CN117315783A - Personnel detection method, device, equipment and computer storage medium - Google Patents
Personnel detection method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN117315783A CN117315783A CN202311293056.6A CN202311293056A CN117315783A CN 117315783 A CN117315783 A CN 117315783A CN 202311293056 A CN202311293056 A CN 202311293056A CN 117315783 A CN117315783 A CN 117315783A
- Authority
- CN
- China
- Prior art keywords
- region
- human body
- living
- visible light
- area
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 107
- 241000282414 Homo sapiens Species 0.000 claims abstract description 192
- 210000000746 body region Anatomy 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000004891 communication Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 description 17
- 238000004422 calculation algorithm Methods 0.000 description 15
- 238000010801 machine learning Methods 0.000 description 13
- 238000003384 imaging method Methods 0.000 description 10
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 230000003068 static effect Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000005855 radiation Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 239000010703 silicon Substances 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 241000124008 Mammalia Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 210000002858 crystal cell Anatomy 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Classifications
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention relates to the technical field of computer data processing, and discloses a personnel detection method, a device, equipment and a computer storage medium, wherein the method comprises the following steps: acquiring a visible light image and an infrared thermal image corresponding to a target area in real time; real-time motion tracking is carried out on a human body contour area in the visible light image, and whether the position of the human body contour area in the visible light image changes or not is determined; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; when the position of the human body contour area is determined to be changed and the area contour of the living body area is matched with the preset human body contour, calculating the coincidence ratio between the human body contour area and the living body area; and determining a person detection result in the target area according to the coincidence degree. Through the mode, the embodiment of the invention realizes high-efficiency and accurate real-time personnel quantity detection.
Description
Technical Field
The embodiment of the invention relates to the technical field of computer data processing, in particular to a personnel detection method, a device, equipment and a computer storage medium.
Background
At present, when personnel detection is carried out in a space, a camera is generally used for collecting visible light images in the space to be detected, and whether personnel appear is judged by identifying the visible light images. Or, the infrared camera is used for carrying out living body detection on the space to be detected, and judging whether personnel exist or not. However, on the one hand, infrared image analysis cannot accurately distinguish a human body from other human-like bodies capable of radiating heat, while visible light image analysis cannot distinguish a living body from other human-like bodies. Therefore, in order to accurately detect a person in a space, the inventors have conceived combining a visible light image with an infrared image to realize person detection.
However, in practicing the prior art, the inventors found that: the existing method generally uses a machine learning algorithm to carry out image fusion on a visible light image and an infrared image, and personnel detection is directly carried out according to the fused image, and the method has the problems that the complexity of the image fusion algorithm is high, the training period of a machine learning model is long, and the existing personnel detection has the problems of high complexity and low timeliness.
There is therefore a need for a less complex and high accuracy human detection scheme.
Disclosure of Invention
In view of the above problems, the embodiments of the present invention provide a method, an apparatus, a device, and a computer storage medium for detecting personnel, which are used to solve the problems of high complexity and low timeliness of personnel detection in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a person detection method including:
acquiring a visible light image and an infrared thermal image corresponding to a target area in real time;
detecting the human body of the visible light image to obtain a human body contour area in the visible light image;
performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not;
performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image;
determining whether the region outline of the living body region is matched with a preset human body outline;
calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour;
And determining a person detection result in the target area according to the overlapping ratio.
In an alternative way, the number of human body contour regions is at least one; the number of living body regions is at least one; the method further comprises the steps of:
determining the corresponding human body contour region and the corresponding living body region with the contact ratio larger than a preset contact ratio threshold value as corresponding to the same living body person in the target region;
the number of living persons in the target area is determined according to the number of human body contour areas or living areas corresponding to the same living person in the target area.
In an alternative, the method further comprises:
performing jitter detection on the visible light images of two adjacent frames;
when it is determined that picture jitter exists between the visible light images of two adjacent frames, it is determined that a change exists in the position of the human body contour region within the visible light images.
