Automobile data recorder system for cloud data storage and real-time remote access

Abstract

The invention relates to the technical field of automobile data recorders, in particular to an automobile data recorder system for cloud data storage and real-time remote access, which is characterized in that a data acquisition module acquires real-time audio and video data of driving, and the real-time audio and video data are separated according to a preset time interval; the data acquisition module acquires real-time audio and video data in different time periods, locally stores the real-time audio and video data acquired by the data acquisition module through the local storage module and uploads the real-time audio and video data to the cloud server, and a danger feature recognition library is established based on the cloud server. Real-time audio and video data are compared through a feature recognition module, hidden danger feature information in the storage archive is recognized, the corresponding real-time audio and video data are marked based on the danger feature information, priority division is established according to the danger degree of the danger feature information, and access permission is established through a cloud server; the method is used for guaranteeing user privacy.

Description

Technical Field

[0001] The present invention relates to the technical field of driving recorders, and more specifically, it relates to a driving recorder system with cloud data storage and real-time remote access. Background Art

[0002] A driving recorder is one of the important tools for recording driving safety. The driving record of the driving recorder can record the driving situation in real time and provide strong evidence for the determination of liability in traffic accidents.

[0003] With consumers paying increasing attention to vehicle safety, the automotive industry has been continuously innovating and improving in terms of safety measures. Although the probability of vehicle spontaneous combustion is relatively low, once a spontaneous combustion accident occurs, the consequences are often catastrophic, not only may lead to the complete destruction of the vehicle, but also may cause casualties and property losses. Research shows that many spontaneous combustion events can be avoided through timely early warning and intervention in the early stage, but currently, many drivers often do not have enough time to take effective extinguishing measures when they find the vehicle on fire, because the fire usually spreads rapidly in a short time. This makes the fire very fierce when professional fire-fighting personnel and equipment arrive, and the resulting losses are often irreversible.

[0004] The damage caused by spontaneous combustion to the whole vehicle is devastating. Once it occurs, in most cases, due to the destruction of the vehicle, the cause of the accident cannot be identified. The traffic police, insurance companies, etc. are difficult to divide the accident liability due to the unclear cause of the accident, which may further exacerbate the compensation liability and losses of the vehicle owner. Summary of the Invention

[0005] Aiming at the deficiencies of the above-mentioned existing technologies, the purpose of the present invention is to provide a driving recorder system with cloud data storage and real-time remote access, which has the advantages of being able to collect real-time audio and video data in time periods, quickly save the real-time audio and video data, and establishing access permissions through a cloud server to protect user privacy.

[0006] The above technical purpose of the present invention is achieved through the following technical solutions: A driving recorder system with cloud data storage and real-time remote access, a data acquisition module, which acquires real-time audio and video data of driving and performs segmentation processing on the real-time audio and video data according to a preset time interval;

[0007] A local storage module, which locally stores the real-time audio and video data of the data acquisition module;

[0008] A cloud server, which receives the real-time audio and video data uploaded by the data acquisition module, sets a storage file according to the uploaded user information, and establishes a secure access permission;

[0009] A feature recognition module that establishes a dangerous feature recognition library in the cloud server, identifies implicit dangerous feature information in the stored archives through the feature recognition module, marks the corresponding real-time audio and video data based on the dangerous feature information, and establishes a priority classification based on the degree of danger of the dangerous feature information;

[0010] The security access permission includes the following access steps:

[0011] S1: The visitor sends an access request to the cloud server through the mobile terminal. The cloud server performs binding identity recognition on the visitor information. If the visitor information is not bound to the cloud server, the access jumps. If the visitor information is consistent with the information bound to the cloud server, the access logs in;

[0012] S2: For incorrect recognition information, a rejection request is directly sent by the cloud server; if the recognition information is correct, the stored archive is opened through the cloud server;

[0013] S3: An accessor information document is established in the cloud server, including the visitor's identity information, device information, and access time, so as to facilitate the visitor to access the stored archive in real time.

