CN113938622B - A blood pressure detection device and storage medium based on asynchronous video recording - Google Patents

A blood pressure detection device and storage medium based on asynchronous video recording Download PDF

Info

Publication number
CN113938622B
CN113938622B CN202111532750.XA CN202111532750A CN113938622B CN 113938622 B CN113938622 B CN 113938622B CN 202111532750 A CN202111532750 A CN 202111532750A CN 113938622 B CN113938622 B CN 113938622B
Authority
CN
China
Prior art keywords
video
blood pressure
recording
pressure detection
original
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
Application number
CN202111532750.XA
Other languages
Chinese (zh)
Other versions
CN113938622A (en
Inventor
王炳坤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
De Rucci Healthy Sleep Co Ltd
Original Assignee
De Rucci Healthy Sleep Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by De Rucci Healthy Sleep Co Ltd filed Critical De Rucci Healthy Sleep Co Ltd
Priority to CN202111532750.XA priority Critical patent/CN113938622B/en
Publication of CN113938622A publication Critical patent/CN113938622A/en
Application granted granted Critical
Publication of CN113938622B publication Critical patent/CN113938622B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment
    • H04N5/262Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/268Signal distribution or switching
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/76Television signal recording

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention relates to the technical field of health management and discloses a blood pressure detection device based on an asynchronously recorded video and a storage medium. The blood pressure detection device includes: the video acquisition unit is used for acquiring at least two sections of original videos which are recorded asynchronously and recording time thereof, wherein different original videos are recorded aiming at different human body parts of the same target user, and the time difference of the recording time of each section of original video is within a preset range; the video conversion unit is used for converting all the asynchronously recorded original videos into target videos at the same recording time; and the video analysis unit is used for carrying out blood pressure detection according to the target video to obtain a blood pressure detection result. Because the embodiment of the invention realizes the support of asynchronously recording the video, the user can asynchronously record different videos for blood pressure detection, thereby improving the convenience of recording operation of the user; meanwhile, the method is suitable for the terminal users who do not support front-back synchronous shooting, the application range is improved, and the development difficulty and the development cost of developers are reduced.

Description

一种基于异步录制视频的血压检测装置及存储介质A blood pressure detection device and storage medium based on asynchronous video recording

技术领域technical field

本发明涉及健康管理技术领域,尤其涉及一种基于异步录制视频的血压检测装置及存储介质。The invention relates to the technical field of health management, in particular to a blood pressure detection device and a storage medium based on asynchronous video recording.

背景技术Background technique

随着人们对自身健康问题的重视,市面上也出现了各种各样的具备健康参数检测的技术方案,但是大部分方案需要搭载在特定的设备上,用户若要使用,要么需要将设备佩戴在身上,额外增加了负担;要么需要在安装了特定设备的场景中才能获得健康参数检测结果。这些方案共同的问题是不够便捷、方便,对于大多数用户来说,难以适用。而另外一些直接搭载在手机或其它终端上的健康参数检测类软件,要实现血压检测的功能,大部分都需要同步录制两个视频,对用户来说,增加了操作难度;对开发者来说,在本身不支持前后同步双摄的终端上实现该功能,增加了开发难度和开发成本。As people pay more attention to their own health problems, various technical solutions with health parameter detection have appeared on the market, but most of the solutions need to be mounted on a specific device. If users want to use it, they need to wear the device. On the body, an additional burden is added; either the health parameter detection results need to be obtained in a scenario where a specific device is installed. The common problem of these solutions is that they are not convenient and convenient, and are difficult to apply to most users. For other health parameter detection software directly mounted on mobile phones or other terminals, to realize the function of blood pressure detection, most of them need to record two videos simultaneously, which increases the difficulty of operation for users; for developers , to implement this function on a terminal that does not support dual-camera synchronization before and after, which increases the difficulty and cost of development.

发明内容SUMMARY OF THE INVENTION

本发明的目的在于提供一种基于异步录制视频的血压检测装置及存储介质,以解决现有技术中不支持通过异步录制视频来实现血压检测的问题。The purpose of the present invention is to provide a blood pressure detection device and a storage medium based on asynchronous video recording, so as to solve the problem that blood pressure detection by asynchronous video recording is not supported in the prior art.

