CN115378980B - Directional storage method and device for driving monitoring data - Google Patents
Directional storage method and device for driving monitoring data Download PDFInfo
- Publication number
- CN115378980B CN115378980B CN202211287085.7A CN202211287085A CN115378980B CN 115378980 B CN115378980 B CN 115378980B CN 202211287085 A CN202211287085 A CN 202211287085A CN 115378980 B CN115378980 B CN 115378980B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- monitoring
- video
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
- G07C5/0866—Registering performance data using electronic data carriers the electronic data carrier being a digital video recorder in combination with video camera
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The embodiment of the application discloses a directional storage method and device of driving monitoring data. According to the technical scheme, the driving monitoring data are extracted, the data compression storage with strong privacy and partial driving requirements are selected, the residual target data are encrypted and uploaded to the cloud background, the driving monitoring data can be cached locally, the driving monitoring data can be timely checked by a user, the driving data is prevented from being leaked, the residual target data are uploaded to the cloud background for storage, and the data storage pressure of the driving recorder can be relieved.
Description
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to a directional storage method and device for driving monitoring data.
Background
The automobile data recorder is used for recording monitoring audios and videos of the driving environment in the driving process of the automobile. By recording the monitoring audio and video of the driving environment, important evidence can be provided for the judgment of the responsibility of the traffic accident. Therefore, the automobile data recorder needs to store a large amount of monitoring audio and video data. In order to relieve the storage pressure of the automobile data recorder, the internal memory is usually cleaned at regular time, and the monitoring audio and video are transferred and uploaded to the cloud background for storage.
However, the monitoring audios and videos may contain some driving environment information of the locomotive, and privacy information such as user conversation information and travel information. The monitoring audio and video is uploaded to the cloud background for storage, the content of the monitoring audio and video can be easily inquired at one end of the cloud background, and once the cloud background is attacked by a network, the content of the monitoring audio and video is easily leaked. The protection of the privacy information of the user and the protection of the environmental essential information are not facilitated, and the safety of monitoring the audio and video content storage is influenced.
Disclosure of Invention
The embodiment of the application provides a directional storage method and device of driving monitoring data, which can reduce the storage pressure of local data of a driving recorder, ensure the storage safety of part of important driving monitoring data and solve the safety problem when the driving monitoring data is uploaded.
In a first aspect, an embodiment of the present application provides a directional storage method for driving monitoring data, including:
acquiring target data to be uploaded, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information;
identifying a monitoring audio of the target data based on specified voiceprint features, determining a target audio frame containing the specified voiceprint features in the monitoring audio, identifying a monitoring video of the target data based on specified image features, determining a target video frame containing specified image features, and defining a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining that the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area are confidential data, and defining a second target time period based on the confidential data;
intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of a vehicle data recorder, and encrypting and uploading the rest target data to a cloud background.
Further, after the cache data is compressed and stored in a designated storage space of the automobile data recorder, the method further includes:
and periodically detecting the designated storage space, and selecting the cache data to encrypt and upload the cache data to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
Further, before obtaining the target data to be uploaded, the method further includes:
detecting a target storage space of the automobile data recorder, and determining the storage capacity of the automobile monitoring data;
and under the condition that the storage amount reaches a set threshold value, selecting the driving monitoring data of a specified period from the target storage space as target data to be uploaded.
Further, the selecting the driving monitoring data of a specified period from the target storage space as the target data to be uploaded includes:
and selecting the driving monitoring data of the appointed time period from the target storage space as target data to be uploaded according to the storage time sequence of the driving monitoring data and the set reporting time length.
Further, the identifying the surveillance video of the target data based on the specified image features and determining the target video frame containing the specified image features includes:
inputting the surveillance video of the target data into a pre-constructed target detection model, identifying the surveillance video of the target data based on the pre-constructed target detection model, and determining a target video frame containing specified image characteristics, wherein the target detection model is trained and constructed based on the specified image characteristics in advance.