[0014] Preferably, it further includes an emergency handling mechanism for handling in emergency situations. The emergency handling mechanism includes a signal transmission module electrically connected to the vehicle machine. The vehicle machine transmits the driving status to the signal transmission module in real time, and transmits it to the emergency handling center module through the signal transmission module. The emergency handling center module controls the data acquisition module and the local storage module to start an emergency danger warning according to the danger priority level of the driving status.

[0015] Preferably, based on the emergency danger warning, the emergency handling center module controls the data acquisition module to continuously acquire real-time audio and video data and shorten the preset time interval;

[0016] The emergency handling center module controls the data calibration and comparison between the local storage module and the cloud server, and uploads the audio and video data that has not been uploaded by the data acquisition module.

[0017] Preferably, the cloud server is connected to the data acquisition module through a wireless transmission module to realize wireless data transmission. The data acquisition module acquires real-time audio and video data of the driving, evaluates the transmission quality of the transmission path through dynamic adaptive streaming technology, formulates the priority of the transmission method, and performs transmission.

[0018] Preferably, the transmission quality of the transmission path is evaluated based on evaluation indicators such as path bandwidth, delay, packet loss rate, and jitter, and an evaluation model formula is established:

[0019] S = W1*B + W2*(1 - P) + W3*(1 - L) + W4*(1 - J);

[0020] Among them, S is used to measure the quality of the transmission path;

[0021] B is the bandwidth utilization rate, representing the ratio of the actually used bandwidth to the available bandwidth;

[0022] P is the packet loss rate, representing the proportion of data packets lost during transmission;

[0023] L is the latency, representing the transmission time of data from the source to the destination;

[0024] J is the jitter, representing the degree of change in latency;

[0025] Based on the calculation of the quality of the transmission path, set the path transmission quality evaluation threshold and priority;

[0026] When the transmission path with a quality greater than the path transmission quality evaluation threshold is preferentially transmitted, and the transmission path with a quality less than or equal to the path transmission quality evaluation threshold is compressed and transmitted.

[0027] Preferably, among the real-time audio and video data processed at preset time intervals, multiple images of the vehicle area are randomly obtained, edge detection is performed based on the recognition target information to generate recognition target edge information, and based on the obtained target edge information, preliminary recognition is performed by capturing the information of the target object in the image. First, it is judged whether the border between the vehicle and the target intersects; if it intersects, it is determined that there may be contact, and if it does not intersect, it is determined that there is no contact.

[0028] Preferably, based on the target edge information as the recognition frame, when the border between the vehicle and the target intersects, the center point of the target is found by taking the focus position of the diagonal of the recognition frame, and according to the same target, the preset threshold of the height change value is set based on the height change value of the center point before and after the preset time interval to judge whether the target has fallen;

[0029] Take single-frame images before and after the preset time interval, where the preset time is Δt, the center point of the target in single-frame image one is (x1, y1), the center point of the same target in single-frame image two is (x2, y2), and Δy is the change rate of the center point of the target within the preset time;

[0030] The formula algorithm is:

[0031] Combined with the magnitude of the Δy change rate, the dangerous feature information is deeply bound to it, and whether the target collides and falls with the vehicle is judged by the height change of the target within the preset time.

[0032] Preferably, according to the access step S1, when the visitor information is not bound to the cloud server, by jumping to the access interface, enter the new registration area and the relative login area;

[0033] New registration area: Based on the user's login request, prompt the user to input a set of linked accounts, identity names, ID numbers, and passwords, and identify and bind them with the corresponding driving recorder codes;

[0034] Relative login area: Based on the user's relative login request, prompt the user to input the identity name and ID number of the original registrant, and prompt the user to input the identity name and ID number of the relative login person. If there is no bound information for the original registrant or the information of the original registrant is incorrect, then reject the user's access request. If there is bound information for the original registrant, then the user's registration access is successful.

[0035] Preferably, establish a relative visitor information document in the cloud server, including the identity information, device information, and access time of the relative visitor.

