motorcycle is in a tilted state and the vertical distance is less than a preset threshold, the environmental image information and / or the second warning instruction recorded by the camera within the fourth preset time period is sent to the selected operation and maintenance personnel; that is, when the motorcycle is parked in a random position for a long time or the helmet falls on the ground for a long time, no matter what the situation is, the environmental image information and / or the second warning instruction recorded by the camera within the fourth preset time period is sent to the selected operation and maintenance personnel, so that the selected operation and maintenance personnel can deal with the situation in time.

[0082] At step S56, if neither of the conditions that the motorcycle is in a tilted state and the vertical distance is less than a preset threshold is satisfied, the camera is maintained in the snapshot mode. That is, the motorcycle is not in a tilted state and the helmet is not on the ground, indicating that the motorcycle has not been involved in a traffic accident exceeding the preset level. In this case, the camera only needs to be maintained in the snapshot mode.

[0083] In this embodiment, by detecting the posture of the motorcycle and whether the helmet is in a grounded state, it is comprehensively judged whether the motorcycle has been involved in a traffic accident greater than a preset level, and different situations are handled separately. If the motorcycle is in a tilted state for a long period of time or the helmet is in a grounded state for a long period of time, instructions are immediately sent to the selected operation and maintenance personnel for timely processing, thereby improving the operation and maintenance management efficiency of the motorcycle.

[0084] As another preferred embodiment, the step S54 further includes the following steps:

[0085] S541, when two of the following conditions are met simultaneously: the motorcycle is in a tilted state and the vertical distance is less than a preset threshold, it is determined that the motorcycle is in a serious traffic accident level, and the environmental image information recorded by the camera within the fourth preset time period and the third warning instruction are sent to the second target object.

[0086] In this embodiment, when both the motorcycle is in a tilted state and the vertical distance is less than a preset threshold are simultaneously met, that is, when the motorcycle body is in a tilted state for a long time and the helmet is on the ground for a long time, in a preferred example, by detecting whether the helmet is being worn, and when the helmet is worn and on the ground, it can be determined that the motorcycle is in a serious traffic accident level. At this time, the environmental image information recorded by the camera during the fourth preset time period and the third warning instruction can be sent to the second target object.

[0087] As another preferred embodiment, the step S3 further includes the following steps:

[0088] S301, when the environmental image information does not contain a preset traffic accident image, obtaining an angle change rate of the helmet detected by a helmet tilt angle detection device, and obtaining a speed change rate of the motorcycle body, and determining whether the angle change rate is greater than a first preset threshold within a first set time, and determining whether the speed change rate of the motorcycle is greater than a second preset threshold within a second set time;

[0089] S302, when either the angle change rate is greater than a first preset threshold within a first set time or the speed change rate of the motorcycle is greater than a second preset threshold within a second set time, determining that the motorcycle is in a serious traffic accident level, and sending the environmental image information recorded by the camera within the set time and a third warning instruction to a second target object;

[0090] S303, when both of the angle change rate being greater than the first preset threshold within the first set time and the speed change rate of the motorcycle being greater than the second preset threshold within the second set time are not true, return to step S301.

[0091] Similarly, when the environmental image information does not contain a preset traffic accident image, the user himself may or may not have a traffic accident. This embodiment provides another detection method. Specifically, the helmet tilt angle detection device is used to detect the angle change rate of the helmet, and the speed change rate of the motorcycle body is obtained to determine whether the angle change rate is greater than the first preset threshold within the first set time, and whether the speed change rate of the motorcycle is greater than the second preset threshold within the second set time. It can be understood that in the event of a serious traffic accident, that is, after the motorcycle is hit violently, the angle of the motorcycle helmet and the speed of the motorcycle change greatly in a short period of time. At this time, by determining the angle change rate and the speed change rate, it can be determined whether the motorcycle has had a serious traffic accident.

[0092] If either the angle change rate is greater than a first preset threshold within a first set time (e.g., 1 second) or the motorcycle speed change rate is greater than a second preset threshold within a second set time (e.g., 2 seconds), the motorcycle is determined to be in a serious traffic accident level. The system then sends the environmental image information recorded by the camera within the set time and a third warning instruction to a second target object. The second target object may be one or more of a backend management system, a selected operation and maintenance personnel, the motorcycle's corresponding rider, or a medical system. The third warning instruction may include sending an alarm instruction, the accident severity level, and the motorcycle's current location and time to the second target object. This allows for a rapid response and relevant processing of the motorcycle and user involved in the traffic accident.

[0093] In addition, when both of the angle change rate being greater than the first preset threshold within the first set time and the speed change rate of the motorcycle being greater than the second preset threshold within the second set time are not true, it means that the motorcycle has not had a traffic accident or the traffic accident is minor, and the process returns to step S301 to continue subsequent detection.

