Movatterモバイル変換


[0]ホーム

URL:


CN110236547A - Respiratory frequency detection method and detection device for respiratory frequency detection - Google Patents

Respiratory frequency detection method and detection device for respiratory frequency detection
Download PDF

Info

Publication number
CN110236547A
CN110236547ACN201810194475.7ACN201810194475ACN110236547ACN 110236547 ACN110236547 ACN 110236547ACN 201810194475 ACN201810194475 ACN 201810194475ACN 110236547 ACN110236547 ACN 110236547A
Authority
CN
China
Prior art keywords
mark
marker
tester
distance
time
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.)
Granted
Application number
CN201810194475.7A
Other languages
Chinese (zh)
Other versions
CN110236547B (en
Inventor
黄浦
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.)
Institute of Flexible Electronics Technology of THU Zhejiang
Original Assignee
Institute of Flexible Electronics Technology of THU Zhejiang
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 Institute of Flexible Electronics Technology of THU ZhejiangfiledCriticalInstitute of Flexible Electronics Technology of THU Zhejiang
Priority to CN201811126359.8ApriorityCriticalpatent/CN110236548B/en
Priority to CN201810194475.7Aprioritypatent/CN110236547B/en
Publication of CN110236547ApublicationCriticalpatent/CN110236547A/en
Application grantedgrantedCritical
Publication of CN110236547BpublicationCriticalpatent/CN110236547B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

A method for detecting respiratory rate and a detection device for detecting respiratory rate comprise the following steps: providing a first mark and a second mark, wherein the relative positions of the first mark and the second mark are periodically changed along with the respiration of a tester; acquiring a video image of the position change of the first mark and the second mark when the tester breathes; separating the video image into video frames in sequence of time; selecting specific video frames and identifying the positions of the first mark and the second mark in each selected video frame; measuring the distance between the first mark and the second mark in each selected video frame and forming a time-distance curve graph; the cycles of the time-distance graph are counted over a particular time. The detection method is simple to apply, low in cost and capable of accurately detecting the respiratory frequency of a tester.

Description

Translated fromChinese
呼吸频率的检测方法及用于呼吸频率检测的检测装置Respiratory frequency detection method and detection device for respiratory frequency detection

技术领域technical field

本发明涉及医疗检测设备领域,尤其是一种呼吸频率的检测方法及应用该呼吸频率的检测方法进行呼吸频率检测的检测装置。The invention relates to the field of medical detection equipment, in particular to a method for detecting respiratory frequency and a detecting device for detecting respiratory frequency using the method for detecting respiratory frequency.

背景技术Background technique

呼吸是衡量人体生理健康指标的重要因素之一。呼吸频率的检测对感冒发烧、咳嗽、哮喘、肺病、心脏病、睡眠呼吸暂停综合症等呼吸类疾病具有重要意义。Respiration is one of the important factors to measure human physiological health indicators. The detection of respiratory rate is of great significance for respiratory diseases such as colds, fever, cough, asthma, lung disease, heart disease, sleep apnea syndrome, etc.

在现有技术中,呼吸频率的检测方式主要有接触式测量法和非接触式测量法。在接触式测量法中,需要测量者携带、捆绑或者粘贴呼吸类传感器到对应身体部位,该传感器的线路布设复杂,使得数据传输、供电、测量都不方便,且成本较高。In the prior art, the detection methods of respiratory frequency mainly include contact measurement method and non-contact measurement method. In the contact measurement method, the measurer needs to carry, bundle or paste the respiratory sensor to the corresponding body part. The circuit layout of the sensor is complicated, which makes data transmission, power supply, and measurement inconvenient, and the cost is high.

非接触式测量方法为医生观察测试人员一分钟的胸廓起伏次数或者使用棉花丝至于测试人员鼻孔处,观察棉花丝的变化,从而检测呼吸频率。该种测量方法虽然较为简便,但是却容易受到干扰,测量不准确。The non-contact measurement method is for the doctor to observe the tester's thoracic ups and downs in one minute or use cotton silk to the tester's nostrils to observe the change of the cotton silk to detect the breathing rate. Although this measurement method is relatively simple, it is easily disturbed and the measurement is inaccurate.

发明内容SUMMARY OF THE INVENTION

有鉴于此,本发明提供了一种呼吸频率的检测方法及应用该呼吸频率的检测方法进行呼吸频率检测的检测装置,该检测方法应用简单,成本较低,且能够较为准确地对测试者的呼吸频率进行检测。In view of this, the present invention provides a method for detecting respiratory frequency and a detecting device for detecting respiratory frequency by using the method for detecting respiratory frequency. Check breathing rate.

本发明提供了一种呼吸频率的检测方法,包括如下步骤:The present invention provides a method for detecting respiratory frequency, comprising the following steps:

提供第一标记及第二标记,所述第一标记与所述第二标记的相对位置随测试者的呼吸而发生周期性变化;providing a first marker and a second marker, the relative positions of the first marker and the second marker periodically change with the tester's breathing;

获取所述第一标记及所述第二标记在测试者呼吸时位置变化的视频图像;acquiring a video image of the position change of the first mark and the second mark when the tester breathes;

将所述视频图像分离为以时间先后为顺序的视频帧;separating the video image into video frames in chronological order;

选取特定的视频帧,并识别每一选取的所述视频帧中所述第一标记与所述第二标记的位置;Selecting a specific video frame, and identifying the positions of the first marker and the second marker in each of the selected video frames;

测得每一选取的所述视频帧中所述第一标记与所述第二标记之间的距离,并形成时间-距离曲线图;measuring the distance between the first mark and the second mark in each selected video frame, and forming a time-distance curve diagram;

在特定的时间内对所述时间-距离曲线图的周期进行计数。Periods of the time-distance graph are counted for a specific time.