[0036] In summary, the beneficial effects of the present invention are as follows: The data acquisition module acquires the real-time audio and video data of the vehicle, separates and processes the real-time audio and video data according to a preset time interval, collects the real-time audio and video data in time segments. At the same time, the local storage module locally stores the real-time audio and video data collected by the data acquisition module, and uploads the real-time audio and video data to the cloud server. Based on the danger feature recognition library established by the cloud server, the feature recognition module compares the real-time audio and video data, identifies the hidden danger feature information in the stored file, marks the corresponding real-time audio and video data based on the danger feature information, establishes a priority classification according to the danger level of the danger feature information, and uses the cloud server to establish access permissions to protect user privacy. Description of the Drawings

[0037] Figure 1 is a schematic diagram of the module electrical signal connection of the embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of the user access method of the embodiment of the present invention.

[0039] Reference numerals: 1, data acquisition module; 11, local storage module; 13, cloud server module; 14, feature recognition module; 15, signal transmission module; 16, emergency handling center module. Detailed Embodiment

[0040] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0041] It should be noted that when a component is referred to as "fixed to" or "disposed on" another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as "connected to" another component, it can be directly or indirectly connected to the other component.

[0042] It should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0043] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0044] A driving recorder system for cloud data storage and real-time remote access, see Figure 1 and Figure 2 , including:

[0045] A data acquisition module 1, which acquires real-time audio and video data of driving and performs segmentation processing on the real-time audio and video data according to a preset time interval;

[0046] A local storage module 11, which locally stores the real-time audio and video data of the data acquisition module 1; a cloud server, which receives the real-time audio and video data uploaded by the data acquisition module 1, sets a storage file according to the uploaded user information, and establishes a secure access permission;

[0047] A feature recognition module 14, which establishes a dangerous feature recognition library in the cloud server, compares the characteristic data of the storage file with the dangerous feature recognition library, identifies the hidden dangerous feature information in the storage file, marks the corresponding real-time audio and video data based on the dangerous feature information, and establishes a priority division according to the degree of danger of the dangerous feature information;

[0048] The said secure access permission includes the following access steps:

[0049] S1: The visitor sends an access request to the cloud server through a mobile terminal. The cloud server performs bound identity recognition on the visitor information. If the visitor information is not bound to the cloud server, the access jumps. If the visitor information is consistent with the information bound to the cloud server, the access logs in.

[0050] S2: For incorrect identification information, a rejection request is directly sent by the cloud server; if the identification information is correct, the stored file is opened through the cloud server.

[0051] S3: A visitor information document is established in the cloud server, including the visitor's identity information, device information, and access time.

[0052] In this embodiment, the data acquisition module 1 acquires the real-time audio and video data of the vehicle driving, performs segmentation processing on the real-time audio and video data according to a preset time interval, collects the real-time audio and video data in time segments. At the same time, the local storage module 11 locally stores the real-time audio and video data collected by the data acquisition module 1, and uploads the real-time audio and video data to the cloud server. Based on the dangerous feature recognition library established by the cloud server, the feature recognition module 14 compares the real-time audio and video data, identifies the implicit dangerous feature information in the stored file, marks the corresponding real-time audio and video data based on the dangerous feature information, establishes a priority division according to the danger level of the dangerous feature information, and uses the cloud server to establish access permissions to protect user privacy.

[0053] Among them, the data acquisition module 1 corresponds the video captured by the camera module and the sound recorded by the microphone in the driving recorder in the same time period, so as to complete the real-time audio and video data of the data acquisition module 1.

[0054] A preset time interval is set in the data acquisition module 1. For example, the duration of the video captured by the camera module is set to 10 minutes, and the duration of the sound recorded by the microphone is also set to 10 minutes. If the duration collected by the data acquisition module 1 is less than 10 minutes, it is calculated according to the actual duration, that is, every 10 minutes, the previously collected real-time audio and video data is stored in the local storage module 11.