[0094] As a preferred embodiment, the step S3 further includes the following steps:

[0095] S31, when the environment image information does not contain a preset traffic accident image, determining whether the environment image information contains a target obstacle;

[0096] S32: When the target obstacle is present in the environmental image information, adjust the first preset time interval to a second preset time interval; wherein the second preset time interval is smaller than the first preset time interval.

[0097] It should be noted that when the environmental image information does not contain a preset traffic accident image, the user wearing a helmet may have noticed a target obstacle between the vehicle and the accident site, such as a large truck or building, or the user may have only paid attention to the traffic accident for a short while. In order to detect whether a traffic accident has occurred in this situation as much as possible, this embodiment further processes the environmental image information to determine whether the environmental image information contains a target obstacle. The target obstacle can be set in advance, such as a large truck or building. The image recognition / detection algorithm is already very mature and will not be described in detail here. For example, an image matching algorithm can be used to match whether the current environmental image information contains a target obstacle. Alternatively, in other embodiments, a deep learning approach can be used, such as a YOLO V5 model, to compare the current environmental image information with a pre-trained YOLO V5 model to detect whether the label corresponding to the current environmental image information contains a target obstacle.

[0098] In this embodiment, when the target obstacle is present in the environmental image information, the first preset time interval is adjusted to the second preset time interval. In other words, when the target obstacle is present, the camera will detect at a higher frequency to maximize the chance of detecting whether the user has captured traffic accident images during riding. As a specific example, the first preset time interval can be set to 2 seconds, and the second preset time interval can be set to 0.6 seconds.

[0099] Furthermore, the step S32 further includes the following steps:

[0100] S33, determining whether the corresponding environment image information has the target obstacle at a third time point at the end of a fifth preset time period after the target obstacle is first detected;

[0101] S34, when the environmental image information does not have the target obstacle, adjusting the second preset time interval to the first time interval;

[0102] S35 , when the environmental image information contains the target obstacle, maintaining the camera to continue capturing images according to the second preset time interval.

[0103] In this embodiment, in order to avoid the situation where the user fails to detect obstacles and traffic accidents for a long time during riding, and this scenario will cause the camera to be in high-frequency detection mode, on the one hand, too many useless images are detected, and on the other hand, the ineffective workload of the camera is increased, shortening the service life of the camera. This implementation determines whether the corresponding environmental image information has the target obstacle at the third time node at the end of the fifth preset time period (for example, 30 seconds) after the first detection of the target obstacle. When the environmental image information does not have the target obstacle, the second preset time interval is adjusted to the first time interval, that is, after the camera has not captured the target obstacle for a long time, the camera is switched back to low-frequency detection mode. When the environmental image information has the target obstacle, the camera is maintained to continue capturing according to the second preset time interval.

[0104] As a preferred embodiment, the step S4 further includes the following steps:

[0105] S401, obtaining historical position data of the motorcycle within a sixth preset time period before the current moment and determining a vector motion path of the motorcycle based on the historical position data set;

[0106] S402, determining, based on the current position of the motorcycle and the vector motion path, whether there is a target shared vehicle located behind the current motorcycle and within a preset range from the current position; wherein the target shared vehicle is in communication with the motorcycle;

[0107] S403 : When there is a target shared vehicle behind the current motorcycle and within a preset range from the current position, a fourth warning instruction is sent to the target shared vehicle.

[0108] It is worth noting that in this embodiment, after determining that the environmental image information contains a preset traffic accident image, in order to provide a warning and alert to the following vehicle, this embodiment obtains the motorcycle's historical location data within a sixth preset time period and determines the motorcycle's vector motion path based on this historical location data set. For example, the historical location data set is obtained within 3 seconds before the current moment. This can be used to define the motorcycle's current direction of travel. Based on this direction of travel, the fourth warning instruction is then issued to vehicles within a preset range behind the current motorcycle and within the current position, such as motorcycles within 50 meters behind the current motorcycle. The target shared vehicle and the motorcycle can be communicatively connected, for example, they can be vehicles of the same model, or vehicles of different models that can establish a communication connection. The fourth warning instruction can include sending a deceleration warning message or detour information to the target shared vehicle. In this way, early warnings can be provided to following vehicles, improving traffic safety.