In an alternative, the method further comprises:
when it is determined that there is a change in position of the human body contour region, determining that the human body contour region corresponds to a living person in the target region;
And determining the number of living persons in the target area according to the number of the human body contour areas with the position change.
In an alternative, the method further comprises:
determining the living body region matching the preset human body contour as corresponding to one living body person in the target region;
the number of living persons in the target area is determined according to the number of living areas corresponding to one living person in the target area.
In an alternative, the method further comprises:
when the positions of all the human body contour areas in the target area are determined to be unchanged, determining that no living person is included in the target area;
when the area outline of all living body areas in the target area is not matched with the preset human body outline, determining that living body personnel are not included in the target area.
In an alternative, the method further comprises:
performing target recognition on a visible light image corresponding to a region to be detected to obtain a person movable region in the region to be detected;
the person movable area is determined as the target area.
According to another aspect of an embodiment of the present invention, there is provided a person detection apparatus including:
the acquisition module is used for acquiring the visible light image and the infrared thermal image corresponding to the target area in real time;
the first detection module is used for detecting the human body of the visible light image to obtain a human body contour area in the visible light image;
the tracking module is used for carrying out real-time motion tracking on the human body contour area and determining whether the position of the human body contour area in the visible light image changes or not;
the second detection module is used for carrying out living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image;
the matching module is used for determining whether the area outline of the living body area is matched with the preset human body outline;
a calculating module for calculating the degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour;
and the determining module is used for determining a person detection result in the target area according to the contact ratio.
According to another aspect of an embodiment of the present invention, there is provided a person detection apparatus including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
The memory is configured to store at least one executable instruction that causes the processor to perform the operations of the person detection method embodiment as described in any of the preceding claims.
According to yet another aspect of an embodiment of the present invention, there is provided a computer-readable storage medium having stored therein at least one executable instruction for causing a person detection apparatus to perform operations of an embodiment of a person detection method as set forth in any one of the preceding claims.
The embodiment of the invention acquires the visible light image and the infrared thermal image corresponding to the target area in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio. Therefore, the method is different from the conventional method that a machine learning algorithm is used for fusing a visible light image and an infrared image, the complexity of the algorithm according to the fused image is high, the training period of a machine learning model is long, and the problems of high complexity and low timeliness of the conventional personnel detection are caused.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific embodiments of the present invention are given for clarity and understanding.
Drawings
The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a schematic flow chart of a person detection method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a person detection device according to an embodiment of the present invention;
fig. 3 shows a schematic structural diagram of a person detection device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein.
Description of related nouns: the process of obtaining the visible light image by imaging the camera comprises the following steps: (1) capturing: and the camera changes the irradiation of the light into an electronic signal. This process has three parts: optics, sensors, and circuitry. Firstly, the optical device collects light into the camera, then the light is converted into an electronic signal by the sensor, and finally, the circuit converts the signal into a digital signal and sends the digital signal to a computer for processing. (2) display: and converting the electronic signals into images by the camera. This process has three parts: display, chip and display device. Firstly, after the electronic signals are processed by a chip, the electronic signals are sent to a display; then, the display converts the electronic signal into an image; finally, the image is displayed on a display device. Among them, the screen display imaging technology includes a variety of, among which common ones include: (1) LCD display technology: an LCD (Liquid Crystal Display ) is a liquid crystal display technology that realizes picture display by changing the transmittance or reflectance of a liquid crystal cell by utilizing the photoelectric effect of liquid crystal molecules. LCD display technology is mature, and low in cost, but imaging effect is general. (2) 3LCD display technology: the 3LCD is a display technology composed of three LCD display panels, and can make the colors interweaved with each other to form brightness variation by respectively controlling the light transmittance of liquid crystal pixels with three colors of red, green and blue, so as to improve imaging effect. The 3LCD display technology has higher imaging quality, but also higher cost. (3) DLP display technology: DLP (Digital Light Processor, digital light processing) is a digital light processing technology that achieves display by decomposing an image into digital pixels and projecting it onto a screen. The DLP display technology has the characteristics of high brightness, high contrast, high resolution and the like, and is suitable for large-screen display. LCoS display technology: LCoS (Liquid Crystal on Silicon ) is a liquid crystal display technology, which uses a silicon wafer as a substrate, and makes liquid crystal pixels and driving circuits on the silicon wafer, so as to achieve a high resolution and high brightness display effect. LCoS display technology has higher imaging quality but also higher cost. Different screen display imaging technologies have different cost, imaging quality, applicable scene and the like, and proper technologies need to be selected according to actual requirements. The imaging principle of a camera is the physical principle that the camera must follow when taking images: the camera captures light first, converts it into an electronic signal, then converts the electronic signal into an image, and finally the image is displayed on the display device.