[0055] Through the establishment based on the cloud server, the audio and video data recorded in real time ten minutes ago is uploaded to the cloud server for storage.

[0056] Based on the segmented interval processing of the real-time audio and video data, the real-time audio and video data can be saved quickly and effectively, avoiding the loss of driving record data due to vehicle damage or combustion.

[0057] Based on the consideration of safety data, this embodiment further includes an emergency handling mechanism established on the data acquisition module 1 for handling in emergency situations. The emergency handling mechanism includes a signal transmission module 15 electrically connected to the vehicle machine. The vehicle machine transmits the driving conditions in real time to the signal transmission module 15, and through the signal transmission module 15, it is transmitted to the emergency handling center module 16. The emergency handling center module 16 divides the priority levels according to the danger of the driving conditions, and controls the data acquisition module 1 and the local storage module 11 to start emergency danger warnings.

[0058] The vehicle machine in this embodiment is the vehicle-mounted vehicle machine system. Among them, the emergency handling mechanism is triggered by the signal transmission module 15. According to the vehicle machine transmitting the driving conditions in real time to the signal transmission module 15, the vehicle's distress situation is transmitted to the emergency handling center module 16 through the signal transmission module 15, and the operation of the data acquisition module 1 is controlled through the emergency handling center module 16. Since the priority levels of the danger of the driving conditions include minor collisions, moderate injuries, and severe damages, different emergency handling methods are divided according to the danger level of the vehicle.

[0059] Specifically, the originally set preset time interval of 10 minutes of the data acquisition module 1 is shortened to a shorter time, such as 8 minutes or 5 minutes, etc., so as to be able to upload the real-time audio and video data collected by the data acquisition module 1 faster and avoid the loss of real-time audio and video data due to vehicle damage and destruction.

[0060] In addition, the cloud server is connected to the data acquisition module 1 through a wireless transmission module to achieve wireless data transmission. The data acquisition module 1 collects real-time audio and video data of driving, evaluates the transmission quality of the transmission path through dynamic adaptive streaming technology, formulates the priority of the transmission method, and performs transmission.

[0061] During the process of uploading real-time audio and video data, affected by the transmission quality of the transmission path, in order to be able to upload the lost audio and video data in time, it is evaluated based on evaluation indicators such as path bandwidth, delay, packet loss rate, and jitter, and an evaluation model formula is established:

[0062] S = W1*B + W2*(1 - P) + W3*(1 - L) + W4*(1 - J);

[0063] Among them, S is used to measure the quality of the transmission path;

[0064] B is the bandwidth utilization rate, which represents the ratio of the actually used bandwidth to the available bandwidth;

[0065] P is the packet loss rate, which represents the proportion of lost data packets during transmission;

[0066] L is the delay, which represents the transmission time of data from the source to the destination;

[0067] J is the jitter, representing the degree of change in delay;

[0068] Based on the calculation of the quality of the transmission path, set the path transmission quality evaluation threshold and priority;

[0069] When preferentially transmitting the transmission paths greater than the path transmission quality evaluation threshold and compressing and transmitting the transmission paths less than or equal to the path transmission quality evaluation threshold, real-time audio and video data can be quickly uploaded in this way, avoiding the delay in uploading real-time audio and video data due to the transmission quality problems of the transmission paths.

[0070] Specifically, among the real-time audio and video data processed by separating at preset time intervals, randomly obtain multiple images of the vehicle area, perform edge detection based on the target information to generate target edge information, and based on the obtained target edge information, initially identify by grasping the information of the target in the image, and first determine whether the border between the vehicle and the target object intersects; if it intersects, it is determined that there may be contact, and if it does not intersect, it is determined that there is no contact.

[0071] After a preset interval, take two images successively, obtain the target in the image through edge detection, first determine whether there is an associated causality between the grasped target and the vehicle, and after determining that the two intersect, proceed to the next step.