为达此目的,本发明采用以下技术方案:For this purpose, the present invention adopts the following technical solutions:

一种基于异步录制视频的血压检测装置,包括:A blood pressure detection device based on asynchronously recorded video, comprising:

视频采集单元,用于获取异步录制的至少两段原始视频及其录制时间,不同的所述原始视频针对同一目标用户的不同人体部位录制而成,且各段所述原始视频的录制时间的时间差在预设范围内;A video acquisition unit, configured to acquire at least two original videos recorded asynchronously and their recording times, where the different original videos are recorded for different body parts of the same target user, and the time difference between the recording times of each segment of the original videos within the preset range;

视频转换单元,用于将异步录制的所述原始视频全部转换为同一录制时间的目标视频;A video conversion unit, which is used to convert all the asynchronously recorded original videos into target videos of the same recording time;

视频分析单元,用于根据所述目标视频进行血压检测,获得血压检测结果。A video analysis unit, configured to perform blood pressure detection according to the target video, and obtain a blood pressure detection result.

可选的,所述视频转换单元,具体用于:Optionally, the video conversion unit is specifically used for:

比较各段所述原始视频的录制时间,确定其中的最早录制起始时间点作为所述同一录制时间的录制起始时间点,确定其中的最晚录制终止时间点作为所述同一录制时间的录制终止时间点;Compare the recording time of each segment of the original video, determine the earliest recording start time point as the recording start time point of the same recording time, and determine the latest recording termination time point as the recording of the same recording time. termination time point;

按照所述最早录制起始时间点和所述最晚录制终止时间点,通过机器学习方法对各段所述原始视频的空缺时间段内容分别进行预测补足,获得同一录制时间的目标视频。According to the earliest recording start time point and the latest recording termination time point, the content of the vacant time period of each segment of the original video is respectively predicted and supplemented by the machine learning method, and the target video of the same recording time is obtained.

可选的,所述视频转换单元,具体用于:Optionally, the video conversion unit is specifically used for:

比较各段所述原始视频的录制时间,确定其中的最晚录制起始时间点作为所述同一录制时间的录制起始时间点,确定其中的最早录制终止时间点作为所述同一录制时间的录制终止时间点;Compare the recording time of each segment of the original video, determine the latest recording start time point as the recording start time point of the same recording time, and determine the earliest recording termination time point as the recording of the same recording time. termination time point;

按照所述最晚录制起始时间点和所述最早录制终止时间点,将各段所述原始视频的多余时间段内容分别裁剪掉,获得同一录制时间的目标视频。According to the latest recording start time point and the earliest recording termination time point, the redundant time segment content of each segment of the original video is cut out respectively to obtain a target video of the same recording time.

可选的,所述人体部位包括面部、指端、腕部、手臂、下肢、颈部。Optionally, the body parts include face, fingertips, wrists, arms, lower limbs, and necks.

可选的,还包括视频审核单元,用于在所述视频转换单元将所述原始视频转换为目标视频之前,判断所述原始视频中的所述目标用户是否处于静息状态,若不是,则提示所述原始视频不符合要求。Optionally, it also includes a video review unit for determining whether the target user in the original video is in a resting state before the video conversion unit converts the original video into a target video, and if not, then Notice that the original video does not meet the requirements.

可选的,在所述原始视频为面部视频或者手腕部视频时,所述视频审核单元判断所述原始视频中的所述目标用户是否处于静息状态的方法,包括:Optionally, when the original video is a face video or a wrist video, the video review unit determines whether the target user in the original video is in a resting state, including:

对所述原始视频进行分解,提取含首帧和尾帧的多张单帧画面;Decomposing the original video, extracting multiple single-frame pictures containing the first frame and the last frame;

对所述多张单帧画面进行相似度分析,若相似度高则判定所述目标用户处于静息状态,否则判定所述目标用户未处于静息状态;Perform similarity analysis on the plurality of single-frame images, and if the similarity is high, determine that the target user is in a resting state, otherwise determine that the target user is not in a resting state;

在所述原始视频为指端视频时,所述视频审核单元判断所述原始视频中的所述目标用户是否处于静息状态的方法,包括:When the original video is a fingertip video, the method for determining by the video review unit whether the target user in the original video is in a resting state includes:

从所述指端视频中提取脉搏波参数;extracting pulse wave parameters from the fingertip video;

判断所述脉搏波参数在所述指端视频的录制时间内的波动范围是否超出预设范围,若未超出则判定所述目标用户处于静息状态,若超出则判定所述目标用户未处于静息状态。Determine whether the fluctuation range of the pulse wave parameter during the recording time of the fingertip video exceeds the preset range, if not, it is determined that the target user is in a resting state, and if it exceeds, it is determined that the target user is not in a resting state interest status.

可选的,还包括滤波单元,用于在所述视频分析单元根据所述目标视频进行血压检测之前,使用滤波算法对所述目标视频进行滤波处理,消除运动频段干扰。Optionally, a filtering unit is further included, configured to use a filtering algorithm to filter the target video before the video analysis unit performs blood pressure detection according to the target video to eliminate motion frequency band interference.

