CN113034458B - Indoor personnel track analysis method, device and storage medium - Google Patents
Indoor personnel track analysis method, device and storage medium Download PDFInfo
- Publication number
- CN113034458B CN113034458B CN202110292638.7A CN202110292638A CN113034458B CN 113034458 B CN113034458 B CN 113034458B CN 202110292638 A CN202110292638 A CN 202110292638A CN 113034458 B CN113034458 B CN 113034458B
- Authority
- CN
- China
- Prior art keywords
- effective
- moving
- data blocks
- data block
- personnel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an indoor personnel track analysis method, a device and a storage medium, wherein the method comprises the following steps: video picture acquisition is carried out on multiple paths of video signals input from the outside, and one path to two paths of video pictures are selected for personnel action track detection analysis: continuously capturing target video pictures, screening out effective mobile data blocks in a detection area, storing the effective data blocks in two cache pools in a classified manner to continuously update the two cache pools, selecting corresponding effective data blocks in the two cache pools after each update for comparison analysis, thereby obtaining transverse continuity and longitudinal continuity among the effective mobile data blocks at each moment, and finally obtaining indoor personnel track analysis results according to the transverse continuity and the longitudinal continuity among the effective mobile data blocks at each moment. By adopting the embodiment of the invention, the personnel action track analysis can be carried out on a plurality of targets in two paths of video pictures at the same time, so that the additional installation of a new camera is avoided, and the complexity and the deployment difficulty of a track analysis system are reduced.
Description
Technical Field
The present invention relates to the field of video monitoring, and in particular, to a method and apparatus for analyzing indoor personnel trajectories, and a storage medium.
Background
Currently, in order to detect and analyze various movement tracks of a person indoors, a camera installed indoors may be used. The camera converts the moving track of the person in the room into track signals, and then the track signals are provided for other system components to complete track analysis in cooperation with the system. The motion trajectory generally includes linear movement, longitudinal upward movement, longitudinal downward movement, lateral left movement, lateral right movement, standing and sitting.
However, this requires that the camera have a function of detecting the movement track of the person, so that the track analysis can be completed in cooperation with the whole analysis system. The camera with the function of detecting the human action track will increase the purchase cost of the system, especially in some occasions, a common camera may be already installed, which will cause additional resource waste because a camera with the function of detecting the human action track is newly installed. Meanwhile, the cameras can only detect the action track of personnel on the video pictures shot by the cameras, so that the application range of the action track analysis system is greatly limited, and equipment deployment and installation are not facilitated.
Finally, the prior art personnel action track system cannot track and analyze multiple video pictures and multiple targets at the same time, which greatly restricts the use occasions of track analysis equipment.
Disclosure of Invention
The embodiment of the invention provides an indoor personnel track analysis method, an indoor personnel track analysis device and a storage medium, which integrate multi-path video picture detection, can simultaneously analyze personnel action tracks of a plurality of targets in two paths of video pictures, avoid additionally installing a new camera, and reduce the complexity and the deployment difficulty of a track analysis system.
A first aspect of an embodiment of the present application provides a method for analyzing an indoor personnel trajectory, where the method includes:
video picture acquisition is carried out on the externally input multi-channel video signals to obtain multi-channel video pictures;
selecting one or two paths of video pictures in the multiple paths of video pictures as target video pictures;
setting a detection area on a video pre-configuration picture according to the target video picture;
continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area to obtain an effective moving data block, and recording position coordinates of a person corresponding to the effective moving data block after moving; the moving data block refers to a data block generated by the movement of a person in the target video picture;
continuously updating a current effective personnel position coordinate buffer pool and a past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment;
after updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool each time, comparing and analyzing corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one to obtain transverse continuity and longitudinal continuity among the effective mobile data blocks at the current moment;
and obtaining the personnel movement track, the movement track value and the corresponding analysis log in the target video picture according to the transverse continuity and the longitudinal continuity among the effective movement data blocks at a plurality of moments.
In a possible implementation manner of the first aspect, the continuously capturing the target video frame, performing moving area validity analysis and moving data block center point coordinate position analysis on a moving data block in a detection area, obtaining an effective moving data block, and recording position coordinates of a person corresponding to the effective moving data block after moving, specifically includes:
continuously capturing the target video picture to obtain moving data blocks at all moments;
screening out the mobile data blocks in the detection area by adopting a ray-guiding method;
calculating the corresponding moving area of each screened moving data block;
if the area size of the moving area is in the preset moving area range, confirming that the moving area has effectiveness;
calculating to obtain an ideal area, an ideal head wide range, an ideal shoulder wide range and an ideal displacement range according to the moving area and the video pre-configuration picture;
if the center point coordinate of the moving area is in the ideal area, in the ideal head wide range, in the ideal shoulder wide range and in the ideal displacement range, confirming that the center point coordinate position of the moving data block has validity;
and taking the mobile data block with the mobile area validity and the mobile data block with the mobile data block center point coordinate position validity as an effective mobile data block, and recording the position coordinates of the personnel corresponding to the effective mobile data block after the personnel move.
In a possible implementation manner of the first aspect, the screening the mobile data blocks located in the detection area by using a projection method specifically includes:
a ray is led from the data points forming the moving data block, and if the number of intersection points of the ray and the polygon formed by the detection area is odd, the data points are in the detection area;
if the number of intersecting points of the polygon formed by the ray and the detection area is even, the data point is in the detection area.
In a possible implementation manner of the first aspect, the comparing and analyzing the corresponding valid mobile data blocks in the current valid personnel position coordinate buffer pool and the past valid personnel position coordinate buffer pool one by one to obtain the transverse continuity and the longitudinal continuity between the valid mobile data blocks at the current time specifically includes:
selecting a corresponding valid mobile data block from each of the current valid personnel position coordinate buffer pool and the past valid personnel position coordinate buffer pool;
calculating the leftmost horizontal coordinate difference value and the rightmost horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks;
if the leftmost horizontal coordinate difference value is smaller than a preset left threshold value and the rightmost horizontal coordinate difference value is smaller than a preset right threshold value, horizontally continuing between the two effective moving data blocks, and obtaining an up-down movement trend according to the central point vertical coordinate difference value of the two effective moving data blocks;
if the leftmost horizontal coordinate difference value is larger than a preset left threshold value or the rightmost horizontal coordinate difference value is larger than a preset right threshold value, calculating the top vertical coordinate difference value and the top horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks;
and if the top longitudinal coordinate difference value is smaller than a preset longitudinal threshold value and the top transverse coordinate difference value is larger than a transverse threshold value, the two effective moving data blocks are longitudinally continuous, and the left-right movement trend is realized according to the top transverse coordinate difference value.
In a possible implementation manner of the first aspect, the obtaining, according to the lateral continuity and the longitudinal continuity between the valid moving data blocks at a plurality of moments, the moving track of the person, the moving track value and the corresponding analysis log in the target video frame specifically includes:
and obtaining a moving track, a moving track value and a corresponding analysis log of the corresponding personnel according to the up-down moving trend and the left-right moving trend among the effective moving data blocks at a plurality of moments.
In a possible implementation manner of the first aspect, after the setting a detection area according to the target video frame and the video pre-configuration frame, the method further includes:
and setting head information, shoulder information and a shielding area in a video pre-configuration picture according to the target video picture.
A second aspect of the embodiments of the present application provides an indoor personnel trajectory analysis device, including:
the acquisition module is used for acquiring video pictures of the externally input multi-path video signals to obtain multi-path video pictures;
the selection module is used for selecting one path of video pictures or two paths of video pictures in the multiple paths of video pictures as target video pictures;
the preset module is used for setting a detection area on a video preset picture according to the target video picture;
the effective screening module is used for continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area, obtaining an effective moving data block and recording the position coordinates of the personnel corresponding to the effective moving data block after moving; the moving data block refers to a data block generated by the movement of a person in the target video picture;
the updating module is used for continuously updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment;
the comparison module is used for comparing and analyzing the corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one after the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool are updated each time, so as to obtain the transverse continuity and the longitudinal continuity between the effective mobile data blocks at the current moment;
and the analysis module is used for obtaining the personnel movement track, the movement track value and the corresponding analysis log in the target video picture according to the transverse continuity and the longitudinal continuity among the effective movement data blocks at a plurality of moments.
A third aspect of the embodiments of the present application provides a computer readable storage medium, including a stored computer program, where the computer readable storage medium is controlled to execute the indoor personnel trajectory analysis method according to the foregoing embodiments when the computer program runs.
Compared with the prior art, the indoor personnel track analysis method, the indoor personnel track analysis device and the storage medium provided by the embodiment of the invention have the advantages that under the condition that a new camera is not introduced, video picture acquisition is carried out on a plurality of paths of video signals input from outside, one path to two paths of video pictures are selected for personnel action track detection analysis: continuously capturing target video pictures, screening out effective mobile data blocks in a detection area, storing the effective data blocks in two cache pools in a classified manner to continuously update the two cache pools, selecting corresponding effective data blocks in the two cache pools after each update for comparison analysis, thereby obtaining transverse continuity and longitudinal continuity among the effective mobile data blocks at each moment, and finally obtaining an indoor multi-person track analysis result according to the transverse continuity and the longitudinal continuity among the effective mobile data blocks at each moment.
The invention can utilize the common camera which is installed at present and can support the detection of a plurality of camera pictures at the same time, thereby greatly reducing the installation cost of the track analysis system; the multi-path picture detection is integrated, so that the integration level of the system can be improved, and the laying of equipment and cables is reduced, so that the complexity of the track analysis system is reduced, and the stability of the track analysis system is improved.
Drawings
FIG. 1 is a schematic flow chart of an indoor personnel trajectory analysis method according to an embodiment of the present invention;
fig. 2 is a flow chart of a multi-channel video image acquisition method according to an embodiment of the invention;
FIG. 3 is a flowchart of a method for analyzing validity of a mobile area and analyzing coordinates of a center point of a mobile data block according to an embodiment of the present invention;
fig. 4 is a flow chart of a method for analyzing transversal continuity and longitudinal continuity between effective mobile data blocks according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides an indoor personnel trajectory analysis method, which includes:
s10, video picture acquisition is carried out on the externally input multi-channel video signals, and multi-channel video pictures are obtained.
S11, selecting one or two paths of video pictures in the multiple paths of video pictures as target video pictures.
S12, setting a detection area on a video pre-configuration picture according to the target video picture.
S13, continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area to obtain an effective moving data block, and recording position coordinates of a person corresponding to the effective moving data block after moving; the moving data block refers to a data block generated by human movement in the target video picture.
S14, continuously updating a current effective personnel position coordinate buffer pool and a past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; and the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment.
And S15, after updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool each time, comparing and analyzing the corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one to obtain the transverse continuity and the longitudinal continuity between the effective mobile data blocks at the current moment.
S16, according to the transverse continuity and the longitudinal continuity among the effective mobile data blocks at a plurality of moments, the personnel movement track, the movement track value and the corresponding analysis log in the target video picture are obtained.
In practical application, the ARM Cortex-A9 architecture-based processor can be adopted to collect video pictures of multiple paths of video signals input from the outside at the same time, and at most, two paths of video pictures in the ARM Cortex-A9 architecture-based processor can be subjected to personnel action track detection and analysis at the same time, and the external video signals can be connected through external interfaces such as HDMI, VGA, SDI, ethernet and the like. The effective data block analysis method provided by combining the collected multiple paths of video pictures with the embodiment can analyze the moving tracks of the personnel in the multiple video pictures in real time, and can obtain the moving tracks of the personnel including the longitudinal upward movement, the longitudinal upward downward movement, the transverse left movement and the transverse right movement.
It should be noted that other architecture processors may be adopted, so long as the adopted architecture processor is guaranteed to be capable of collecting video pictures of multiple paths of video signals input from the outside at the same time.
Referring to fig. 1, illustratively, the local camera 1, the remote camera 2, the local camera 3 and the remote camera 4 are all input to the architecture processor through external interfaces, a user can set video signals needing to perform detection of a person action track in a video pre-configuration picture in advance, and two of the video signals are selected through two 2-to-1 selectors in the figure. In this embodiment, the resolution of the input video signal is at the level of 1080p@60fps. The user may set a plurality of areas (detection areas) for detecting the movement track of the person in the video preconfigured screen page, or may directly set a plurality of areas (shielding areas) for not needing detection. After the video signals and the areas to be detected for the action track of the personnel are set, the capturing input video service of S13 can be started immediately, and after the service is started, one path to two paths of video signals are continuously captured and analyzed in real time.
Compared with the prior art, the indoor personnel track analysis method provided by the embodiment of the invention has the advantages that under the condition that a new camera is not introduced, video picture acquisition is carried out on a plurality of paths of video signals input from outside, one path to two paths of video pictures are selected for personnel action track detection analysis: continuously capturing target video pictures, screening out effective mobile data blocks in a detection area, storing the effective data blocks in two cache pools in a classified manner to continuously update the two cache pools, selecting corresponding effective data blocks in the two cache pools after each update for comparison analysis, thereby obtaining transverse continuity and longitudinal continuity among the effective mobile data blocks at each moment, and finally obtaining an indoor multi-person track analysis result according to the transverse continuity and the longitudinal continuity among the effective mobile data blocks at each moment.
The invention can utilize the common camera which is installed at present and can support the detection of a plurality of camera pictures at the same time, thereby greatly reducing the installation cost of the track analysis system; the multi-path picture detection is integrated, so that the integration level of the system can be improved, and the laying of equipment and cables is reduced, so that the complexity of the track analysis system is reduced, and the stability of the track analysis system is improved.
Illustratively, the S13 body includes:
and S130, continuously capturing the target video picture to obtain moving data blocks at all moments.
S131, screening out the mobile data blocks in the detection area by adopting a ray-guiding method.
S132, calculating the corresponding moving area of each screened moving data block.
S133, if the area size of the moving area is in the preset moving area range, confirming that the moving area has effectiveness.
S134, calculating to obtain an ideal area, an ideal head wide range, an ideal shoulder wide range and an ideal displacement range according to the moving area and the video pre-configuration picture.
And S135, confirming that the coordinate position of the center point of the moving data block is valid if the coordinate of the center point of the moving area is in the ideal area, in the ideal head wide range, in the ideal shoulder wide range and in the ideal displacement range.
S136, taking the mobile data block with the mobile area validity and the mobile data block with the mobile data block center point coordinate position validity as an effective mobile data block, and recording the position coordinates of the personnel corresponding to the effective mobile data block after the personnel move.
The embodiment can analyze video pictures of two paths of video signals at the same time, and a large amount of personnel movement data blocks can be generated for each detection of each video picture. FIG. 3 is a block movement area validity analysis and block movement center point coordinate position analysis method, i.e. a single block movement data captured in a single video frame is valid.
S133 is to determine whether the movement area Sa corresponding to the movement data block is valid. Since the area of the polygonal area generated when the human body moves varies within a certain range, in the present embodiment, the minimum value of the range is 500 units, and the maximum value is 8000 units. Therefore, if 500< Sa <8000, the effective area is represented. Then, it is further determined whether the area Sa of the moving area corresponding to the moving data block corresponds to the ideal area St where the coordinates of the center point thereof are located.
A ratio variable s16slope will be introduced here, s16slope representing the proportion of the lowest point ordinate u16Bottom of the polygon area to be detected in the whole video picture. The calculation formula is as follows:
s16 slope= (u 16Bottom-u16 mean)/(float) (u 16 mean-u 16 face) (equation 1)
Where u16Bottom represents the ordinate of the lowest point of the Sa region, u16 ry represents the top-most ordinate in the video preset screen, and u16near represents the Bottom-most ordinate in the video preset screen.
The ideal area corresponding to the moving area can be calculated by the following formula:
st= (pNear- > u32 MinValidObjSizeTh) +s16slope + (pNear- > u32MinValidObjSizeTh-pFar- > u32 MinValidObjSizeTh) (equation 2)
The pFar- > u32MinValidObjSizeTh represents the top ideal area in the video preset picture, the Near- > u32MinValidObjSizeTh represents the bottom ideal area in the video preset picture, and s16slope is the ratio variable calculated by the formula 1.
And then judging whether the data block accords with the ideal head width where the coordinates of the center point are located, and if so, continuing to carry out the next analysis. The ideal human head width u16HeadWidth of the moving area can be calculated by using the formula 3, and the calculation formula is as follows:
u16 HeadWidth= (StudentNearTh. StHeadDown. U16 HeadWidth+s16slope) (StudentNearTh. StHeadDown. U16 HeadWidWidStutFarTh. StHeadDown. U16 HeadWidth)) (1-0.3) (equation 3)
Wherein, stheaddown.u16headwidth represents the bottom end width in the video preset picture, stheaddown.u16headwidth represents the top end width in the video preset picture, and s16slope is the ratio variable calculated by formula 1.
Then, whether the moving data block accords with the fact that the coordinates of the center point of the moving data block are in the ideal shoulder width range is judged, and if so, the next analysis is continued. The ideal human shoulder width u16 shoulderewidth of the region to be moved can be calculated by using the formula 4, and the calculation formula is as follows:
u16 shoulderwidth= (sttrudingnearth. Stheaddown. U16 shoulderwidth+s16slope) 1+0.3 (equation 4)
Wherein, stheaddown.u16 shoulderer width represents the bottom-most shoulder width in the video preset picture, stheaddown.u16 shoulderer width represents the top-most shoulder width in the video preset picture, and s16slope is the ratio variable calculated by formula 1.
And then judging whether the moving data block accords with the ideal displacement of the position where the center point coordinate is located, and if so, continuing to carry out the next analysis. Since a certain displacement occurs when the person moves normally, since exceeding the ideal displacement range is regarded as an invalid data block. The ideal displacement u16VerScale of the moving region can be calculated by using equation 5, which is as follows:
u16 verscale= (u 16 spardistance + s16 slope: (u 16 spardistance-u 16 FarDistance))/10 (equation 5)
Wherein u16FarDistance and u16Neardistance can be calculated by equation 6 and equation 7, respectively.
u16 fardistance=ststudent farth.stHeadDown.u16HeadPosCoort-ststudent farth.stHeadUp.u16HeadPosCoort (equation 6)
Wherein stheaddown.u16headposcoory represents the ordinate of the topmost person sitting in the video preset screen. studentfarth.stheadup.u16headposcoory represents the ordinate of the video preset screen when the topmost person stands up.
u16 nearest distance=ststudent nearest th.stHeadDown.u16HeadPosCoort-ststudent nearest th.stHeadUp.u16HeadPosCoort (equation 7)
The studentneutral th.stheaddown.u16headposcoory represents the ordinate of the bottommost person in the video preset screen when sitting down. studentneutral th.stheadup.u16headposcoory represents the ordinate of the video preset screen when the bottommost person stands.
After the operation is finished, if all the judgment is passed, the position coordinates of the movement of the personnel are recorded, and a basis is provided for the judgment of the following movement direction and position.
Illustratively, S131 specifically includes:
s1310, a ray is started from the data points forming the moving data block, and if the number of intersection points of the ray and the polygon formed by the detection area is odd, the data points are in the detection area.
S1311, if the number of intersections of the polygon formed by the ray and the detection area is even, the data point is within the detection area.
The moving area and the detecting area are usually polygonal areas, wherein the moving area is a target area to be detected, the coordinates a (x 0, y 0) of a center point of the moving area and the area Sa of the polygon are calculated, the coordinates are assumed to be (x 0, y 0), a horizontal left or right ray is led to the point, the number of intersection points of the left ray and the polygon is 5, and the number of intersection points of the right ray and the polygon is 3, so that the point is in the polygonal area corresponding to the detecting area. And reserving all points meeting the conditions, and integrating the obtained point set into the screened mobile data block.
After a plurality of valid unit shift data blocks are recorded, the movement track of the personnel needs to be analyzed. Firstly, a personnel movement track system opens up two effective personnel position coordinate buffer pools, namely a buffer pool A and a buffer pool B, wherein the buffer pools store data blocks and part of accessory information of effective movement tracks of all personnel. The buffer pool A stores all effective moving track data blocks of the current picture, and the buffer pool B stores all effective moving track data blocks of the previous picture. The buffer pool data are updated alternately according to the change of the video picture, and the main basis of track judgment is that the moving track data blocks are analyzed continuously and rapidly for many times in a certain time, the moving track of the same person presents continuous change data, and the specific moving track can be analyzed through the data.
Illustratively, S15 specifically includes:
and S150, selecting a corresponding effective mobile data block from the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool each time.
S151, calculating the leftmost horizontal coordinate difference value and the rightmost horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks.
And S152, if the leftmost horizontal coordinate difference value is smaller than a preset left threshold value and the rightmost horizontal coordinate difference value is smaller than a preset right threshold value, horizontally continuing between the two effective moving data blocks, and obtaining an up-and-down movement trend according to the central point vertical coordinate difference value of the two effective moving data blocks.
And S153, if the leftmost horizontal coordinate difference value is larger than a preset left threshold value or the rightmost horizontal coordinate difference value is larger than a preset right threshold value, calculating the top vertical coordinate difference value and the top horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks.
And S154, if the top longitudinal coordinate difference value is smaller than a preset longitudinal threshold value and the top transverse coordinate difference value is larger than a transverse threshold value, the two effective moving data blocks are longitudinally continuous, and the left-right movement trend is realized according to the top transverse coordinate difference value.
Referring to fig. 4, first, buffer pool a data blocks acquired from a current picture need to be analyzed one by one, buffer pool a data blocks An (where n=1, 2, …) are taken, and buffer pool B data blocks Bn (where n=1, 2, …) are taken. First, it is determined whether the equation an_f (xl) -bn_f (xl) <Δx1holds, where an_f (xl) represents the left-most abscissa of the polygon area corresponding to the buffer pool a data block n, bn_f (xl) represents the left-most abscissa of the polygon area corresponding to the buffer pool B data block n, and Δx1=u16 sholderwidth-u 16Headwidth, u16 sholderwidth, and u16Headwidth can be obtained by the formulas 3 and 4, respectively. When an_f (xl) -bn_f (xl) <Δx1, it is indicated that the two moving data blocks are consecutive to the left. Similarly, the equation an_f (xr) -bn_f (xr) <Δx2is continued to be established, where an_f (xr) represents the right-most abscissa of the buffer pool a data block n corresponding to the polygonal area, bn_f (xr) represents the right-most abscissa of the buffer pool B data block n corresponding to the polygonal area, and Δx2=u16 sholderwidth-u 16HeadWidth. When an_f (xr) -bn_f (xr) <Δx2, it is indicated that the two moving data blocks are consecutive to the right. When the two sides between the moving data blocks are continuous, the specific moving track is judged by judging the sizes of an_F (yt) and Bn_F (yt), and when an_F (yt) < Bn_F (yt), the moving track is expressed as a vertical downward movement, and otherwise, the moving track is expressed as a vertical upward movement. After the judgment is finished, the coordinate position information of the mobile data block is updated and stored for the upper layer application to continue to use.
