阅读说明：本技术 基于执法记录仪的信息采集方法及执法记录仪 (Information acquisition method based on law enforcement recorder and law enforcement recorder ) 是由 郭金宇 温顺君 于 2021-07-23 设计创作，主要内容包括：本发明涉及执法记录的技术领域,尤其是涉及一种基于执法记录仪的信息采集方法及执法记录仪,基于执法记录仪的信息采集方法包括：接收语音信息；根据语音信息推理出事故类型；根据事故类型匹配对应的一种或多种事故要素；根据事故要素在视频流数据中筛选出要素图像,并将要素图像与事故要素相关联,所述视频流数据由安装在执法记录仪上的摄像头拍摄所得。本申请具有便于执法人员较为方便地查找相关数据的效果。(The invention relates to the technical field of law enforcement record, in particular to an information acquisition method based on a law enforcement recorder and the law enforcement recorder, wherein the information acquisition method based on the law enforcement recorder comprises the following steps: receiving voice information; reasoning accident types according to the voice information; matching one or more corresponding accident elements according to the accident type; and screening element images from video stream data according to the accident elements, wherein the video stream data is obtained by shooting a camera installed on a law enforcement recorder, and associating the element images with the accident elements. The method and the device have the effect of facilitating the law enforcement officers to conveniently search the related data.)

1. An information acquisition method based on a law enforcement recorder is characterized by comprising the following steps:

receiving voice information;

reasoning accident types according to the voice information;

matching one or more corresponding accident elements according to the accident type;

and screening element images from video stream data according to the accident elements, wherein the video stream data is obtained by shooting a camera installed on a law enforcement recorder, and associating the element images with the accident elements.

2. The information collection method based on law enforcement recorder according to claim 1, wherein the screening of the video stream data for the element image associated with the accident element according to the accident element comprises:

acquiring termination information, and taking one frame image in the video stream data as a termination frame image when the termination information is acquired;

matching a corresponding neural network model according to the accident factor;

analyzing the images in the video stream data according to the neural network model to mark the characteristic areas of the corresponding accident elements in each frame of image;

and screening one or more frames of images from the video stream data to the images of the ending frame of images according to the time sequence, wherein when the multiple frames of images are sequenced according to the time sequence, the last frame of image is the ending frame of image.

3. The information collection method based on law enforcement recorder according to claim 1, wherein the voice information is received in case of acquiring the trigger signal.

4. The law enforcement recorder-based information collection method according to claim 1, wherein the inferring of the type of incident from the voice information comprises:

and inputting the voice information into a pre-trained neural network model, and reasoning the voice information by the neural network model to generate an accident type.

5. The law enforcement recorder-based information collection method according to claim 2, wherein the acquiring termination information comprises:

and analyzing the voice information to acquire termination information.

6. The information collection method based on law enforcement recorder according to claim 3, wherein the trigger signal comprises at least one or two of the following:

voice signal, touch signal, press signal.

7. An information acquisition system based on a law enforcement recorder, comprising:

the receiving module is used for receiving voice information;

the reasoning module is used for reasoning the accident type according to the voice information;

the matching module is used for matching one or more corresponding accident elements according to the accident type;

and the screening association module is used for screening the element images from the video stream data according to the accident elements and associating the element images with the accident elements, wherein the video stream data is shot by a camera installed on the law enforcement recorder.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the law enforcement recorder-based information collection method according to any one of claims 1 to 6 when executing the computer program.

9. A computer storage medium, characterized in that the computer readable storage medium stores a computer program which, when being executed by a processor, carries out the steps of the law enforcement recorder based information collection method according to any one of claims 1 to 6.

10. A law enforcement recorder, characterized in that it is provided with at least one of the following:

the electronic device of claim 7, the computer storage medium of claim 8.

Technical Field

The invention relates to the technical field of law enforcement record, in particular to an information acquisition method based on a law enforcement recorder and the law enforcement recorder.