Further, after identifying the surveillance video of the target data based on the pre-constructed target detection model and determining the target video frame containing the specified image feature, the method further comprises the following steps:
and putting the target video frame into a training data set of the target detection model, and performing iterative training of the target detection model.
In a second aspect, an embodiment of the present application provides a directional storage device for driving monitoring data, including:
the acquisition module is used for acquiring target data to be uploaded, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information;
the identification module is used for identifying the monitoring audio of the target data based on the specified voiceprint characteristics, determining a target audio frame containing the specified voiceprint characteristics in the monitoring audio, identifying the monitoring video of the target data based on the specified image characteristics, determining a target video frame containing the specified image characteristics, and defining a first target time period based on the timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data;
and the uploading module is used for intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of the automobile data recorder, and encrypting and uploading the rest target data to the cloud background.
Further, after the cache data is compressed and stored in a designated storage space of the automobile data recorder, the method further includes:
and periodically detecting the designated storage space, and selecting the cache data to be encrypted and uploaded to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory and one or more processors;
the memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for directionally storing driving monitoring data according to the first aspect.
In a fourth aspect, the present application provides a storage medium containing computer executable instructions, which when executed by a computer processor, are used to perform the method for directional storage of traffic monitoring data according to the first aspect.
According to the method and the device, target data to be uploaded are acquired, the target data comprise monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information; identifying a target audio frame containing specified voiceprint features in the monitored audio based on the monitored audio of the specified voiceprint feature identification target data, identifying a monitored video of the target data based on the specified image features, determining a target video frame containing the specified image features, and delimiting a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on the set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data; monitoring audio and monitoring video corresponding to the time stamp are intercepted from the target data according to the first target time interval and the second target time interval to serve as cache data, the cache data are compressed and stored to a designated storage space of the automobile data recorder, and the rest target data are encrypted and uploaded to the cloud background. By adopting the technical means, the driving monitoring data are extracted, the data which are partially important and have strong privacy are compressed and stored, and the rest target data are encrypted and uploaded to the cloud background, so that the driving monitoring data which are partially important can be cached locally, a user can check the driving monitoring data in time, the leakage of the driving data which are partially important is avoided, the rest target data are uploaded to the cloud background for storage, and the data storage pressure of the driving recorder can be relieved.
Drawings
Fig. 1 is a flowchart of a method for directionally storing driving monitoring data according to an embodiment of the present application;
FIG. 2 is a flow chart of the screening of target data according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a directional storage device for driving monitoring data according to a second embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to a second embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but could have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, subprograms, and the like.
The first embodiment is as follows:
fig. 1 is a flowchart of a method for directionally storing driving monitoring data according to an embodiment of the present application, where the method for directionally storing driving monitoring data provided in this embodiment may be executed by a directional storage device for driving monitoring data, the directional storage device for driving monitoring data may be implemented in a software and/or hardware manner, and the directional storage device for driving monitoring data may be formed by two or more physical entities or may be formed by one physical entity. Generally speaking, the directional storage device of the driving monitoring data can be a processing device such as a driving recorder processor, a controller and the like.
The following description will be given by taking the directional storage device of the driving monitoring data as an example of a main body of the directional storage method for executing the driving monitoring data. Referring to fig. 1, the directional storage method of driving monitoring data specifically includes:
s110, target data to be uploaded are obtained, the target data comprise monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information.
The directional storage method of the driving monitoring data aims at compressing and caching the driving monitoring data which are to be uploaded and are required by a selected part of the target data to be uploaded and have strong privacy to the local, and the rest target data are encrypted and uploaded to the cloud background, so that the driving monitoring data which are required by the part of the driving monitoring data can be cached to the local, a user can check the driving monitoring data in time, the leakage of the driving monitoring data which are required by the driving monitoring data is avoided, meanwhile, the rest target data are uploaded to the cloud background for storage, and the data storage pressure of the driving recorder can be relieved. In a driving monitoring data storage scene, the data storage pressure of the driving recorder is relieved, the query efficiency of part of important data is guaranteed, and downloading from a cloud background is not needed. And the storage safety of the data of the monitoring of the running vehicles is improved, and the privacy information of the user is prevented from being easily stolen.