The imaging process of the infrared thermal imaging technology mainly comprises three steps of radiation detection, signal processing and image display.
(1) Radiation detection: the infrared detector is used for converting the power signal radiated by the heating part of the object into an electric signal. The signal is then transmitted to a signal processing circuit for processing
(2) And (3) signal processing: the signal processing circuit performs operations such as amplification, filtering, conditioning, temperature measurement, compensation and the like on the signals.
(3) And (3) image display: the image generation process comprises scanning, frame accumulation, graying and other operations. The processed signals are converted into images and graphs which can be distinguished by human vision, and the temperature value can be further calculated. Finally, the infrared thermal image of the measured object is displayed through a television screen or a monitor.
The working principle of the thermal infrared imager is as follows: an infrared detector, an optical imaging objective lens and an optical-mechanical scanning system (an advanced focal plane technology omits the optical-mechanical scanning system) are utilized to receive an infrared radiation energy distribution pattern of a detected object and reflect the infrared radiation energy distribution pattern onto a photosensitive element of the infrared detector, an optical-mechanical scanning mechanism (the focal plane thermal imager does not have the mechanism) is arranged between the optical system and the infrared detector to scan an infrared thermal image of the detected object, the infrared thermal image is focused on a unit or a spectral detector, the infrared radiation energy is converted into an electric signal by the detector, and an infrared thermal image is displayed by a television screen or a monitor through amplification treatment, conversion or standard video signals.
Fig. 1 shows a flowchart of a person detection method provided by an embodiment of the present invention, which is performed by a computer processing device. The computer processing device may include a cell phone, a notebook computer, etc. As shown in fig. 1, the method comprises the steps of:
step 10: and acquiring a visible light image and an infrared thermal image corresponding to the target area in real time.
The target area is an area to be detected by a person, and may be an indoor or outdoor space where a person may enter or exit, such as a hall, an airport, a classroom, or the like. The visible light image is collected through the camera and used for representing the appearance characteristics of objects in the environment, and the infrared thermal image can be collected through the thermal infrared imager and used for representing the temperature of the objects in the environment. The visible light image is affected by light in the collecting environment, and correspondingly, the infrared thermal image is not affected by light in the collecting environment. It will be appreciated that the visible light images are acquired in real time and therefore the position of the object within the visible light images of adjacent preceding and following frames will change as it moves within the target area. Correspondingly, the temperature and the position of the heating of different types of objects are different, so that the image characteristics of the corresponding infrared thermal images are different. The infrared thermal image and the visible light image are acquired in real time, and the infrared thermal image and the visible light image sense and represent the conditions in the same space at the same moment in different sensing modes.
Considering that the area of the target area may be larger, and meanwhile, static objects of non-living persons at fixed positions, such as walls, electrical appliances, plants and other ornaments, generally exist in the target area, in order to improve the efficiency and accuracy of detection of the persons in the target area, before the living person detection is performed on the visible light image and the infrared thermal image corresponding to the target area, the area to be detected may be divided first, so as to obtain an area where the person can move, and the area is used as the target area to perform corresponding image identification.
Specifically, in yet another embodiment of the present invention, step 10 further comprises:
step 101: and carrying out target recognition on the visible light image corresponding to the region to be detected to obtain the personnel movable region in the region to be detected.
The method comprises the steps of carrying out target recognition on visible light images corresponding to a region to be detected according to visible light image features corresponding to various preset types of objects, and obtaining positions of the preset types of objects included in the region to be detected, wherein the preset types are used for representing static objects of non-living persons in fixed positions, such as walls, electrical appliances, plants and other decorations.
Dividing the region to be detected into a plurality of subspaces according to the positions of the objects of the preset types included in the region to be detected, wherein the region to be detected can be divided into a plurality of subspaces by taking the detected wall as a dividing line, and the regions which do not include the objects of the preset types in each subspace are respectively used as a corresponding target region.
Step 102: the person movable area is determined as the target area.
By identifying the static objects in the to-be-detected area, the to-be-detected area is divided into a plurality of independent subspaces where the personnel may have activities according to the functional attributes of the identified static objects, and the influence of the immovable static objects in the subspaces is eliminated, so that the efficiency and the accuracy of personnel detection in the to-be-detected area are improved.
Step 20: and detecting the human body of the visible light image to obtain a human body contour area in the visible light image.
The method comprises the steps of detecting a visible light image according to preset human visible light image characteristics, and obtaining at least one human outline area included in the visible light image. Human visible light image features are used to characterize image features that a human would have in a visible light image, such as the contour, brightness, and color of the human. It will be appreciated that when the image area conforming to the human body contour feature in the visible light image is identified as the human body contour area, other existing means may be adopted in addition to the target detection according to the preset image feature, which is not limited in the present invention.
Step 30: and carrying out real-time motion tracking on the human body contour area, and determining whether the position of the human body contour area in the visible light image is changed or not.
In the method, in consideration of the characteristics of the human body contour, living body personnel and also human-shaped static objects, such as human-shaped standing plates, human models and the like, in order to screen out the human body contour area corresponding to the non-living body personnel in the target area, in consideration of the fact that the living body personnel generally cannot keep absolute rest in space, namely, motion exists in a visible light image sequence acquired frame by frame in real time, the motion is captured in the form of the change of the position of the human body contour area in a picture, and therefore, real-time motion tracking is carried out on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not. The real-time motion tracking can adopt modes such as target tracking, an optical flow method, picture jitter detection and the like.
Preferably, step 30 further comprises:
step 301: and performing jitter detection on the visible light images of two adjacent frames.
Wherein, whether the picture jitter exists between the visible light images of two adjacent frames is determined. When the position of an object in the visible light images of two adjacent frames changes, judging that picture jitter exists between the visible light images of two adjacent frames.
Step 302: when it is determined that picture jitter exists between the visible light images of two adjacent frames, it is determined that a change exists in the position of the human body contour region within the visible light images.
The motion of the object corresponding to the human body contour area in the target area can cause the visible light image acquired in real time to have picture jitter, so that when the picture jitter exists between the visible light images of two adjacent frames, the position of the human body contour area in the visible light image is determined to have change.
Alternatively, considering that only living persons will have a human-shaped contour while there is motion, it is thus possible to determine the number of living persons corresponding to the target area according to whether there is a human-shaped contour and whether there is motion, specifically, further including, after step 30:
step 310: when it is determined that there is a change in position of the human body contour region, it is determined that the human body contour region corresponds to one living person in the target region.
When it is determined that there is a positional change in the human body contour area, it is determined that the human body contour area corresponds to one living person in the target area, so that interference of other non-human running objects and human-shaped stills in the target area is avoided, considering that only living persons have a human-shaped contour while having a motion.
Step 311: and determining the number of living persons in the target area according to the number of the human body contour areas with the position change.
And counting the number of the human body contour areas with the position change to obtain the number of living body personnel in the target area.
Step 40: and performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image.
The temperature emitted by each pixel point area in the infrared thermal image is detected according to a preset temperature threshold value, and adjacent pixel points are combined in the pixel point area with the area temperature being greater than the temperature threshold value, so that a living body area in the infrared thermal image is obtained.
Step 50: and determining whether the area outline of the living body area is matched with the preset human body outline.
Considering that the body temperature of living beings is generally concentrated in a region, such as that the body temperature of human beings and other non-human living beings, particularly constant temperature mammals, is not greatly different, but there is a significant difference in the heat distribution condition of human beings and other non-human living beings species in an infrared thermal image (including the temperatures corresponding to different parts in a living body region and the connection condition between the parts), after the region outline corresponding to a heat source is identified according to a temperature threshold value, in order to improve the accuracy of personnel identification, the region outline of the living body region needs to be matched with a preset human body outline, and only the living body region of which the outline of the living body region meets the characteristics of the human body outline is determined to correspond to one living body personnel, rather than a human heat source.
Considering that the living body is detected first by temperature screening and the living body is detected by heat source distribution screening when the personnel detection is performed according to the infrared thermal image, the accuracy of the personnel detection based on the infrared thermal image according to the embodiment of the present invention is high, and therefore, the method further includes, after step 50:
step 501: the living body region matching the preset human body contour is determined to correspond to one living body person within the target region.
Only a living body region whose contour satisfies the characteristics of the human body contour is determined to correspond to one living body person, thereby eliminating interference of non-human heat sources present in the target region.
Step 502: the number of living persons in the target area is determined according to the number of living areas corresponding to one living person in the target area.
And counting the number of the living body areas corresponding to one living body person in the target area to obtain the number of the living body persons in the target area.
Step 60: when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour, the degree of coincidence between the human body contour region and the living body region is calculated.
Wherein, considering that only living persons will have movement, heat dissipation and a human-shaped contour at the same time, when there is a position change in a human contour region, the human contour region corresponds to one living person with a high probability, and correspondingly, when a living region satisfies a human contour feature, the living region corresponds to one living person with a high probability, based on which, in order to further improve accuracy of human detection, only when it is determined that there is a position change in the human contour region and that a region contour of the living region matches the preset human contour, the degree of coincidence between the human contour region and the living region is calculated.
The overlap ratio between the human body contour region and the living body region may be determined according to the area ratio of the overlap region of the human body contour region and the living body region. The area ratio may be a ratio of the overlap area to the contour area and/or the living body area of the human body. When the contact ratio is calculated, the infrared thermal image can be mapped and fitted to the visible light image, so that the calculation efficiency of the contact ratio is improved.
Step 70: and determining a person detection result in the target area according to the overlapping ratio.
Considering that the infrared thermal image and the visible light image are acquired in real time, the two images sense and represent the situation in the same space under the same moment by using different sensing acquisition principles, and based on the fact that the motion behavior of the same living person in the target area has the simultaneity and the relativity in the infrared thermal image and the characterized situation in the visible light image, when the coincidence degree is greater than the preset coincidence degree threshold, the human body contour area in the visible light image and the living area in the infrared thermal image can be considered to actually correspond to the same living person, namely, the living person in the target area is counted according to the existence and the motion of the same specific living person, and the quantity of the human body contour area-living area pairs with the coincidence degree greater than the preset coincidence degree threshold in the target area.
Specifically, the number of human body contour regions is at least one; the number of living body regions is at least one; in an embodiment of the present invention, step 70 includes:
step 701: and determining the corresponding human body contour area and the corresponding living body area, the contact ratio of which is larger than a preset contact ratio threshold value, as corresponding to the same living body personnel in the target area.
In consideration of that there may be a certain deviation in the algorithms of target detection and motion tracking, and correspondingly, there may be a certain deviation in the identification of the living body region, so, in order to improve the accuracy of the detection of the living body personnel and the reliability of the detection result, a coincidence threshold may be set for characterizing the coincidence degree of the human body contour region and the living body region corresponding to the same living body personnel in the case of allowing the error of the machine learning algorithm, and preferably, the coincidence threshold may be set to 80% or more.
Step 702: the number of living persons in the target area is determined according to the number of human body contour areas or living areas corresponding to the same living person in the target area.
And counting the number of the human body contour area-living body area pairs with the contact ratio larger than the preset contact ratio threshold value to obtain the number of living body persons in the target area. For example, when there are 10 human contour region-living body region correspondence overlap ratios greater than the aforementioned overlap ratio threshold, it is determined that 10 living body persons are included in the target region.
Alternatively, considering that only living persons may have motion, heat dissipation, and a human-shaped profile at the same time, it may be determined that no living person is present in the target area when there is no motion in the human-shaped profile area or the living area does not satisfy the human-shaped profile feature. Specifically, the embodiment of the invention further comprises:
step 801: when it is determined that there is no change in the positions of all the human body contour regions within the target region, it is determined that no living person is included within the target region.
Based on the fact that there is generally motion of the living person, it is difficult to keep the living person absolutely stationary, and this motion is recorded by the visible light image acquired in real time, it is determined that the living person is not included in the target area when it is determined that there is no change in the position of all the human body contour areas in the target area.
Step 802: when the area outline of all living body areas in the target area is not matched with the preset human body outline, determining that living body personnel are not included in the target area.
Considering that a heat source other than a living body person corresponds to a living body area of a certain area in an infrared heat image, the heat value and the heat distribution situation in the living body area of the non-human heat source are greatly different from those of the living body person, for example, the infrared heat image characteristics corresponding to a small animal are completely different from those of the infrared heat image corresponding to a human, and therefore, when it is determined that the area outline of all the living body areas in the target area does not match with the preset human body outline, it is determined that the living body person is not included in the target area.
The embodiment of the invention acquires the visible light image and the infrared thermal image corresponding to the target area in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio. Therefore, the method is different from the conventional method that a machine learning algorithm is used for fusing a visible light image and an infrared image, the complexity of the algorithm according to the fused image is high, the training period of a machine learning model is long, and the problems of high complexity and low timeliness of the conventional personnel detection are caused.
Fig. 2 shows a schematic structural diagram of a person detection device according to an embodiment of the present invention. As shown in fig. 2, the apparatus 90 includes: an acquisition module 901, a first detection module 902, a tracking module 903, a second detection module 904, a matching module 905, a calculation module 906, and a determination module 907.
The acquisition module 901 is used for acquiring a visible light image and an infrared thermal image corresponding to the target area in real time;
the first detection module 902 is configured to perform human body detection on the visible light image to obtain a human body contour area in the visible light image;
the tracking module 903 is configured to perform real-time motion tracking on the human body contour area, and determine whether a position of the human body contour area in the visible light image has a change;
a second detection module 904, configured to perform living body detection on the infrared thermal image, so as to obtain a living body region in the infrared thermal image;
a matching module 905, configured to determine whether an area contour of the living body area matches a preset human body contour;
a calculating module 906 for calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour;
A determining module 907, configured to determine a person detection result in the target area according to the contact ratio.
The operation process of the personnel detection device provided by the embodiment of the invention is approximately the same as that of the foregoing method embodiment, and will not be repeated.
The operation process of the personnel detection device provided by the embodiment of the invention is that the visible light image and the infrared thermal image corresponding to the target area are acquired in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio. Therefore, the method is different from the conventional method that a machine learning algorithm is used for fusing a visible light image and an infrared image, the complexity of the algorithm according to the fused image is high, the training period of a machine learning model is long, and the problems of high complexity and low timeliness of the conventional personnel detection are caused.
Fig. 3 is a schematic structural diagram of a personnel detection device according to an embodiment of the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the personnel detection device.
As shown in fig. 3, the person detection apparatus may include: a processor 1002, a communication interface Communications Interface, a memory 1006, and a communication bus 1008.
Wherein: the processor 1002, communication interface 1004, and memory 1006 communicate with each other via a communication bus 1008. Communication interface 1004 is used for communicating with network elements of other devices, such as clients or other servers. The processor 1002 is configured to execute the program 1010, and may specifically perform the relevant steps in the above-described embodiment of the method for detecting a person.
In particular, program 1010 may include program code comprising computer-executable instructions.
The processor 1002 may be a Central Processing Unit (CPU) or a specific integrated circuit ASIC (Application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors comprised by the person detection device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 1006 for storing programs 1010. The memory 1006 may include high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as disk memory.
The program 1010 may be specifically invoked by the processor 1002 to cause a person detection device to:
acquiring a visible light image and an infrared thermal image corresponding to a target area in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio.