可选的,所述视频分析单元,具体用于采用成像式光电容积描记法IPPG技术,根据所述目标视频进行血压检测。Optionally, the video analysis unit is specifically configured to use the imaging photoplethysmography IPPG technology to perform blood pressure detection according to the target video.

可选的,所述视频采集单元包括前置摄像头和/或后置摄像头。Optionally, the video capture unit includes a front camera and/or a rear camera.

一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现如下步骤:A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

获取异步录制的至少两段原始视频及其录制时间,不同的所述原始视频针对同一目标用户的不同人体部位录制而成,且各段所述原始视频的录制时间的时间差在预设范围内;Acquiring at least two original videos asynchronously recorded and their recording times, different original videos are recorded for different body parts of the same target user, and the time difference between the recording times of each segment of the original video is within a preset range;

将异步录制的所述原始视频全部转换为同一录制时间的目标视频;Converting all the asynchronously recorded original videos into target videos of the same recording time;

根据所述目标视频进行血压检测,获得血压检测结果。Blood pressure detection is performed according to the target video to obtain a blood pressure detection result.

与现有技术相比,本发明的有益效果为:Compared with the prior art, the beneficial effects of the present invention are:

本发明实施例将至少两段异步录制的原始视频转换处理为相应的至少两段同一录制时间的目标视频,进而基于目标视频按照常规技术进行血压检测。由于实现了异步录制视频的支持,用户可以异步录制用于血压检测的不同视频,提高了用户录制操作的便利性;同时,适用于不支持前后同步拍摄的终端用户,提高了适用范围,降低了开发者的开发难度和开发成本。The embodiment of the present invention converts at least two asynchronously recorded original videos into corresponding at least two target videos with the same recording time, and then performs blood pressure detection according to conventional techniques based on the target videos. Due to the support of asynchronous video recording, users can asynchronously record different videos for blood pressure detection, which improves the convenience of user recording operations; at the same time, it is suitable for end users who do not support synchronous shooting before and after, which improves the scope of application and reduces the The development difficulty and development cost of developers.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其它的附图。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

图1为本发明实施例提供的血压检测装置结构示意图。FIG. 1 is a schematic structural diagram of a blood pressure detection device according to an embodiment of the present invention.

图2为本发明实施例提供的基于异步录制视频的血压检测方法流程图。FIG. 2 is a flowchart of a blood pressure detection method based on an asynchronously recorded video provided by an embodiment of the present invention.

图3为本发明实施例提供的原始视频转换为目标视频的一种方法流程图。FIG. 3 is a flowchart of a method for converting an original video into a target video according to an embodiment of the present invention.

图4为本发明实施例提供的原始视频转换为目标视频的另一种方法流程图。FIG. 4 is a flowchart of another method for converting an original video into a target video according to an embodiment of the present invention.

具体实施方式Detailed ways

为使得本发明的发明目的、特征、优点能够更加的明显和易懂,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,下面所描述的实施例仅仅是本发明一部分实施例,而非全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

由于现有的血压检测方案仅支持同步录制视频,无法通过异步录制视频来实现血压检测功能,给用户造成了操作不便的困扰,也给开发者带来了增加开发难度和开发成本的问题,为此,如图1所示,本发明实施例提供了一种基于异步录制视频的血压检测装置,至少包括:用于采集视频信号的视频采集单元、用于对视频信号进行转换处理的视频转换单元,以及对视频信号分析获得检测结果的视频分析单元。Since the existing blood pressure detection solution only supports synchronous video recording, the blood pressure detection function cannot be realized by asynchronously recording video, which causes inconvenience to users, and also brings problems to developers that increase development difficulty and development cost. Therefore, as shown in FIG. 1 , an embodiment of the present invention provides a blood pressure detection device based on asynchronously recorded video, which at least includes: a video acquisition unit for acquiring video signals, and a video conversion unit for converting video signals. , and a video analysis unit that analyzes the video signal to obtain the detection result.

请参阅图2,本发明实施例提供的血压检测装置,其具体的基于异步录制视频的血压检测方法,包括:Referring to FIG. 2, the blood pressure detection device provided by the embodiment of the present invention, its specific blood pressure detection method based on asynchronous recording video, includes:

步骤101、视频采集单元获取异步录制的至少两段原始视频及其录制时间,不同的原始视频针对同一目标用户的不同人体部位录制而成,且各段原始视频的录制时间的时间差在预设范围内。Step 101: The video acquisition unit acquires at least two original videos recorded asynchronously and their recording times. Different original videos are recorded for different body parts of the same target user, and the time difference between the recording times of each original video is within a preset range. Inside.