Specifically, referring to fig. 2, when determining target data to be uploaded, the method includes:
s1001, detecting a target storage space of the automobile data recorder and determining the storage capacity of automobile monitoring data;
s1002, under the condition that the storage amount reaches a set threshold value, selecting the driving monitoring data of a specified time period from the target storage space as target data to be uploaded.
In the application scene of the driving recorder, monitoring audio and monitoring video in the driving monitoring process can be continuously generated, and the driving monitoring data can be uniformly stored in the storage space of the driving recorder. Along with the continuous accumulation of driving monitoring data, can occupy the too big memory space of vehicle event data recorder, influence vehicle event data recorder's normal operating. Therefore, the storage space of the automobile data recorder needs to be periodically detected, and the storage space is defined as a target storage space. And under the condition that the storage amount of the driving monitoring data reaches a set threshold value, triggering the selection and uploading of the target data.
According to actual data uploading requirements, the automobile data recorder can detect the storage space according to a set period (such as every day, every week and the like). In each detection period, if the storage capacity of the driving monitoring data reaches a set threshold (such as 95% of the storage space), which indicates that the current storage space is insufficient, the driving monitoring data is accumulated too much, and the memory needs to be cleaned in time, at this time, the screening and uploading of the driving monitoring data is triggered. Otherwise, the vehicle driving monitoring data does not need to be screened and uploaded.
Further, under the condition that the storage amount of the driving monitoring data reaches a set threshold value, the selection of the driving monitoring data in the target storage space of the driving recorder is triggered, and the selected driving monitoring data is defined as the target data. Optionally, when the target data is selected, the driving monitoring data of the specified period is selected from the target storage space as the target data to be uploaded according to the storage time sequence of the driving monitoring data and the set reporting time.
It can be understood that, for a part of the driving monitoring data with a longer storage time than the current time, the driving recorder will preferentially report the part of the driving monitoring data, so as to ensure that the driving monitoring data can be uploaded according to a time sequence. In addition, according to actual use habits, when looking up the locally stored driving monitoring data, the probability that the part of the driving monitoring data with the storage time closer to the current time is checked is higher, so that the part of the driving monitoring data with the storage time longer than the current time needs to be uploaded to the cloud background. Based on the above, according to the upper limit of the data amount which needs to be uploaded to the cloud background every time, the embodiment of the application adaptively sets a reporting time length, and based on the set reporting time length, the driving monitoring data is selected as the target monitoring data from the driving monitoring data with the earliest time. For example, if the reporting time is set to be 7 days, the time period of 7 days is determined from the driving monitoring data with the storage time being the longest from the current time, and the driving monitoring data in the specified time period is extracted as the target data.
It should be noted that the target data in the embodiment of the present application includes the monitoring audio and the monitoring video, where the monitoring audio and the monitoring video include corresponding acquisition location information, and for the monitoring audio and the monitoring video that include the privacy information of the user or are acquired at an essential location (such as a part of confidential demand places), the monitoring audio and the monitoring video need to be screened and cached locally, so as to avoid uploading the part of information to a cloud background, and increase the risk that the essential and privacy information is cracked.
S120, identifying the monitoring audio of the target data based on specified voiceprint characteristics, determining a target audio frame containing the specified voiceprint characteristics in the monitoring audio, identifying the monitoring video of the target data based on specified image characteristics, determining a target video frame containing the specified image characteristics, and defining a first target time period based on the timestamp information of the target audio frame and the target video frame; the monitoring audio and the monitoring video are detected based on a set travel area, the collecting position information of the monitoring audio and the monitoring video is determined to fall into the set travel area, the monitoring audio and the monitoring video are confidential data, and a second target time period is defined based on the confidential data.