进一步地,至少所述第一标记及所述第二标记的其中之一的位置随着测试者的呼吸而发生周期性的变化。Further, the position of at least one of the first mark and the second mark periodically changes with the tester's breathing.

进一步地,所述第一标记与所述第二标记位于测试者的鼻孔与嘴部之间,所述第一标记形成一自由端,该自由端的位置随着测试者呼吸产生的气流而发生周期性变化。Further, the first mark and the second mark are located between the nostrils and the mouth of the tester, and the first mark forms a free end, and the position of the free end occurs periodically with the airflow generated by the tester's breathing. sexual changes.

进一步地,所述第一标记与所述第二标记均随着所述测试者呼吸时身体的运动而运动。Further, both the first mark and the second mark move with the movement of the tester's body when breathing.

进一步地,所述第一标记及所述第二标记分别固定于人体的左胸部及右胸部,或者分别固定于鼻翼的两侧。Further, the first marker and the second marker are respectively fixed on the left chest and the right chest of the human body, or on both sides of the nose.

进一步地,在选取特定的视频帧,并识别每一选取的所述视频帧中所述第一标记与所述第二标记的位置的步骤后,该方法还包括,在所述第一标记上提取第一特征点,在所述第二标记上提取第二特征点,通过测量每一选取的所述视频帧中所述第一特征点与所述第二特征点之间的距离,以得到所述第一标记与所述第二标记之间的距离。Further, after the steps of selecting a specific video frame and identifying the positions of the first mark and the second mark in each selected video frame, the method further includes, on the first mark Extracting a first feature point, extracting a second feature point on the second mark, by measuring the distance between the first feature point and the second feature point in each selected video frame, to obtain The distance between the first marker and the second marker.

进一步地,以时间先后为顺序,识别每一视频帧中第一标记与第二标记的位置;然后测得每一所述视频帧中所述第一标记与所述第二标记之间的距离,并形成时间-距离曲线图;最后在特定的时间内对所述时间-距离曲线图的周期进行计数。Further, in the order of time, identify the positions of the first mark and the second mark in each video frame; then measure the distance between the first mark and the second mark in each of the video frames , and a time-distance graph is formed; finally, the period of the time-distance graph is counted within a specific time.

本发明还提供了一种用于呼吸频率检测的检测装置,包括第一标记及第二标记,所述第一标记及所述第二标记之间的相对位置会随着测试者的呼吸而做周期性变化;The present invention also provides a detection device for respiratory frequency detection, which includes a first mark and a second mark, and the relative position between the first mark and the second mark will change with the tester's breathing. cyclical changes;

图像获取单元,所述图像获取单元获取所述第一标记及所述第二标记在测试者呼吸时位置变化的视频图像;an image acquisition unit, the image acquisition unit acquires a video image of the position change of the first mark and the second mark when the tester breathes;

以及处理单元,所述处理单元将所述视频图像分离为以时间先后为顺序的视频帧,选取特定的所述视频帧,并识别每一选取的所述视频帧中所述第一标记及所述第二标记的位置;测得每一选取的所述视频帧中,所述第一标记及所述第二标记之间的距离,并形成时间-距离曲线图;在特定时间内对时间-距离曲线图的周期进行计数。and a processing unit, which separates the video image into video frames in chronological order, selects a specific video frame, and identifies the first mark and all the selected video frames in each selected video frame. the position of the second mark; measure the distance between the first mark and the second mark in each selected video frame, and form a time-distance curve; The cycles of the distance graph are counted.

进一步地,该装置还包括标记片,所述第一标记与所述第二标记形成于同一所述标记片的两个相对的边缘上,所述标记片上第一标记所在的一端的厚度小于第二标记所在一端的厚度。Further, the device further comprises a marking sheet, the first mark and the second mark are formed on two opposite edges of the same marking sheet, and the thickness of the end of the marking sheet where the first mark is located is smaller than the thickness of the first mark. The thickness of the end where the two marks are located.

进一步地,该装置还包括标记片,所述第一标记与所述第二标记分别形成于两个独立的所述标记片上。Further, the device further includes a marking sheet, and the first mark and the second mark are respectively formed on two independent marking sheets.

总上所述,在本发明中通过对选出的特定视频帧内第一标记及第二标记之间距离的测量,能够反映出第一标记及第二标记之间距离的变化趋势,即使在某些视频帧内,由于某些原因第一标记与第二标记之间的距离不能够反映测试者的呼吸状况,但是,该测试方法是从整体趋势上对测试者的呼吸频率进行计数,这能够较为准确地对测试者的呼吸频率进行检测,由于在测试时,仅需要固定两个标记的位置,因此,该方法应用简单,且成本较低。To sum up, in the present invention, by measuring the distance between the first mark and the second mark in the selected specific video frame, the change trend of the distance between the first mark and the second mark can be reflected, even in the In some video frames, for some reasons, the distance between the first marker and the second marker cannot reflect the tester's breathing condition. However, this test method counts the tester's breathing frequency from the overall trend. The respiration rate of the tester can be detected more accurately, and since only the positions of the two markers need to be fixed during the test, the method is simple to apply and has low cost.

上述说明仅是本发明技术方案的概述,为了能够更清楚了解本发明的技术手段,而可依照说明书的内容予以实施,并且为了让本发明的上述和其他目的、特征和优点能够更明显易懂,以下特举较佳实施例,并配合附图,详细说明如下。The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the following specific preferred embodiments, and in conjunction with the accompanying drawings, are described in detail as follows.