[0109] Furthermore, the "selection of operation and maintenance personnel" in step S55 is obtained through the following steps:

[0110] S551, obtaining the real-time location of the motorcycle, and obtaining, based on the real-time location of the motorcycle, the operation and maintenance task amounts of multiple candidate operation and maintenance personnel within a preset range from the real-time location, as well as the distances between the candidate operation and maintenance personnel and the real-time location;

[0111] S552: Determine, as the selected operation and maintenance personnel, a candidate operation and maintenance personnel whose distance is within a preset range and whose operation and maintenance task load is less than a preset task load among the plurality of candidate operation and maintenance personnel;

[0112] S553: ​​When there are multiple candidate operation and maintenance personnel whose distances are within a preset range and whose operation and maintenance task amounts are less than a preset task amount, randomly select one of the candidate operation and maintenance personnel as the selected operation and maintenance personnel.

[0113] It is worth noting that this embodiment takes into account the spatial distance between the motorcycle and the operator, as well as the operation and maintenance task volume of each operator. Among multiple candidate operators, the operator whose distance is within a preset range and whose operation and maintenance task volume is less than the preset task volume is selected as the selected operator. When there are multiple candidate operators whose distance is within a preset range and whose operation and maintenance task volume is less than the preset task volume, one of the candidate operators is randomly selected as the selected operator. This ensures that a better candidate operator is selected as the selected operator, thereby improving the management efficiency of motorcycles and shortening the disposal time as much as possible.

[0114] The present invention also provides an electric motorcycle, comprising a body, a helmet, and a control system arranged in the body; wherein, the body is also provided with an inclination sensor device for detecting body posture information, the inclination sensor is connected to the control system, the helmet is provided with a communication module connected to the control system, a camera for acquiring riding environment images is installed in front of the helmet, the control system comprises a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the computer program, the steps of the method for detecting and handling traffic accidents based on an electric motorcycle helmet are implemented as described above.

[0115] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting and handling traffic accidents based on motorcycle helmets, characterized in that: Includes steps: S1, obtaining real-time status information of an electric motorcycle, and determining whether the electric motorcycle is in an on state according to the real-time status information; S2, when the motorcycle is in the on-state, controlling the camera mounted on the front of the motorcycle helmet to enter a capture mode, and acquiring environmental image information captured by the camera at a first preset time interval; S3, determining whether the environmental image information contains a preset traffic accident image; S4, when the environmental image information contains the preset traffic accident image, control the camera to enter the first video recording mode, and after waiting for a first preset time, send the environmental image information and / or the first warning instruction recorded by the camera within the first preset time to the first target object.

2. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 1, characterized in that: The step S4 specifically includes the following steps: S41, when the preset traffic accident image is included in the environmental image information, determining the traffic accident assessment level corresponding to the preset traffic accident image according to the preset traffic accident image, and judging whether the traffic accident assessment level is greater than the preset severity level; when the traffic accident assessment level is greater than the preset severity level, executing steps S42 to S44; when the traffic accident assessment level is less than or equal to the preset severity level, executing steps S45 to S47; S42, controlling the camera to enter the first video recording mode, and obtaining the current running speed of the motorcycle and the interval distance between the motorcycle and the traffic accident point; S43, determining the theoretical calculation time for the motorcycle to move to the traffic accident point according to the interval distance and the current running speed, and using the theoretical calculation time as the first preset time length; S44, after waiting for the first preset time, sending the environmental information recorded by the camera within the first preset time, the traffic accident assessment level, and the current position of the motorcycle to the first target object; S45, controlling the camera to enter the first video recording mode, and recording the environmental information video obtained by the camera within a second preset time period after entering the first video recording mode, and determining whether the environmental information node video corresponding to the first time node at the end of the second preset time period has a preset traffic accident image; S46, when the environment information node video corresponding to the first time node at the end of the second preset time has a preset traffic accident image, the second preset time is extended by a third preset time as the first preset time; S47, after waiting for the first preset time period, sending the environmental image information recorded by the camera within the first preset time period, the traffic accident assessment level and the current position of the motorcycle to the first target object.

3. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 2, characterized in that: The step S3 further includes the following steps: S51, when the environment image information does not contain a preset traffic accident image, obtaining a real-time running speed of the motorcycle, and determining whether the motorcycle is in a stationary state according to the real-time running speed; S52, when the motorcycle is in a stationary state, obtaining the body posture information detected by the body inclination detection device, and obtaining the vertical distance between the camera and the ground; wherein the body inclination detection device is disposed in the body of the motorcycle; S53, judging whether the motorcycle is in a dumped state and judging whether the vertical distance is less than a preset threshold according to the vehicle posture information; S54, when any one of the following is true: the motorcycle is in a tipping state and the vertical distance is less than a preset threshold, controlling the camera to enter a second video recording mode, acquiring an environmental information video obtained by the camera within a fourth preset time period after entering the second video recording mode, and determining whether the motorcycle is in a tipping state and whether the vertical distance between the camera and the ground is less than a preset threshold at a second time point at the end of the fourth preset time period; S55, when any one of the following conditions holds true: the motorcycle is in a tipping state and the vertical distance is less than a preset threshold, sending the environmental image information recorded by the camera within the fourth preset time period and / or the second warning instruction to the selected operation and maintenance personnel; S56, when neither of the two conditions, namely, that the motorcycle is in a tipping state and that the vertical distance is less than a preset threshold, is true, maintaining the camera in the capture mode.

4. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 3 is characterized in that: The step S54 further includes the following steps: S541, when two of the conditions that the motorcycle is in a tipping state and the vertical distance is less than a preset threshold value are simultaneously met, it is determined that the motorcycle is in a serious traffic accident level, and the environmental image information recorded by the camera within the fourth preset time period and the third warning instruction are sent to the second target object.

5. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 2, characterized in that: The step S3 further includes the following steps: S301, when the environmental image information does not contain a preset traffic accident image, obtaining an angle change rate of the helmet detected by a helmet tilt angle detection device, and obtaining a speed change rate of a motorcycle body, and determining whether the angle change rate is greater than a first preset threshold within a first set time, and determining whether the speed change rate of the motorcycle is greater than a second preset threshold within a second set time; S302, when any one of the angle change rate is greater than a first preset threshold within a first set time and the speed change rate of the motorcycle is greater than a second preset threshold within a second set time is established, it is determined that the motorcycle is in a serious traffic accident level, and the environmental image information recorded by the camera within the set time and the third warning instruction are sent to the second target object; S303, when both of the angle change rate being greater than the first preset threshold within the first set time and the speed change rate of the motorcycle being greater than the second preset threshold within the second set time are not true, return to step S301.

6. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 1, characterized in that: The step S3 further includes the following steps: S31, when the environment image information does not contain a preset traffic accident image, determining whether the environment image information contains a target obstacle; S32: When the target obstacle is present in the environmental image information, the first preset time interval is adjusted to a second preset time interval; wherein the second preset time interval is smaller than the first preset time interval.

7. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 5, characterized in that: The step S32 further includes the following steps: S33, judging whether the corresponding environment image information has the target obstacle at a third time point at the end of a fifth preset time period after the target obstacle is first detected; S34, when the environment image information does not have the target obstacle, adjusting the second preset time interval to the first time interval; S35, when the environmental image information contains the target obstacle, maintaining the camera to continue capturing images at the second preset time interval.

8. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 1, characterized in that: The step S4 further includes the following steps: S401, obtaining historical position data of the motorcycle within a sixth preset time period before the current moment and determining a vector motion path of the motorcycle according to the historical position data set; S402, judging whether there is a target shared vehicle in an area behind the current motorcycle and within a preset range from the current position according to the current position of the motorcycle and the vector motion path; wherein the target shared vehicle is in communication connection with the motorcycle; S403: When there is a target shared vehicle behind the current motorcycle and within a preset range from the current position, a fourth warning instruction is sent to the target shared vehicle.

9. The method for detecting and handling traffic accidents based on motorcycle helmets according to claim 3, characterized in that: The "selected operation and maintenance personnel" in step S55 is obtained through the following steps: S551, obtaining the real-time position of the motorcycle, and obtaining, according to the real-time position of the motorcycle, the operation and maintenance task amounts of a plurality of candidate operation and maintenance personnel within a preset range from the real-time position, and the distances between the candidate operation and maintenance personnel and the real-time position; S552, determining, as the selected operation and maintenance personnel, a candidate operation and maintenance personnel whose distance is within a preset range and whose operation and maintenance task amount is less than a preset task amount among the plurality of candidate operation and maintenance personnel; S553: ​​When there are multiple candidate operation and maintenance personnel whose distances are within a preset range and whose operation and maintenance task amounts are less than a preset task amount, randomly select one of the candidate operation and maintenance personnel as the selected operation and maintenance personnel.

10. An electric motorcycle, characterized in that: It includes a vehicle body, a helmet and a control system arranged in the vehicle body; wherein, the vehicle body is also provided with an inclination sensor device for detecting vehicle body posture information, the inclination sensor is connected to the control system, the helmet is provided with a communication module connected to the control system, a camera for acquiring riding environment images is installed in front of the helmet, the control system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method for detecting and handling traffic accidents based on a motorcycle helmet as described in any one of claims 1 to 9 are implemented.

Citation Information

Patent Citations

  • Riding state acquisition and accident analysis processing method and system

    CN114359805A

  • Motorcycle, road-occupied driving monitoring method thereof and storage medium

    CN114446055A

  • Motorcycle helmet having camera function

    CN2708694Y

  • Folding tailgate for vehicle

    KR1020230025644A

  • A rider assistance system and method

    US20210221368A1

Cited By

  • Electric vehicle safety management method and system based on Internet of Things

    CN119379521A