Further, based on the selected target data, the embodiment of the application further screens the target data to select part of the driving monitoring data which contains the user privacy information or is collected at the confidential position, so as to compress and cache the part of the driving monitoring data. In the driving process of the user, information such as driving sound recording and pedestrian video recording may contain privacy information. Therefore, for the driving monitoring data containing information such as driving sound records, pedestrian video records and the like in the target data, in order to protect the part of private information, the part of private information is screened and cached in the designated storage space, so that the risk that the private information is cracked due to the fact that the part of important driving monitoring data is uploaded to the cloud background is avoided.
Based on this, in the embodiment of the application, a mode of combining voiceprint recognition and pedestrian target detection is adopted, driving monitoring data containing information such as driving sound recording and pedestrian video recording are screened out from target data to be cached in a predetermined storage space, and the storage space is defined as an appointed storage space.
Specifically, for the identification of the specified voiceprint features, the specified voiceprint features corresponding to the driving recording are stored in advance, the voiceprint features extracted from the monitoring audio of the target data are compared with the specified voiceprint features, and the voiceprint features and the specified voiceprint features are matched to determine the monitoring audio containing the driving recording in a partial time period and define the monitoring audio as a target audio frame.
For the identification of the specified image characteristics, the surveillance video of the target data is input into a pre-constructed target detection model, the surveillance video of the target data is identified based on the pre-constructed target detection model, a target video frame containing the specified image characteristics is determined, and the target detection model is trained and constructed based on the specified image characteristics in advance.
The target detection model may adopt a neural network model such as a YOLOv3 target detection model. When the target detection model is trained, a training data set is constructed by collecting data containing pedestrian image features. And further designing a neural network structure and a loss function of the target detection model, and training network parameters of the target detection model by using the training data set marked with the specified target. After the model training is completed, the model structure and parameters are saved for subsequent specified target detection to determine specified image characteristics.
The YOLOv3 target detection model mainly comprises a convolutional layer and a pooling layer, wherein the naming rule of the layer in the network comprises the category and the number appearing for the second time in the network, for example, conv8 represents the 8 th convolutional layer in the network, upsampling represents the upsampling layer in the network, the size of the output feature map of each layer in the network is represented as resolution width multiplied by resolution height multiplied by channel number, and rectangular frames and classifications of all targets in the image are finally obtained through a multilayer convolution hierarchical pooling layer so as to complete the detection of the targets. The pooling layer is an image down-sampling operation, and although parameters of the convolution feature layer are reduced and the model operation speed is increased, semantic information loss is caused to the convolution feature map of the previous layer. The YOLOv3 target detection network considers the problem of computing resources, and the basic framework of the YOLOv3 target detection network in the embodiment of the application is tiny-dark net, the parameters of which are only 4M, and the small amount of which is suitable for landing.
Based on the detection result of the target detection model, whether the monitoring video contains the image characteristics of the pedestrian can be determined. And determining the monitoring video of a partial time period containing the image characteristics of the pedestrian according to the detection result, and defining the monitoring video as a target video frame.
Optionally, in an embodiment, in a case that a surveillance video includes a pedestrian image feature, the target video frame is further placed into a training data set of the target detection model, and iterative training of the target detection model is performed.
It can be understood that, for the surveillance video for identifying the image features of the pedestrians, since the surveillance video contains the image features of the pedestrians, in order to enable the target detection model to identify and detect the image features of the pedestrians more accurately and rapidly, the detection precision and efficiency of the target detection model can be further improved by adding the surveillance video into the training data set to perform iterative training of the target detection model, and the detection efficiency of the surveillance video is optimized.
Based on the voiceprint recognition and the pedestrian target detection, a time interval containing information such as a target audio frame and a target video frame in the target data can be determined, and the time interval is defined as a first target time interval so as to be used for extracting the subsequent corresponding driving monitoring data.
