CN118247494B - Flight training safety management system based on vision technology - Google Patents
Flight training safety management system based on vision technology Download PDFInfo
- Publication number
- CN118247494B CN118247494B CN202410667879.9A CN202410667879A CN118247494B CN 118247494 B CN118247494 B CN 118247494B CN 202410667879 A CN202410667879 A CN 202410667879A CN 118247494 B CN118247494 B CN 118247494B
- Authority
- CN
- China
- Prior art keywords
- heart rate
- region
- safety management
- acquiring
- pixel points
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the field of flight training safety management, and discloses a flight training safety management system based on a vision technology, which comprises a shooting device and an interested region acquisition device; the shooting device is used for acquiring a color image and an infrared image containing the face of the pilot by adopting an adaptive shooting interval; the region of interest acquisition device comprises an infrared segmentation module and a color segmentation module; the infrared segmentation module is used for acquiring a plurality of connected domains consisting of pixel points with pixel values larger than a set pixel value threshold in an infrared image, wherein the connected domains comprise a connected domain A with the largest number of the pixel points; the color segmentation module is used for acquiring a connected domain B formed by pixel points with the same coordinates as the pixel points in the connected domain A in the color image, acquiring an intermediate region corresponding to the connected domain B, and carrying out image segmentation on the intermediate region to obtain a region of interest in the color image. The invention can timely obtain the heart rate of the pilot to realize the safety management of flight training.
Description
Technical Field
The invention relates to the field of flight training safety management, in particular to a flight training safety management system based on a vision technology.
Background
In the process of flight training of a pilot, the heart rate state of the pilot is usually required to be monitored, the heart rate state influences the training safety of the pilot, and when the heart rate of the pilot is abnormal (for example, too high), the control right is required to be handed over in time, so that the safety management of the flight training is realized. In heart rate monitoring, one way to monitor heart rate is to use a touch sensor to measure heart rate, which requires the pilot to wear equipment for measurement, making the pilot's experience poor. Another monitoring approach is to acquire the heart rate of the pilot by capturing an image containing the face of the pilot, i.e. rpg technology, by analyzing the image. The rpg technique requires that a region of interest (typically a face region) be acquired from a color image at the time of measurement, and then analyzed to obtain the heart rate. In the prior art, the region of interest is usually obtained by using a threshold segmentation mode and the like, but all pixel points in the color image are required to be calculated by the calculation modes, so that the speed of obtaining a calculation result is relatively slow, and the accurate region of interest is difficult to obtain from the color image quickly, so that the timeliness of measuring the heart rate of a pilot is influenced, and further the safety management of flight training is influenced.
Disclosure of Invention
The invention aims to disclose a flight training safety management system based on a vision technology, which solves the problem of how to improve the speed of acquiring an image containing the face of a pilot in a region of interest, thereby improving the timeliness of measuring the heart rate of the pilot.
In order to achieve the above purpose, the present invention provides the following technical solutions:
The invention provides a flight training safety management system based on a vision technology, which comprises a shooting device and an interested region acquisition device;
the shooting device is used for acquiring a color image and an infrared image containing the face of the pilot by adopting an adaptive shooting interval;
The region of interest acquisition device comprises an infrared segmentation module and a color segmentation module;
the infrared segmentation module is used for acquiring a plurality of connected domains consisting of pixel points with pixel values larger than a set pixel value threshold in an infrared image, wherein the connected domains comprise a connected domain A with the largest number of the pixel points;
the color segmentation module is used for acquiring a connected domain B formed by pixel points with the same coordinates as the pixel points in the connected domain A in the color image, acquiring an intermediate region corresponding to the connected domain B, and carrying out image segmentation on the intermediate region to obtain a region of interest in the color image;
obtaining an intermediate region corresponding to the connected domain B includes:
Obtaining maximum value xmax and minimum value xmin of the abscissa and maximum value ymax and minimum value ymin of the ordinate of the pixel points in the connected domain B;
the abscissa x and the ordinate y of the pixel point in the middle region satisfy the following inequality:
， Is a range control coefficient.
Preferably, the heart rate calculating device is further included;
The heart rate calculation device is used for identifying the region of interest obtained by the color segmentation module and obtaining the heart rate of the pilot.
Preferably, the system further comprises a safety management device;
The safety management device comprises a judging module and an early warning module;
the judging module is used for judging whether the heart rate obtained by the heart rate calculating device is larger than a preset heart rate threshold value or not;
the early warning module is used for carrying out early warning on safety management personnel of flight training when the heart rate is greater than a preset heart rate threshold value.
Preferably, the photographing device comprises a photographing interval calculating module and a photographing module;
The shooting interval calculation module is used for calculating the self-adaptive shooting interval by adopting a preset calculation period;
the shooting module is used for acquiring a color image and an infrared image containing the face of the pilot based on the shooting interval.
Preferably, calculating the adaptive photographing interval using a preset calculation period includes:
Shooting interval corresponding to the (h+1) th calculation period The calculation formula of (2) is as follows:
Representing the shooting interval corresponding to the h calculation period, AndRespectively representing the heart rate coefficients of the h-1 th calculation period and the h calculation period,Representing a fixed length of time;
Judging Whether or not it is greater than the maximum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2);
Judging Whether or not it is smaller than the minimum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2).
Preferably, the heart rate coefficient is calculated as follows:
hrU denotes a set of heart rates whose acquisition instants lie within a time range t1, t2, t1 and t2 denote the start instant and the end instant, respectively, of the h-th calculation cycle, nhrU denotes the number of heart rates contained in hrU, i denotes the heart rate in hrU, midhr denotes the median of the heart rates contained in hrU, Represents the maximum value of the heart rate contained in hrU,AndRepresenting the fluctuation parameter and the numerical parameter, respectively.
Preferably, acquiring a color image and an infrared image containing the face of the pilot based on the shooting interval includes:
during the calculation period, color images and infrared images containing the pilot's face are acquired once every other shooting interval,
Preferably, the resolution of the color image and the infrared image are the same.
Preferably, image segmentation is performed on the intermediate region to obtain a region of interest in the color image, including:
Acquiring a set PU of pixel points in the middle area, wherein the pixel points accord with a preset recognition model;
Acquiring a set AU of connected domains formed by pixel points in the PU;
Acquiring a connected domain C with the largest number of pixel points in an AU;
And optimizing the connected domain C to obtain the region of interest.
Preferably, the preset recognition model is as follows:
、 And The values of the red, green and blue components of the pixel point px in the RGB color model are represented, respectively.
The invention has the advantages that:
In the process of safety management of the flight training, not only the color image containing the face of the pilot is acquired, but also the infrared image and the color image are acquired at the same time, then the feature that the face region has obvious distinction between the infrared image and the background is utilized to acquire the connected domain A in the infrared image, then the connected domain B in the color image is acquired based on the connected domain A, and then the region of interest is acquired based on the connected domain B, so that calculation of all pixels in the color image is avoided to acquire the face region, the acquisition speed of the region belonging to the face of the pilot in the color image can be effectively improved, and the heart rate of the pilot can be timely acquired to realize safety management of the flight training.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present 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 first schematic diagram of a vision-based flight training safety management system according to the present invention.
FIG. 2 is a second schematic diagram of a vision-based flight training safety management system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which a person of ordinary skill in the art would obtain without inventive faculty, are within the parameters of the scope of the invention.
The invention provides a flight training safety management system based on a vision technology, which is shown in an embodiment in FIG. 1 and comprises a shooting device and a region-of-interest acquisition device;
the shooting device is used for acquiring a color image and an infrared image containing the face of the pilot by adopting an adaptive shooting interval;
The region of interest acquisition device comprises an infrared segmentation module and a color segmentation module;
the infrared segmentation module is used for acquiring a plurality of connected domains consisting of pixel points with pixel values larger than a set pixel value threshold in an infrared image, wherein the connected domains comprise a connected domain A with the largest number of the pixel points;
the color segmentation module is used for acquiring a connected domain B formed by pixel points with the same coordinates as the pixel points in the connected domain A in the color image, acquiring an intermediate region corresponding to the connected domain B, and carrying out image segmentation on the intermediate region to obtain a region of interest in the color image;
obtaining an intermediate region corresponding to the connected domain B includes:
Obtaining maximum value xmax and minimum value xmin of the abscissa and maximum value ymax and minimum value ymin of the ordinate of the pixel points in the connected domain B;
the abscissa x and the ordinate y of the pixel point in the middle region satisfy the following inequality:
， Is a range control coefficient.
Since the human body has a high temperature, after photographing through the infrared image, the region where the human face is located is easily recognized in the infrared image, but since the temperature is diffused to the surrounding space, the region of the human face cannot be accurately obtained from the infrared image only through a single threshold, and since the infrared image and the color image are photographed at the same time, the positions of the lenses of the device for photographing the infrared image and the device for photographing the color image are different, which also causes that the coordinates of the pixel point in the color image and the pixel point in the infrared image do not completely correspond, but have a certain displacement. Therefore, after the connected domain A is obtained, the coordinates of the pixel points in the connected domain A and the connected domain B in the color image are used for obtaining, but because the pixel points in the connected domain B have parts which do not belong to the face of the pilot, the invention realizes the expansion of the region by adding the range control coefficient when obtaining the middle region, thereby completely containing the parts which belong to the face in the color image in the middle region, thus greatly reducing the number of the pixel points participating in the calculation process in the color image when obtaining the region of interest, and realizing the effective improvement of the obtaining speed of the region of interest.
In the invention, the temperature in the cab is basically fixed, so the range control coefficient does not need to be calculated repeatedly, only needs to be calculated once according to the temperature in the cab at the beginning, and hardly increases extra calculation amount.
In addition, the infrared image only contains information of one channel, so that conversion of a color space is not needed, judgment is directly carried out according to a pixel value threshold, compared with the process of calculating pixels outside an intermediate area in the color image by adopting a threshold segmentation algorithm, the time complexity is much smaller, the calculation amount is much smaller, and therefore, the effective improvement of the speed of acquiring the region of interest in the color image is realized.
In other words, since there may be a small area in the background, which is close to the temperature of the face, the present invention can accurately detect the face area in the infrared image by determining the number of the pixel points included in the obtained connected area.
Preferably, the infrared image is an 8-bit image. At this time, the value of the pixel point in the infrared image ranges from 0 to 255.
Preferably, the set pixel value threshold is determined by:
the integer obtained after rounding the current temperature in the cab is denoted by V;
The set pixel value threshold value for V is Vthre.
The Vthre acquisition process is as follows:
When the ambient temperature is V, an infrared image shooting device is adopted to shoot the face of the pilot, so that an image K is obtained;
and calculating the image K by using a single-threshold segmentation algorithm to obtain a segmentation threshold of the image K, wherein the segmentation threshold is used as a value of Vthre.
The single threshold segmentation algorithm includes otsu algorithm, etc.
The invention can acquire infrared images containing the face of the pilot in each temperature in advance, and then adopts a single-threshold segmentation algorithm to calculate the pixel value threshold value of the infrared images at each temperature.
Preferably, the calculation formula of the range control coefficient is:
row represents the number of lines of the color image, rowstd represents the number of lines set in advance, distrow represents the distance between the center of the lens that captures the infrared image and the center of the lens that captures the color image, diststd represents the distance set in advance, N represents an integer set in advance, The dimensional parameters are represented by a number of dimensions,Representing distance parameters, norl represents normalization of the values in brackets.
In the present invention, the range control coefficient is not fixed but can be changed with a change in resolution of a color image and a change in distance between the center of a lens that captures an infrared image and the center of a lens that captures a color image, specifically, the greater the resolution of a color image, the greater the distance between the center of a lens that captures an infrared image and the center of a lens that captures a color image, so that the range control coefficient is changed adaptively. The human face part of the pilot can be completely contained in the middle area while the pixel points which are contained in the middle area and do not belong to the human face part of the pilot are reduced as much as possible, so that the acquisition efficiency of the region of interest is improved.
Preferably, the number of lines set in advance is 4000, the distance set in advance is 20 cm, and the integer set in advance is 50.
Distrow are given in cm.
Preferably, the size parameter and the distance parameter are 0.4 and 0.6, respectively.
Preferably, as shown in fig. 2, the heart rate calculating device is further included;
The heart rate calculation device is used for identifying the region of interest obtained by the color segmentation module and obtaining the heart rate of the pilot.
Specifically, calculating the heart rate based on the region of interest belongs to the prior art, and the invention is not repeated.
Preferably, the system further comprises a safety management device;
The safety management device comprises a judging module and an early warning module;
the judging module is used for judging whether the heart rate obtained by the heart rate calculating device is larger than a preset heart rate threshold value or not;
the early warning module is used for carrying out early warning on safety management personnel of flight training when the heart rate is greater than a preset heart rate threshold value.
Preferably, the preset heart rate threshold is 130.
Preferably, the pre-warning is carried out to a safety manager of flight training, comprising:
And playing the early warning prompt record to a safety manager of flight training.
After receiving the early warning, the safety manager can communicate with the pilot in training in time so as to ensure the flight safety.
Preferably, the photographing device comprises a photographing interval calculating module and a photographing module;
The shooting interval calculation module is used for calculating the self-adaptive shooting interval by adopting a preset calculation period;
the shooting module is used for acquiring a color image and an infrared image containing the face of the pilot based on the shooting interval.
Preferably, the preset calculation period is 5 minutes.
After each calculation period is finished, the shooting interval of the next calculation period is calculated, and when the shooting interval is calculated, the next calculation period is entered.
Preferably, calculating the adaptive photographing interval using a preset calculation period includes:
Shooting interval corresponding to the (h+1) th calculation period The calculation formula of (2) is as follows:
Representing the shooting interval corresponding to the h calculation period, AndRespectively representing the heart rate coefficients of the h-1 th calculation period and the h calculation period,Representing a fixed length of time;
Judging Whether or not it is greater than the maximum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2);
Judging Whether or not it is smaller than the minimum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2).
The shooting interval of the invention is not fixed, but can be adaptively changed along with the change of heart rate coefficients in the two previous calculation periods, so that the heart rate measurement frequency of a pilot can be reduced and the power consumption of the heart rate measurement can be reduced when the heart rate of the pilot has a decreasing trend or is basically kept stable.
When the heart rate of the pilot tends to increase, the invention shortens the shooting interval, so as to more timely identify the abnormal heart rate of the pilot in training.
Therefore, the change mode of the shooting interval can effectively control the overall power consumption and realize timely finding of heart rate abnormality of the pilot in training.
Preferably, the value of h is equal to or greater than 2, and in this case, the first calculation period corresponds to 1 second of the shooting interval, and the second calculation period corresponds to 1 second of the shooting interval.
Preferably, the fixed length of time is 2 seconds.
Preferably, the maximum value and the minimum value of the photographing interval are 3 seconds and 1 second, respectively.
By controlling the minimum value and the maximum value of the shooting interval, the situation that the shooting interval cannot be timely reduced due to overlarge numerical value when the heart rate of a pilot changes rapidly can be avoided.
Preferably, the heart rate coefficient is calculated as follows:
hrU denotes a set of heart rates whose acquisition instants lie within a time range t1, t2, t1 and t2 denote the start instant and the end instant, respectively, of the h-th calculation cycle, nhrU denotes the number of heart rates contained in hrU, i denotes the heart rate in hrU, midhr denotes the median of the heart rates contained in hrU, Represents the maximum value of the heart rate contained in hrU,AndRepresenting the fluctuation parameter and the numerical parameter, respectively.
The heart rate coefficient is not only calculated based on the data of the type of the median value of the heart rate, but also the fluctuation condition of the heart rate is introduced, so that the numerical value is larger when the median value is larger and the fluctuation range is larger, and the comprehensive representation of the heart rate condition of the pilot in training is realized. The accurate shooting interval is calculated.
Preferably, the fluctuation parameter and the numerical parameter are 0.45 and 0.55, respectively.
Preferably, acquiring a color image and an infrared image containing the face of the pilot based on the shooting interval includes:
during the calculation period, color images and infrared images containing the pilot's face are acquired once every other shooting interval,
Preferably, the resolution of the color image and the infrared image are the same.
Further, the shooting directions and shooting heights of the color image and the infrared image are the same.
The lens for shooting the color image and the lens for shooting the infrared image can be arranged left and right or arranged up and down.
Preferably, image segmentation is performed on the intermediate region to obtain a region of interest in the color image, including:
Acquiring a set PU of pixel points in the middle area, wherein the pixel points accord with a preset recognition model;
Acquiring a set AU of connected domains formed by pixel points in the PU;
Acquiring a connected domain C with the largest number of pixel points in an AU;
And optimizing the connected domain C to obtain the region of interest.
The filtering of the pixel points is performed through the recognition model, so that most of the pixels in the set PU are the pixel points in the face area. And because the middle area still has partial pixels belonging to the background, the pixels in the background also form the connected domain, so the invention eliminates the pixels in the background by the number of the pixels contained in the connected domain, and obtains the pixels only belonging to the area of the human face.
Preferably, the optimizing process is performed on the connected domain C to obtain a region of interest, including:
performing expansion calculation on the connected domain C to obtain a connected domain D;
and (5) performing corrosion operation on the connected domain D to obtain a region of interest.
Specifically, since a cavity may exist in the connected domain C, the cavity can be effectively repaired by the calculation, and a more complete region of interest is obtained.
Preferably, the preset recognition model is as follows:
、 And The values of the red, green and blue components of the pixel point px in the RGB color model are represented, respectively.
The identification model is based on the RGB color model, and the color image is the RGB color model in the initial state, so that the conversion of the color model is avoided, and the pixel points which accord with the pixel value characteristics of the area of the face can be obtained quickly.
In the process of safety management of the flight training, not only the color image containing the face of the pilot is acquired, but also the infrared image and the color image are acquired at the same time, then the feature that the face region has obvious distinction between the infrared image and the background is utilized to acquire the connected domain A in the infrared image, then the connected domain B in the color image is acquired based on the connected domain A, and then the region of interest is acquired based on the connected domain B, so that calculation of all pixels in the color image is avoided to acquire the face region, the acquisition speed of the region belonging to the face of the pilot in the color image can be effectively improved, and the heart rate of the pilot can be timely acquired to realize safety management of the flight training.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (7)
1. The flight training safety management system based on the vision technology is characterized by comprising a shooting device and an interested region acquisition device;
the shooting device is used for acquiring a color image and an infrared image containing the face of the pilot by adopting an adaptive shooting interval;
The region of interest acquisition device comprises an infrared segmentation module and a color segmentation module;
the infrared segmentation module is used for acquiring a plurality of connected domains consisting of pixel points with pixel values larger than a set pixel value threshold in an infrared image, wherein the connected domains comprise a connected domain A with the largest number of the pixel points;
the color segmentation module is used for acquiring a connected domain B formed by pixel points with the same coordinates as the pixel points in the connected domain A in the color image, acquiring an intermediate region corresponding to the connected domain B, and carrying out image segmentation on the intermediate region to obtain a region of interest in the color image;
obtaining an intermediate region corresponding to the connected domain B includes:
Obtaining maximum value xmax and minimum value xmin of the abscissa and maximum value ymax and minimum value ymin of the ordinate of the pixel points in the connected domain B;
the abscissa x and the ordinate y of the pixel point in the middle region satisfy the following inequality:
， is a range control coefficient;
the shooting device comprises a shooting interval calculation module and a shooting module;
The shooting interval calculation module is used for calculating the self-adaptive shooting interval by adopting a preset calculation period;
the shooting module is used for acquiring a color image and an infrared image containing the face of the pilot based on the shooting interval;
Calculating an adaptive photographing interval using a preset calculation period, including:
Shooting interval corresponding to the (h+1) th calculation period The calculation formula of (2) is as follows:
Representing the shooting interval corresponding to the h calculation period, AndRespectively representing the heart rate coefficients of the h-1 th calculation period and the h calculation period,Representing a fixed length of time;
Judging Whether or not it is greater than the maximum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2);
Judging Whether or not it is smaller than the minimum value of the shooting intervalIf yes, useValue of (2) instead ofIs a value of (2);
The heart rate coefficient is calculated as follows:
hrU denotes a set of heart rates whose acquisition instants lie within a time range t1, t2, t1 and t2 denote the start instant and the end instant, respectively, of the h-th calculation cycle, nhrU denotes the number of heart rates contained in hrU, i denotes the heart rate in hrU, midhr denotes the median of the heart rates contained in hrU, Represents the maximum value of the heart rate contained in hrU,AndRepresenting the fluctuation parameter and the numerical parameter, respectively.
2. The vision-based flight training safety management system of claim 1, further comprising a heart rate computing device;
The heart rate calculation device is used for identifying the region of interest obtained by the color segmentation module and obtaining the heart rate of the pilot.
3. A vision-based flight training safety management system as claimed in claim 2, further comprising safety management means;
The safety management device comprises a judging module and an early warning module;
the judging module is used for judging whether the heart rate obtained by the heart rate calculating device is larger than a preset heart rate threshold value or not;
the early warning module is used for carrying out early warning on safety management personnel of flight training when the heart rate is greater than a preset heart rate threshold value.
4. The vision-based flight training safety management system of claim 1, wherein acquiring color images and infrared images containing the pilot's face based on the capture interval comprises:
during the calculation cycle, color images and infrared images containing the pilot's face are acquired every other shooting interval.
5. A vision-based flight training safety management system as claimed in claim 1, wherein the resolution of the colour image and the infra-red image are the same.
6. The vision-based flight training safety management system of claim 1, wherein image segmentation of the intermediate region to obtain a region of interest in the color image comprises:
Acquiring a set PU of pixel points in the middle area, wherein the pixel points accord with a preset recognition model;
Acquiring a set AU of connected domains formed by pixel points in the PU;
Acquiring a connected domain C with the largest number of pixel points in an AU;
And optimizing the connected domain C to obtain the region of interest.
7. The vision-based flight training safety management system of claim 6, wherein the predetermined recognition model is as follows:
、 And The values of the red, green and blue components of the pixel point px in the RGB color model are represented, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667879.9A CN118247494B (en) | 2024-05-28 | 2024-05-28 | Flight training safety management system based on vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667879.9A CN118247494B (en) | 2024-05-28 | 2024-05-28 | Flight training safety management system based on vision technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118247494A CN118247494A (en) | 2024-06-25 |
| CN118247494B true CN118247494B (en) | 2024-08-06 |
Family
ID=91562820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410667879.9A Active CN118247494B (en) | 2024-05-28 | 2024-05-28 | Flight training safety management system based on vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118247494B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114767115A (en) * | 2022-04-28 | 2022-07-22 | 郑州铁路职业技术学院 | Fatigue driving visual detection method and system based on facial multi-modal deep learning |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5294091B2 (en) * | 2010-12-16 | 2013-09-18 | キヤノンマーケティングジャパン株式会社 | Imaging apparatus, control method thereof, and program |
| CN104113691B (en) * | 2014-07-18 | 2015-10-14 | 小米科技有限责任公司 | Image pickup method and device |
| JP7144678B2 (en) * | 2018-08-03 | 2022-09-30 | 日本電信電話株式会社 | Image processing device, image processing method, and image processing program |
| CN116682052B (en) * | 2023-04-20 | 2024-08-23 | 北京北水融智教育科技有限公司 | Teaching service platform based on cloud service |
| CN116151848B (en) * | 2023-04-21 | 2023-08-11 | 深圳市普燃计算机软件科技有限公司 | Gas cylinder quality safety traceability system based on Internet of things |
| CN116916157B (en) * | 2023-06-01 | 2024-10-29 | 仲恺农业工程学院 | Water sampling diving robot control system |
| CN117908031B (en) * | 2024-01-20 | 2024-08-02 | 广东图灵智新技术有限公司 | Autonomous navigation system of robot |
-
2024
- 2024-05-28 CN CN202410667879.9A patent/CN118247494B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114767115A (en) * | 2022-04-28 | 2022-07-22 | 郑州铁路职业技术学院 | Fatigue driving visual detection method and system based on facial multi-modal deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118247494A (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111407245B (en) | Non-contact heart rate and body temperature measuring method based on camera | |
| CN110197169A (en) | A kind of contactless learning state monitoring system and learning state detection method | |
| US20040136579A1 (en) | Method for monitoring wounds | |
| CN113327263B (en) | Image vision-based fish school activity monitoring method | |
| Kurihara et al. | Non-contact heart rate estimation via adaptive rgb/nir signal fusion | |
| CN109147005A (en) | It is a kind of for the adaptive colouring method of infrared image, system, storage medium, terminal | |
| CN112861645A (en) | Infrared camera dim light environment compensation method and device and electronic equipment | |
| Das et al. | Bvpnet: Video-to-bvp signal prediction for remote heart rate estimation | |
| CN118037742B (en) | A multimedia image quality evaluation system and method based on scene recognition | |
| CN110348385B (en) | Living body face recognition method and device | |
| CN116977727A (en) | Image processing-based gas combustion flame real-time monitoring method and system | |
| CN107610675A (en) | A kind of image processing method and device based on dynamic level | |
| Gu et al. | Nonlinear additive model based saliency map weighting strategy for image quality assessment | |
| CN118247494B (en) | Flight training safety management system based on vision technology | |
| CN113810683B (en) | A No-Reference Evaluation Method for Objectively Assessing Underwater Video Quality | |
| CN116843582B (en) | Denoising enhancement system and method of 2CMOS camera based on deep learning | |
| CN118297837B (en) | Infrared simulator virtual image enhancement system based on image processing | |
| Zheng et al. | Hand-over-face occlusion and distance adaptive heart rate detection based on imaging photoplethysmography and pixel distance in online learning | |
| CN109498038B (en) | Autism assessment method and device | |
| CN113657345B (en) | A non-contact heart rate variability feature extraction method based on real application scenarios | |
| CN112950479B (en) | Image gray level region stretching algorithm | |
| CN108939409B (en) | Cloud computing type speed correction method | |
| CN115063848A (en) | Non-contact human face heart rate detection method, system and medium based on photoplethysmography | |
| CN112672072A (en) | Segmented steady video amplification method based on improved Euler amplification | |
| CN119151934B (en) | Extracardiac operation monitoring system and method based on image processing |
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 |