[0072] Specifically, using the target edge information as the recognition frame, when the border between the vehicle and the target intersects, find the center point of the target by taking the focus position of the diagonal of the recognition frame, and according to the same target, set the preset threshold of the height change value based on the height change value of the center point before and after the preset time interval, and determine whether the target has fallen;

[0073] Take single-frame images before and after a preset time interval, where the preset time is t, the center point of the target in the first single-frame image is (x1, y1), and the center point of the same target in the second single-frame image is (x2, y2), which is the change rate of the center point of the target within the preset time;

[0074] The formula algorithm is:

[0075] Combined with the magnitude of the change rate, deeply bind the dangerous feature information to it, and judge whether the target and the vehicle have collided and fallen through the height change of the target within the preset time.

[0076] Since there will be a height difference in the height of the falling object, an identification frame of the target is established through the target edge information. Based on the same target before and after a preset time, the height difference change that occurs within the preset time is used as the basis for determining a collision and fall, which can quickly identify the dangerous feature information and mark the real-time audio and video data containing the dangerous feature information, so as to facilitate the review and viewing of the real-time audio and video during this period.

[0077] Among them, a priority division is established for the degree of danger of the dangerous feature information, which is represented by the color distinction of the mark, divided into yellow and red. Due to the different degrees of injury of the target, after a collision, the target with minor injuries can sit or squat, but the target with serious injuries usually can only lie on the ground.

[0078] Therefore, the real-time audio and video data of the target with minor injuries is marked in yellow, and the real-time audio and video data of the target with serious injuries is marked in red.

[0079] When accessing the cloud server, according to step S1 of the access, when the visitor information is not bound to the cloud server, by jumping to the access interface, enter the new registration area and the relative login area, and there are two types of access subjects respectively;

[0080] In the new registration area, based on the user's login request, prompt the user to enter a set of link accounts, identity names, ID numbers and passwords, and identify and bind them with the corresponding driving recorder codes;

[0081] In the relative login area, based on the user's relative login request, prompt the user to enter the identity name and ID number of the original registrant, and prompt the user to enter the identity name and ID number of the relative login person. If there is no binding information for the original registrant or the information of the original registrant is incorrect, the user's access request will be rejected. If there is binding information for the original registrant, the user's registration access is successful.

[0082] After the relative logs in, a relative visitor information document is established in the cloud server, including the identity information, device information and access time of the relative visitor, so as to protect the user's privacy.

[0083] The above embodiments are only explanations of the present invention, and they are not limitations of the present invention. Those skilled in the art can make modifications to the embodiments without creative contributions according to needs after reading this specification, but as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A driving recorder system with cloud data storage and real-time remote access, characterized by: include: The data acquisition module collects real-time audio and video data of the vehicle and separates and processes the real-time audio and video data according to a preset time interval; The local storage module locally stores the real-time audio and video data of the data acquisition module; The cloud server receives real-time audio and video data uploaded by the data acquisition module, sets up storage files based on the uploaded user information, and establishes security access permissions; A feature recognition module is used to establish a dangerous feature recognition library in the cloud server, identify the hidden dangerous feature information in the storage file through the feature recognition module, mark the corresponding real-time audio and video data based on the dangerous feature information, and establish priority classification according to the degree of danger of the dangerous feature information; The security access rights include the following access steps: S1: The visitor sends an access request to the cloud server through a mobile terminal. The cloud server binds the visitor's information to the cloud server for identity recognition. If the visitor's information is not bound to the cloud server, the visit is redirected. If the visitor's information is consistent with the information bound to the cloud server, the visit is logged in. S2: If the identification information is wrong, the cloud server directly issues a rejection request; if the identification information is correct, the storage file is opened through the cloud server; S3: A visitor information document is created in the cloud server, including the visitor's identity information, device information, and access time, so that the visitor can access the stored files in real time.

2. The driving recorder system with cloud data storage and real-time remote access according to claim 1, characterized in that: It also includes an emergency handling mechanism for handling emergency situations, the emergency handling mechanism includes a signal transmission module electrically connected to the vehicle computer, the vehicle computer transmits the driving conditions to the signal transmission module in real time, and the signal transmission module transmits it to the emergency handling center module through the signal transmission module, the emergency handling center module controls the data acquisition module and the local storage module to start the emergency danger warning according to the danger priority level of the driving conditions.