附图说明Description of drawings

图1为本发明提供的呼吸频率的检测方法中各步骤的示意图。FIG. 1 is a schematic diagram of each step in the method for detecting respiratory frequency provided by the present invention.

图2为本发明提供的呼吸频率的检测方法的第一实施例中,第一标记及第二标记的安放位置示意图。FIG. 2 is a schematic diagram of the placement positions of the first marker and the second marker in the first embodiment of the respiratory rate detection method provided by the present invention.

图3为在本发明第一实施例中标记片与固定片之间的位置关系示意图。FIG. 3 is a schematic diagram of the positional relationship between the marking sheet and the fixing sheet in the first embodiment of the present invention.

图4为本发明第一实施例中,沿时间顺序,在各特定帧的图像内,第一标记及第二标记的位置关系示意图。FIG. 4 is a schematic diagram of the positional relationship of the first marker and the second marker in the image of each specific frame along the time sequence according to the first embodiment of the present invention.

图5为本发明第一实施例中,沿时间顺序,第一标记及第二标记之间距离变化的时间-距离曲线图。FIG. 5 is a time-distance graph showing the change of the distance between the first mark and the second mark along the time sequence in the first embodiment of the present invention.

图6为本发明提供的呼吸频率的检测方法的第二实施例中,第一标记及第二标记的安放位置示意图。FIG. 6 is a schematic diagram of the placement positions of the first marker and the second marker in the second embodiment of the respiratory rate detection method provided by the present invention.

图7为本发明第二实施例中,沿时间顺序,在各特定帧的图像内,第一标记及第二标记的位置关系示意图。FIG. 7 is a schematic diagram of the positional relationship between the first marker and the second marker in the image of each specific frame along the time sequence according to the second embodiment of the present invention.

图8为本发明第二实施例中,沿时间顺序,第一标记及第二标记之间距离变化的时间-距离曲线图。FIG. 8 is a time-distance graph showing the change of the distance between the first mark and the second mark along the time sequence in the second embodiment of the present invention.

图9为本发明提供的检测装置的系统框图。FIG. 9 is a system block diagram of the detection apparatus provided by the present invention.

具体实施方式Detailed ways

为更进一步阐述本发明为达成预定发明目的所采取的技术手段及功效,以下结合附图及较佳实施例,详细说明如下。In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following detailed description is given in conjunction with the accompanying drawings and preferred embodiments.

本发明提供了一种呼吸频率的检测方法及应用该呼吸频率的检测方法进行呼吸频率检测的检测装置,该检测方法应用简单,成本较低,且能够较为准确地对测试者的呼吸频率进行检测。The present invention provides a method for detecting respiratory frequency and a detecting device for detecting respiratory frequency by using the method for detecting respiratory frequency. The detecting method is simple in application, low in cost, and can more accurately detect the respiratory frequency of a tester. .

图1为本发明提供的呼吸频率的检测方法中各步骤的示意图,如图1所示,本发明提供了一种呼吸频率的检测方法,该检测方法包括以下步骤:1 is a schematic diagram of each step in the method for detecting respiratory frequency provided by the present invention. As shown in FIG. 1 , the present invention provides a method for detecting respiratory frequency, which includes the following steps:

提供第一标记及第二标记,第一标记与第二标记的相对位置会随测试者的呼吸而发生周期性变化;Provide a first mark and a second mark, and the relative positions of the first mark and the second mark will periodically change with the tester's breathing;

获取第一标记及第二标记在测试者呼吸时位置变化的视频图像;Obtain a video image of the position change of the first marker and the second marker when the tester breathes;

将上述视频图像分离为以时间先后为顺序的视频帧;Separating the above video images into video frames in chronological order;

选取特定的视频帧,并识别每一选取的视频帧中第一标记及第二标记的位置;Selecting a specific video frame, and identifying the positions of the first marker and the second marker in each selected video frame;

测得每一选取的视频帧中第一标记与第二标记之间的距离,并形成时间-距离曲线图;Measure the distance between the first mark and the second mark in each selected video frame, and form a time-distance curve diagram;

在特定时间内对时间-距离曲线图的周期进行计数,以得到测试者的呼吸频率。Periods of the time-distance graph are counted over a specified time period to obtain the test subject's breathing rate.

图2为本发明提供的呼吸频率的检测方法的第一实施例中,第一标记及第二标记的安放位置示意图,图3为在本发明第一实施例中标记片与固定片之间的位置关系示意图,图4为本发明第一实施例中,沿时间顺序,在各特定帧的图像内,第一标记及第二标记的位置关系示意图,图5为本发明第一实施例中,沿时间顺序,第一标记及第二标记之间距离变化的时间-距离曲线图。如图2至图5所示,在本实施例中,第一标记11及第二标记12均设置于测试者的鼻孔与嘴部之间,第一标记11形成一个自由端,该自由端的位置会随着测试者的呼吸产生的气流而发生周期性变化,第二标记12固定于测试者的人体上。2 is a schematic diagram of the placement positions of the first marker and the second marker in the first embodiment of the method for detecting respiratory rate provided by the present invention, and FIG. 3 is a schematic diagram of the position between the marker sheet and the fixing sheet in the first embodiment of the present invention. A schematic diagram of the positional relationship, FIG. 4 is a schematic diagram of the positional relationship between the first marker and the second marker in the image of each specific frame along the time sequence in the first embodiment of the present invention, and FIG. 5 is a schematic diagram of the first embodiment of the present invention, Time-distance graph of the change in distance between the first marker and the second marker along the time sequence. As shown in FIG. 2 to FIG. 5 , in this embodiment, the first mark 11 and the second mark 12 are both disposed between the nostril and the mouth of the tester, the first mark 11 forms a free end, and the position of the free end Periodic changes occur with the airflow generated by the tester's breathing, and the second marker 12 is fixed on the tester's body.