On the other hand, for the part of the driving monitoring data of which the acquisition position is in the machine important position, the embodiment of the application also adaptively performs screening and caching. The collected position information of the monitoring audio and the monitoring video in the target data is compared with a preset travel range, if the collected position information is located in the preset travel range, the part of the driving monitoring data is represented as confidential data, and the confidential data cannot be uploaded to the cloud background, so that the risk of secret divulgence of confidential information is avoided. Based on the method, the corresponding confidential data can be determined by defining the set driving area corresponding to each confidential position and comparing the positions. And further defining a second target time interval according to the time interval of the secret data.
S130, intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of a vehicle data recorder, and encrypting and uploading the rest target data to a cloud background.
And finally, intercepting the monitoring audio and the monitoring video with the timestamps in the first target time period and the second target time period from the target data according to the determined first target time period and the second target time period, wherein the part of driving monitoring data contains user privacy information and confidential data and cannot be uploaded to a cloud background for storage. Therefore, the part of data is filtered and cached to the local designated storage space. And encrypting and uploading the residual target data to the cloud background.
In one embodiment, after the compressing and storing the cache data to the specified storage space of the automobile data recorder, the method further includes:
and periodically detecting the designated storage space, and selecting the cache data to encrypt and upload the cache data to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
It can be understood that, because the cache data that can be accommodated by the second storage space is limited, for a part of data that is stored for a long time, the part of data is periodically uploaded to the cloud background to make room for storing newly screened cache data, thereby ensuring the freshness of the cache data.
The target data to be uploaded is acquired, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information; identifying a target audio frame containing specified voiceprint features in the monitored audio based on the monitored audio of the specified voiceprint feature identification target data, identifying a monitored video of the target data based on the specified image features, determining a target video frame containing the specified image features, and delimiting a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on the set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data; monitoring audio and monitoring video corresponding to the time stamp are intercepted from the target data according to the first target time interval and the second target time interval to serve as cache data, the cache data are compressed and stored to a designated storage space of the automobile data recorder, and the rest target data are encrypted and uploaded to the cloud background. By adopting the technical means, the driving monitoring data are extracted, the data which are partially important and have strong privacy are compressed and stored, and the rest target data are encrypted and uploaded to the cloud background, so that the driving monitoring data which are partially important can be cached locally, a user can check the driving monitoring data in time, the leakage of the driving data which are partially important is avoided, the rest target data are uploaded to the cloud background for storage, and the data storage pressure of the driving recorder can be relieved.
Example two:
on the basis of the foregoing embodiment, fig. 3 is a schematic structural diagram of a directional storage device for driving monitoring data according to a second embodiment of the present application. Referring to fig. 3, the directional storage device for driving monitoring data provided in this embodiment specifically includes: an acquisition module 21, an identification module 22 and an upload module 23.
The acquisition module 21 is configured to acquire target data to be uploaded, where the target data includes a monitoring audio and a monitoring video, and the monitoring audio and the monitoring video of the target data include corresponding acquisition position information;
the identification module 22 is configured to identify a surveillance audio of the target data based on a specified voiceprint feature, determine a target audio frame in the surveillance audio that includes the specified voiceprint feature, identify a surveillance video of the target data based on a specified image feature, determine a target video frame that includes a specified image feature, and define a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data;
the uploading module 23 is configured to intercept the monitoring audio and the monitoring video corresponding to the timestamp from the target data as cache data according to the first target time period and the second target time period, compress and store the cache data in a specified storage space of the automobile data recorder, and encrypt and upload the remaining target data to the cloud background.
Further, after the cache data is compressed and stored in a designated storage space of the automobile data recorder, the method further includes:
and periodically detecting the designated storage space, and selecting the cache data to be encrypted and uploaded to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
Further, before obtaining the target data to be uploaded, the method further includes:
detecting a target storage space of the automobile data recorder, and determining the storage capacity of the automobile monitoring data;
and under the condition that the storage amount reaches a set threshold value, selecting the driving monitoring data of a specified period from the target storage space as target data to be uploaded.
