CN114431849B - Aquatic animal heart rate detection method based on video image processing - Google Patents
Aquatic animal heart rate detection method based on video image processing Download PDFInfo
- Publication number
- CN114431849B CN114431849B CN202210023274.7A CN202210023274A CN114431849B CN 114431849 B CN114431849 B CN 114431849B CN 202210023274 A CN202210023274 A CN 202210023274A CN 114431849 B CN114431849 B CN 114431849B
- Authority
- CN
- China
- Prior art keywords
- interest
- region
- heart
- signal sequence
- heart rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/40—Animals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Abstract
The invention discloses an aquatic animal heart rate detection method based on video image processing, which comprises the steps of acquiring an aquatic animal ventral video image sequence, selecting heart and background interested areas, keeping track, extracting an environmental noise component shared by the heart and the background interested areas by adopting a multi-dataset joint analysis method, and setting the environmental noise component to zero; then further eliminating static components in the model according to the bicolor reflection model, and selecting specular reflection components and diffuse reflection components; then, independent component analysis is carried out on a time signal sequence composed of specular reflection components and diffuse reflection components, and the independent component with the greatest heart rate information is obtained through correlation calculation; finally, carrying out frequency domain decomposition on the aquatic animal, screening out the subcomponent with the highest matching degree on the frequency domain according to the specific heart rate range of the aquatic animal, and outputting a cardiac waveform chart to output or calculating the heart rate value; the scheme provides a robust and accurate method for non-contact detection of the heart rate of the aquatic animals, and has wide application prospects in the aspects of aquaculture monitoring and biological stress resistance evaluation.
Description
Technical Field
The invention relates to the technical field of biological image information, in particular to an aquatic animal heart rate detection method based on video image processing.
Background
The aquaculture industry is an important component of fishery in China, but under the conditions of climate change and unreasonable cultivation modes, the problems of disease outbreak, high-temperature death and the like can occur. The breeding of aquatic animals with higher stress resistance or tolerance by selective breeding is one of the most effective measures against this problem.
Heart rate is an important physiological index and is closely related to the metabolic state of aquatic animals and the stress on environmental changes. Accordingly, technicians typically use heart rate as an evaluation index to assess the ability of aquatic animals to cope with changes in internal or external environments and to assist in their genetic breeding efforts. At present, the heart rate measurement of aquatic animals has certain limitations, mainly including the need of limiting the activities of organisms, continuous contact and even surgical operation, and the heart rate measurement of aquatic animals is mostly carried out by adopting an implanted electrode method, a Doppler ultrasonic method and the like. Conventional remote non-contact heart rate measurement methods often lack high-precision signal denoising and signal separation methods. Because the aquatic animal has special physiological structure and most of the aquatic animal does not have abundant capillaries distributed under the superficial epidermis, the physiological information contained in the video image is very weak, and more accurate and more robust technical means are often required to extract heart rate information. Thus, in existing breeding studies, there is a lack of methods for conveniently observing the heart rate of an individual aquatic animal under non-contact conditions, thus providing an accurate and robust method for detecting the impending heart rate of an aquatic animal.
Disclosure of Invention
Therefore, the invention aims to provide the aquatic animal heart rate detection method based on video image processing, so that the stress resistance evaluation index range can be widened for genetic breeding researchers, and the evaluation dimension in the genetic breeding process is increased.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
an aquatic animal heart rate detection method based on video image processing, comprising:
1) Acquiring a video image of the ventral surface of a t-frame aquatic animal, selecting an interested region according to preset conditions, tracking and keeping the interested region to obtain a time signal sequence of a heart region and a background region, wherein the interested region comprises the heart interested region and the background interested region;
2) Screening out common environmental noise shared by a heart region of interest and a background region of interest according to a multi-dataset joint analysis method and removing the common environmental noise;
3) According to the bicolor reflection model, the time signal sequence of the heart region of interest after the common environmental noise is removed in the step 2) is regarded as the linear combination of illumination change components, specular reflection components and diffuse reflection components, static components are eliminated, and the linear combination is projected to an orthogonal plane to remove the illumination change components;
4) Analyzing the independent components of the time signal sequence of the heart region of interest, which is obtained through the processing in the step 3) and only contains specular reflection components and diffuse reflection components, and screening out the independent components with the strongest correlation with the green channel in the signal sequence of the original heart region of interest;
5) Decomposing the independent components obtained in the step 4) in a frequency domain, and screening the subcomponent with highest matching degree with the special heart rate distribution range of aquatic animal species in the frequency domain;
6) The cardiac waveform map or heart rate value is further output according to the subcomponents obtained by the processing in step 5).
As a possible implementation manner, in step 1), the video image is a digital image illustrating colors in different color spaces; the aquatic animal is an aquatic animal having a heart organ and comprising red blood cells in its blood tissue component.
As a possible implementation manner, in step 1), further, selecting a heart region of interest and a background region of interest through a manual selection or target detection algorithm and tracking and maintaining the heart region of interest and the background region of interest through the target detection algorithm; the obtained time signal sequence of the heart and background region is a time signal sequence obtained by removing quantization noise by spatial averaging.
As a possible implementation manner, in step 2), the multi-dataset joint analysis method is a joint blind source separation method based on multiple datasets.
As a possible implementation manner, in step 3), further, the static component is eliminated by performing a time domain normalization process on the signal.
As a possible implementation manner, in step 5), the independent components obtained in the step 4) are decomposed from the frequency domain according to the method of decomposing the ensemble empirical mode.
As a possible implementation manner, in step 6), the heart rate value corresponding to the signal is calculated by a frequency domain or time domain method according to the subcomponent obtained by processing in step 5), and then the heart rate value is output or converted into a cardiac waveform diagram to be output.
Based on the above scheme, the invention also provides a computer readable storage medium, wherein at least one instruction, at least one section of program, code set or instruction set is stored in the storage medium, and the at least one instruction, the at least one section of program, the code set or the instruction set is loaded by a processor and executed to realize the aquatic animal heart rate detection method based on video image processing.
By adopting the technical scheme, compared with the prior art, the invention has the beneficial effects that:
1. the scheme of the invention utilizes the background content which is originally redundant information: for removing background noise, a traditional and general processing method is not adopted, but a background region of interest is additionally arranged, and a source signal component vector shared by the heart region of interest and the background region of interest is extracted through joint blind source separation and is regarded as background noise removal.
2. The proposal of the invention adopts a bicolor reflection model to separate signals containing heart rate information: according to the bicolor reflection model, the signal is regarded as three parts of illumination change component, specular reflection component and diffuse reflection component, wherein the illumination change becomes the change of brightness intensity along with the light source and the distance between the light source, the shooting object and the camera, the specular reflection component is the specular reflection component generated by direct reflection on the skin surface, and the diffuse reflection component is the diffuse reflection component which is absorbed again by subcutaneous tissue and blood after transmitting the skin surface. It has the advantage that it interprets the source of the formation of heart rate information from a physiological and physical level and in combination with other components, may provide a more accurate and more robust extraction of the components containing heart rate information.
3. When the method is used for further screening the components containing heart rate information, physiological structures of aquatic animals are fully considered, and the original signal green channel signal is used as a screening standard. Hemoglobin is a constituent of blood of aquatic animals, is colored, and has an absorption spectrum in the visible region. The maximum absorption of hemoglobin from aquatic animals is between 540 and 575 nanometers for oxygen (Oxy) type and 538 and 568 nanometers for carbonyl (carbonyl) type, with no significant difference from mammals. The adoption of the green channel signal as a standard can be a more theoretical support and a more accurate screening approach.
4. According to the scheme, the independent components after analysis and screening of the independent components are subjected to further frequency domain separation by adopting an ensemble empirical mode decomposition method. Through the integrated empirical mode decomposition, the selected independent components are divided into eigenmode functions on a plurality of frequency bands, and according to the unique heart rate distribution range of the aquatic animal species in theory, the eigenmode function with the highest expected frequency can be selected for outputting a cardiac waveform diagram or calculating the heart rate. The method has the advantages that the signal-to-noise ratio is further improved from the frequency domain, the interference of components except the expected frequency is eliminated, and the reliability of the calculation result is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a non-contact aquatic animal heart rate detection method based on video image processing;
FIG. 2 is a schematic diagram of selection of a region of interest of a heart and a background region of interest in accordance with an embodiment of the present invention;
FIG. 3 is a signal sequence diagram of a region of interest of the heart in accordance with an embodiment of the present invention;
FIG. 4 is a signal sequence diagram of a background region of interest in accordance with an embodiment of the present invention;
FIG. 5 is a vector diagram of source signal components after joint blind source separation in accordance with an embodiment of the present invention;
FIG. 6 is a time signal sequence diagram of a heart region of interest reconstructed after removal of ambient noise according to an embodiment of the present invention;
FIG. 7 is a time signal sequence diagram of a region of interest of a heart including only specular and diffuse components after projection elimination of time-varying illumination variation components, as contemplated by an embodiment of the present invention;
FIG. 8 is a graph of independent components after independent component analysis according to an embodiment of the present invention;
FIG. 9 is a graph of eigenmode functions of each frequency band after the method of decomposition of the aggregated empirical mode according to an embodiment of the present invention;
FIG. 10 is a diagram of a cardiac waveform involved in an embodiment of the present invention;
FIG. 11 is a chart of a fast Fourier transform spectrum involved in an embodiment of the present invention;
fig. 12 is a graph of peaks and valleys in a peak detection method according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is specifically noted that the following examples are only for illustrating the present invention, but do not limit the scope of the present invention. Likewise, the following examples are only some, but not all, of the examples of the present invention, and all other examples, which a person of ordinary skill in the art would obtain without making any inventive effort, are within the scope of the present invention.
In the embodiment, after the large yellow croaker is anesthetized, an implantable electrocardiograph is connected around the pericardium through a surgical operation, and a video image sequence is acquired by shooting a large yellow croaker ventral video through a camera while the electrocardiograph collects data.
Referring to fig. 1, the scheme provides an aquatic animal heart rate detection method based on video image processing, which has the following general technical ideas: acquiring video images of t frames of aquatic animals, then respectively selecting a heart region of interest and a background region of interest, obtaining a signal sequence of which the average pixel intensity changes along with time, extracting an environmental noise component shared by the two by adopting joint blind source separation, and setting the environmental noise component to zero to obtain a heart region of interest time signal sequence from which the environmental noise is removed; then, according to a bicolor reflection model, the new time signal sequence of the heart region of interest is regarded as the linear combination of illumination change components, specular reflection components and diffuse reflection components, time domain normalization is carried out on the time signal sequence to eliminate static components in the time signal sequence, and then the normalized time signal sequence is projected to a plane orthogonal to the illumination change components to screen out specular reflection components and diffuse reflection components; then, independent component analysis is carried out on a time signal sequence composed of specular reflection components and diffuse reflection components, and the correlation between each independent component and a green channel signal in the time signal sequence of the original heart region of interest is calculated, so that the independent component with the most diffuse reflection components is obtained; and finally, performing aggregate empirical mode decomposition on the independent components with the greatest diffuse reflection components, screening out the eigenmode function with the highest matching degree on the frequency domain according to the specific heart rate range of the aquatic animal species, and performing moving average on the eigenmode function on the time domain to output as a cardiac waveform diagram or further calculate the heart rate value.
Specifically, the scheme comprises the following implementation steps:
1) After the video image of the ventral surface of the t-frame large yellow croaker is obtained and converted into an RGB video image, a heart region of interest and a background region of interest in the video image can be selected respectively in a manual selection mode in the 1 st frame video image, then tracking and keeping of the region of interest are completed in the subsequent t-1 frame video image by adopting a target tracking algorithm, so that the work of selecting the heart region of interest and the background region of interest and completing tracking and keeping of the region of interest by a target detection algorithm is completed; then, for each region of interest, calculating the average pixel intensities of three color channels of each frame of RGB video image respectively to obtain a heart region of interest signal sequence shown in FIG. 3 and a background region of interest signal sequence shown in FIG. 4, wherein the formula of the heart region of interest signal sequence is as follows:
X hr (t)＝[R hr (t)；G hr (t)；B hr (t)] T ，
wherein R is hr (t)、G hr (t)、B hr (t) average pixel intensities of R, G, B color channels of the video image of the region of interest of the heart, respectively;
the formula of the background region of interest signal sequence is as follows:
X bg (t)＝[R bg (t)；G bg (t)；B bg (t)] T ；
wherein R is bg (t)、G bg (t)、B bg (t) average pixel intensities of R, G, B color channels of the background region of interest video image, respectively;
2) According to the joint blind source separation method, the signal sequence X of the heart region of interest is determined by using a mathematical formula SCV (t) =W×X (t) hr (t) and background region of interest Signal sequence X bg (t) carrying out joint blind source separation processing to obtain a unmixed matrix W, wherein W is the unmixed matrix, and SCV (t) is a source signal component vector;
further calculations may result in the source signal component vector matrix shown in fig. 5
SCV(t)＝[SCV hr1 ；SCV hr2 ；SCV hr3 ；SCV bg1 ；SCV bg2 ；SCV bg3 ] T ；
The joint blind source separation method is a joint blind source separation framework realized based on Gaussian independent vector analysis;
based on this, the respective source signal component vector SCV of the cardiac region of interest signal sequence can be obtained from the source signal component vector matrix calculation hr(n) (t) and the respective source signal component vector SCV of the background region-of-interest Signal sequence bg(n) (t)；The respective source signal component vectors SCV of the computed cardiac region of interest signal sequence may then be used to determine the position of the target region hr(n) (t) and the respective source signal component vector SCV of the background region-of-interest Signal sequence bg(n) (t) correlating the source signal component vectors SCV of the region-of-interest signal sequence corresponding to the largest correlation coefficient hr(m) (t) obtaining SCV after zeroing new (t) and then obtaining the heart region-of-interest signal sequence and the background region-of-interest signal sequence X after removing the common environmental noise according to SCV (t) =W.times.X (t) new (t)＝W\SCV new (t)；
3) According to the bicolor reflection model, the heart region-of-interest time signal sequence X obtained in the step 2) after removing the environmental noise as shown in FIG. 6 is obtained new (t)[1:3]The linear combination of illumination change component, specular reflection component and diffuse reflection component is regarded as X after time domain normalization new (t) projection onto a plane p= [ P ] orthogonal to the illumination variation component 1 ；p 2 ] T Thus, a time signal sequence X of the region of interest of the heart, which is shown in FIG. 7 and contains only specular reflection components and diffuse reflection components, is obtained rflct (t)＝P*X new (t)；
4) For a region of interest of the heart time signal sequence X obtained in step 3) which contains only specular and diffuse reflecting components rflct (t) performing independent component analysis, i.e., X rflct (t) =a×s (t), where a is the mixing matrix and S (t) is the independent component of the source signal (as shown in fig. 8), S (t) =can be obtained
[s 1 (t)；s 2 (t)] T Calculate s 1 (t)；s 2 (t)] T Signal sequence X of region of interest of original heart hr G in (t) hr Screening out an independent component s (t) with strongest correlation with the original signal green channel signal by the correlation coefficient of (t);
5) Processing the s (t) obtained in the step 4) by adopting an ensemble empirical mode decomposition method to obtain s (t) = Σimf (t) +r (t), as shown in fig. 9, wherein imf (t) is an eigenmode function of each frequency band, r (t) is a residual term, then screening imf (t), selecting imf (t) with highest matching degree with the distribution range of the heart rate of the large yellow croaker on a frequency domain, carrying out sliding average, calculating the average value of continuous n terms before and after to replace the current value in imf (t), and marking the result as HR (t);
6) Outputting the HR (t) obtained in the step 5) directly as a cardiac waveform map; or further, transforming the HR (t) into the frequency domain by Fourier transformation in the frequency domain, and obtaining the frequency value f with the largest amplitude from the frequency spectrum max Heart rate hr=f max *60; peak detection method is adopted in time domain to obtain the heart rate when there are peak a and trough b coexisting in HR (t)Where t is the video duration in seconds.
As shown in fig. 10, 11 and 12, which are respectively a cardiac waveform chart, a fast fourier transform spectrum and peaks and troughs in the peak detection method, the heart rate is calculated to be 65BPM by a frequency domain method, the heart rate value is calculated to be 68BPM by a time domain method, and the heart rate of the large yellow croaker is synchronously measured to be 67BPM by an electrode method.
The results show that the results generated by the two heart rate calculation methods are consistent with the results obtained by adopting the verified method (electrode method) at the same time, so that the effectiveness and the reliability of the method for detecting the heart rate of the large yellow croaker are verified to a certain extent.
According to the embodiment, after the target large yellow croaker video is acquired through the low-cost common camera, the heart rate of the large yellow croaker can be obtained through a digital signal processing means, so that a sensor or an electrode is not required to be placed on the large yellow croaker body, and the non-contact heart rate measurement can be completed through the camera or the camera, and the non-contact and non-invasive large yellow croaker heart rate detection is realized.
The scheme of the invention can be widely applied to the genetic breeding work of large yellow croaker, and has the advantages of low price, simple and convenient implementation mode and real-time and rapid operation; the tolerance state of the large yellow croaker can be effectively observed, and the large yellow croaker can not generate stress response due to long-term contact measurement.
In the scheme of the embodiment, the original data is acquired based on two interested areas (the heart interested area and the background interested area), compared with the mode of acquiring the original data by only adopting a single interested area (only acquiring the heart interested area) (namely, the initial signal is the difference between a multi-channel and a single channel), the detection result obtained by the scheme is more accurate, and the interference factors in the process calculation are fewer, so that the result has more reference value; in addition, the scheme carries out projection decomposition on the signals based on a physical model-a bicolor reflection model, and the bicolor reflection model fully considers the interaction between incident light and the surface of biological skin, so that the reflected light signals containing heart rate components can be more accurately separated; the method utilizes an independent component analysis method to decompose the signals, and the independent component analysis can further separate sub-components with stronger heart rate components according to the reflected light characteristics of blood tissues; the method also utilizes the integrated empirical mode decomposition to complete the frequency domain decomposition, the integrated empirical mode decomposition is an adaptive method, a cut-off frequency range is not required to be set, the cut-off frequency is required to be set in advance for traditional frequency filtering, and the method is a predictive method, and is not neglected.
The foregoing description is only a partial embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent devices or equivalent processes using the descriptions and the drawings of the present invention or directly or indirectly applied to other related technical fields are included in the scope of the present invention.
Claims (5)
1. An aquatic animal heart rate detection method based on video image processing is characterized by comprising the following steps:
1) Acquiring a video image of the ventral surface of a t-frame aquatic animal, selecting an interested region according to preset conditions, tracking and keeping the interested region to obtain a time signal sequence of a heart region and a background region, wherein the interested region comprises the heart interested region and the background interested region;
2) Screening out common environmental noise shared by a heart region of interest and a background region of interest according to a multi-dataset joint analysis method and removing the common environmental noise;
3) According to the bicolor reflection model, the time signal sequence of the heart region of interest after the common environmental noise is removed in the step 2) is regarded as the linear combination of illumination change components, specular reflection components and diffuse reflection components, static components are eliminated, and the linear combination is projected to an orthogonal plane to remove the illumination change components;
4) Analyzing the independent components of the time signal sequence of the heart region of interest, which is obtained through the processing in the step 3) and only contains specular reflection components and diffuse reflection components, and screening out the independent components with the strongest correlation with the green channel in the signal sequence of the original heart region of interest;
5) Decomposing the independent components obtained in the step 4) in a frequency domain, and screening the subcomponent with highest matching degree with the special heart rate distribution range of aquatic animal species in the frequency domain;
6) Further outputting a cardiac waveform map or heart rate value according to the subcomponents obtained by the processing in step 5);
wherein it includes:
1) Acquiring t frames of video images of the ventral surfaces of the aquatic animals, converting the video images into RGB video images, selecting a heart region of interest and a background region of interest, and completing tracking and maintaining of the region of interest by a target detection algorithm; and then, for each region of interest, respectively calculating the average pixel intensities of three color channels of each frame of RGB video image to obtain a heart region of interest signal sequence and a background region of interest signal sequence, wherein the heart region of interest signal sequence has the following formula:
X nr ()＝[ hr (t)； hr (t)； hr ()] T ，
wherein R is hr (t)、G hr (t)、B hr () Average pixel intensity of R, G, B color channels of video images of heart region of interest, respectivelyA degree;
the formula of the background region of interest signal sequence is as follows:
X bg ()＝[ bg (t)； bg (t)； bg ()] T ；
wherein R is bg (t)、G bg (t)、B bg () Average pixel intensities of R, G, B color channels of the background region of interest video image, respectively;
2) According to the joint blind source separation method, the signal sequence X of the heart region of interest is determined by using a mathematical formula SCV (t) = X (t) hr () And background region of interest signal sequence X bg () Performing joint blind source separation processing to obtain a unmixed matrix W, wherein W is the unmixed matrix, and SCV (t) is a source signal component vector;
further calculating to obtain a vector matrix of the source signal components
SCV(t)＝[SCV hr1 ；CV hr2 ；CV hr3 ；CV bg1 ；CV bg2 ；CV bg3 ] T ；
Obtaining each source signal component vector SCV of the heart region of interest signal sequence according to the source signal component vector matrix calculation hr() () And the respective source signal component vector SCV of the background region-of-interest signal sequence bg() ()；
The vector SCV of each source signal component of the cardiac region of interest signal sequence obtained by calculation hr() () And the respective source signal component vector SCV of the background region-of-interest signal sequence bg() () Correlation coefficient between the two, and the source signal component vector SCV of the signal sequence of the region of interest of the heart corresponding to the maximum correlation coefficient hr() () Obtaining SCV after setting zero new () Then, the heart region-of-interest signal sequence and the background region-of-interest signal sequence X after common environmental noise removal can be obtained according to SCV (t) = X (t) new (t)＝\SCV new ()；
3) According to the bicolor reflection model, the heart region of interest time signal sequence X obtained in the step 2) after removing the environmental noise is carried out new (t) is regarded as a linear group of an illumination variation component, a specular reflection component, and a diffuse reflection componentCombining, normalizing the time domain to X new () Projection onto plane p= [ P ] orthogonal to illumination variation component 1 ； 2 ] T Thereby obtaining a time signal sequence X of the heart region of interest comprising only specular reflection components and diffuse reflection components rflct (t)＝*X new ()；
4) For a region of interest of the heart time signal sequence X obtained in step 3) which contains only specular and diffuse reflecting components rflct (t) performing independent component analysis processing, i.e
X rflct () =a×s (t), where a is the mixing matrix and S (t) is the independent component of the source signal, S (t) = [ S 1 (t)； 2 ()] T Calculation [ 1 (T)； 2 ()] T Signal sequence X of region of interest of original heart hr () Middle G hr () Screening out an independent component s (t) with strongest correlation with the green channel signal of the original signal;
5) Processing s (t) obtained in the step 4) by adopting a set empirical mode decomposition method to obtain s (t) = Σimf (t) + (t), wherein imf (t) is an eigenmode function of each frequency band, r (t) is a residual error term, screening imf (t), selecting imf (t) with highest matching degree with the heart rate distribution range of aquatic animals on a frequency domain, carrying out moving average, calculating the average value of continuous n terms before and after to replace the current value in imf (t), and marking the result as HR ();
6) Outputting the HR () obtained in step 5) directly as a cardiac waveform map; or further, transforming the HR () into the frequency domain by adopting Fourier transformation from the frequency domain, and obtaining the frequency value f with the largest amplitude from the frequency spectrum max Heart rate hr=f max *60; peak detection method is adopted in time domain to obtain that there are peak a and trough b coexistent in HR (), heart rateWhere t is the video duration in seconds.
2. The method for detecting the heart rate of an aquatic animal based on video image processing as recited in claim 1, wherein in the step 1), the video images are digital images for explaining colors in different color spaces; the aquatic animal is an aquatic animal having a heart organ and comprising red blood cells in its blood tissue component.
3. The method for detecting heart rate of aquatic animals based on video image processing as recited in claim 1, wherein in the step 1), the heart region of interest and the background region of interest are selected by a manual selection or a target detection algorithm and tracked and maintained by the target detection algorithm;
the obtained time signal sequence of the heart and background region is a time signal sequence obtained by removing quantization noise by spatial averaging.
4. The method for detecting the heart rate of the aquatic animal based on video image processing as claimed in claim 1, wherein in the step 1), a heart region of interest and a background region of interest in a video image are selected respectively in a manual selection mode in a 1 st frame of video image, and then tracking and maintaining the region of interest are completed in a subsequent t-1 frame of video image by adopting a target tracking algorithm;
in the step 2), the joint blind source separation method refers to a joint blind source separation framework realized based on Gaussian independent vector analysis.
5. A computer-readable storage medium, characterized by: the storage medium stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded by a processor and executed to implement the aquatic animal heart rate detection method based on video image processing according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023274.7A CN114431849B (en) | 2022-01-10 | 2022-01-10 | Aquatic animal heart rate detection method based on video image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023274.7A CN114431849B (en) | 2022-01-10 | 2022-01-10 | Aquatic animal heart rate detection method based on video image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114431849A CN114431849A (en) | 2022-05-06 |
| CN114431849B true CN114431849B (en) | 2023-08-11 |
Family
ID=81367553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210023274.7A Active CN114431849B (en) | 2022-01-10 | 2022-01-10 | Aquatic animal heart rate detection method based on video image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114431849B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678780A (en) * | 2016-01-14 | 2016-06-15 | 合肥工业大学智能制造技术研究院 | Video heart rate detection method removing interference of ambient light variation |
| EP3459446A1 (en) * | 2017-09-22 | 2019-03-27 | Leibniz-Institut für Nutztierbiologie | Method for identifying a farm animal having an impairment of regulative capacity in response to metabolic stress |
| CN110269600A (en) * | 2019-08-06 | 2019-09-24 | 合肥工业大学 | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating |
| CN110276271A (en) * | 2019-05-30 | 2019-09-24 | 福建工程学院 | Merge the non-contact heart rate estimation technique of IPPG and depth information anti-noise jamming |
| CN110384491A (en) * | 2019-08-21 | 2019-10-29 | 河南科技大学 | A kind of heart rate detection method based on common camera |
| CN110680317A (en) * | 2019-10-15 | 2020-01-14 | 中国科学技术大学 | High-density surface electromyographic signal denoising method based on independent vector analysis |
| CN111280098A (en) * | 2020-03-17 | 2020-06-16 | 中国海洋大学 | Rapid determination method for temperature resistance character index ABT of chlamys farreri |
| CN112043254A (en) * | 2020-08-12 | 2020-12-08 | 厦门大学 | Prawn heart rate detection method and system based on video image |
| CN112043257A (en) * | 2020-09-18 | 2020-12-08 | 合肥工业大学 | Non-contact video heart rate detection method for motion robustness |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103765436B (en) * | 2011-08-26 | 2017-05-31 | 皇家飞利浦有限公司 | The signal detection that distortion reduces |
-
2022
- 2022-01-10 CN CN202210023274.7A patent/CN114431849B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678780A (en) * | 2016-01-14 | 2016-06-15 | 合肥工业大学智能制造技术研究院 | Video heart rate detection method removing interference of ambient light variation |
| EP3459446A1 (en) * | 2017-09-22 | 2019-03-27 | Leibniz-Institut für Nutztierbiologie | Method for identifying a farm animal having an impairment of regulative capacity in response to metabolic stress |
| CN110276271A (en) * | 2019-05-30 | 2019-09-24 | 福建工程学院 | Merge the non-contact heart rate estimation technique of IPPG and depth information anti-noise jamming |
| CN110269600A (en) * | 2019-08-06 | 2019-09-24 | 合肥工业大学 | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating |
| CN110384491A (en) * | 2019-08-21 | 2019-10-29 | 河南科技大学 | A kind of heart rate detection method based on common camera |
| CN110680317A (en) * | 2019-10-15 | 2020-01-14 | 中国科学技术大学 | High-density surface electromyographic signal denoising method based on independent vector analysis |
| CN111280098A (en) * | 2020-03-17 | 2020-06-16 | 中国海洋大学 | Rapid determination method for temperature resistance character index ABT of chlamys farreri |
| CN112043254A (en) * | 2020-08-12 | 2020-12-08 | 厦门大学 | Prawn heart rate detection method and system based on video image |
| CN112043257A (en) * | 2020-09-18 | 2020-12-08 | 合肥工业大学 | Non-contact video heart rate detection method for motion robustness |
Non-Patent Citations (1)
| Title |
|---|
| 秦睿星，陈兆学.人脸运动状态下的非接触式心率稳定测量算法.《光学技术》.2021,第47卷(第1期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114431849A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110269600B (en) | Non-contact video heart rate detection method based on multivariate empirical mode decomposition and combined blind source separation | |
| US8335550B2 (en) | Optical sensor device and image processing unit for measuring chemical concentrations, chemical saturations and biophysical parameters | |
| CN110384491A (en) | A kind of heart rate detection method based on common camera | |
| CN105989357A (en) | Human face video processing-based heart rate detection method | |
| Fan et al. | Non-contact remote estimation of cardiovascular parameters | |
| DE102013208588A1 (en) | PROCESSING A VIDEO TO ESTIMATE A RESPIRATORY RATE | |
| CN111243739A (en) | Anti-interference physiological parameter telemetering method and system | |
| CN109497977A (en) | Human heart rate and method for detecting blood oxygen saturation and device | |
| CN112233813A (en) | Non-contact non-invasive heart rate and respiration measurement method and system based on PPG | |
| Wedekind et al. | Automated identification of cardiac signals after blind source separation for camera-based photoplethysmography | |
| Yin et al. | Heart rate estimation based on face video under unstable illumination | |
| CN112294282A (en) | Self-calibration method of emotion detection device based on RPPG | |
| CN113591769B (en) | Non-contact heart rate detection method based on photoplethysmography | |
| Ibrahim et al. | Analysis of non-invasive video based heart rate monitoring system obtained from various distances and different facial spot | |
| CN110755090A (en) | Human body blood oxygen saturation measuring method based on network camera | |
| Gupta et al. | A motion and illumination resistant non-contact method using undercomplete independent component analysis and Levenberg-Marquardt algorithm | |
| CN114431849B (en) | Aquatic animal heart rate detection method based on video image processing | |
| Madhav et al. | Monitoring respiratory activity using PPG signals by order reduced-modified covariance AR technique | |
| CN115153473B (en) | Non-contact heart rate detection method based on multivariate singular spectrum analysis | |
| CN115381444A (en) | Rapid detection method for blood oxygen saturation | |
| CN114387479A (en) | Non-contact heart rate measurement method and system based on face video | |
| Hu et al. | Study on Real-Time Heart Rate Detection Based on Multi-People. | |
| Deng et al. | Non-invasive methods for heart rate measurement in fish based on photoplethysmography | |
| Wang et al. | KLT algorithm for non-contact heart rate detection based on image photoplethysmography | |
| CN114246570A (en) | Near-infrared heart rate detection method with peak signal-to-noise ratio and Pearson correlation coefficient fused |
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 |