CN114724172A - A kind of infrared imaging human body gesture recognition method and device - Google Patents

Abstract

The invention relates to an infrared imaging human body posture identification method, which comprises the following steps: s1: receiving an image acquired by a thermal imaging sensor, forming a human body thermal distribution image, and obtaining a temperature high point in the human body thermal distribution image; s2: and judging the posture of the human body according to the position of the temperature high point in the human body thermal distribution image and the distribution form of the human body thermal distribution image. The infrared imaging human body posture identification method provided by the invention realizes low-cost human body posture identification and is beneficial to large-area popularization of human body monitoring products.

Description

A kind of infrared imaging human body gesture recognition method and device

technical field

The invention relates to the technical field of human body gesture recognition, in particular to an infrared imaging human body gesture recognition method and device.

Background technique

With the rapid growth of my country's population and economy, the advancement of science and technology, the improvement of people's medical conditions and the improvement of living standards, the life expectancy of the population has been greatly extended. Since 2010, the baby boomers born after the founding of the People's Republic of China have entered the elderly one after another. As of 2014, the total number of elderly people aged 60 and above in my country has reached 212 million, making it the country with the largest total elderly population in the world. As of May 11, 2021, China's population aged 60 and above was 264.02 million, and the aging of the population has further deepened. With the development of the aging population in our country, how to provide timely care and care for the daily life of the elderly has become a social problem that needs to be faced and solved. Due to the aging of the elderly, the functions of various organs in the body degenerate, the balance, coordination and stability of the body are greatly reduced, and the bones are fragile due to osteoporosis. , It is very prone to fall injury accidents. In addition, in terms of the current elderly care situation in our country, the daily life of most elderly people depends on the care of their children, and home care is the main way of care. In life, the children of the elderly often have a lot of their own things to do, and they cannot focus all their energy on caring for the elderly. The elderly often live alone, and it is difficult for children to know the accident at the first time when a fall injury occurs. This is also a problem that is greatly troubled in the current home care life and has a great impact on the normal life of the elderly.

At present, infrared thermal imaging technology has developed rapidly, and the cost of thermal imaging sensors has dropped significantly, which makes it possible for thermal imaging technology to gradually expand from high-end applications to popular civilian fields. It is this change that makes the market multiply Many low-cost, low-resolution thermal imaging sensors have been developed. Therefore, how to make good use of these low-cost, low-resolution thermal imaging sensors to meet the monitoring needs of human body posture has become a problem that needs to be solved.

SUMMARY OF THE INVENTION

Aiming at market demand, the present invention provides an infrared imaging human body gesture recognition method and device which realizes low-cost human body gesture recognition and is beneficial to the large-scale popularization of human body monitoring products.

In order to achieve the purpose of the present invention, the present invention provides an infrared imaging human body gesture recognition method, comprising the following steps:

S1: Receive the image collected by the thermal imaging sensor, form a human body thermal distribution image, and obtain the temperature high points in the human thermal distribution image;

S2: Determine the posture of the human body according to the position of the high temperature point in the human body thermal distribution image and the distribution shape of the human body thermal distribution image.

Preferably, in step S2: when the thermal distribution image of the human body is vertically distributed and the temperature high point is located at the upper part of the thermal distribution image of the human body, it is determined that the human body is in an upright state;

When the thermal distribution image of the human body has a horizontally long distribution and the high temperature point is located at the left end or the right end of the thermal distribution image of the human body, it is determined that the human body is in a lying state.

Preferably, step S2 further includes the following sub-steps:

S21: Determine the vertical distance between the upper and lower endpoints of the human body thermal distribution image as its height value, and determine the horizontal distance between the left and right endpoints of the human body thermal distribution image as its width value;

S22: Calculate the ratio of the height value to the width value of the human body thermal distribution image;

S23: According to the ratio of the height value and the width value of the human body thermal distribution image, it is determined that the human body thermal distribution image is vertically distributed or horizontally distributed.

Preferably, step S2 further includes the following sub-steps:

S221: Obtain one or more temperature high points from the human body thermal distribution image;

S222: Determine the distribution shape of the human body thermal distribution image according to the relative positional relationship between the high temperature point and the low temperature area.

Preferably, step S1 further includes the following sub-steps:

S11: Collect the spatial temperature distribution through a thermal imaging sensor, and eliminate sudden temperature fluctuations by smoothing multiple frames of data to form a stable temperature distribution image;

S12: adopt the differential algorithm for the multi-frame stable temperature distribution images, eliminate the fixed constant temperature objects, and form the protrusion temperature distribution images;

S13: Calculate the temperature distribution image surface of the protrusions, and remove the temperature distribution images of protrusions that are lower than the preset value in the image surface;

S14: Scan the temperature distribution image of the protrusion, find out the highest temperature point with the temperature value within the preset temperature range, that is, the temperature high point, and then take the temperature high point as the center, within the preset temperature range Gradually reduce the temperature value to form a thermal distribution contour line, and obtain a human body thermal distribution image according to the thermal distribution contour line.

Preferably, described step S14 further comprises sub-step:

S141: Find the high temperature point, take the high temperature point as the center point, and obtain temperature values of multiple adjacent points around the high temperature point, if the temperature values of the adjacent points are within a preset temperature range , the adjacent point is marked as a human body position point, otherwise it is marked as a non-human body position point;

S142: Taking the marked human body position point as the center point, obtain temperature values of multiple unmarked adjacent points around the center point, and if the temperature values of the adjacent points are within a preset temperature range, set the adjacent points The point is marked as a human body position point, otherwise it is marked as a non-human body position point;

S143: Repeat step S142 until the temperature values of all unmarked adjacent points around the center point are not within the preset temperature range; or repeat step S142 until all data points of the protrusion temperature distribution image are traversed;

S144: Connect all continuous human body position points including the high temperature points to obtain a human body thermal distribution image.

Preferably, the present invention also provides an infrared imaging human body gesture recognition device, comprising:

Image analysis module: receive the image collected by the thermal imaging sensor, form a human body thermal distribution image, and obtain the temperature high points in the human thermal distribution image;

Attitude judgment module: according to the temperature high point obtained by the image processing module, and according to the position of the temperature high point in the human body thermal distribution image and the distribution shape of the thermal distribution image, the human body attitude is judged.

Preferably, in the attitude judgment module:

When the thermal distribution image of the human body is vertically distributed and the temperature high point is located in the upper part of the thermal distribution image of the human body, it is determined that the human body is in an upright state;

When the thermal distribution image of the human body has a horizontally long distribution and the high temperature point is located at the left end or the right end of the thermal distribution image of the human body, it is determined that the human body is in a lying state.

Preferably, the posture judging module further comprises a first posture judging sub-module 1, a first posture judging sub-module 2 and a first posture judging sub-module 3:

The first attitude judgment sub-module 1: determine the vertical distance of the upper and lower endpoints of the human body thermal distribution image as its height value, and determine the horizontal distance between the left and right endpoints of the human body thermal distribution image as its width value;

The first attitude judgment sub-module 2: calculate the ratio of the height value to the width value of the human body thermal distribution image;

The first attitude determination sub-module 3: according to the ratio of the height value to the width value of the human body thermal distribution image, it is judged that the human body thermal distribution image is vertically distributed or horizontally distributed.

Preferably, the posture judging module further includes a second posture judging sub-module 1 and a second posture judging sub-module 2:

The second attitude judgment sub-module 1: obtain one or more temperature high points from the human body thermal distribution image;

The second attitude determination sub-module 2: determine the distribution shape of the human body thermal distribution image according to the relative positional relationship between the temperature high point and the low temperature area.

The beneficial effects of the present invention are as follows: the infrared imaging human body posture recognition method and device provided by the present invention realizes low-cost human body posture recognition, which is beneficial to the large-scale promotion of human body monitoring products.

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent from a more detailed description of the preferred embodiments of the present invention shown in the accompanying drawings. The same reference numerals refer to the same parts throughout the drawings, and the drawings have not been intentionally drawn to scale, the emphasis being placed on illustrating the subject matter of the present invention.

1 is a specific flowchart of a method and device for infrared imaging human body gesture recognition provided by an embodiment of the present invention;

2 is a specific flowchart of step S1 in an infrared imaging human body gesture recognition method and device provided by an embodiment of the present invention;

3 is a schematic diagram of a human body thermal contour distribution diagram provided by an embodiment of the present invention;

4 is a schematic diagram of a first real-time human body gesture recognition provided by an embodiment of the present invention;

5 is a schematic diagram of a second real-time human gesture recognition provided by an embodiment of the present invention;

Detailed ways

In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings.

It should be noted that when an element is referred to as being "connected" to another element, it can be directly connected to and integrated with the other element, or intervening elements may also be present. The terms "installed," "one end," "the other end," and similar expressions used herein are for illustrative purposes only.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this document belongs. The terminology used in the specification herein is for the purpose of describing specific embodiments only and is not intended to limit the present invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Referring to FIGS. 1-5, an embodiment of the present invention provides a low-cost infrared imaging human body gesture recognition method, including the following steps:

S1: Receive the image collected by the thermal imaging sensor, form a human body thermal distribution image, and obtain the temperature high points in the human thermal distribution image;

S2: Determine the posture of the human body according to the position of the high temperature point in the human body thermal distribution image and the distribution shape of the human body thermal distribution image.

Please refer to FIGS. 1-5 , the infrared imaging human body gesture recognition method provided by the present invention, the specific recognition method is as follows: first, data is collected from the corresponding area (bathroom, bedroom, kitchen, etc.) through the thermal imaging sensor, and then the collected data is collected. The corresponding sequence is arranged and corresponding images are formed, and the spatial temperature distribution in the area can be known through the collected images, and then the sudden temperature fluctuations are eliminated through the smoothing operation of multiple frames of data to form a stable temperature distribution image, and then use The difference between two frames of stable temperature distribution images, eliminate fixed constant temperature objects, form a projection temperature distribution image, and then calculate multiple image surfaces in the projection temperature distribution image, and remove the image surfaces that are lower than the preset value (not conforming to the preset value). Then, scan the temperature distribution image of the protrusion to find the highest temperature point (high temperature point) that matches the human body temperature, and then take the high temperature point as the center and surround the high temperature point. point and obtain multiple adjacent points adjacent to the high temperature point, and judge the multiple adjacent points. When the adjacent point is within the preset temperature range (the temperature range that conforms to the human body temperature), mark the adjacent point, And mark it as a human body position point (the position of the body part of the human body), when the adjacent point is not within the preset temperature range, mark the adjacent point as a non-human body position point, and then take the marked human body position point as the center, and obtain the surrounding points. The temperature values of multiple unmarked adjacent points of the marked human body position points are judged again to determine whether they are human body position points. The specific judgment process is the same as the above judgment process. When the marked human body position points are When the temperature value of the center, and all the surrounding unmarked adjacent points are not within the preset temperature range, the temperature value acquisition process ends, and then all the continuous human body position points including the high temperature point are connected to form a human body thermal distribution image; Or when traversing the temperature data points in the temperature distribution image of the protrusion, all continuous human body position points including high temperature points are connected to form a human body thermal distribution image. (The high temperature value is specifically the temperature value of the upper half of the human body)

After the thermal distribution contour line is drawn, determine the specific position of the temperature high point in the thermal distribution contour line, and judge the posture of the human body according to the thermal distribution image of the human body. The specific judgment is as follows:

When the thermal distribution image of the human body is vertically distributed and the high temperature point is located in the upper part of the thermal distribution image of the human body, it is determined that the human body is in an upright state;

When the thermal distribution image of the human body is horizontally distributed and the high temperature point is located at the left or right end of the thermal distribution image of the human body, it is determined that the human body is in a lying state;

At the same time, the present invention can also judge the posture of the human body according to the specific ratio of the length and width of the thermal distribution image of the human body, and the specific judgment is as follows:

Determine the vertical distance of the upper and lower end points of the human body thermal distribution image as its height value, determine the horizontal distance between the left and right endpoints of the human body thermal distribution image as its width value, and calculate the ratio of the height value to the width value of the human body thermal distribution image, according to The ratio of the height value to the width value of the thermal distribution image of the human body determines whether the thermal distribution image of the human body has a vertical distribution (in an upright state, a low posture or a bent state, etc.) or a horizontal distribution (recumbent state). The relative positional relationship between the temperature high point and the temperature low point of the thermal distribution image is used to judge the posture of the human body.

The beneficial effects of the present invention are as follows: according to the temperature distribution image of the protrusion, find the highest temperature point close to the human body temperature, and then take the temperature high point as the center, gradually reduce the temperature threshold appropriately, and form a contour line of thermal distribution. The human body posture can be judged by the specific shape of the thermal distribution contour, the relative position between the temperature high point and the temperature low point, and the ratio of the length and width in the human body thermal distribution image, realizing low-cost human posture recognition. , which is beneficial to the large-scale promotion of human monitoring products.

Please refer to FIG. 1, in a preferred embodiment, in step S2:

When the thermal distribution image of the human body is vertically distributed and the high temperature point is located in the upper part of the thermal distribution image of the human body, it is determined that the human body is in an upright state;

When the thermal distribution image of the human body has a horizontally long distribution and the high temperature point is located at the left end or the right end of the thermal distribution image of the human body, it is determined that the human body is in a lying state.

Please refer to FIG. 1, in a preferred embodiment, step S2 further includes the following sub-steps:

S21: Determine the vertical distance between the upper and lower endpoints of the human body thermal distribution image as its height value, and determine the horizontal distance between the left and right endpoints of the human body thermal distribution image as its width value;

S22: Calculate the ratio of the height value to the width value of the human body thermal distribution image;

S23: According to the ratio of the height value and the width value of the human body thermal distribution image, it is determined that the human body thermal distribution image is vertically distributed or horizontally distributed.

It is mainly judged according to the ratio of the specific length and width of the formed image, that is to say, the contour formed by the contour line connection,

For example: set the height value to h and the width value to d, when the ratio of the height value to the width value is t, t=h/d:

When t>1.5, it is determined that the human body is in an upright state;

When 0.75<t<1.5, it is determined that the human body is in a low posture state;

When t<0.75, it is determined that the human body is in a lying state; (this embodiment is only for illustration and does not represent specific values, and the ratio of the length and width of the image can be adjusted, mainly to improve the accuracy of the human body to determine posture )

Please refer to Fig. 1-3, in a further preferred embodiment, step S2 further includes the following sub-steps:

S221: Obtain one or more temperature high points from the human body thermal distribution image;

S222: Determine the distribution shape of the human body thermal distribution image according to the relative positional relationship between the high temperature point and the low temperature area.

First determine the high temperature point close to the human body temperature, which can be one or more, and then obtain the low temperature area that matches the human body from the image (the area formed by multiple low temperature points, assuming that the high temperature points are 37, 37.5, 37.4, the temperature data of the low temperature area are 35.5, 36.5, 36, 6.7), and then judge the human body posture according to the specific positions of the high temperature and low temperature areas in the human body thermal distribution image. This judgment method can be more accurate.

The specific judgment steps are:

When the high temperature point is in the upper part of the human body thermal distribution image, and the low temperature area is in the lower part of the human body thermal distribution image, it can be determined that the human body is in an upright state;

When the high temperature point is in the lower part of the human body thermal distribution image, and the low temperature area is in the lower part of the human body thermal distribution image, it can be determined that the human body is in a lying state;

When the high temperature point is in the middle of the human body thermal distribution image, and the low temperature area is in the lower part of the human thermal distribution image, it can be determined that the human body is in a low posture state. The low-stance state is the state of bowing the head or bending over.

Please refer to Fig. 1-3, in a further preferred embodiment, step S1 further includes the following sub-steps:

S11: Collect the spatial temperature distribution through a thermal imaging sensor, and eliminate sudden temperature fluctuations by smoothing multiple frames of data to form a stable temperature distribution image;

S12: adopt the differential algorithm for the multi-frame stable temperature distribution images, eliminate the fixed constant temperature objects, and form the protrusion temperature distribution images;

S13: Calculate the temperature distribution image surface of the protrusions, and remove the temperature distribution images of protrusions that are lower than the preset value in the image surface;

The preset value is mainly a set value of the overall outline of the human body, which can be adjusted. The image surface lower than the preset value is mainly the image outline of the non-human body and will be eliminated. The temperature distribution image surface of the protrusion is mainly in the shape of the human body. Image outline.

S14: Scan the temperature distribution image of the protrusion to find out the highest temperature point with the temperature value within the preset temperature range, that is, the temperature high point, and then take the temperature high point as the center, and gradually reduce the temperature value within the preset temperature range to form Thermal distribution contour line, according to the thermal distribution contour line to obtain the human body thermal distribution image.

The specific algorithm name is moving average:

That is, the variable v is recorded as vt at time t, and θt is the value of variable v at time t, that is, vt=θt. After using the moving average model, the update formula of vt is as follows:

vt=β·vt-1+(1-β)·θt (1)

In the above formula, β∈[0,1]

To remove bias at the start, divide vt by (1-βt) to correct the estimate of the mean.

The update formulas of vt and v_biasedt are as follows:

vt=β·vt-1+(1-β)·θt

v_biasedt=vt1-βt (2)

Using formula (2) to calculate all temperature points, the mutation data can be eliminated. When β=0.9, it is roughly equal to the average of the past 10 theta values; if β=0.99, it is roughly equal to the past 100 Theta values are averaged.

The image formed by the smoothed temperature data can be considered as a 32x32 matrix, in which the data is the temperature. The fixed object is between two frames of data, and the temperature does not change much. Through matrix subtraction, there is no change in the data. They will cancel each other out, and the changed data will be highlighted. By setting the appropriate threshold, the data that is too small will be zeroed, so that the background can be cleared. The purpose of clearing the background is to remove the distraction of static objects such as tables, chairs, benches, etc. After clearing the background data, the rainbow image is used to form a pseudo-color image. In the specific object temperature distribution map, the low temperature area will be displayed in blue, and the high temperature area will be displayed in red, which highlights the outline of the human body and can better identify the human body. Posture judgment.

Please refer to Fig. 3, in a preferred embodiment, step S14 further comprises sub-steps:

S141: Find the temperature high point, take the temperature high point as the center point, obtain the temperature values of multiple adjacent points around the temperature high point, and mark the adjacent points if the temperature values of the adjacent points are within a preset temperature range It is a human body position point, otherwise it is marked as a non-human body position point;

S142: Taking the marked human body position point as the center point, obtain the temperature values of a plurality of unmarked adjacent points around the center point, and if the temperature values of the adjacent points are within the preset temperature range, mark the adjacent point as the human body position point , otherwise it is marked as a non-human body position point;

S143: Repeat step S142 until the temperature values of all unmarked adjacent points around the center point are not within the preset temperature range; or repeat step S142 until all data points of the protrusion temperature distribution image are traversed;

S144: Connect all continuous human body position points including high temperature points to obtain a human body thermal distribution image.

Specific examples are:

First, extract the temperature high point from the data that matches the human body temperature value (assuming the human body temperature value is 35-37°, and the temperature high point is 36.9°), then take the temperature high point as the center, and obtain the temperature near the temperature high point Numerical value, when the temperature value of the adjacent point is within the preset temperature range (assuming the preset temperature range is 35-37°), the adjacent point that meets the conditions will be marked as the human body position point (the temperature point that conforms to the human body temperature). The adjacent points of the condition are marked as non-human body position points (belonging to the temperature value of a thermostatic object or other non-human body), and then take the body position point as the center, and judge the temperature value of the adjacent point around the body position point. When the temperature value of the adjacent point is Within the preset temperature range, determine that the adjacent point is a human body position point, and then repeat the judgment of the unmarked adjacent point. When the unmarked adjacent points do not conform to the human body temperature value, the judgment can be made according to the image and the adjacent points. It is determined that the points that do not meet the human body temperature value are non-human body position points, and then the adjacent points that meet the human body temperature value are connected to the high temperature points (specifically, continuous human body position points. When determining the adjacent points, there may be more than one point. image contours, such as two human bodies, or temperature image contours of one person and multiple non-human bodies, etc., determine that the contours of the human body image are mainly formed by the connection of multiple consecutive adjacent points and high temperature points);

When there are multiple image contours, when judging the adjacent points, there will be two images, and the two images are discontinuous, then the main judgment condition is mainly based on the continuous adjacent points formed with the high temperature point ( Human body temperature value), and the images of adjacent points that do not conform to the human body temperature value are removed accordingly.

Or repeatedly perform the judgment of unmarked adjacent points, and judge each temperature point in the image, mark the temperature points that belong to the preset temperature range, and exclude the temperature points that do not belong to the preset temperature range. The temperature points within the temperature range are connected to form the outline of the human body image;

It is more convenient and simpler to recognize the human body image by judging the human body contour through the above two methods.

(There may be some errors when taking the value of adjacent points, such as the influence of ambient temperature, and the specific value can be preset)

For example: when the selected adjacent point is 22-25°, the temperature value of the adjacent point selected at this time does not conform to the temperature value of the human body, so it can be excluded.

The specific steps are as follows: First, find the maximum value close to the human body temperature in the data center, which can be completed by simply traversing 1024 data. The specific value process is as follows:

Determine the maximum value at the Max_x, Max_y coordinates, denoted as x, y.

Then it is considered that the range of t∈[max-n,max] is the reasonable temperature of the human body,

Compare eight points around x, y (X+1, Y)(X+1, Y+1)(X-1, Y)(X-1, Y+1)(X, Y-1)(X, Whether Y+1)(X-1, Y-1)(X+1, Y-1) conforms to t, if it conforms to mark this point, then take this point as the center, check the surrounding 8 points, until all points are Marked or no points matching t, the set of all marked points is a temperature contour plane, different n, different contour planes can be made, that is, starting from a point on the area, by visiting a known point The 8 adjacent points of , traverse all the data points in the region under the premise of conforming to t ∈ [max-n, max].

Please refer to Figures 1-5, in a further preferred embodiment, the present invention also provides an infrared imaging human body gesture recognition device, including:

Image analysis module: receive the image collected by the thermal imaging sensor, form a human body thermal distribution image, and obtain the temperature high points in the human thermal distribution image;

Attitude judgment module: According to the temperature high point obtained by the image processing module, and according to the position of the temperature high point in the human body thermal distribution image and the distribution shape of the thermal distribution image, the human body posture is judged.

Please refer to Figures 1-5, in a preferred embodiment, in the attitude judgment module:

When the thermal distribution image of the human body is vertically distributed and the high temperature point is located in the upper part of the thermal distribution image of the human body, it is determined that the human body is in an upright state;

When the thermal distribution image of the human body has a horizontally long distribution and the high temperature point is located at the left end or the right end of the thermal distribution image of the human body, it is determined that the human body is in a lying state.

Please refer to Figures 1-5, in a preferred embodiment, the attitude judgment module further includes a first attitude judgment sub-module:

The first sub-module 1: determine the vertical distance of the upper and lower endpoints of the human body thermal distribution image as its height value, and determine the horizontal distance between the left and right endpoints of the human body thermal distribution image as its width value;

The first sub-module 2: Calculate the ratio of the height value to the width value of the human body thermal distribution image;

The first sub-module 3: According to the ratio of the height value and the width value of the human body thermal distribution image, it is judged that the human body thermal distribution image is vertically distributed or horizontally distributed.

Please refer to Figures 1-5, in a preferred embodiment, the attitude judgment module further includes a second attitude judgment sub-module:

The second sub-module 1: obtain one or more temperature high points from the human body thermal distribution image;

The second sub-module 2: Determine the distribution shape of the human body thermal distribution image according to the relative positional relationship between the high temperature point and the low temperature area.

The beneficial effects of the present invention are as follows: the present invention provides an infrared imaging human body posture recognition method and device which realizes low-cost human body posture recognition and is beneficial to the large-scale popularization of human body monitoring products.

In this specification, unless otherwise expressly stated and defined, a first feature "on" or "under" a second feature may be in direct contact with the first and second features, or indirectly through an intermediary between the first and second features touch. Also, the first feature being "above", "over" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is level higher than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature has a lower level than the second feature.

In the description of this specification, description with reference to the terms "preferred embodiment", "further embodiment", "other embodiment" or "specific example" etc. means specific features, structures, structures, A material or feature is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations to the present application. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (10)

1. An infrared imaging human body posture recognition method is characterized by comprising the following steps:

s1: receiving an image acquired by a thermal imaging sensor, forming a human body thermal distribution image, and obtaining a temperature high point in the human body thermal distribution image;

s2: and judging the posture of the human body according to the position of the temperature high point in the human body thermal distribution image and the distribution form of the human body thermal distribution image.

2. The infrared imaging human body posture identifying method as claimed in claim 1, characterized in that in step S2:

when the human body thermal distribution image is vertically long and the temperature high point is positioned at the upper part of the human body thermal distribution image, the human body is judged to be in an upright state;

when the human body thermal distribution image is in transverse long distribution and the temperature high point is positioned at the left end or the right end of the human body thermal distribution image, the human body is judged to be in a lying state.

3. The infrared imaging human body posture identifying method as claimed in claim 2, characterized in that the step S2 further comprises the following sub-steps:

s21: determining the vertical distance between the upper end point and the lower end point of the human body thermal distribution image as the height value of the vertical distance, and determining the horizontal distance between the left end point and the right end point of the human body thermal distribution image as the width value of the horizontal distance;

s22: calculating the ratio of the height value to the width value of the human body thermal distribution image;

s23: and judging whether the human body thermal distribution image is vertically or horizontally distributed according to the ratio of the height value to the width value of the human body thermal distribution image.

4. The infrared imaging human body posture identifying method as claimed in claim 1, characterized in that the step S2 further comprises the following sub-steps:

s221: acquiring one or more temperature high points from a human body thermal distribution image;

s222: and determining the distribution form of the human body thermal distribution image according to the relative position relationship between the temperature high point and the temperature low area.

5. The infrared imaging human body posture identifying method as claimed in claim 1, characterized in that the step S1 further includes the sub-steps of:

s11: acquiring the spatial temperature distribution condition through a thermal imaging sensor, and eliminating abrupt temperature fluctuation through the smooth operation of multi-frame data to form a stable temperature distribution image;

s12: eliminating a fixed constant-temperature object by adopting a difference algorithm on a plurality of frames of stable temperature distribution images to form a protrusion temperature distribution image;

s13: calculating a temperature distribution image surface of the protrusion, and eliminating the temperature distribution image of the protrusion in the image surface, which is lower than a preset value;

s14: scanning the temperature distribution image of the protrusion, finding out the highest temperature point of the temperature value in a preset temperature range, namely the temperature high point, then gradually reducing the temperature value in the preset temperature range by taking the temperature high point as the center to form a thermal distribution contour line, and obtaining the thermal distribution image of the human body according to the thermal distribution contour line.

6. The infrared imaging human body posture identifying method as claimed in claim 5, characterized in that said step S14 further includes the sub-steps of:

s141: finding out the temperature high point, taking the temperature high point as a central point, obtaining temperature values of a plurality of adjacent points surrounding the temperature high point, marking the adjacent points as human body position points if the temperature values of the adjacent points are within a preset temperature range, and otherwise marking the adjacent points as non-human body position points;

s142: taking the marked human body position point as a central point, acquiring temperature values of a plurality of unmarked adjacent points surrounding the central point, marking the adjacent points as human body position points if the temperature values of the adjacent points are within a preset temperature range, and otherwise marking the adjacent points as non-human body position points;

s143: repeating the step S142 until the temperature values of all the unmarked adjacent points surrounding the central point are not in the preset temperature range; or repeating step S142 until all data points of the protrusion temperature distribution image are traversed;

s144: and connecting all the continuous human body position points containing the temperature high points to obtain a human body thermal distribution image.

7. An infrared imaging human body posture recognition device, comprising:

an image analysis module: receiving an image acquired by a thermal imaging sensor, forming a human body thermal distribution image, and obtaining a temperature high point in the human body thermal distribution image;

an attitude judgment module: and judging the posture of the human body according to the temperature high points obtained by the image processing module, the positions of the temperature high points in the human body thermal distribution image and the distribution form of the thermal distribution image.

8. The infrared imaging human body gesture recognition apparatus of claim 7, wherein in the gesture determination module:

when the human body thermal distribution image is vertically long and the temperature high point is positioned at the upper part of the human body thermal distribution image, the human body is judged to be in an upright state;

when the human body thermal distribution image is in transverse long distribution and the temperature high point is positioned at the left end or the right end of the human body thermal distribution image, the human body is judged to be in a lying state.

9. The infrared imaging human body posture identifying device of claim 7, wherein the posture judging module further comprises a first posture judging submodule one, a second posture judging submodule and a third posture judging submodule:

the first posture judgment submodule I: determining the vertical distance between the upper end point and the lower end point of the human body thermal distribution image as the height value of the vertical distance, and determining the horizontal distance between the left end point and the right end point of the human body thermal distribution image as the width value of the horizontal distance;

the second posture judgment submodule is: calculating the ratio of the height value to the width value of the human body thermal distribution image;

the first posture judgment submodule is three: and judging whether the human body thermal distribution image is vertically or horizontally distributed according to the ratio of the height value to the width value of the human body thermal distribution image.

10. The infrared imaging human body posture identifying device of claim 7, characterized in that the posture judging module further comprises a first second posture judging submodule and a second posture judging submodule:

the second posture judgment submodule I: acquiring one or more temperature high points from a human body thermal distribution image;

the second posture judgment submodule is two: and determining the distribution form of the human body thermal distribution image according to the relative position relationship between the temperature high point and the temperature low area.

Images