在本实施例中,第一标记11与第二标记12均可以为纸质材质,同样地,也可以为丝线或塑料等。为了便于第一标记11及第二标记12的固定,第一标记11及第二标记12可以形成于同一标记片10的两个相对的边缘上,在固定时,第一标记11相比于第二标记12更靠近鼻孔部位。在标记片10上第一标记11所在一端的厚度小于第二标记12所在一端的厚度,以便测试者鼻孔呼吸产生的气流能够带动第一标记11运动,同时使第二标记12更稳定地固定在鼻孔与嘴部之间相应位置。如在本实施例中,标记片10的宽度可以为40-60mm,高度可以为20-40mm,标记片10上第一标记11所在一端的厚度可以为0.03-0.08mm,以便于呼吸的气流能够带动第一标记11运动,标记片10上第二标记12所在一端的厚度可以为1-5mm。如图3所示,为了便于标记片10的固定,标记片10可以固定于固定片20上,标记片10上第一标记11所在的一端与固定片20呈小于90°的夹角,以便于气流能够带动第一标记11运动。在本实施例中,固定片20的宽度可以为50-90mm,高度可以为10-30mm。In this embodiment, both the first mark 11 and the second mark 12 can be made of paper material, and similarly, they can also be made of wire or plastic. In order to facilitate the fixing of the first mark 11 and the second mark 12, the first mark 11 and the second mark 12 can be formed on two opposite edges of the same mark sheet 10. The second mark 12 is closer to the nostril site. The thickness of the end where the first marker 11 is located on the marker sheet 10 is smaller than the thickness of the end where the second marker 12 is located, so that the airflow generated by the tester's nostril breathing can drive the first marker 11 to move, and at the same time make the second marker 12 more stably fixed on the Corresponding position between the nostrils and the mouth. As in this embodiment, the width of the marking sheet 10 may be 40-60 mm, the height may be 20-40 mm, and the thickness of the end of the marking sheet 10 where the first mark 11 is located may be 0.03-0.08 mm, so that the airflow for breathing can be The first mark 11 is driven to move, and the thickness of the end of the mark sheet 10 where the second mark 12 is located may be 1-5 mm. As shown in FIG. 3, in order to facilitate the fixing of the marking sheet 10, the marking sheet 10 can be fixed on the fixing sheet 20, and the end of the marking sheet 10 where the first mark 11 is located forms an included angle of less than 90° with the fixing sheet 20, so as to facilitate the fixing of the marking sheet 10. The airflow can drive the first marker 11 to move. In this embodiment, the width of the fixing piece 20 may be 50-90 mm, and the height may be 10-30 mm.

在固定第一标记11及第二标记12时,先将固定片20贴附于测试者鼻孔与上嘴唇之间,然后将标记片10固定于固定片20上,并使第一标记11相比于第二标记12更靠近鼻孔所在的一侧。When fixing the first marker 11 and the second marker 12, firstly attach the fixing sheet 20 between the nostrils and the upper lip of the tester, then fix the marker sheet 10 on the fixing sheet 20, and make the first marker 11 compare On the side where the second mark 12 is closer to the nostril.

通过摄像机,优选为高清摄像机,在测试者呼吸的过程中,采集第一标记11及第二标记12的视频图像,也即标记片10变化的视频图像。在实际的测试中,人体的呼吸范围大致为一分钟16至44次,为了较好地获取到呼吸过程中标记片10的变化状态,摄像机采集帧率大于1fps,优选为10fps,当摄像机采集帧率为10fps时,摄像机一分钟可以采集到600张反应标记片10变化的视频帧。Through a camera, preferably a high-definition camera, during the breathing process of the tester, the video images of the first marker 11 and the second marker 12, that is, the video images of the changes of the marker sheet 10, are collected. In the actual test, the breathing range of the human body is roughly 16 to 44 times per minute. In order to better obtain the changing state of the marker sheet 10 during the breathing process, the camera capture frame rate is greater than 1fps, preferably 10fps, when the camera captures frames When the rate is 10fps, the camera can collect 600 video frames in one minute that reflect the changes of 10 markers.

对采集的视频进行分离,使其形成以时间先后为顺序的视频帧。The captured video is separated to form video frames in chronological order.

识别每一视频帧内第一标记11及第二标记12的位置。具体地,在本实施例中,可以通过canny边缘检测算子、sobel边缘检测算子、laplacian边缘检测算子及prewitt边缘检测算子等方法检测出标记片10上下两个边缘,即为第一标记11与第二标记12的位置。The positions of the first marker 11 and the second marker 12 in each video frame are identified. Specifically, in this embodiment, the canny edge detection operator, the sobel edge detection operator, the laplacian edge detection operator, and the prewitt edge detection operator can be used to detect the upper and lower edges of the marking sheet 10, which are the first and second edges. The position of the marker 11 and the second marker 12.

可以理解地,在其它实施例中,也可以选取特定的视频帧,如每间隔10帧选取一幅视频帧,并对该视频帧内第一标记11及第二标记12进行识别,在保证准确度的前提下以减少识别时的计算量。It can be understood that, in other embodiments, a specific video frame can also be selected, for example, a video frame is selected every 10 frames, and the first mark 11 and the second mark 12 in the video frame are identified, so as to ensure accuracy. On the premise of degree, to reduce the amount of calculation in recognition.