Further, the selecting the driving monitoring data of the specified time period from the target storage space as the target data to be uploaded includes:
and selecting the driving monitoring data of the appointed time period from the target storage space as target data to be uploaded according to the storage time sequence of the driving monitoring data and the set reporting time length.
Further, the identifying the surveillance video of the target data based on the specified image features and determining the target video frame containing the specified image features comprises:
inputting the surveillance video of the target data into a pre-constructed target detection model, identifying the surveillance video of the target data based on the pre-constructed target detection model, and determining a target video frame containing specified image characteristics, wherein the target detection model is trained and constructed based on the specified image characteristics in advance.
Further, after identifying the surveillance video of the target data based on a pre-constructed target detection model and determining a target video frame containing specified image features, the method further includes:
and putting the target video frame into a training data set of the target detection model, and performing iterative training of the target detection model.
In the above, by acquiring target data to be uploaded, the target data includes a monitoring audio and a monitoring video, and the monitoring audio and the monitoring video of the target data include corresponding acquisition position information; identifying a target audio frame containing specified voiceprint features in the monitored audio based on the monitored audio of the specified voiceprint feature identification target data, identifying a monitored video of the target data based on the specified image features, determining a target video frame containing the specified image features, and delimiting a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on the set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data; monitoring audio and monitoring video corresponding to the time stamp are intercepted from the target data according to the first target time interval and the second target time interval to serve as cache data, the cache data are compressed and stored to a designated storage space of the automobile data recorder, and the rest target data are encrypted and uploaded to the cloud background. By adopting the technical means, the driving monitoring data are extracted, the data which are partially important and have strong privacy are compressed and stored, and the rest target data are encrypted and uploaded to the cloud background, so that the driving monitoring data which are partially important can be cached locally, a user can check the driving monitoring data in time, the leakage of the driving data which are partially important is avoided, the rest target data are uploaded to the cloud background for storage, and the data storage pressure of the driving recorder can be relieved.
The directional storage device for the driving monitoring data provided by the second embodiment of the application can be used for executing the directional storage method for the driving monitoring data provided by the first embodiment, and has corresponding functions and beneficial effects.
Example three:
an embodiment of the present application provides an electronic device, and with reference to fig. 4, the electronic device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors in the electronic device may be one or more, and the number of memories in the electronic device may be one or more. The processor, memory, communication module, input device, and output device of the electronic device may be connected by a bus or other means.
The memory 32 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the directional storage method for driving monitoring data according to any embodiment of the present application (for example, an acquisition module, an identification module, and an upload module in a directional storage device for driving monitoring data). The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication module 33 is used for data transmission.
The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory, that is, the above-mentioned directional storage method of the driving monitoring data is realized.
The input device 34 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 35 may include a display device such as a display screen.
The electronic device provided by the embodiment can be used for executing the directional storage method of the driving monitoring data provided by the embodiment one, and has corresponding functions and beneficial effects.
Example four:
the embodiment of the present application further provides a storage medium containing computer executable instructions, which when executed by a computer processor, are configured to perform a directional storage method for driving monitoring data, where the directional storage method for driving monitoring data includes: acquiring target data to be uploaded, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information; identifying a monitoring audio of the target data based on specified voiceprint features, determining a target audio frame containing the specified voiceprint features in the monitoring audio, identifying a monitoring video of the target data based on specified image features, determining a target video frame containing specified image features, and defining a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data; intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of a vehicle data recorder, and encrypting and uploading the rest target data to a cloud background.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations, e.g., in different computer systems connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application includes computer-executable instructions, and the computer-executable instructions are not limited to the above-mentioned directional storage method for driving monitoring data, and may also perform related operations in the directional storage method for driving monitoring data provided in any embodiment of the present application.