Background

The law enforcement recorder is also called a single police law enforcement video and audio recorder. The digital camera shooting, digital camera shooting and talkback function are integrated, dynamic and static field conditions can be digitally recorded in the law enforcement process, and law enforcement personnel can conveniently use the system in various environments.

The inventor thinks that the video and photo files collected by the law enforcement recorder generally only provide simple preview, and law enforcement personnel need to screen and search massive video files and photo files one by one for a large amount of license plate information in the video files and photo files generated by evidence collection, so that the law enforcement personnel is very inconvenient to use.

Disclosure of Invention

In order to facilitate law enforcement personnel to conveniently search related data, the application provides an information acquisition method based on a law enforcement recorder and the law enforcement recorder.

The above object of the present invention is achieved by the following technical solutions:

an information acquisition method based on a law enforcement recorder comprises the following steps:

receiving voice information;

reasoning accident types according to the voice information;

matching one or more corresponding accident elements according to the accident type;

and screening element images from video stream data according to the accident elements, wherein the video stream data is obtained by shooting a camera installed on a law enforcement recorder, and associating the element images with the accident elements.

By adopting the technical scheme, the law enforcement recorder receives the voice information of the wearer, then infers the voice information to obtain the accident type, then matches the corresponding accident element according to the inferred accident type, then screens out the corresponding element image from the video stream data according to the accident element, and associates the element image with the accident, thereby realizing the screening of the related data, and facilitating the law enforcement personnel to conveniently search the related data.

The present application may be further configured in a preferred example to: the screening out the element image associated with the accident element from the video stream data according to the accident element comprises:

acquiring termination information, and taking one frame image in the video stream data as a termination frame image when the termination information is acquired;

matching a corresponding neural network model according to the accident factor;

analyzing the images in the video stream data according to the neural network model to mark the characteristic areas of the corresponding accident elements in each frame of image;

and screening one or more frames of images from the video stream data to the images of the ending frame of images according to the time sequence, wherein when the multiple frames of images are sequenced according to the time sequence, the last frame of image is the ending frame of image.

By adopting the technical scheme, when the termination information is acquired, the accident processing is finished, one frame of image of the same time node is taken as a termination frame image, then the corresponding neural network model is matched according to accident elements, then the image in the video stream data is analyzed through the neural network model, the characteristic area of the corresponding accident element in each frame of image is marked, one or more frames of images are screened out from the image in the video stream data to the termination frame image according to the time sequence, the last frame of image of the multiple frames of images is the termination frame image, the area change of the characteristic area in the multiple frames of images is gradually increased from small to large and then gradually decreased from large to small, so that the accident situation development process can be known clearly through the multiple frames of images, and therefore law enforcement personnel can conveniently search related data.

The present application may be further configured in a preferred example to: and receiving voice information under the condition of acquiring the trigger signal.

By adopting the technical scheme, the law enforcement recorder starts to receive the voice information only under the condition of acquiring the trigger signal, so that the electric energy can be saved, and the processing pressure is reduced.

The present application may be further configured in a preferred example to: the reasoning of the accident type according to the voice information comprises the following steps:

and inputting the voice information into a pre-trained neural network model, and reasoning the voice information by the neural network model to generate an accident type.

By adopting the technical scheme, the neural network model carries out reasoning on the voice information, so that the accident type can be determined more accurately.

The present application may be further configured in a preferred example to: and analyzing the voice information to acquire termination information.

By adopting the technical scheme, the termination information is also acquired by analyzing the voice information, so that the method is more intelligent.

The present application may be further configured in a preferred example to: the trigger signal at least comprises one or two of the following:

voice signal, touch signal, press signal.

The second purpose of the invention of the application is realized by the following technical scheme:

an information collection system based on a law enforcement recorder, comprising:

the receiving module is used for receiving voice information;

the reasoning module is used for reasoning the accident type according to the voice information;

the matching module is used for matching one or more corresponding accident elements according to the accident type;

and the screening association module is used for screening the element images from the video stream data according to the accident elements and associating the element images with the accident elements, wherein the video stream data is shot by a camera installed on the law enforcement recorder.