The operation process of the personnel detection device provided by the embodiment of the invention is approximately the same as that of the foregoing method embodiment, and will not be repeated.
The operation process of the personnel detection equipment provided by the embodiment of the invention is that the visible light image and the infrared thermal image corresponding to the target area are acquired in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio. Therefore, the method is different from the conventional method that a machine learning algorithm is used for fusing a visible light image and an infrared image, the complexity of the algorithm according to the fused image is high, the training period of a machine learning model is long, and the problems of high complexity and low timeliness of the conventional personnel detection are caused.
An embodiment of the present invention provides a computer readable storage medium storing at least one executable instruction that, when executed on a person detection device, causes the person detection device to perform a person detection method according to any of the above method embodiments.
The executable instructions may be specifically for causing a person detection device to:
acquiring a visible light image and an infrared thermal image corresponding to a target area in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio.
The operation process of the executable instructions stored in the computer storage medium provided in the embodiment of the present invention is substantially the same as that of the foregoing method embodiment, and will not be repeated.
The operation process of the executable instructions stored in the computer storage medium provided by the embodiment of the invention is realized by collecting the visible light image and the infrared thermal image corresponding to the target area in real time; detecting the human body of the visible light image to obtain a human body contour area in the visible light image; performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not; performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image; determining whether the region outline of the living body region is matched with a preset human body outline; calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour; and determining a person detection result in the target area according to the overlapping ratio. Therefore, the method is different from the conventional method that a machine learning algorithm is used for fusing a visible light image and an infrared image, the complexity of the algorithm according to the fused image is high, the training period of a machine learning model is long, and the problems of high complexity and low timeliness of the conventional personnel detection are caused.
The embodiment of the invention provides a personnel detection device which is used for executing the personnel detection method.
An embodiment of the present invention provides a computer program that can be invoked by a processor to cause a person detection device to perform the person detection method of any of the method embodiments described above.
An embodiment of the present invention provides a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when run on a computer, cause the computer to perform the person detection method of any of the method embodiments described above.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component, and they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. A method of person detection, the method comprising:
acquiring a visible light image and an infrared thermal image corresponding to a target area in real time;
Detecting the human body of the visible light image to obtain a human body contour area in the visible light image;
performing real-time motion tracking on the human body contour area to determine whether the position of the human body contour area in the visible light image changes or not;
performing living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image;
determining whether the region outline of the living body region is matched with a preset human body outline;
calculating a degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour;
and determining a person detection result in the target area according to the overlapping ratio.
2. The method of claim 1, wherein the number of body contour regions is at least one; the number of living body regions is at least one; the step of determining the person detection result in the target area according to the contact ratio comprises the following steps:
determining the corresponding human body contour region and the corresponding living body region with the contact ratio larger than a preset contact ratio threshold value as corresponding to the same living body person in the target region;
The number of living persons in the target area is determined according to the number of human body contour areas or living areas corresponding to the same living person in the target area.
3. The method of claim 1, wherein the real-time motion tracking of the human body contour region to determine whether there is a change in the position of the human body contour region within the visible light image comprises:
performing jitter detection on the visible light images of two adjacent frames;
when it is determined that picture jitter exists between the visible light images of two adjacent frames, it is determined that a change exists in the position of the human body contour region within the visible light images.
4. The method of claim 1, wherein after said real-time motion tracking of said body contour region, determining whether there is a change in the position of said body contour region within said visible light image, further comprising:
when it is determined that there is a change in position of the human body contour region, determining that the human body contour region corresponds to a living person in the target region;
and determining the number of living persons in the target area according to the number of the human body contour areas with the position change.
5. The method according to claim 1, characterized by, after said determining whether the region contour of the living body region matches a preset human body contour, comprising:
determining the living body region matching the preset human body contour as corresponding to one living body person in the target region;
the number of living persons in the target area is determined according to the number of living areas corresponding to one living person in the target area.