3. The driving recorder system with cloud data storage and real-time remote access according to claim 2 is characterized by: Based on the emergency danger warning, the emergency processing center module controls the data acquisition module to continuously collect real-time audio and video data, shortening the preset time interval; The emergency processing center module controls the data between the local storage module and the cloud server to perform data calibration and comparison, and uploads the audio and video data that has not been uploaded by the data acquisition module.

4. The driving recorder system with cloud data storage and real-time remote access according to claim 2, characterized in that: The cloud server and the data acquisition module are connected via a wireless transmission module to achieve wireless data transmission. The data acquisition module collects real-time audio and video data of driving, evaluates the transmission quality of the transmission path through dynamic adaptive streaming media technology, determines the priority of the transmission method, and then transmits it.

5. The driving recorder system with cloud data storage and real-time remote access according to claim 4 is characterized by: The transmission quality of the transmission path is evaluated based on evaluation indicators of path bandwidth, delay, packet loss rate and jitter, and an evaluation model formula is established: S=W1*B+W2*(1-P)+W3*(1-L)+W4*(1-J); Among them, S is used to measure the quality of the transmission path; B is the bandwidth utilization, which indicates the ratio of the actually used bandwidth to the available bandwidth; P is the packet loss rate, which indicates the proportion of data packets lost during transmission; L is latency, which indicates the transmission time of data from source to destination; J is jitter, which indicates the degree of delay variation; Based on the calculation of the quality of the transmission path, the path transmission quality evaluation threshold and priority are set; When a transmission path with a value greater than the path transmission quality evaluation threshold is given priority transmission, a transmission path with a value less than or equal to the path transmission quality evaluation threshold is compressed transmission.

6. The driving recorder system with cloud data storage and real-time remote access according to claim 1, characterized in that: In the real-time audio and video data processed at preset time intervals, multiple images of the vehicle area are randomly acquired, and edge detection is performed based on the recognition target information to generate recognition target edge information. Based on the acquired target edge information, preliminary recognition is performed by grabbing the information of the target object in the image to first determine whether the borders between the vehicle and the target intersect; if so, it is determined that there may be contact; if not, it is determined that there is no contact.

7. The driving recorder system with cloud data storage and real-time remote access according to claim 6 is characterized by: Based on the target edge information as the identification frame, when the frame between the vehicle and the target intersects, the center point of the target is found by taking the focal point of the diagonal of the identification frame, and according to the height change value of the center point before and after the preset time interval of the same target, the preset threshold of the height change value is set to determine whether the target has fallen; Take single-frame images before and after a preset time interval, where the preset time is Δt, the target center point of single-frame image one is (x1, y1), the same target center point of single-frame image two is (x2, y2), and Δy is the rate of change of the target center point within the preset time; The formula algorithm is: Combined with the size of the Δy change rate, the dangerous feature information is deeply bound to it, and the height change of the target within the preset time is used to determine whether the target collides with the vehicle and falls.

8. The driving recorder system with cloud data storage and real-time remote access according to claim 1, characterized in that: According to the access step S1, when the visitor information is not bound to the cloud server, the new registration area and the relative login area are entered by jumping to the access interface; New registration area, based on the user's login request, prompts the user to enter a set of linked account, identity name, ID number and password, which is identified and bound with the corresponding dashcam code; The relative login area prompts the user to enter the identity name and ID number of the original registrant based on the user's relative login request, and prompts the user to enter the identity name and ID number of the relative login. If the original registrant has no binding information or the original registrant's information is incorrect, the user's access request will be rejected. If the original registrant has binding information, the user's registration access is successful.

9. The driving recorder system with cloud data storage and real-time remote access according to claim 8, characterized in that: A relative visitor information document is created in the cloud server, including the relative visitor's identity information, device information, and access time.

Images