The directional storage device, the storage medium, and the electronic device for driving monitoring data provided in the above embodiments may execute the directional storage method for driving monitoring data provided in any embodiment of the present application, and reference may be made to the directional storage method for driving monitoring data provided in any embodiment of the present application without detailed technical details described in the above embodiments.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.
Claims (10)
1. A directional storage method of driving monitoring data is characterized by comprising the following steps:
acquiring target data to be uploaded, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information;
identifying a monitoring audio of the target data based on specified voiceprint features, determining a target audio frame containing the specified voiceprint features in the monitoring audio, identifying a monitoring video of the target data based on specified image features, determining a target video frame containing specified image features, and defining a first target time period based on timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data;
intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of a vehicle data recorder, and encrypting and uploading the rest target data to a cloud background.
2. The directional storage method for vehicle monitoring data according to claim 1, further comprising, after compressing and storing the cache data to a designated storage space of a vehicle event recorder:
and periodically detecting the designated storage space, and selecting the cache data to be encrypted and uploaded to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
3. The method for directionally storing driving monitoring data according to claim 1, wherein before acquiring the target data to be uploaded, the method further comprises:
detecting a target storage space of the automobile data recorder and determining the storage amount of the automobile monitoring data;
and under the condition that the storage amount reaches a set threshold value, selecting the driving monitoring data of a specified period from the target storage space as target data to be uploaded.
4. The directional storage method for the driving monitoring data according to claim 3, wherein the selecting the driving monitoring data of the designated period from the target storage space as the target data to be uploaded comprises:
and selecting the driving monitoring data of the appointed time period from the target storage space as target data to be uploaded according to the storage time sequence of the driving monitoring data and the set reporting time length.
5. The method for directionally storing driving monitoring data according to claim 1, wherein the identifying the monitoring video of the target data based on the specified image characteristics and determining the target video frame containing the specified image characteristics comprises:
inputting the surveillance video of the target data into a pre-constructed target detection model, identifying the surveillance video of the target data based on the pre-constructed target detection model, and determining a target video frame containing specified image characteristics, wherein the target detection model is trained and constructed based on the specified image characteristics in advance.
6. The method for directionally storing driving monitoring data according to claim 5, wherein after identifying the monitoring video of the target data based on a pre-constructed target detection model and determining the target video frame containing the specified image features, the method further comprises:
and putting the target video frame into a training data set of the target detection model, and performing iterative training of the target detection model.
7. A directional storage device of driving monitoring data is characterized by comprising:
the acquisition module is used for acquiring target data to be uploaded, wherein the target data comprises monitoring audio and monitoring video, and the monitoring audio and the monitoring video of the target data comprise corresponding acquisition position information;
the identification module is used for identifying the monitoring audio of the target data based on the specified voiceprint characteristics, determining a target audio frame containing the specified voiceprint characteristics in the monitoring audio, identifying the monitoring video of the target data based on the specified image characteristics, determining a target video frame containing the specified image characteristics, and defining a first target time period based on the timestamp information of the target audio frame and the target video frame; detecting the acquisition position information of the monitoring audio and the monitoring video based on a set travel area, determining the monitoring audio and the monitoring video of which the acquisition position information falls into the set travel area as confidential data, and defining a second target time period based on the confidential data;
and the uploading module is used for intercepting the monitoring audio and the monitoring video corresponding to the time stamp from the target data according to the first target time interval and the second target time interval to serve as cache data, compressing and storing the cache data to a specified storage space of the automobile data recorder, and encrypting and uploading the rest target data to the cloud background.
8. The directional storage device for vehicle monitoring data according to claim 7, further comprising, after compressing and storing the cached data to a designated storage space of a vehicle event data recorder:
and periodically detecting the designated storage space, and selecting the cache data to be encrypted and uploaded to a cloud background according to the cache sequence of the cache data under the condition that the data volume of the cache data reaches a cache threshold value.