The third purpose of the application is realized by the following technical scheme:

an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor when executing the computer program implementing the steps of a law enforcement recorder based information collection method as claimed in any one of the preceding claims.

The fourth purpose of the application is realized by the following technical scheme:

a computer storage medium, the computer readable storage medium storing a computer program which, when executed by a processor, carries out the steps of a law enforcement recorder-based information collection method as claimed in any one of the preceding claims.

The fifth purpose of the application is realized by the following technical scheme:

a law enforcement recorder provided with at least one of:

an electronic device as described above, a computer storage medium as described above.

The sixth purpose of the application is realized by the following technical scheme:

a terminal, the terminal being provided with at least one of:

an electronic device as described above, a computer storage medium as described above.

In summary, the present application includes at least one of the following beneficial technical effects:

1. the law enforcement recorder receives the voice information of a wearer, then infers the voice information to obtain an accident type, then matches a corresponding accident element according to the inferred accident type, then screens out a corresponding element image from video stream data according to the accident element, and associates the element image with the accident, thereby realizing screening of related data and facilitating law enforcement personnel to conveniently search the related data;

2. when the termination information is acquired, indicating that the accident processing is completed, taking a frame of image of the same time node as a termination frame image, matching a corresponding neural network model according to accident elements, analyzing the image in the video stream data through the neural network model, marking a characteristic area of the corresponding accident element in each frame of image, screening one or more frames of images in the video stream data until the image of the termination frame image according to a time sequence, wherein the last frame of image of the multiple frames of images is the termination frame image, and the area change of the characteristic area in the multiple frames of images is gradually increased from small to large and then gradually decreased from large to small, so that the accident situation development process can be known more clearly through the multiple frames of images, and law enforcement personnel can conveniently search related data;

3. the neural network model carries out reasoning on the voice information, so that the accident type can be determined more accurately.

Drawings

FIG. 1 is a flow chart of an implementation of a law enforcement recorder-based information collection method according to an embodiment of the present application;

FIG. 2 is a flow chart of an implementation of a law enforcement recorder-based information collection method according to another embodiment of the present application;

FIG. 3 is a schematic block diagram of a law enforcement recorder based information collection system in one embodiment of the present application;

fig. 4 is a schematic diagram of an electronic device in an embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to the attached drawings.

The application discloses an information acquisition method based on a law enforcement recorder, which specifically comprises the following steps with reference to fig. 1:

s100, receiving voice information;

the voice information refers to external voice information, and after the law enforcement recorder receives the voice information, the law enforcement recorder can perform noise reduction and other processing on the voice information, and can strip the voice of a wearer out as the voice information through the tone color characteristics, so that the influence of noise and the voice of other people is reduced.

In a preferred embodiment, the law enforcement recorder only starts receiving voice information in case the trigger signal is acquired. Wherein, the trigger signal at least comprises one or two of the following: voice signal, touch signal, press signal. When the trigger signal is set to be a voice signal, it may be the following voice signal: standing, how to get back, on a dry horse, on a fire, on a stop, etc. The setting can be specifically carried out according to the commonly used scenes of the law enforcement recorder and the commonly used voice of the wearer.

S102, reasoning accident types according to the voice information;

specifically, a first neural network model is adopted for reasoning;

in one embodiment, voice information is input into a first neural network model which is trained in advance, and the first neural network model carries out reasoning on the voice information to generate an accident type;

wherein, first neural network model is drawn through machine learning training by the multiunit experimental data, and every group experimental data in the multiunit experimental data all includes: voice information, and a type of incident corresponding to the voice information.

The reasoning accuracy is improved along with the increase of the number of experimental data groups.

S104, matching one or more corresponding accident elements according to the accident type;

specifically, after the accident type is obtained, the corresponding accident element is matched in the preset database, for example, if the accident type is fighting, a fighting scene is matched in the preset database, the number of the accident elements is set according to different accident types, that is, the accident type and the accident element are associated, and one accident type can be associated with a plurality of accident elements and all stored in the preset database.

And S106, screening element images from the video stream data according to the accident elements, and associating the element images with the accident elements, wherein the video stream data is obtained by shooting through a camera installed on a law enforcement recorder.

Referring to fig. 2, in a preferred embodiment, screening the element image associated with the accident element in the video stream data according to the accident element includes:

s1061, acquiring termination information, and taking one frame image in the video stream data as a termination frame image when the termination information is acquired;

the termination information can be voice information, touch information and press information, and the termination information can be different from the trigger information;

in one embodiment, the acquisition of the termination information is obtained by analyzing the voice information;

the analysis of the speech information can also be inferred by the first neural network model.

The termination information may also be set, so that the acquisition of the termination frame image can be in accordance with the field processing condition, and the occurrence of the condition that the accident is not processed and the video stream data is terminated is avoided.

S1062, matching a corresponding second neural network model according to the accident elements;

s1063, analyzing the images in the video stream data according to the second neural network model to mark the characteristic areas of the corresponding accident elements in each frame of images;

the second neural network model is trained in advance, one accident element corresponds to the second neural network model, the second neural network model is obtained by carrying out machine learning training on a plurality of groups of experimental data, and each group of experimental data in the plurality of groups of experimental data comprises: an image, and a feature region corresponding to an accident element of the image.

S1064, screening one or more frames of images from the images of the video stream data to the ending frame of image, wherein when the multiple frames of images are sequenced according to time sequence, the last frame of image is the ending frame of image.

Specifically, all images containing characteristic areas are screened out from video stream data, and then a thumbnail number a is generated according to the number n of the images containing the characteristic areas, wherein a is in a proportional relation with n, and a and n can be 1: 160. I.e., 160 images, and 1 image is screened. After the multi-frame images are screened out, the multi-frame images are sorted according to time sequence and are associated with accident elements, a folder with the accident elements as names is generated in a storage space of the law enforcement recorder, and the element images associated with the accident elements are divided into the folder.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In one embodiment, an information acquisition system based on a law enforcement recorder is provided, and the information acquisition system based on the law enforcement recorder corresponds to the information acquisition method based on the law enforcement recorder in the embodiment one to one. Referring to fig. 3, the information collection system based on law enforcement recorder includes a receiving module, an inference module, a matching module and a screening association module. The functional modules are explained in detail as follows:

the receiving module is used for receiving voice information;

the reasoning module is used for reasoning the accident type according to the voice information;

the matching module is used for matching one or more corresponding accident elements according to the accident type;

and the screening association module is used for screening the element images from the video stream data according to the accident elements and associating the element images with the accident elements, and the video stream data is obtained by shooting through a camera arranged on the law enforcement recorder.

For specific limitations of the information collection system based on law enforcement recorder, reference may be made to the above limitations of the information collection method based on law enforcement recorder, which are not described herein again. The modules in the information acquisition system based on the law enforcement recorder can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the electronic device, or can be stored in a memory in the electronic device in a software form, so that the processor can call and execute operations corresponding to the modules.

Referring to fig. 4, in one embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 4. The electronic device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a law enforcement recorder based information collection method:

receiving voice information;

reasoning accident types according to the voice information;

matching one or more corresponding accident elements according to the accident type;

and screening element images from the video stream data according to the accident elements, and associating the element images with the accident elements, wherein the video stream data is obtained by shooting through a camera installed on a law enforcement recorder.

The computer program can realize any one of the information acquisition methods based on the law enforcement recorder in the embodiment of the method when being executed by a processor.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

receiving voice information;

reasoning accident types according to the voice information;

matching one or more corresponding accident elements according to the accident type;

and screening element images from the video stream data according to the accident elements, and associating the element images with the accident elements, wherein the video stream data is obtained by shooting through a camera installed on a law enforcement recorder.

The computer program can realize any one of the information acquisition methods based on the law enforcement recorder in the embodiment of the method when being executed by a processor.

In one embodiment, a law enforcement recorder is provided, the law enforcement recorder being provided with at least one of: an electronic device as described above, a computer storage medium as described above.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to perform all or part of the above-mentioned functions.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.