6. The method according to claim 1, wherein the method further comprises:
when the positions of all the human body contour areas in the target area are determined to be unchanged, determining that no living person is included in the target area;
when the area outline of all living body areas in the target area is not matched with the preset human body outline, determining that living body personnel are not included in the target area.
7. The method according to claim 1, wherein the real-time acquisition of the visible light image and the infrared thermal image corresponding to the target area includes:
performing target recognition on a visible light image corresponding to a region to be detected to obtain a person movable region in the region to be detected;
The person movable area is determined as the target area.
8. A person detection device, the device comprising:
the acquisition module is used for acquiring the visible light image and the infrared thermal image corresponding to the target area in real time;
the first detection module is used for detecting the human body of the visible light image to obtain a human body contour area in the visible light image;
the tracking module is used for carrying out real-time motion tracking on the human body contour area and determining whether the position of the human body contour area in the visible light image changes or not;
the second detection module is used for carrying out living body detection on the infrared thermal image to obtain a living body region in the infrared thermal image;
the matching module is used for determining whether the area outline of the living body area is matched with the preset human body outline;
a calculating module for calculating the degree of coincidence between the human body contour region and the living body region when it is determined that there is a change in the position of the human body contour region and the region contour of the living body region matches the preset human body contour;
and the determining module is used for determining a person detection result in the target area according to the contact ratio.
9. A person detection apparatus, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the person detection method according to any one of claims 1-7.
10. A computer readable storage medium, wherein at least one executable instruction is stored in the storage medium, which when run on a person detection device causes the person detection device to perform the operations of the person detection method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311293056.6A CN117315783A (en) | 2023-10-08 | 2023-10-08 | Personnel detection method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311293056.6A CN117315783A (en) | 2023-10-08 | 2023-10-08 | Personnel detection method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117315783A true CN117315783A (en) | 2023-12-29 |
Family
ID=89259976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311293056.6A Pending CN117315783A (en) | 2023-10-08 | 2023-10-08 | Personnel detection method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117315783A (en) |
-
2023
- 2023-10-08 CN CN202311293056.6A patent/CN117315783A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240118218A1 (en) | Stroboscopic stepped illumination defect detection system | |
| CN106446873B (en) | Face detection method and device | |
| CN111579083B (en) | Body temperature measuring method and device based on infrared image face detection | |
| CN111414887A (en) | Secondary detection mask face recognition method based on YO L OV3 algorithm | |
| CN106384106A (en) | Anti-fraud face recognition system based on 3D scanning | |
| CN110400315A (en) | A kind of defect inspection method, apparatus and system | |
| WO2024051067A1 (en) | Infrared image processing method, apparatus, and device, and storage medium | |
| Fa et al. | Development of an all-sky imaging system for cloud cover assessment | |
| CN111323125B (en) | Temperature measurement method and device, computer storage medium and electronic equipment | |
| Ismail et al. | Development of a webcam based lux meter | |
| CN114445330A (en) | Method and system for detecting appearance defects of components | |
| JP2010217984A (en) | Image detector and image detection method | |
| CN113762161A (en) | Intelligent obstacle monitoring method and system | |
| CN112418251A (en) | Infrared body temperature detection method and system | |
| CN115601712B (en) | Image data processing method and system suitable for site safety measures | |
| CN111898427A (en) | Multispectral pedestrian detection method based on feature fusion deep neural network | |
| CN117315783A (en) | Personnel detection method, device, equipment and computer storage medium | |
| KR101625471B1 (en) | Method and apparatus for enhancing resolution of popular low cost thermal image camera | |
| TW201445458A (en) | Testing device and method for camera | |
| KR102487590B1 (en) | Method for measuring of object based on face-recognition | |
| AU2021100634A4 (en) | Image target recognition system based on rgb depth-of-field camera and hyperspectral camera | |
| CN110888536B (en) | Finger interaction recognition system based on MEMS laser scanning | |
| CN114002704A (en) | Laser radar monitoring method and device for bridge tunnel and medium | |
| Ribeiro et al. | Algorithms for face detection on infrared thermal images | |
| CN112907454B (en) | Method, device, computer equipment and storage medium for acquiring image |
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 |