When the left offset or the right offset is discontinuous, the analysis of the moving data block is continued. When the moving track of the personnel moves transversely, the change of the vertical coordinate of the topmost end of the polygon area corresponding to the generated moving data block is small, the change of the horizontal coordinate is large, and the generated displacement is within a reasonable range when the personnel moves normally, and invalid data which is discontinuous is judged to be beyond the range. By utilizing the characteristics, whether the equation an_F (yl) -Bn_F (yl) <deltay 1 is established is firstly judged, wherein an_F (yl) represents the ordinate of the buffer pool A data block n corresponding to the topmost end of the polygonal area, bn_F (xl) represents the abscissa of the buffer pool B data block n corresponding to the topmost end of the polygonal area, and delta y1=240 is a picture preset value. When the difference value does not exceed deltay 1, it means that the movement locus is continuous in the longitudinal direction. Then, whether an_f (xl) -bn_f (xl) <Δx3is true or not is determined, wherein Δx3=100 is a preset value of the picture. Then, whether an_f (xl) -bn_f (xl) >. DELTA.x4 is true or not is determined, wherein DELTA.x4=30, which is a preset value of the picture. When the difference value does not exceed Δx3 and is greater than Δx4, it means that the movement locus is laterally continuous.
Finally, judging left shift or right shift according to the values of an_F (xl) and Bn_F (xl). When an_f (xl) > bn_f (xl), a lateral right shift is indicated, whereas a lateral left shift is indicated.
Illustratively, S16 specifically includes:
and obtaining a moving track, a moving track value and a corresponding analysis log of the corresponding personnel according to the up-down moving trend and the left-right moving trend among the effective moving data blocks at a plurality of moments.
Illustratively, after the setting of the detection area according to the target video picture in the video pre-configuration picture, the method further comprises:
and setting head information, shoulder information and a shielding area in a video pre-configuration picture according to the target video picture.
The embodiment of the application provides an indoor personnel track analysis device, which comprises: the device comprises an acquisition module, a selection module, a preset module, an effective screening module, an updating module, a comparison module and an analysis module.
The acquisition module is used for acquiring video pictures of the externally input multi-path video signals to obtain multi-path video pictures.
And the selection module is used for selecting one video picture or two video pictures in the multiple video pictures as target video pictures.
The preset module is used for setting a detection area on a video preset picture according to the target video picture;
the effective screening module is used for continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area, obtaining an effective moving data block and recording the position coordinates of the personnel corresponding to the effective moving data block after moving; the moving data block refers to a data block generated by human movement in the target video picture.
The updating module is used for continuously updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; and the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment.
And the comparison module is used for comparing and analyzing the corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one after the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool are updated each time, so as to obtain the transverse continuity and the longitudinal continuity between the effective mobile data blocks at the current moment.
And the analysis module is used for obtaining the personnel movement track, the movement track value and the corresponding analysis log in the target video picture according to the transverse continuity and the longitudinal continuity among the effective movement data blocks at a plurality of moments.
The embodiment of the application provides a computer readable storage medium, which comprises a stored computer program, wherein when the computer program runs, equipment where the computer readable storage medium is located is controlled to execute the indoor personnel track analysis method according to the embodiment.
The computer readable storage medium of the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include at least the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (6)
1. An indoor personnel trajectory analysis method, comprising:
video picture acquisition is carried out on the externally input multi-channel video signals to obtain multi-channel video pictures;
selecting one or two paths of video pictures in the multiple paths of video pictures as target video pictures;
setting a detection area on a video pre-configuration picture according to the target video picture;
continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area to obtain an effective moving data block, and recording the position coordinates of the moving personnel corresponding to the effective moving data block, wherein the moving area effectiveness analysis and the moving data block center point coordinate position analysis specifically comprise the following steps: continuously capturing the target video picture to obtain moving data blocks at all moments; screening out the mobile data blocks in the detection area by adopting a ray-guiding method; calculating the corresponding moving area of each screened moving data block; if the area size of the moving area is in the preset moving area range, confirming that the moving area has effectiveness; calculating to obtain an ideal area, an ideal head wide range, an ideal shoulder wide range and an ideal displacement range according to the moving area and the video pre-configuration picture; if the center point coordinate of the moving area is in the ideal area, in the ideal head wide range, in the ideal shoulder wide range and in the ideal displacement range, confirming that the center point coordinate position of the moving data block has validity; taking a mobile data block with mobile area validity and mobile data block center point coordinate position validity as an effective mobile data block, and recording position coordinates of a person corresponding to the effective mobile data block after the person moves; the moving data block refers to a data block generated by the movement of a person in the target video picture;
continuously updating a current effective personnel position coordinate buffer pool and a past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment; after updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool each time, comparing and analyzing corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one to obtain transverse continuity and longitudinal continuity between the effective mobile data blocks at the current moment, wherein the method specifically comprises the following steps: selecting a corresponding effective mobile data block from the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool respectively; calculating the leftmost horizontal coordinate difference value and the rightmost horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks; if the leftmost horizontal coordinate difference value is smaller than a preset left threshold value and the rightmost horizontal coordinate difference value is smaller than a preset right threshold value, horizontally continuing between the two effective moving data blocks, and obtaining an up-down movement trend according to the central point vertical coordinate difference value of the two effective moving data blocks; if the leftmost horizontal coordinate difference value is larger than a preset left threshold value or the rightmost horizontal coordinate difference value is larger than a preset right threshold value, calculating the top vertical coordinate difference value and the top horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks; if the top longitudinal coordinate difference value is smaller than a preset longitudinal threshold value and the top transverse coordinate difference value is larger than a transverse threshold value, the two effective moving data blocks are longitudinally continuous, and the left-right movement trend is realized according to the top transverse coordinate difference value;
and obtaining the personnel movement track, the movement track value and the corresponding analysis log in the target video picture according to the transverse continuity and the longitudinal continuity among the effective movement data blocks at a plurality of moments.
2. The method for analyzing the track of indoor personnel according to claim 1, wherein the screening out the moving data blocks in the detection area by adopting a projection method specifically comprises the following steps:
a ray is led from the data points forming the moving data block, and if the number of intersection points of the ray and the polygon formed by the detection area is odd, the data points are in the detection area;
if the number of intersecting points of the polygon formed by the ray and the detection area is even, the data point is in the detection area.
3. The method for analyzing the indoor personnel trajectory according to claim 2, wherein the step of obtaining the personnel movement trajectory, the movement trajectory value and the corresponding analysis log in the target video frame according to the lateral continuity and the longitudinal continuity between the effective movement data blocks at a plurality of moments comprises the following steps:
and obtaining a moving track, a moving track value and a corresponding analysis log of the corresponding personnel according to the up-down moving trend and the left-right moving trend among the effective moving data blocks at a plurality of moments.
4. The indoor personnel trajectory analysis method of claim 1, further comprising, after the setting of the detection area according to the target video picture, a video pre-configuration picture:
and setting head information, shoulder information and a shielding area in a video pre-configuration picture according to the target video picture.
5. An indoor personnel trajectory analysis device, comprising:
the acquisition module is used for acquiring video pictures of the externally input multi-path video signals to obtain multi-path video pictures;
the selection module is used for selecting one path of video pictures or two paths of video pictures in the multiple paths of video pictures as target video pictures;
the preset module is used for setting a detection area on a video preset picture according to the target video picture;
the effective screening module is used for continuously capturing the target video picture, carrying out moving area effectiveness analysis and moving data block center point coordinate position analysis on the moving data block in the detection area, obtaining an effective moving data block and recording the position coordinates of the personnel corresponding to the effective moving data block after moving, and specifically comprises the following steps: continuously capturing the target video picture to obtain moving data blocks at all moments; screening out the mobile data blocks in the detection area by adopting a ray-guiding method; calculating the corresponding moving area of each screened moving data block; if the area size of the moving area is in the preset moving area range, confirming that the moving area has effectiveness; calculating to obtain an ideal area, an ideal head wide range, an ideal shoulder wide range and an ideal displacement range according to the moving area and the video pre-configuration picture; if the center point coordinate of the moving area is in the ideal area, in the ideal head wide range, in the ideal shoulder wide range and in the ideal displacement range, confirming that the center point coordinate position of the moving data block has validity; taking a mobile data block with mobile area validity and mobile data block center point coordinate position validity as an effective mobile data block, and recording position coordinates of a person corresponding to the effective mobile data block after the person moves; the moving data block refers to a data block generated by the movement of a person in the target video picture;
the updating module is used for continuously updating the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool according to the effective mobile data block; the current effective personnel position coordinate buffer pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the current moment; the past effective personnel position coordinate cache pool stores all effective mobile data blocks and auxiliary coordinate information of the target video picture at the last moment;
the comparison module is used for comparing and analyzing the corresponding effective mobile data blocks in the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool one by one after the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool are updated each time to obtain the transverse continuity and the longitudinal continuity between the effective mobile data blocks at the current moment, and specifically comprises the following steps: selecting a corresponding effective mobile data block from the current effective personnel position coordinate buffer pool and the past effective personnel position coordinate buffer pool respectively; calculating the leftmost horizontal coordinate difference value and the rightmost horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks; if the leftmost horizontal coordinate difference value is smaller than a preset left threshold value and the rightmost horizontal coordinate difference value is smaller than a preset right threshold value, horizontally continuing between the two effective moving data blocks, and obtaining an up-down movement trend according to the central point vertical coordinate difference value of the two effective moving data blocks; if the leftmost horizontal coordinate difference value is larger than a preset left threshold value or the rightmost horizontal coordinate difference value is larger than a preset right threshold value, calculating the top vertical coordinate difference value and the top horizontal coordinate difference value of the corresponding moving areas of the two effective moving data blocks; if the top longitudinal coordinate difference value is smaller than a preset longitudinal threshold value and the top transverse coordinate difference value is larger than a transverse threshold value, the two effective moving data blocks are longitudinally continuous, and the left-right movement trend is realized according to the top transverse coordinate difference value;
and the analysis module is used for obtaining the personnel movement track, the movement track value and the corresponding analysis log in the target video picture according to the transverse continuity and the longitudinal continuity among the effective movement data blocks at a plurality of moments.
6. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the indoor personnel trajectory analysis method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292638.7A CN113034458B (en) | 2021-03-18 | 2021-03-18 | Indoor personnel track analysis method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292638.7A CN113034458B (en) | 2021-03-18 | 2021-03-18 | Indoor personnel track analysis method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034458A CN113034458A (en) | 2021-06-25 |
| CN113034458B true CN113034458B (en) | 2023-06-23 |
Family
ID=76471582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110292638.7A Active CN113034458B (en) | 2021-03-18 | 2021-03-18 | Indoor personnel track analysis method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034458B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115225963A (en) * | 2022-06-24 | 2022-10-21 | 浪潮通信技术有限公司 | Indoor positioning monitoring method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090022154A (en) * | 2007-08-29 | 2009-03-04 | 순환엔지니어링 주식회사 | Method for tracing real time the trace of transfer and apparatus and recoding media for the same |
| CN110555397A (en) * | 2019-08-21 | 2019-12-10 | 武汉大千信息技术有限公司 | crowd situation analysis method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680557A (en) * | 2015-03-10 | 2015-06-03 | 重庆邮电大学 | Intelligent detection method for abnormal behavior in video sequence image |
| CN105760826B (en) * | 2016-02-03 | 2020-11-13 | 歌尔股份有限公司 | Face tracking method and device and intelligent terminal |
| CN110210276A (en) * | 2018-05-15 | 2019-09-06 | 腾讯科技（深圳）有限公司 | A kind of motion track acquisition methods and its equipment, storage medium, terminal |
| CN109726683B (en) * | 2018-12-29 | 2021-06-22 | 北京市商汤科技开发有限公司 | Target object detection method and device, electronic equipment and storage medium |
| CN110062272B (en) * | 2019-04-30 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Video data processing method and related device |
| CN111611433B (en) * | 2020-05-22 | 2023-06-02 | 浙江大华技术股份有限公司 | Video processing method, device, equipment and medium |
| CN111767798B (en) * | 2020-06-01 | 2022-07-15 | 武汉大学 | Intelligent broadcasting guide method and system for indoor networking video monitoring |
| CN111815675B (en) * | 2020-06-30 | 2023-07-21 | 北京市商汤科技开发有限公司 | Target object tracking method and device, electronic equipment and storage medium |
| CN112200830A (en) * | 2020-09-11 | 2021-01-08 | 山东信通电子股份有限公司 | Target tracking method and device |
-
2021
- 2021-03-18 CN CN202110292638.7A patent/CN113034458B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090022154A (en) * | 2007-08-29 | 2009-03-04 | 순환엔지니어링 주식회사 | Method for tracing real time the trace of transfer and apparatus and recoding media for the same |
| CN110555397A (en) * | 2019-08-21 | 2019-12-10 | 武汉大千信息技术有限公司 | crowd situation analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034458A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4568009B2 (en) | Monitoring device with camera cooperation | |
| DE69831181T2 (en) | location | |
| US6741725B2 (en) | Motion tracking using image-texture templates | |
| CN105611230B (en) | Image processing apparatus and image processing method | |
| US7522186B2 (en) | Method and apparatus for providing immersive surveillance | |
| JP4727117B2 (en) | Intelligent feature selection and pan / zoom control | |
| KR101533686B1 (en) | Apparatus and method for tracking gaze, recording medium for performing the method | |
| CN106488115B (en) | For tracking and sensing the control device and method of the image sensing apparatus of tracking target | |
| JP4470759B2 (en) | Information processing system, information processing apparatus, information processing method, program, and recording medium | |
| US9615062B2 (en) | Multi-resolution image display | |
| JP2005504457A (en) | Motion detection by image alignment | |
| CN110324572B (en) | Monitoring system, monitoring method, and non-transitory computer-readable storage medium | |
| US8134614B2 (en) | Image processing apparatus for detecting an image using object recognition | |
| US10122984B2 (en) | Pan/tilt/zoom camera based video playing method and apparatus | |
| US20150049185A1 (en) | Method and apparatus for detecting posture of surveillance camera | |
| CN105898107A (en) | Target object snapping method and system | |
| CN106604005A (en) | Automatic projection TV focusing method and system | |
| CN113034458B (en) | Indoor personnel track analysis method, device and storage medium | |
| JP5854951B2 (en) | Panorama image generator | |
| US20120229678A1 (en) | Image reproducing control apparatus | |
| CN105303563A (en) | Fall-down detection method and device | |
| CN104104902B (en) | Holder direction fault detection method and device | |
| JPH09293141A (en) | Mobile object detection device | |
| US20130265420A1 (en) | Video processing apparatus, video processing method, and recording medium | |
| KR102107137B1 (en) | Method and Apparatus for Detecting Event by Using Pan-Tilt-Zoom Camera |
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 |