视频采集单元包括前置摄像头和/或后置摄像头。即,所获得的至少两段原始视频,具体可以同时来源于前置摄像头或者后置摄像头,也可以分别来源于前置摄像头和后置摄像头。The video capture unit includes a front camera and/or a rear camera. That is, the obtained at least two original videos may be derived from the front camera or the rear camera at the same time, or may be derived from the front camera and the rear camera respectively.

步骤102、视频转换单元将异步录制的原始视频全部转换为同一录制时间的目标视频。Step 102: The video converting unit converts all the asynchronously recorded original videos into target videos of the same recording time.

步骤103、视频分析单元根据目标视频进行血压检测,获得血压检测结果。Step 103: The video analysis unit performs blood pressure detection according to the target video to obtain a blood pressure detection result.

需要说明的是,异步录制指的是各段原始视频的录制时间可以完全不重合,也可以部分重合。在录制时间完全不重合的情况下,为确保后续操作的可实现性以及准确性,本发明实施例需要控制两段原始视频的时间差异控制在一定范围内,例如2S。当然,该预设范围的设计值,可以根据实际经验、后续预测补足操作的技术水平以及精度需求等方面来选定,本发明实施例对此不作具体限定。It should be noted that asynchronous recording means that the recording times of the original videos may not overlap at all, or may partially overlap. In the case where the recording times do not overlap at all, in order to ensure the achievability and accuracy of subsequent operations, the embodiment of the present invention needs to control the time difference between the two original videos within a certain range, such as 2S. Certainly, the design value of the preset range may be selected according to actual experience, the technical level of the subsequent prediction and complement operation, and the accuracy requirement, which are not specifically limited in the embodiment of the present invention.

为实现血压检测,获得的原始视频需针对不同的人体部位录制而成,这些人体部位具体可以包括面部、指端、腕部、手臂、下肢或颈部。实际应用中,优先选择指端视频和面部视频,因为手指的血管分布丰富,且透射性较好,相对其他部位,由指端采集到的信号的信噪比较高,是人体裸露皮肤中最方便拍摄的部位。而面部视频,也比较方便用户拍摄获得。In order to realize blood pressure detection, the obtained original video needs to be recorded for different human body parts, and these human body parts can specifically include the face, fingertips, wrists, arms, lower limbs or necks. In practical applications, the fingertip video and the face video are preferred, because the blood vessels of the fingers are abundant and the transmittance is good. A location that is convenient for shooting. The facial video is also more convenient for users to capture.

在一种可选的实施方式中,上述步骤102中,视频转换单元将异步录制的原始视频全部转换为同一录制时间的目标视频的方法如图3所示,包括:In an optional embodiment, in the above step 102, the method for the video conversion unit to convert all the asynchronously recorded original videos into target videos of the same recording time is shown in Figure 3, including:

步骤201、比较各段原始视频的录制时间,确定其中的最早录制起始时间点作为上述同一录制时间的录制起始时间点,确定其中的最晚录制终止时间点作为上述同一录制时间的录制终止时间点。Step 201, compare the recording time of each original video, determine the earliest recording start time point as the recording start time point of the above-mentioned same recording time, and determine the latest recording termination time point as the recording termination time of the same recording time. point in time.

基于每段原始视频的录制时间,可以确定每段原始视频的录制起始时间点和录制终止时间点;进而,通过比对全部的录制起始时间点和比对全部的录制终止时间点,即可以确定其中的最早录制起始时间点和最晚录制终止时间点。Based on the recording time of each original video, the recording start time point and recording end time point of each original video can be determined; then, by comparing all recording start time points and all recording end time points, that is, The earliest recording start time point and the latest recording end time point can be determined.

步骤202、按照最早录制起始时间点和最晚录制终止时间点,通过机器学习方法对各段原始视频的空缺时间段内容分别进行预测补足,获得同一录制时间的目标视频。Step 202 : According to the earliest recording start time point and the latest recording termination time point, use machine learning method to predict and supplement the content of the vacant time period of each original video respectively, and obtain the target video of the same recording time.

本步骤中,由于各段原始视频的录制起止时间可能存在差异,因此本实施例采用以最早录制起始时间点和最晚录制终止时间点为前后时间截点,对各段原始视频进行预测补足处理,以将所有的原始视频的录制时间均统一调整为统一范围,使得后续能够按照常规的视频处理技术实现血压检测。In this step, since the recording start and end times of each segment of the original video may be different, in this embodiment, the earliest recording start time point and the latest recording end time point are used as the front and rear time cutoff points to predict and supplement each segment of the original video. processing, so as to uniformly adjust the recording time of all the original videos to a uniform range, so that the blood pressure detection can be realized in the follow-up according to the conventional video processing technology.

在另一种可选的实施方式中,上述步骤102中,视频转换单元将异步录制的原始视频全部转换为同一录制时间的目标视频的方法如图4所示,包括:In another optional embodiment, in the above step 102, the method for the video conversion unit to convert all the asynchronously recorded original videos into target videos of the same recording time is shown in Figure 4, including:

步骤301、比较各段原始视频的录制时间,确定其中的最晚录制起始时间点作为上述同一录制时间的录制起始时间点,确定其中的最早录制终止时间点作为上述同一录制时间的录制终止时间点。Step 301, compare the recording time of each original video, determine the latest recording start time point as the recording start time point of the above-mentioned same recording time, and determine the earliest recording termination time point therein as the recording termination of the same recording time. point in time.

步骤302、按照最晚录制起始时间点和最早录制终止时间点,将各段原始视频的多余时间段内容分别裁剪掉,获得同一录制时间的目标视频。Step 302 , according to the latest recording start time point and the earliest recording termination time point, cut out the redundant time segment content of each original video respectively to obtain a target video of the same recording time.

针对上述两种实施方式,可以理解的是,前一实施方式适用于录制时间完全不重合和部分重合的两种情况,而后一实施方式由于通过视频裁剪方式来将多个原始视频裁剪至相同的录制时间范围,因此仅适用于录制时间部分重合的情况。Regarding the above two implementations, it can be understood that the former implementation is applicable to two situations where the recording times are completely non-overlapping and partially overlapping, while the latter implementation cuts multiple original videos to the same The recording time range is therefore only applicable when the recording time partially overlaps.

当然,针对录制时间部分重合的情况,实际也可以选择结合使用预测补足和裁剪两种方式。示例性的,根据最早录制起始时间点和最早录制终止时间点确定目标视频的录制时间,对同时具有空缺时间段和多余时间段的原始视频,可以对其空缺时间段内容进行预测补足,同时将其多余时间段内容裁减掉。Of course, for the case where the recording time is partially overlapped, you can actually choose to use the two methods of prediction complementation and cropping in combination. Exemplarily, the recording time of the target video is determined according to the earliest recording start time point and the earliest recording end time point, and the content of the vacant time period can be predicted and supplemented for the original video that has both a vacant time period and a redundant time period, and at the same time. Cut out the redundant time period content.

为保证检测结果的准确性,原始视频中目标用户优选处于静息状态,该静息状态指的是在原始视频的录制过程中目标用户保持基本静止状态。为此,本发明实施例中,还包括视频审核单元,用于在视频转换单元将原始视频转换为目标视频之前,用于判断原始视频中的目标用户是否处于静息状态,若不是,则提示原始视频不符合要求。In order to ensure the accuracy of the detection result, the target user in the original video is preferably in a resting state, and the resting state means that the target user maintains a basically still state during the recording process of the original video. To this end, in the embodiment of the present invention, a video review unit is further included, which is used to determine whether the target user in the original video is in a resting state before the video conversion unit converts the original video into the target video, and if not, prompting Original video does not meet the requirements.

进一步的,在所述原始视频为面部视频或者手腕部视频时,视频审核单元判断所述原始视频中的所述目标用户是否处于静息状态的方法,包括:对所述原始视频进行分解,提取含首帧和尾帧的多张单帧画面;对所述多张单帧画面进行相似度分析,若相似度高则判定所述目标用户处于静息状态,否则判定所述目标用户未处于静息状态。Further, when the original video is a face video or a wrist video, the method for the video review unit to determine whether the target user in the original video is in a resting state includes: decomposing the original video, extracting Multiple single-frame images including the first frame and last frame; similarity analysis is performed on the multiple single-frame images, if the similarity is high, it is determined that the target user is in a resting state, otherwise it is determined that the target user is not in a resting state.

在所述原始视频为指端视频时,视频审核单元判断所述原始视频中的所述目标用户是否处于静息状态的方法,包括:从所述指端视频中提取脉搏波参数;判断所述脉搏波参数在所述指端视频的录制时间内的波动范围是否超出预设范围,若未超出则判定所述目标用户处于静息状态,若超出则判定所述目标用户未处于静息状态。When the original video is a fingertip video, a method for determining whether the target user in the original video is in a resting state by a video review unit includes: extracting pulse wave parameters from the fingertip video; Whether the fluctuation range of the pulse wave parameter within the recording time of the fingertip video exceeds the preset range, if not, it is determined that the target user is in a resting state, and if it exceeds, it is determined that the target user is not in a resting state.

另外,为进一步提高检测结果的精确度,本发明实施例提供的血压检测装置还包括滤波单元,用于在所述视频分析单元根据所述两段目标视频进行血压检测之前,使用滤波算法对所述目标视频进行滤波处理,消除运动频段干扰。In addition, in order to further improve the accuracy of the detection result, the blood pressure detection device provided by the embodiment of the present invention further includes a filtering unit, configured to use a filtering algorithm to detect the blood pressure of the blood pressure by the video analysis unit according to the two target videos. The target video is filtered to eliminate the interference of the motion frequency band.

在步骤103中,视频分析单元具体可以采用IPPG(成像式光电容积描记法)技术,根据所述目标视频进行血压检测。关于IPPG技术的具体实现,由于为已知技术,本发明实施例不再赘述。In step 103, the video analysis unit may specifically use IPPG (imaging photoplethysmography) technology to perform blood pressure detection according to the target video. Regarding the specific implementation of the IPPG technology, since it is a known technology, details are not described in this embodiment of the present invention.

本发明实施例提供的血压检测装置可以是智能手机、平板电脑、智能手表、服务器、独立的健康检测设备等任意场景下的设备。The blood pressure detection device provided by the embodiment of the present invention may be a device in any scenario, such as a smart phone, a tablet computer, a smart watch, a server, and an independent health detection device.

本领域普通技术人员可以理解,上述基于异步录制视频的血压检测方法中的全部或部分步骤可以通过指令来完成,或通过指令控制相关的硬件来完成,该指令可以存储于一计算机可读存储介质中,并由处理器进行加载和执行。Those of ordinary skill in the art can understand that all or part of the steps in the above-mentioned asynchronous video-based blood pressure detection method can be completed through instructions, or through instructions to control relevant hardware, and the instructions can be stored in a computer-readable storage medium is loaded and executed by the processor.

为此,本发明实施例还提供一种存储介质,其中存储有多条指令,该指令能够被处理器进行加载,以执行本发明实施例所提供的基于异步录制视频的血压检测方法中的步骤。To this end, an embodiment of the present invention further provides a storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in the blood pressure detection method based on asynchronously recorded video provided by the embodiment of the present invention .

其中,该存储介质可以包括:只读存储器(ROM,Read Only Memory)、随机存取记忆体(RAM,Random Access Memory)、磁盘或光盘等。Wherein, the storage medium may include: a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and the like.

以上所述,以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A blood pressure detection device based on asynchronously recorded video, comprising:
the video acquisition unit is used for acquiring at least two sections of asynchronously recorded original videos and recording time thereof, wherein different original videos are recorded aiming at different human body parts of the same target user, and the time difference of the recording time of each section of the original video is within a preset range;
the video conversion unit is used for converting all the asynchronously recorded original videos into target videos at the same recording time;
and the video analysis unit is used for carrying out blood pressure detection according to the target video to obtain a blood pressure detection result.
2. The blood pressure detection device based on the asynchronously recorded video of claim 1, wherein the video conversion unit is specifically configured to:
comparing the recording time of each original video, determining the earliest recording starting time point as the recording starting time point of the same recording time, and determining the latest recording ending time point as the recording ending time point of the same recording time;
and predicting and complementing the content of the vacant time periods of the original videos by a machine learning method according to the earliest recording starting time point and the latest recording ending time point to obtain the target videos at the same recording time.
3. The blood pressure detection device based on the asynchronously recorded video of claim 1, wherein the video conversion unit is specifically configured to:
comparing the recording time of each original video, determining the latest recording starting time point as the recording starting time point of the same recording time, and determining the earliest recording ending time point as the recording ending time point of the same recording time;
and cutting off the content of the redundant time periods of the original videos according to the latest recording starting time point and the earliest recording ending time point to obtain the target videos at the same recording time.
4. The asynchronously recorded video-based blood pressure detection device of claim 1, wherein the body part comprises a face, a finger tip, a wrist, an arm, a lower limb, or a neck.
5. The device for detecting blood pressure based on asynchronously recorded video of claim 1, further comprising a video auditing unit, configured to determine whether the target user in the original video is in a resting state before the video converting unit converts the original video into a target video, and if not, prompt that the original video is not in compliance with the requirements.
6. The blood pressure detection device based on the asynchronously recorded video, as recited in claim 5, wherein when the original video is a facial video or a wrist video, the method for the video auditing unit to determine whether the target user in the original video is in a resting state includes:
decomposing the original video, and extracting a plurality of single-frame pictures containing a first frame and a last frame;
carrying out similarity analysis on the multiple single-frame pictures, judging that the target user is in a resting state if the similarity is high, and otherwise, judging that the target user is not in the resting state;
when the original video is a finger-end video, the method for judging whether the target user in the original video is in a resting state by the video auditing unit comprises the following steps:
extracting pulse wave parameters from the fingertip video;
and judging whether the fluctuation range of the pulse wave parameters in the recording time of the finger-end video exceeds a preset range, if not, judging that the target user is in a resting state, and if so, judging that the target user is not in the resting state.
7. The device for detecting blood pressure based on asynchronously recorded video of claim 1, further comprising a filtering unit, configured to perform filtering processing on the target video by using a filtering algorithm before the video analysis unit performs blood pressure detection according to the target video, so as to eliminate motion band interference.
8. The asynchronously recorded video based blood pressure detection apparatus according to claim 1, wherein the video analysis unit is specifically configured to perform blood pressure detection based on the target video by using an imaging photoplethysmography IPPG technique.
9. The asynchronously recorded video based blood pressure detection device of claim 1, wherein the video capture unit comprises a front-facing camera and/or a rear-facing camera.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of:
acquiring at least two sections of asynchronously recorded original videos and recording time thereof, wherein different original videos are recorded aiming at different human body parts of the same target user, and the time difference of the recording time of each section of the original video is within a preset range;
all the asynchronously recorded original videos are converted into target videos at the same recording time;
and carrying out blood pressure detection according to the target video to obtain a blood pressure detection result.
CN202111532750.XA 2021-12-15 2021-12-15 A blood pressure detection device and storage medium based on asynchronous video recording Active CN113938622B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111532750.XA CN113938622B (en) 2021-12-15 2021-12-15 A blood pressure detection device and storage medium based on asynchronous video recording

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111532750.XA CN113938622B (en) 2021-12-15 2021-12-15 A blood pressure detection device and storage medium based on asynchronous video recording

Publications (2)

Publication Number Publication Date
CN113938622A CN113938622A (en) 2022-01-14
CN113938622B true CN113938622B (en) 2022-02-15

Family

ID=79289139

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111532750.XA Active CN113938622B (en) 2021-12-15 2021-12-15 A blood pressure detection device and storage medium based on asynchronous video recording

Country Status (1)

Country Link
CN (1) CN113938622B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002135270A (en) * 2000-10-26 2002-05-10 Sharp Corp Data asynchronous transfer system
DE102013001553A1 (en) * 2013-01-30 2014-07-31 Holger Redtel Method for determining vital parameters of human body by device, particularly smart device, involves recording sequence of individual image data of single limited area of skin of human body by optical recording unit
CN104537645A (en) * 2014-12-15 2015-04-22 北京工业大学 ROI mark point matching method based on intravascular unltrasound image
CN106343986A (en) * 2016-09-20 2017-01-25 浙江大学 Ambulatory blood pressure non-contact monitoring device based on camera
CN106709967A (en) * 2016-12-23 2017-05-24 天津恒宇医疗科技有限公司 Endoscopic imaging algorithm and control system
CN107529221A (en) * 2017-08-22 2017-12-29 上海兴容信息技术有限公司 A kind of follow-up analysis system and method for combination video monitoring and Wi Fi positioning
CN107592460A (en) * 2017-09-25 2018-01-16 努比亚技术有限公司 A kind of video recording method, equipment and computer-readable storage medium
CN108683852A (en) * 2018-05-23 2018-10-19 努比亚技术有限公司 A kind of video recording method, terminal and computer readable storage medium
CN109698965A (en) * 2017-10-20 2019-04-30 株洲中车时代电气股份有限公司 A kind of audio video synchronization playback method, device, equipment and computer storage medium
CN110611784A (en) * 2019-10-17 2019-12-24 江苏省水利科学研究院 Shooting storage method of multi-camera recorder capable of preventing tampering
CN111787286A (en) * 2020-07-22 2020-10-16 杭州当虹科技股份有限公司 Method for realizing multichannel synchronous recording system
CN111993442A (en) * 2020-09-02 2020-11-27 厦门理工学院 High-intelligence general medical practice robot based on big data
CN112399227A (en) * 2021-01-19 2021-02-23 南京新广云信息科技有限公司 Method and system for simultaneously and synchronously playing multiple paths of medical images and time axis
CN112890792A (en) * 2020-11-25 2021-06-04 合肥工业大学 Cloud computing cardiovascular health monitoring system and method based on network camera
CN113288092A (en) * 2021-05-06 2021-08-24 福建师范大学 Blood pressure detection method and terminal for extracting pulse wave based on video
CN113786179A (en) * 2021-09-27 2021-12-14 北方工业大学 Human body blood pressure real-time measuring method and device with infrared and optical image fusion

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9251852B2 (en) * 2006-07-20 2016-02-02 Panopto, Inc. Systems and methods for generation of composite video

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002135270A (en) * 2000-10-26 2002-05-10 Sharp Corp Data asynchronous transfer system
DE102013001553A1 (en) * 2013-01-30 2014-07-31 Holger Redtel Method for determining vital parameters of human body by device, particularly smart device, involves recording sequence of individual image data of single limited area of skin of human body by optical recording unit
CN104537645A (en) * 2014-12-15 2015-04-22 北京工业大学 ROI mark point matching method based on intravascular unltrasound image
CN106343986A (en) * 2016-09-20 2017-01-25 浙江大学 Ambulatory blood pressure non-contact monitoring device based on camera
CN106709967A (en) * 2016-12-23 2017-05-24 天津恒宇医疗科技有限公司 Endoscopic imaging algorithm and control system
CN107529221A (en) * 2017-08-22 2017-12-29 上海兴容信息技术有限公司 A kind of follow-up analysis system and method for combination video monitoring and Wi Fi positioning
CN107592460A (en) * 2017-09-25 2018-01-16 努比亚技术有限公司 A kind of video recording method, equipment and computer-readable storage medium
CN109698965A (en) * 2017-10-20 2019-04-30 株洲中车时代电气股份有限公司 A kind of audio video synchronization playback method, device, equipment and computer storage medium
CN108683852A (en) * 2018-05-23 2018-10-19 努比亚技术有限公司 A kind of video recording method, terminal and computer readable storage medium
CN110611784A (en) * 2019-10-17 2019-12-24 江苏省水利科学研究院 Shooting storage method of multi-camera recorder capable of preventing tampering
CN111787286A (en) * 2020-07-22 2020-10-16 杭州当虹科技股份有限公司 Method for realizing multichannel synchronous recording system
CN111993442A (en) * 2020-09-02 2020-11-27 厦门理工学院 High-intelligence general medical practice robot based on big data
CN112890792A (en) * 2020-11-25 2021-06-04 合肥工业大学 Cloud computing cardiovascular health monitoring system and method based on network camera
CN112399227A (en) * 2021-01-19 2021-02-23 南京新广云信息科技有限公司 Method and system for simultaneously and synchronously playing multiple paths of medical images and time axis
CN113288092A (en) * 2021-05-06 2021-08-24 福建师范大学 Blood pressure detection method and terminal for extracting pulse wave based on video
CN113786179A (en) * 2021-09-27 2021-12-14 北方工业大学 Human body blood pressure real-time measuring method and device with infrared and optical image fusion

Also Published As

Publication number Publication date
CN113938622A (en) 2022-01-14

Similar Documents

Publication Publication Date Title
KR102445699B1 (en) Electronic device and method of operation thereof
JP7292325B2 (en) Video clip extraction method, video clip extraction device and storage medium
WO2017177768A1 (en) Information processing method, terminal, and computer storage medium
KR20180013325A (en) Providing Method For Video Contents and Electronic device supporting the same
US9565350B2 (en) Storyboards for capturing images
CN103873492B (en) A kind of electronic equipment and data transmission method
EP3104304B1 (en) Electronic apparatus and method of extracting still images
CN106331497B (en) A kind of image processing method and terminal
US11163822B2 (en) Emotional experience metadata on recorded images
WO2017049485A1 (en) Information processing method and smart wristband
CN111510785A (en) Video playback control method, device, terminal and computer-readable storage medium
KR102638468B1 (en) Electronic apparatus and operating method thereof
CN114706484A (en) Sight line coordinate determination method and device, computer readable medium and electronic equipment
WO2023051215A1 (en) Gaze point acquisition method and apparatus, electronic device and readable storage medium
CN113938622B (en) A blood pressure detection device and storage medium based on asynchronous video recording
CN111464864A (en) Reverse order video acquisition method and device, electronic equipment and storage medium
US10798337B2 (en) Communication device, communication system, and non-transitory computer readable medium storing program
CN111416936B (en) Image processing method, image processing device, electronic equipment and storage medium
CN105120153A (en) Image photographing method and device
JP7398817B2 (en) Electrocardiographic signal detection method and device
CN114079728A (en) Shooting anti-shake method, device, electronic device and storage medium
CN112749414B (en) Data storage method, device, equipment and storage medium
CN111626075A (en) A target recognition method and device
CN114358792B (en) Face-scanning payment method, device and face-scanning device
WO2024103994A1 (en) Method and apparatus for posture-based control of display device, device, and circuit board

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