9. An electronic device, comprising:
a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of targeted storage of driving monitoring data as claimed in any one of claims 1 to 6.
10. A storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method of targeted storage of driving monitoring data according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211287085.7A CN115378980B (en) | 2022-10-20 | 2022-10-20 | Directional storage method and device for driving monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211287085.7A CN115378980B (en) | 2022-10-20 | 2022-10-20 | Directional storage method and device for driving monitoring data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115378980A CN115378980A (en) | 2022-11-22 |
| CN115378980B true CN115378980B (en) | 2023-01-10 |
Family
ID=84073752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211287085.7A Active CN115378980B (en) | 2022-10-20 | 2022-10-20 | Directional storage method and device for driving monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115378980B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117319611B (en) * | 2023-11-28 | 2024-03-29 | 重庆华悦生态环境工程研究院有限公司深圳分公司 | Monitoring image transmission method and device |
| CN117812582B (en) * | 2024-03-01 | 2024-04-30 | 合肥工业大学 | Guard mode data supervision method and system for vehicle |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410955A (en) * | 2018-12-07 | 2019-03-01 | 广州势必可赢网络科技有限公司 | A kind of time slot scrambling of voice data, system, device and storage medium |
| TWI712519B (en) * | 2019-08-26 | 2020-12-11 | 神達數位股份有限公司 | Cooperative driving image collection method and system |
| CN111405220B (en) * | 2019-09-30 | 2022-07-05 | 杭州海康威视***技术有限公司 | Video prerecording method and cloud storage system |
| CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
| CN113473075A (en) * | 2020-07-14 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Video monitoring data privacy protection method and device |
| CN113408006B (en) * | 2021-06-17 | 2024-06-18 | 深圳市九洲电器有限公司 | Monitoring data access method and device, indoor monitoring system and storage medium |
-
2022
- 2022-10-20 CN CN202211287085.7A patent/CN115378980B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115378980A (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115378980B (en) | Directional storage method and device for driving monitoring data | |
| US11397502B2 (en) | Systems and methods for bulk redaction of recorded data | |
| US20180053110A1 (en) | Method of predicting crime occurrence in prediction target region using big data | |
| CN104662533B (en) | The collection and use of the vehicle data captured | |
| CN109804367A (en) | Use the distributed video storage and search of edge calculations | |
| JP2017033554A (en) | Video data analysis method and device, and parking place monitoring system | |
| KR20200052852A (en) | Method and system for managing event data | |
| CN111508269B (en) | Open type parking space vehicle distinguishing method and device based on image recognition | |
| US10030986B2 (en) | Incident response analytic maps | |
| WO2018024165A1 (en) | Method and device for storing warning image | |
| KR20200115704A (en) | Apparatus and method for image recongnition | |
| US11863815B2 (en) | Methods and systems for managing storage of videos in a storage device | |
| CN116052103A (en) | Method, device, computer equipment and storage medium for processing monitoring data | |
| CN115361112B (en) | Driving monitoring data processing method, device, equipment and storage medium | |
| CN110971826A (en) | Video front-end monitoring device and method | |
| CN115361239B (en) | Driving storage data uploading method, device, equipment and storage medium | |
| JP2024520418A (en) | SELECTIVE OBFUSCATION OF OBJECTS IN MEDIA CONTENT - Patent application | |
| CN112289028B (en) | Method, device, equipment and medium for discovering fake license plate related to vehicle | |
| US11017240B2 (en) | System and method for image analysis based security system | |
| CN112861971A (en) | Cross-point road side perception target tracking method and system | |
| Kim et al. | Data Storage System Requirement for Autonomous Vehicle | |
| US11976940B2 (en) | Vehicle data collection system and method of using | |
| CN115243098B (en) | Screen recording method, device, computer equipment and storage medium | |
| CN112927546A (en) | Method and system for realizing vehicle searching based on mobile terminal | |
| CN117523814A (en) | Monitoring area determining method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |