CN117689709A - Height detection method, system, equipment and medium based on depth image - Google Patents
Height detection method, system, equipment and medium based on depth image Download PDFInfo
- Publication number
- CN117689709A CN117689709A CN202410154607.9A CN202410154607A CN117689709A CN 117689709 A CN117689709 A CN 117689709A CN 202410154607 A CN202410154607 A CN 202410154607A CN 117689709 A CN117689709 A CN 117689709A
- Authority
- CN
- China
- Prior art keywords
- depth
- frame
- height
- corrected
- coordinates
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012937 correction Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000009434 installation Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000007493 shaping process Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 description 8
- 241000287107 Passer Species 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of depth image processing, in particular to a height detection method, a height detection system, height detection equipment and a height detection medium based on a depth image, which comprise the following steps: installing a depth camera, and recording the installation height H1 of the depth camera; selecting a frame depth image, acquiring a central position coordinate of a detection frame, and carrying out distortion correction on the central position coordinate to obtain a pixel coordinate; obtaining a corrected detection frame based on the corrected pixel coordinates, obtaining each pixel point and a depth value S thereof in the corrected detection frame, judging the depth value S of each pixel point, selecting the first N minimum depth values S which are not zero, and calculating to obtain a total depth value SUM; calculating an average depth valueThe method comprises the steps of carrying out a first treatment on the surface of the Calculating a head depth value S1 by scaling the coefficient; calculating a head height H; the invention combines depth image and depth value analysisAnd dynamically selecting the minimum depth value in the target area to calculate the height and the position, thereby effectively improving the accuracy and the reliability of height detection and judgment in a complex scene.
Description
Technical Field
The invention relates to the technical field of depth image processing, in particular to a height detection method, system, equipment and medium based on a depth image.
Background
In modern society, the management and safety monitoring of the gate passageway are increasingly important, and the application of height detection in riding environment is also very wide, so that the height of a human body or an object passing through the gate passageway needs to be accurately measured; conventional methods are often based on sensor measurements, such as infrared or ultrasonic sensors, which can measure the distance between an object and the sensor, but are easily limited in complex scenarios.
The chinese patent with publication number CN110306463B discloses a gate for measuring height, comprising a gate body, a height measuring module, wherein the height measuring module comprises an infrared emitter, an infrared camera, a calculating unit and a fine tuning knob, the infrared emitter emits a beam of vertical infrared rays into a gate channel, the infrared camera can receive the infrared rays reflected back after the infrared emitter emits, the calculating unit finds the head position of the pedestrian through an image processing algorithm and converts the head position into the height of the pedestrian, thereby detecting the height of the pedestrian.
Under the condition of large passenger flow, the method is difficult to distinguish when a plurality of human bodies or objects pass through the channel at the same time, and the real-time performance of height measurement cannot be ensured; but in recent years, due to the development of machine vision technology, three-dimensional information of objects in a scene can be acquired through a depth sensor and an image processing algorithm, and new possibilities are provided for solving the problems.
The automatic height detection method and system based on depth camera shooting of Chinese patent with publication number CN111067530B or the automatic height detection method based on depth camera shooting and height threshold pixel calibration of Chinese patent with publication number CN111079589B are disclosed for height detection through a depth image acquisition module and an image processing module.
However, in the height detection method, the projection size of the human body or the object in the image is ignored, and the projection size may be affected by factors such as angles, light rays, shielding and the like, so that the accuracy of height estimation is affected.
Disclosure of Invention
The invention aims to provide a height detection method, a system, equipment and a medium based on a depth image, which dynamically select a minimum depth value in a target area to calculate the height and the position by combining the depth image and the depth value analysis, and can adaptively adapt to factors such as light change, shielding and the like under different environments, thereby improving the accuracy and the reliability of height detection judgment in a complex scene.
In order to achieve the above purpose, the present invention provides the following technical solutions:
in a first aspect, the present invention provides a height detection method based on a depth image, including the steps of:
s1, a depth camera collects video streams when passengers enter and exit a gate area, a plurality of frame depth images are obtained, and the installation height H1 of the depth camera is recorded;
s2, selecting a frame depth image, detecting a person or an object in the frame depth image, generating an independent detection frame for each individual person or object, acquiring a central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and a depth camera internal reference matrix;
s3, based on the step S2, obtaining a corrected detection frame based on corrected pixel coordinates, obtaining each pixel point and a depth value S thereof in the corrected detection frame, judging the size of the depth value S of each pixel point, selecting the first N minimum depth values S which are not zero, and calculating to obtain a total depth value SUM;
s4, calculating an average depth value based on the step S3，/>=SUM/N；
S5, based on the step S4, calculating head depth values S1, S1 = by scaling coefficientsX (L/P), where L is the depth value and P is the pixel value of the frame depth image;
s6, calculating the head height H, wherein H=H2-S1/10 based on the step S5;
s7, sequentially selecting the frame depth images, repeating the steps S2-S6 to obtain a plurality of head heights H of the same person or object in the plurality of frame depth images, and averaging the plurality of head heights H to obtain the final head height.
Preferably, the method for acquiring the center position coordinate of each detection frame comprises the following steps: selecting two points coordinates (x 1, y 1) and (x 2, y 2) of the diagonal of the detection frame, and then the central position coordinates are as follows:
wherein,x-axis coordinate as center position coordinate, +.>The Y-axis coordinate, which is the center position coordinate.
Further, the specific method for performing distortion correction on the center position coordinate and calculating the corrected pixel coordinate through the center position coordinate after distortion correction and the depth camera internal reference matrix is as follows:
s21, solving the central position coordinates by adopting an motionless point iteration method to obtain the central position coordinates after distortion correction) Wherein, the fixed point iteration method selects +.>Conversion to->In the form of (2), the iteration convergence condition to be satisfied is: />；
S22, based on the step S1, correcting the central position coordinate through distortion) Calculating corrected pixel coordinates with depth camera reference matrix (++>，/>) The following are provided:
wherein,、/>、/>、/>is a matrix point of the camera reference matrix.
Preferably, the method further comprises the following steps: obtaining depth values of corrected pixel coordinatesAccording to the corrected pixel coordinates (+)>，/>) Calculating three-dimensional coordinates of camera internal reference matrix (I)>)；
Wherein,the value of (2) is the depth value of the corrected pixel coordinate +.>。
Further, the specific method of step S3 is as follows:
s31, initializing a shaping vector Depths, acquiring each pixel point in the corrected detection frame and a depth value S thereof, and adding the pixel points into the shaping vector Depths if the depth value S is not zero;
s32, using a partial ordering method to move the first N minimum depth values in the shaping vector Depths to the front part of the vector
And limiting the number of the containable elements in the shaping vector Depths to N through a resize function.
In a second aspect, the present invention provides a depth image-based height detection system for implementing the detection method according to any one of the first aspects, including:
the depth camera is used for collecting video streams when passengers enter and exit the gate area to obtain a plurality of frame depth images;
the detection frame generation unit is used for selecting one frame depth image, detecting people or objects in the frame depth image and generating an independent detection frame for each individual person or object;
the coordinate correction unit is used for acquiring the central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and the depth camera internal reference matrix;
a coordinate conversion unit for converting the two-dimensional pixel coordinates into three-dimensional coordinates;
the image processing unit obtains a corrected detection frame based on the corrected pixel coordinates, obtains each pixel point in the corrected detection frame and a depth value S thereof, and calculates the head height H.
In a third aspect, the present invention provides an electronic device comprising a processor, a memory and a control program stored on the memory and operable on the processor, the control program when executed by the processor implementing a depth image based height detection method as in any one of the first aspects.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the depth image based height detection method according to any one of the first aspects.
The beneficial effects of the invention are as follows:
1) According to the method and the device, by combining the depth image and the depth value analysis, the minimum depth value in the target area is dynamically selected to calculate the height and the position, and the factors such as light change and shielding can be adaptively adapted under different environments, so that the accuracy and the reliability of height detection and judgment in a complex scene are improved.
2) According to the method, the coordinate is subjected to distortion correction before the pixel point is selected, so that the influence of lens distortion on height measurement is effectively reduced, and the accuracy and the stability of measurement are improved; according to the method and the device, through a partial ordering method and vector operation, the minimum N depth values can be extracted and calculated in the region rapidly, and the rapid height position measurement is facilitated.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of height measurement of a gate according to the present invention;
FIG. 2 is a schematic view of the height of the inspection head of the present invention;
FIG. 3 is a schematic diagram of the selected human peak detection of the present invention;
FIG. 4 is a schematic diagram of head depth value detection according to the present invention;
FIG. 5 is a flow chart of height detection according to the present invention.
Detailed Description
Example 1
As shown in fig. 1-5, the invention provides a height detection method based on depth images, in this embodiment 1, the method includes the following steps:
s1, a depth camera collects video streams when passengers enter and exit a gate area, a plurality of frame depth images are obtained, and the installation height H1 of the depth camera is recorded.
As shown in fig. 2, the highest point from the detected object is obtained at high altitude, and for the peer, the highest point is concentrated on the shoulder and the head of the person, while as shown in fig. 2, the depth camera obtains a small visual field range, and lens distortion exists between the coordinates and the real position, and the distortion affects the depth value, so that the coordinate of the real value is obtained as infinitely as possible, the higher the accuracy of the depth value is, and the closer the corresponding height measured value is to the real value.
S2, selecting a frame depth image, detecting a person or an object in the frame depth image, generating an independent detection frame for each individual person or object, acquiring a central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and a depth camera internal reference matrix.
As shown in fig. 3, in the detection frames, the calculation is performed by using a diagonal manner, so that the vicinity of the center position is exactly within the highest point range of the human body, and therefore, the method for acquiring the center position coordinate of each detection frame is as follows: selecting two points coordinates (x 1, y 1) and (x 2, y 2) of the diagonal of the detection frame, and then the central position coordinates are as follows:
wherein,x-axis coordinate as center position coordinate, +.>Y-axis coordinates which are central position coordinates;
the specific method for carrying out distortion correction on the central position coordinate and calculating the corrected pixel coordinate through the central position coordinate after distortion correction and the depth camera internal reference matrix is as follows:
s21, solving the central position coordinates by adopting an motionless point iteration method to obtain the central position coordinates after distortion correction) Wherein, the fixed point iteration method selects +.>Conversion to->In the form of (2), the iteration convergence condition to be satisfied is: />；
Taking X-axis coordinates as an example, the process from undistorted point to distorted point is expressed as follows:
wherein the method comprises the steps ofFor having distortion point->Is a distortion point free->，[/>]For the distortion coefficient +>And->Is the radial distortion coefficient, and->Is the tangential distortion coefficient. The form written in matrix is:
the simplified form is:
wherein,
the construction invariant point equivalent form is:
the construction iteration form is as follows:
to the distortion point known at presentAs initial value, i.e.)>And then, according to the iteration calculation of the undistorted point until the iteration error or the maximum iteration number condition is met, obtaining the X-axis coordinate after distortion correction, and the Y-axis coordinate calculation method is the same as the same, and is not repeated here.
S22, based on the step S1, correcting the central position coordinate through distortion) Calculating corrected pixel coordinates with depth camera reference matrix (++>，/>) The following are provided:
wherein,、/>、/>、/>is a matrix point of the camera reference matrix.
Specifically, the camera reference matrix is a 3×3 matrix, as follows:
wherein f is the focal length in millimeters; dx is the width of the pixel in the X direction, and is in millimeters; 1/dx is how many pixels are within 1 millimeter of the X direction; f/dx is the length of the focal length in the X-axis direction using pixels; f/dy is the length of the focal length in the Y-axis direction using pixels; u0 and v0 are actual positions of principal points, the principal points defining an origin on a camera imaging plane, the units being pixels; in particular, the method comprises the steps of,matrix points correspond to f/dx,/and>the matrix point corresponds to u0 and,matrix points correspond to f/dy,/o>The matrix points correspond to v0.
S3, based on the step S2, obtaining a corrected detection frame based on corrected pixel coordinates, obtaining each pixel point and a depth value S thereof in the corrected detection frame, judging the size of the depth value S of each pixel point, selecting the first N minimum depth values S which are not zero, and calculating to obtain a total depth value SUM;
the specific method of step S3 is as follows:
s31, initializing a shaping vector Depths, acquiring each pixel point in the corrected detection frame and a depth value S thereof, and adding the pixel points into the shaping vector Depths if the depth value S is not zero;
s32, using a partial ordering method to move the first N minimum depth values in the shaping vector Depths to the front part of the vector
And limiting the number of the containable elements in the shaping vector Depths to N through a resize function.
Wherein, the shaping vector is a proper noun in a computer language, specifically, in the programming process using an advanced computer language, a large number of variables, functions and values are put into a set in a data container manner to form a combination, which is similar to a matrix and an array in mathematics, in the computer language, the shaping vector refers to that the internal value is a shaping number, for example, the following types of functions char, int, long, short can be used as the value of the shaping vector, but float is not used; in this embodiment, the shaping vector Depths is then used to accommodate a depth value S that is not zero.
S4, calculating an average depth value based on the step S3，/>=SUM/N。
S5, based on the step S4, calculating head depth values S1, S1 = by scaling coefficientsX (L/P), where L is the depth value and P is the pixel value of the frame depth image; in one embodiment, the frame depth image is an 8-bit image and the pixel value P is 255.
S6, based on the step S5, as shown in fig. 1, calculating the head height H, wherein H=H2-S1/10; because the default camera precision unit is mm, S1/10 is output centimeter-level precision, and the application scene requirement of the application is met.
As shown in fig. 1, the accurate value of the human body height = camera height-highest point of the head to depth value of the camera, i.e., head height H = depth camera mounting height H1-head depth value S1; however, in actual detection, as shown in fig. 4, when the depth camera performs detection, a plurality of depth values S in one area (detection frame), that is, s= [ S 1 、S 2 、S 3 、S 4 、S 5 、S 6 ……Sx]The method comprises the steps of carrying out a first treatment on the surface of the Obviously, there is a large difference between the depth value S of the head edge and the topmost depth value S, if the depth value s= [ S ] 1 、S 2 、S 3 、S 4 、S 5 、S 6 ……Sx]The result obtained by averaging is used as the depth value from the highest point of the head top to the camera, so that the deviation with the real result is larger; and if there are further factors such as angle, light and shieldingWhen the influence is exerted, the deviation between the average value obtained by the depth values S in the acquired region and the actual value is larger; in the present application, after acquiring a plurality of depth values S in a region, the first N minimum depth values S that are not zero are selected, i.e. the depth value s= [ S ] 1 、S 2 、S 3 、S 4 、S 5 、S 6 ……Sx]In the set, the first N minimum depth values S which are not zero are taken, the S value at the most edge can be removed in the mode, the precision is improved, the depth value of the highest point which approaches infinitely can be obtained by continuously extracting the depth value in the shaping vector, and then the height closest to the real height can be further calculated.
S7, sequentially selecting the frame depth images, repeating the steps S2-S6 to obtain a plurality of head heights H of the same person or object in the plurality of frame depth images, and averaging the plurality of head heights H to obtain the final head height.
In a specific embodiment, the depth camera mounting height H1 has a calibration process after the camera is mounted, and during calibration, a software parameter table built in the camera is input with a parameter of a mounting position, that is, a three-dimensional coordinate of the camera, which is derived from a result of measuring an actual scale, and the mounting height is fixed and cannot be changed at will in an actual application scene.
In this embodiment, the center position coordinate of each detection frame is obtained, distortion correction is performed on the center position coordinate, and the corrected pixel coordinate is calculated through the distortion corrected center position coordinate and the depth camera internal reference matrix, and compared with the traditional method of directly performing distortion correction by using distortion parameters, the method effectively reduces the influence of lens distortion on height measurement, and is more conducive to improving the accuracy and stability of measurement.
Example 2
In the three-dimensional coordinates (x, y, z) commonly used in the passing logic, namely, the adopted three-dimensional coordinates are the three-dimensional coordinates of the passers, and in the three-dimensional coordinates, (x, y) are two-dimensional coordinates, so that under the traditional correlation sensor technology, the parallel passers cannot distinguish whether the passers are single or double, and therefore, the escape behavior cannot be judged.
Therefore, on the basis of embodiment 1, the invention provides a height detection method based on a depth image, which further comprises the following steps: obtaining depth values of corrected pixel coordinatesThe value of the depth value val is equal to the value of the depth value S of the "acquire each pixel point and its depth value S in the corrected detection frame" in step S3 of embodiment 1, and is defined as the depth value val secondarily; according to the corrected pixel coordinates (+)>，/>) Calculating three-dimensional coordinates of camera internal reference matrix) The method comprises the steps of carrying out a first treatment on the surface of the The positions of the multiple passers can be judged in real time.
Wherein,the value of (2) is the depth value of the corrected pixel coordinate +.>；/>、、/>、/>The matrix points, which are the camera internal reference matrix, are the same as in embodiment 1.
The other steps of this example 2 are the same as those of example 1.
Example 3
The invention provides a height detection system based on a depth image, which is used for realizing the detection method described in the embodiment 1 or the embodiment 2, and comprises the following steps:
the depth camera is used for collecting video streams when passengers enter and exit the gate area to obtain a plurality of frame depth images;
the detection frame generation unit is used for selecting one frame depth image, detecting people or objects in the frame depth image and generating an independent detection frame for each individual person or object;
the coordinate correction unit is used for acquiring the central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and the depth camera internal reference matrix;
a coordinate conversion unit for converting the two-dimensional pixel coordinates into three-dimensional coordinates;
the image processing unit obtains a corrected detection frame based on the corrected pixel coordinates, obtains each pixel point in the corrected detection frame and a depth value S thereof, and calculates the head height H.
Example 4
The invention provides an electronic device comprising a processor, a memory and a control program stored on the memory and operable on the processor, wherein the control program when executed by the processor implements the depth image based height detection method as in embodiment 1 or embodiment 2.
Example 5
The present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a depth image-based height detection method as in embodiment 1 or embodiment 2.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The height detection method based on the depth image is characterized by comprising the following steps:
s1, a depth camera collects video streams when passengers enter and exit a gate area, a plurality of frame depth images are obtained, and the installation height H1 of the depth camera is recorded;
s2, selecting a frame depth image, detecting a person or an object in the frame depth image, generating an independent detection frame for each individual person or object, acquiring a central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and a depth camera internal reference matrix;
s3, based on the step S2, obtaining a corrected detection frame based on corrected pixel coordinates, obtaining each pixel point and a depth value S thereof in the corrected detection frame, judging the size of the depth value S of each pixel point, selecting the first N minimum depth values S which are not zero, and calculating to obtain a total depth value SUM;
s4, calculating an average depth value based on the step S3，/>=SUM/N；
S5, based on the step S4, calculating head depth values S1, S1 = by scaling coefficientsX (L/P), where L is the depth value and P is the pixel value of the frame depth image;
s6, calculating the head height H, wherein H=H2-S1/10 based on the step S5;
s7, sequentially selecting the frame depth images, repeating the steps S2-S6 to obtain a plurality of head heights H of the same person or object in the plurality of frame depth images, and averaging the plurality of head heights H to obtain the final head height.
2. The depth image-based height detection method according to claim 1, wherein the method for acquiring the center position coordinates of each detection frame comprises the steps of: selecting two points coordinates (x 1, y 1) and (x 2, y 2) of the diagonal of the detection frame, and then the central position coordinates are as follows:
wherein,x-axis coordinate as center position coordinate, +.>The Y-axis coordinate, which is the center position coordinate.
3. The depth image-based height detection method according to claim 1, wherein the specific method for performing distortion correction on the center position coordinates and calculating corrected pixel coordinates by using the distortion corrected center position coordinates and the depth camera reference matrix is as follows:
s21, solving the central position coordinates by adopting an motionless point iteration method to obtain the central position coordinates after distortion correction) Wherein, the fixed point iteration method selects +.>Conversion to->In the form of (2), the iteration convergence condition to be satisfied is: />；
S22, based on the step S1, correcting the central position coordinate through distortion) Calculating corrected pixel coordinates with depth camera reference matrix (++>，/>) The following are provided:
wherein the method comprises the steps of，、/>、/>、/>Is a matrix point of the camera reference matrix.
4. A depth image based height detection method according to claim 3, further comprising the steps of: obtaining depth values of corrected pixel coordinatesAccording to the corrected pixel coordinates (+)>，/>) Calculating three-dimensional coordinates of camera internal reference matrix (I)>)；
Wherein,the value of (1) is the corrected pixel positionTarget depth value +.>。
5. The depth image-based height detection method according to claim 1, wherein the specific method of step S3 is as follows:
s31, initializing a shaping vector Depths, acquiring each pixel point in the corrected detection frame and a depth value S thereof, and adding the pixel points into the shaping vector Depths if the depth value S is not zero;
s32, using a partial ordering method to move the first N minimum depth values in the shaping vector Depths to the front of the vector, and limiting the number of the receivable elements in the shaping vector Depths to N through a resize function.
6. A depth image based height detection system for implementing the detection method according to any one of claims 1-5, comprising:
the depth camera is used for collecting video streams when passengers enter and exit the gate area to obtain a plurality of frame depth images;
the detection frame generation unit is used for selecting one frame depth image, detecting people or objects in the frame depth image and generating an independent detection frame for each individual person or object;
the coordinate correction unit is used for acquiring the central position coordinate of each detection frame, carrying out distortion correction on the central position coordinate, and calculating corrected pixel coordinates through the central position coordinate after distortion correction and the depth camera internal reference matrix;
a coordinate conversion unit for converting the two-dimensional pixel coordinates into three-dimensional coordinates;
the image processing unit obtains a corrected detection frame based on the corrected pixel coordinates, obtains each pixel point in the corrected detection frame and a depth value S thereof, and calculates the head height H.
7. An electronic device comprising a processor, a memory, and a control program stored on the memory and operable on the processor, the control program when executed by the processor implementing the depth image based height detection method of any one of claims 1-5.
8. A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the depth image based height detection method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410154607.9A CN117689709B (en) | 2024-02-04 | 2024-02-04 | Height detection method, system, equipment and medium based on depth image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410154607.9A CN117689709B (en) | 2024-02-04 | 2024-02-04 | Height detection method, system, equipment and medium based on depth image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117689709A true CN117689709A (en) | 2024-03-12 |
| CN117689709B CN117689709B (en) | 2024-04-05 |
Family
ID=90137505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410154607.9A Active CN117689709B (en) | 2024-02-04 | 2024-02-04 | Height detection method, system, equipment and medium based on depth image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117689709B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101878095B1 (en) * | 2017-02-07 | 2018-07-12 | 동의대학교 산학협력단 | Method and device of Estimating the Human Height in Using Depth Image OF FRONT VIEW |
| CN115908370A (en) * | 2022-12-13 | 2023-04-04 | 山东沂蒙抽水蓄能有限公司 | Method for realizing water level detection based on image inverse perspective transformation |
| CN117078735A (en) * | 2023-08-14 | 2023-11-17 | 广州广电运通智能科技有限公司 | Height detection method, system, electronic device and storage medium |
-
2024
- 2024-02-04 CN CN202410154607.9A patent/CN117689709B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101878095B1 (en) * | 2017-02-07 | 2018-07-12 | 동의대학교 산학협력단 | Method and device of Estimating the Human Height in Using Depth Image OF FRONT VIEW |
| CN115908370A (en) * | 2022-12-13 | 2023-04-04 | 山东沂蒙抽水蓄能有限公司 | Method for realizing water level detection based on image inverse perspective transformation |
| CN117078735A (en) * | 2023-08-14 | 2023-11-17 | 广州广电运通智能科技有限公司 | Height detection method, system, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117689709B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020101832A4 (en) | Image collection and depth image enhancement method and apparatus for kinect | |
| CN106683070B (en) | Height measuring method and device based on depth camera | |
| US10861197B2 (en) | Radiographing apparatus, radiographing system, radiographing method, and storage medium | |
| EP3033875B1 (en) | Image processing apparatus, image processing system, image processing method, and computer program | |
| JP5075757B2 (en) | Image processing apparatus, image processing program, image processing method, and electronic apparatus | |
| CN108426640B (en) | A kind of bearing calibration for infrared detector defect pixel | |
| Semeniuta | Analysis of camera calibration with respect to measurement accuracy | |
| JP6577703B2 (en) | Image processing apparatus, image processing method, program, and storage medium | |
| US20120062749A1 (en) | Human body identification method using range image camera and human body identification apparatus | |
| JP4769764B2 (en) | Input method for entering points into the system, setting method, calibration method | |
| WO2021175281A1 (en) | Infrared temperature measurement method, apparatus, and device, and storage medium | |
| CN107203743B (en) | Face depth tracking device and implementation method | |
| CN110111292B (en) | Infrared and visible light image fusion method | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN117689709B (en) | Height detection method, system, equipment and medium based on depth image | |
| CN113749646A (en) | Monocular vision-based human body height measuring method and device and electronic equipment | |
| CN116934833A (en) | Binocular vision-based underwater structure disease detection method, equipment and medium | |
| TWI418914B (en) | Defocus calibration module for light-sensing system and method thereof | |
| CN114648544A (en) | Sub-pixel ellipse extraction method | |
| CN115937325A (en) | Vehicle-end camera calibration method combined with millimeter wave radar information | |
| CN114964032A (en) | Blind hole depth measuring method and device based on machine vision | |
| CN115830131A (en) | Method, device and equipment for determining fixed phase deviation | |
| JP2007036743A (en) | Method of synthesizing multiple images and imaging apparatus | |
| CN113834447A (en) | High-dynamic laser light bar self-adaptive imaging processing method under outdoor complex environment | |
| CN110781712A (en) | Human head space positioning method based on human face detection and recognition |
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 |