为了便于第一标记11及第二标记12的识别,标记片10的颜色可以为与周围环境色差较大的颜色,如白色或黑色。In order to facilitate the identification of the first mark 11 and the second mark 12 , the color of the mark sheet 10 may be a color with a larger color difference from the surrounding environment, such as white or black.

进一步地,为了便于对第一标记11及第二标记12之间的距离进行测量,本发明还可以包括,在第一标记11及第二标记12上提取第一特征点111及第二特征点121,在本实施例中,可以提取标记片10上部边缘的中点作为第一特征点111,提取标记片10下部边缘的中点作为第二特征点121。在本实施例中,上述特征点的提取可以用基于hough变换等方法的线段提取得出。Further, in order to facilitate the measurement of the distance between the first marker 11 and the second marker 12 , the present invention may further include extracting the first feature point 111 and the second feature point on the first marker 11 and the second marker 12 121. In this embodiment, the midpoint of the upper edge of the marking sheet 10 may be extracted as the first feature point 111, and the midpoint of the lower edge of the marking sheet 10 may be extracted as the second feature point 121. In this embodiment, the above-mentioned feature point extraction can be obtained by line segment extraction based on methods such as hough transform.

如图4所示(为了便于表达,图3中仅示出了部分视频帧中第一特征点111及第二特征点121之间的位置关系),测得每一选取的视频帧内第一特征点111与第二特征点121之间的距离,并根据上述的数据,得到时间-距离曲线图。在得到时间-距离曲线图的过程中,可以通过时域滤波、频域滤波高斯滤波或中值滤波等方法对第一特征点111与第二特征点121之间的距离的数据进行处理,以平滑数据曲线。As shown in FIG. 4 (for convenience of expression, FIG. 3 only shows the positional relationship between the first feature point 111 and the second feature point 121 in some video frames), the first feature point 111 in each selected video frame is measured. The distance between the feature point 111 and the second feature point 121, and according to the above data, a time-distance curve graph is obtained. In the process of obtaining the time-distance curve graph, the data of the distance between the first feature point 111 and the second feature point 121 can be processed by methods such as time domain filtering, frequency domain filtering, Gaussian filtering or median filtering, etc. Smooth data curves.

由于测试者的呼吸是一个循环往复的过程,因此,在得到时间-距离曲线图后,如图5所示,该图会呈现一定的周期性,通过计算特定时间内的周期数,如60s内的周期数,即可得到测试者的呼吸频率。Since the tester's breathing is a cyclical process, after obtaining the time-distance curve, as shown in Figure 5, the graph will show a certain periodicity. By calculating the number of cycles within a specific time, such as within 60s The number of cycles, you can get the tester's breathing rate.

在本实施例中,通过对选出的特定视频帧内第一标记11及第二标记12之间距离的测量,能够反映出第一标记11及第二标记12之间距离的变化趋势,即使在某些视频帧内,由于某些原因第一标记11与第二标记12之间的距离不能够反映测试者的呼吸状况,但是,该测试方法是从整体趋势上对测试者的呼吸频率进行计数,这能够较为准确地对测试者的呼吸频率进行检测,由于在测试时,仅需要固定两个标记的位置,因此,该方法应用简单,且成本较低。In this embodiment, by measuring the distance between the first marker 11 and the second marker 12 in the selected specific video frame, the change trend of the distance between the first marker 11 and the second marker 12 can be reflected, even if In some video frames, due to some reasons, the distance between the first marker 11 and the second marker 12 cannot reflect the tester's breathing condition. However, this test method is based on the overall trend of the tester's breathing rate. Counting, which can more accurately detect the tester's breathing rate, because during the test, only the positions of the two markers need to be fixed, so the method is simple to apply and has a low cost.

图6为本发明提供的呼吸频率的检测方法的第二实施例中,第一标记及第二标记的安放位置示意图,图7为本发明第二实施例中,沿时间顺序,在各特定帧的图像内,第一标记及第二标记的位置关系示意图,图8为本发明第二实施例中,沿时间顺序,第一标记及第二标记之间距离变化的时间-距离曲线图。本发明第二实施例提供的呼吸频率的检测方法与第一实施例提供的方法基本相同,其不同之处在于,在本实施例中,第一标记11及第二标记12为两个独立的标记片10,第一标记11及第二标记12分别固定于测试者的左胸部及右胸部,也即,第一标记11及第二标记12均会随着测试者呼吸时身体的运动而运动。通过摄像机记录第一标记11与第二标记12之间距离变化的视频,并对该视频图像进行分析,以得出时间-距离曲线图,最后求得该时间-距离曲线图的周期数,以得到测试者的呼吸频率。FIG. 6 is a schematic diagram of the placement positions of the first marker and the second marker in the second embodiment of the respiratory rate detection method provided by the present invention, and FIG. 7 is the second embodiment of the present invention. In the image of , a schematic diagram of the positional relationship between the first mark and the second mark, FIG. 8 is a time-distance curve diagram of the distance change between the first mark and the second mark along the time sequence in the second embodiment of the present invention. The respiratory rate detection method provided by the second embodiment of the present invention is basically the same as the method provided by the first embodiment, the difference is that in this embodiment, the first marker 11 and the second marker 12 are two independent markers The marker sheet 10, the first marker 11 and the second marker 12 are respectively fixed on the left chest and the right chest of the tester, that is, the first marker 11 and the second marker 12 will move with the movement of the tester's body when breathing . The video of the distance change between the first mark 11 and the second mark 12 is recorded by the camera, and the video image is analyzed to obtain a time-distance curve diagram, and finally the number of cycles of the time-distance curve diagram is obtained to obtain Get the tester's breathing rate.

可以理解地,在本实施例中,同样可以在第一标记11中提取第一特征点111,以及在第二标记12中提取第二特征点121,以便于第一标记11与第二标记12之间距离的测量。在本实施例中,上述特征点的提取可以用基于hough变换的椭圆提取等方法得出。It can be understood that in this embodiment, the first feature point 111 can also be extracted from the first marker 11 and the second feature point 121 can be extracted from the second marker 12, so as to facilitate the first marker 11 and the second marker 12 measurement of the distance between. In this embodiment, the above feature points can be extracted by methods such as ellipse extraction based on hough transform.

在其它实施例中,第一标记11和第二标记12的位置不仅可以设置于测试者的左胸部及右胸部,也可以在腹部或鼻翼部等能够在测试者呼吸时产生运动的位置,以便使第一标记11及第二标记12之间的距离在测试者呼吸的过程中而发生变化。也即在测试者的呼吸中,至少要保证第一标记11及第二标记12的其中之一的位置会随着测试者的呼吸而发生周期性的变化。In other embodiments, the positions of the first mark 11 and the second mark 12 can be set not only on the left chest and right chest of the tester, but also on the abdomen or the alar part of the nose, etc. that can generate movement when the tester breathes, so that The distance between the first mark 11 and the second mark 12 is changed while the test subject is breathing. That is, during the tester's breathing, at least one of the positions of the first mark 11 and the second mark 12 should be guaranteed to periodically change with the tester's breathing.

图8为本发明提供的检测装置的系统框图,如图8所示,本发明还提供了一种应用上述呼吸频率的检测方法进行呼吸频率检测的检测装置,该检测装置包括第一标记11、第二标记12、视频图像获取单元30及处理单元40,第一标记11及第二标记12设置于测试者的身体上,第一标记11及第二标记12之间的相对位置会随着测试者的呼吸而做周期性变化;视频图像获取单元30获取第一标记11及第二标记12在测试者呼吸时位置变化的视频头像;处理单元40将上述视频图像分离为以时间先后为顺序的视频帧,选取特定的视频帧,并识别每一选取的视频帧中第一标记11及第二标记12的位置;然后测得每一选取的视频帧中,第一标记11与第二标记12之间的距离,并形成时间-距离曲线图;最后在特定时间内对时间-距离曲线图的周期进行计数,以得到测试者的呼吸频率。FIG. 8 is a system block diagram of the detection device provided by the present invention. As shown in FIG. 8 , the present invention also provides a detection device for detecting respiratory frequency by applying the above-mentioned method for detecting respiratory frequency. The detecting device includes a first marker 11, The second marker 12, the video image acquisition unit 30 and the processing unit 40, the first marker 11 and the second marker 12 are set on the tester's body, and the relative position between the first marker 11 and the second marker 12 will vary with the test The video image acquisition unit 30 acquires the video avatars whose positions of the first marker 11 and the second marker 12 change when the tester breathes; the processing unit 40 separates the above-mentioned video images into chronological order. Video frame, select a specific video frame, and identify the position of the first mark 11 and the second mark 12 in each selected video frame; then measure in each selected video frame, the first mark 11 and the second mark 12 The distance between them is formed, and a time-distance curve diagram is formed; finally, the cycles of the time-distance curve diagram are counted within a specific time to obtain the tester's breathing rate.

以上所述,仅是本发明的较佳实施例而已,并非对本发明作任何形式上的限制,虽然本发明已以较佳实施例揭露如上,然而并非用以限定本发明,任何熟悉本专业的技术人员,在不脱离本发明技术方案范围内,当可利用上述揭示的技术内容作出些许更动或修饰为等同变化的等效实施例,但凡是未脱离本发明技术方案内容,依据本发明的技术实质对以上实施例所作的任何简单修改、等同变化与修饰,均仍属于本发明技术方案的范围内。The above are only preferred embodiments of the present invention, and do not limit the present invention in any form. Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. The technical personnel, within the scope of the technical solution of the present invention, can make some changes or modifications by using the technical content disclosed above to be equivalent embodiments of equivalent changes, provided that they do not depart from the technical solution content of the present invention, according to the technical solution of the present invention. Any simple modifications, equivalent changes and modifications made to the above embodiments still fall within the scope of the technical solutions of the present invention.

Claims (10)

Translated fromChinese
1.一种呼吸频率的检测方法,其特征在于:包括如下步骤:1. a detection method of respiratory rate, is characterized in that: comprise the steps:提供第一标记及第二标记,所述第一标记与所述第二标记的相对位置随测试者的呼吸而发生周期性变化;providing a first marker and a second marker, the relative positions of the first marker and the second marker periodically change with the tester's breathing;获取所述第一标记及所述第二标记在测试者呼吸时位置变化的视频图像;acquiring a video image of the position change of the first mark and the second mark when the tester breathes;将所述视频图像分离为以时间先后为顺序的视频帧;separating the video image into video frames in chronological order;选取特定的视频帧,并识别每一选取的所述视频帧中所述第一标记与所述第二标记的位置;Selecting a specific video frame, and identifying the positions of the first marker and the second marker in each of the selected video frames;测得每一选取的所述视频帧中所述第一标记与所述第二标记之间的距离,并形成时间-距离曲线图;measuring the distance between the first mark and the second mark in each selected video frame, and forming a time-distance curve diagram;在特定的时间内对所述时间-距离曲线图的周期进行计数。Periods of the time-distance graph are counted for a specific time.2.如权利要求1所述的呼吸频率的检测方法,其特征在于:至少所述第一标记及所述第二标记的其中之一的位置随着测试者的呼吸而发生周期性的变化。2 . The method for detecting breathing frequency according to claim 1 , wherein the position of at least one of the first marker and the second marker periodically changes with the breathing of the tester. 3 .3.如权利要求2所述的呼吸频率的检测方法,其特征在于:所述第一标记与所述第二标记位于测试者的鼻孔与嘴部之间,所述第一标记形成一自由端,该自由端的位置随着测试者呼吸产生的气流而发生周期性变化。3 . The method for detecting breathing frequency according to claim 2 , wherein the first mark and the second mark are located between the nostril and the mouth of the tester, and the first mark forms a free end. 4 . , the position of the free end changes periodically with the airflow generated by the tester's breathing.4.如权利要求2所述的呼吸频率的检测方法,其特征在于:所述第一标记与所述第二标记均随着测试者呼吸时身体的运动而运动。4 . The method for detecting breathing frequency according to claim 2 , wherein both the first mark and the second mark move with the movement of the tester's body when breathing. 5 .5.如权利要求4所述的呼吸频率的检测方法,其特征在于:所述第一标记及所述第二标记分别固定于人体的左胸部及右胸部,或者分别固定于鼻翼的两侧。5 . The method for detecting respiratory frequency according to claim 4 , wherein the first marker and the second marker are respectively fixed on the left chest and the right chest of the human body, or on both sides of the nose. 6 .6.如权利要求1所述的呼吸频率的检测方法,其特征在于:在选取特定的视频帧,并识别每一选取的所述视频帧中所述第一标记与所述第二标记的位置的步骤后,该方法还包括,在所述第一标记上提取第一特征点,在所述第二标记上提取第二特征点,通过测量每一选取的所述视频帧中所述第一特征点与所述第二特征点之间的距离,以得到所述第一标记与所述第二标记之间的距离。6. The method for detecting respiratory rate as claimed in claim 1, wherein: selecting a specific video frame and identifying the positions of the first mark and the second mark in each selected video frame After the step of , the method further includes, extracting a first feature point on the first marker, extracting a second feature point on the second marker, by measuring the first feature point in each selected video frame distance between the feature point and the second feature point to obtain the distance between the first mark and the second mark.7.如权利要求1所述的呼吸频率的检测方法,其特征在于:以时间先后为顺序,识别每一视频帧中第一标记与第二标记的位置;然后测得每一所述视频帧中所述第一标记与所述第二标记之间的距离,并形成时间-距离曲线图;最后在特定的时间内对所述时间-距离曲线图的周期进行计数。7. The detection method of respiratory rate as claimed in claim 1, characterized in that: in order of time, identify the position of the first mark and the second mark in each video frame; then measure each of the video frames The distance between the first mark and the second mark is formed, and a time-distance curve diagram is formed; finally, the period of the time-distance curve diagram is counted within a specific time.8.一种用于呼吸频率检测的检测装置,其特征在于:包括第一标记及第二标记,所述第一标记及所述第二标记之间的相对位置会随着测试者的呼吸而做周期性变化;8. A detection device for respiratory rate detection, characterized in that it comprises a first mark and a second mark, and the relative position between the first mark and the second mark changes with the breathing of the tester. make periodic changes;图像获取单元,所述图像获取单元获取所述第一标记及所述第二标记在测试者呼吸时位置变化的视频图像;以及an image acquisition unit, the image acquisition unit acquires a video image of the position change of the first marker and the second marker when the tester breathes; and处理单元,所述处理单元将所述视频图像分离为以时间先后为顺序的视频帧,选取特定的所述视频帧,并识别每一选取的所述视频帧中所述第一标记及所述第二标记的位置;测得每一选取的所述视频帧中,所述第一标记及所述第二标记之间的距离,并形成时间-距离曲线图;在特定时间内对时间-距离曲线图的周期进行计数。a processing unit, the processing unit separates the video image into video frames in chronological order, selects a specific video frame, and identifies the first mark and the first mark in each selected video frame The position of the second mark; measure the distance between the first mark and the second mark in each selected video frame, and form a time-distance curve; The period of the graph is counted.9.根据权利要求8所述的用于呼吸频率检测的检测装置,其特征在于:该装置还包括标记片,所述第一标记与所述第二标记形成于同一所述标记片的两个相对的边缘上,所述标记片上第一标记所在的一端的厚度小于第二标记所在一端的厚度。9 . The detection device for respiratory rate detection according to claim 8 , wherein the device further comprises a marker sheet, and the first marker and the second marker are formed on two of the same marker sheet. 10 . On the opposite edge, the thickness of the end of the marking sheet where the first mark is located is smaller than the thickness of the end where the second mark is located.10.根据权利要求8所述的用于呼吸频率检测的检测装置,其特征在于:该装置还包括标记片,所述第一标记与所述第二标记分别形成于两个独立的所述标记片上。10 . The detection device for respiratory rate detection according to claim 8 , wherein the device further comprises a marker sheet, and the first marker and the second marker are respectively formed on two independent markers. 11 . a.
CN201810194475.7A2018-03-092018-03-09Method for detecting respiratory frequencyActiveCN110236547B (en)

Priority Applications (2)

Application NumberPriority DateFiling DateTitle
CN201811126359.8ACN110236548B (en)2018-03-092018-03-09Detection device for detecting respiratory frequency
CN201810194475.7ACN110236547B (en)2018-03-092018-03-09Method for detecting respiratory frequency

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201810194475.7ACN110236547B (en)2018-03-092018-03-09Method for detecting respiratory frequency

Related Child Applications (1)

Application NumberTitlePriority DateFiling Date
CN201811126359.8ADivisionCN110236548B (en)2018-03-092018-03-09Detection device for detecting respiratory frequency

Publications (2)

Publication NumberPublication Date
CN110236547Atrue CN110236547A (en)2019-09-17
CN110236547B CN110236547B (en)2022-10-28

Family

ID=67882203

Family Applications (2)

Application NumberTitlePriority DateFiling Date
CN201811126359.8AActiveCN110236548B (en)2018-03-092018-03-09Detection device for detecting respiratory frequency
CN201810194475.7AActiveCN110236547B (en)2018-03-092018-03-09Method for detecting respiratory frequency

Family Applications Before (1)

Application NumberTitlePriority DateFiling Date
CN201811126359.8AActiveCN110236548B (en)2018-03-092018-03-09Detection device for detecting respiratory frequency

Country Status (1)

CountryLink
CN (2)CN110236548B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN111839489A (en)*2020-05-262020-10-30合肥工业大学Non-contact physiological and psychological health detection system
CN112515763A (en)*2020-11-272021-03-19中国科学院深圳先进技术研究院Target positioning display method, system and device and electronic equipment
CN114916926A (en)*2022-04-282022-08-19西安商汤智能科技有限公司Respiration rate detection method, device, equipment, system and storage medium
CN115116146A (en)*2022-06-022022-09-27支付宝(杭州)信息技术有限公司 Liveness detection method, device, equipment and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20070076935A1 (en)*1998-10-232007-04-05Andrew JeungMethod and system for monitoring breathing activity of a subject
US20100125195A1 (en)*2008-11-192010-05-20Kajetan BerlingerDetermination of regions of an analytical image that are subject to vital movement
CN103857338A (en)*2011-10-202014-06-11皇家飞利浦有限公司Device and method for monitoring movement and orientation of the device
CN105705089A (en)*2013-11-012016-06-22皇家飞利浦有限公司System and method for determining vital sign information of a subject
CN107260173A (en)*2017-06-302017-10-20大连理工大学A kind of breath measuring method based on camera Yu spherical label

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20070076935A1 (en)*1998-10-232007-04-05Andrew JeungMethod and system for monitoring breathing activity of a subject
US20100125195A1 (en)*2008-11-192010-05-20Kajetan BerlingerDetermination of regions of an analytical image that are subject to vital movement
CN103857338A (en)*2011-10-202014-06-11皇家飞利浦有限公司Device and method for monitoring movement and orientation of the device
CN105705089A (en)*2013-11-012016-06-22皇家飞利浦有限公司System and method for determining vital sign information of a subject
CN107260173A (en)*2017-06-302017-10-20大连理工大学A kind of breath measuring method based on camera Yu spherical label

Cited By (6)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN111839489A (en)*2020-05-262020-10-30合肥工业大学Non-contact physiological and psychological health detection system
CN111839489B (en)*2020-05-262021-04-13合肥工业大学Non-contact physiological and psychological health detection system
CN112515763A (en)*2020-11-272021-03-19中国科学院深圳先进技术研究院Target positioning display method, system and device and electronic equipment
CN112515763B (en)*2020-11-272021-09-10中国科学院深圳先进技术研究院Target positioning display method, system and device and electronic equipment
CN114916926A (en)*2022-04-282022-08-19西安商汤智能科技有限公司Respiration rate detection method, device, equipment, system and storage medium
CN115116146A (en)*2022-06-022022-09-27支付宝(杭州)信息技术有限公司 Liveness detection method, device, equipment and system

Also Published As

Publication numberPublication date
CN110236547B (en)2022-10-28
CN110236548B (en)2022-08-05
CN110236548A (en)2019-09-17

Similar Documents

PublicationPublication DateTitle
CN110236547B (en)Method for detecting respiratory frequency
EP2617012B1 (en)Method and system for analyzing images
Tan et al.Real-time vision based respiration monitoring system
CN105520724A (en) A method of measuring the human heart rate and respiration rate
WO2018170009A1 (en)Imaging-based spirometry systems and methods
WO2019085805A1 (en)Non-contact neck-based respiratory and pulse signal detection method, device, and imaging apparatus
CN107358220A (en)A kind of human heart rate and the contactless measurement of breathing
Alkali et al.Facial tracking in thermal images for real-time noncontact respiration rate monitoring
CN103976737B (en)A kind of pulmo respiratory impedance correlation analysis and system
JP7464653B2 (en) System for measuring nasal valve stenosis in a patient
US20210169375A1 (en)Sensors and Method for Defining Breathing Signatures for Identifying Respiratory Disease
RumińskiAnalysis of the parameters of respiration patterns extracted from thermal image sequences
CN107616795A (en)A kind of contactless respiratory rate detection method in real time based on camera
CN112363139A (en)Human body breathing time length detection method and device based on amplitude characteristics and storage medium
CN107260173A (en)A kind of breath measuring method based on camera Yu spherical label
US20230301546A1 (en)Imaging human respiratory gas patterns to determine volume, rate and carbon dioxide concentration
CN117357093A (en)Non-contact respiration rate monitoring method and system based on double-spectrum facial video
CN104305996A (en) Respiratory monitoring method and system based on image recognition technology
JP6273940B2 (en) Image analysis apparatus, image photographing system, and image analysis program
JP2019532786A5 (en) A system for measuring nasal flap stenosis in patients
Al-Kalidi et al.Respiratory rate measurement in children using a thermal camera
Nirmala et al.Camera-based non-contact respiratory rate estimation
Farah et al.Respiratory rate measurement in children using a thermal imaging camera
Rao et al.A review on different technical specifications of respiratory rate monitors
Pavan et al.A pilot study on wearable nasal patch sensor for assessment of breathing parameters

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp