CN106910203B - The quick determination method of moving target in a kind of video surveillance - Google Patents
The quick determination method of moving target in a kind of video surveillance Download PDFInfo
- Publication number
- CN106910203B CN106910203B CN201611069001.7A CN201611069001A CN106910203B CN 106910203 B CN106910203 B CN 106910203B CN 201611069001 A CN201611069001 A CN 201611069001A CN 106910203 B CN106910203 B CN 106910203B
- Authority
- CN
- China
- Prior art keywords
- target
- frame
- video
- point
- tracking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a kind of quick determination method of moving target in video surveillance, establishing background model, detection moving region, measure target to be measured and the quick detection that moving target in video surveillance is realized by way of carrying out specific tracking etc. to target to video to be measured.The moving target that the quick determination method of moving target can be in quick detection video in video surveillance provided by the invention, the calculating and detection of characteristic goal are carried out according to the target data Sample Storehouse prestored, the problem of avoiding target missing inspection well and pick up again.
Description
Technical field
The invention belongs to field of video detection, and in particular to the quick determination method of moving target in a kind of video surveillance.
Background technology
With full-scale digital, the development of the video monitoring system of networking, the effect of video monitoring becomes more obvious,
Exploration, integration and the flexibility of its height, more wide development space, intelligence are provided for the development of whole security protection industry
Energy video monitoring turns into video monitoring trend of new generation due to the features such as assigning more intellectuality, activeization, validity.
The demand of intelligent video monitoring system mostlys come from those occasions sensitive to safety requirements, as army, public security,
Bank, road, parking lot etc..When theft occur or it is abnormal occur when, such system can actively to guard promptly and accurately
Ground sends alarm, enables staff to make full use of video surveillance network to implement alarm linkage and emergency command disposal, so as to
Avoid the generation of crime.Decrease the input for employing large quantities of monitoring personnel simultaneously.
Important content and basis as intelligent monitoring technology, to target (especially vehicle and pedestrian target) detect and with
Continuing to optimize for track is the constantly progressive necessary process of intelligent monitoring technology.Following problem existing for the detection of target following at present：
1) moving target monitors the basis as target following, directly affects the effect of tracking.But due to holding during video acquisition
It is vulnerable to the interference of extraneous factor, such as DE Camera Shake, illumination variation, target shadow interference, target occlusion, homochromy ambient interferences
Deng these reality factors can all bring sizable difficulty to target monitoring.Such as exist with the variation targets shade of lighting angle
Target prospect can be detected as by different degrees of in monitoring process, target global shape is produced a very large impact；Target occlusion makes
Detection process is difficult to obtain the overall shape of target, loses target relevant information, is unfavorable for follow-up tracking；Illumination variation, take the photograph
Camera shake, ambient interferences can regard noise as, the same accuracy for influenceing target detection.2) occlusion issue is current target
The Important Problems of tracking, present most of Target Tracking Systems not can effectively solve the problem that with target by background or other mesh
Mutual occlusion issue between mark.Target occlusion during tracking is random, unpredictable the problem of.Asked for such
The simple background modeling that relies on of topic realizes that target detection or track algorithm are insecure, it is necessary to establish preferably object module or
Feature templates, and solved using those visible target parts with model or the accurate match of feature.Therefore, target inspection is improved
The efficiency and accuracy rate of survey are vital contents in intelligent video monitoring system.
Target detection in monitor video, it is broadly divided into two classes：(1) moving object detection；(2) based on image recognition
Target detection.Both respectively have advantage and disadvantage, and moving object detection can fast and effeciently detect the moving target in monitor video, but
The target being still in scene can not be detected, and also seem more powerless in the separation of adhesion target；Based on image
The target detection of identification, all targets in full figure are detected, either moving target or static target, due to relying on
Judge in feature, these are excellent for influence of this kind of method obtain higher accuracy rate, recall rate and be less subject to adhesion situations such as
While gesture, it generally require that more run times.
The content of the invention
It is an object of the invention to provide in a kind of video surveillance in order to overcome above the deficiencies in the prior art and move mesh
Target quick determination method.
Technical scheme is as follows：
The quick determination method of moving target, comprises the following steps in a kind of video surveillance：
Step 1, video V={ I to be measured0,I1,I2,…,Ik, wherein IkIt is the kth frame image in video V, by video
0th two field picture is set as initial back-ground model D0, i.e. D0=I0；
Step 2, by calculating Fk=Ik-Dk-1Extraction prospect, and in FkThe set S of the upper potential moving region of extractionkIf
Determine SkThe initial value O of the set of middle targetk={ } is empty set；It is the image I that currently will analyzing wherein to extract prospectkWith the back of the body
Scape model Dk-1Point-to-point to subtract each other, difference exceedes the point of constant 10 as foreground point, otherwise as background dot；It is point-to-point to have subtracted each other
Into morphology open and close operation is used afterwards, cross noise filtering and make UNICOM region relatively more regular, then obtained using region growing method
All UNICOM regions wherein as prospect are obtained, close region is merged, obtains the set S of potential moving regionk；
Step 3, for step 2 SiIn each potential moving region s, detect s in target to be checked that may be present, institute
There is the target detected to add set OkIn；
Step 4, to Ok-1In all targets, be tracked in kth frame, gained target to be checked is also added to Ok
In, and continue to appear in present frame to the last time of lost target in all short time forward and be tracked, gained target
It is also added to current goal set OkIn；
Step 5, for set OkThe target that middle certain time occurs without makees disappearance processing, by the target from set OkIn delete
Remove；Step 6, update background model；
Step 7, for next two field picture, repeat the above steps and two arrive step 6, until detecting video last frame figure
As after, testing result is obtained.
Further, in described video surveillance moving target quick determination method, detecting in step 3 may deposit in s
Mesh calibration method to be checked be multiple dimensioned, floating window and the method for target identification based on HoG feature calculations.
Further, in described video surveillance moving target quick determination method, based on HoG feature calculations
Target identification, it is also necessary to set a decision mechanism, a target data Sample Storehouse, data sample are first demarcated manually headed by the mechanism
This storehouse is made up of the picture of a large amount of identical sizes, and all having demarcated it per pictures whether there is particular detection target, per pictures
In the HoG features of each pixel be acquired；Decision mechanism is by the HoG features of each pixel in obtaining per pictures and then shape
In pairs in the identification model data of detection target；During particular detection, first by window to be measured be adjusted to in decision mechanism
Picture identical size, then by whether there is particular detection target in identification model data judging window to be measured.
Further, in described video surveillance moving target quick determination method, detecting in step 3 may deposit in s
Mesh calibration method to be checked can also be according to following progress：
1) it is the seat of pixel using the first two field picture as initial background, i.e. C (x, y, 1)=T (x, y, k), wherein x, y
Mark, k is frame number number；
2) to present frame T (x, y, k), the calculating of target identification matrix D (x, y, k) is carried out, calculation formula is：
Wherein C (x, y, k) is current background image, and F (k) span is 20-40；
3) each pixel A is countedi,j,kAnd Ai+n,j+m,k+fProbability within the time and space field of pixel to be measured is close
Degree, calculates the value of information gap and test point pixel, and wherein information gap M (x, y, k) is：
In formula, g (Ai,j,k) and g (Ai+n,j+m,k+f) it is respectively pixel Ai,j,kAnd Ai+n,j+m,k+fIn time-domain and spatial domain
Interior probability density function；Value Z (the A of pixeli,j,k) be：Z(Ai,j,k)=g (Ai,j,k)+M (x, y, k)/26, (k >=2)；
4) by the value Z (A of pixeli,j,kThe region of) >=0.02 marks as prospect, labeled as Qq；The value Z of pixel
(Ai,j,kThe region of)≤0.02 is as context marker, labeled as Qb；
5) the multiscale morphological gradient image g of present frame is calculated using Multiscale Morphological method；
6) mark Q more than utilizingqWith QbOptimize：G ,=imimposemin (g, Qq|Qb), then calculated using watershed
Method obtains target image：Contour=watershed (g)；
7) to next frame image update and establish new background, repeat step 2) -6), until last frame image, examined
Survey result.
Further, in described video surveillance moving target quick determination method, the method tracked in step 4 is such as
Under：
1) initialize first in frame to be tracked with tracking source frame in target location identical position be initial retrieval position p；
2) in frame to be tracked retrieve position p centered on, size and the target equal-sized rectangle frame in source frame is tracked
As potential tracking result, the target in it and tracking source is sought into mean square deviation, if this value is less than threshold value 2, then it is assumed that with
Track is completed, and have found tracking target, algorithm terminates；
3) it is eight positions diamond shaped positions around p if the mean square deviation that previous step obtains is unsatisfactory for condition：It is tiltedly right
Four adjoint points at angle+up and down each every the position of any each calculate respectively as rectangle frame center with tracking target with
Mean square deviation in track source frame, think tracking knot is not present if this eight values exceed the mean square deviation of previous step acquisition
Fruit, algorithm terminate；Otherwise, p is replaced to produce the point of lowest mean square difference；
4) occur to the last time of the target in a range of frame before present frame, all using in above step
Method is tracked.
Further, in described video surveillance moving target quick determination method, update background model in step 6
Specially it is the point of (x, y) to position, such as the brightness value in current background model is d, and the brightness value in present image
It is p, then is updated to D by present image, the value of background modelk=(1- α) × d+ α × p, if the point that position is (x, y) exists
It is determined as background dot in step 2, then α values take 0.1, if being determined as foreground point in step 2, α values take 0.01.
Further, in described video surveillance moving target quick determination method, in step 4) before present frame
A range of frame refers to preceding 25 frame of present frame.
The motion that the quick determination method of moving target can be in quick detection video in video surveillance provided by the invention
Target, the calculating and detection of characteristic goal are carried out according to the target data Sample Storehouse prestored, avoid target leakage well
Inspection and the problem of picking up again.
Brief description of the drawings
Fig. 1 is the flow chart of the moving target quick determination method described in the embodiment of the present invention 1；
Fig. 2 is the picture of the before processing described in the embodiment of the present invention 1；
Fig. 3 is the differentiated picture of background described in the embodiment of the present invention 1；
Fig. 4 is the picture after morphological operation described in the embodiment of the present invention 1；
Fig. 5 is the picture of the final detection structure described in the embodiment of the present invention 1.
Embodiment
Embodiment 1
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and reference
Accompanying drawing, the present invention is described in more detail.
Fig. 1 is the flow chart for the moving target quick determination method that the present embodiment provides, and is comprised the following steps：
Step M1, to each two field picture in video sequence, all potential moving regions therein are detected, and obtain
The position in these regions；
In the present embodiment, we choose the HD video segment of one section of CCTV camera shooting, and resolution ratio is
1920x1080, video scene are the road traffics that both sides are greenbelt, the point pixel of the picture in video sequence, its brightness value
Between 0~255, video is designated as V={ I0,I1,I2,…,Ik, wherein IkIt is the kth frame image in video V, ours is follow-up
Analysis is all based on brightness value progress, and Fig. 2 is the pictures for picking up from the video.
Background model DkIt is the data needed to use in step M1, it represents the prediction to the background of current scene.
Under initial situation, DkIt is set equal to the first pictures in video sequence, i.e. D0=I0, during subsequent execution, D0Carry out
Real-time update；
Step M1 further comprises the steps：
Step M11, the current picture analyzed in video sequence and background model D0It is point-to-point to subtract each other extraction prospect,
That is Fk=Ik-Dk-1, now k=1 (Fig. 3 shows the result that picture and background model subtract each other in Fig. 2), wherein difference exceedes some
The point of constant (such as 10) is considered as foreground point, otherwise it is assumed that being background dot.By the step, we have known current figure
The preliminary judgement of the foreground/background of every bit as in；
Step M12, the preliminary judgement of the foreground/background obtained according to previous step, plucks out the potential fortune in present image
Dynamic region Sk.Set SkThe initial value O of the set of middle targetk={ } is empty set, and then order uses morphology open and close operation, mistake
Noise filtering simultaneously makes UNICOM region relatively more regular, on this basis, the institute wherein as prospect is obtained using region growing method
There is UNICOM region, each UNICOM region is exactly a potential moving region, to these UNICOM regions, is once closed on area
Domain merges：If the minimum in Liang Ge UNICOMs region, which includes the distance between rectangle, is no more than some threshold value (such as 3), then by this
Liang Ge UNICOMs region merging technique.Fig. 3 such as Fig. 4 of the result after morphological operation, it is last all these by UNICOM's region merging technique
Highlight regions form the potential moving region of only one, and (needing also can be as seen from the figure the reason for carrying out adjacent area merging
Come, object vehicle therein has been partitioned into several adjoining UNICOM regions, if without merging, it is possible to which automobile is drawn
It is divided into several fractions)；
Step M13, update background model D with present image0.It is the point of (x, y) to position, it is assumed that in current background model
In value be d, and the value in present image is p, then is updated to D by present image, the value of background model1=(1- α) × d
+ α × p, if the point of the position is judged as background in M11, using a larger α value (such as 0.1), if should
The point of position is judged as prospect in M11, then using a less α value (such as 0.01)；
Step M2, target identification is carried out to each the potential moving region exported in step M12, it is wherein real to find out
Target in meaning, step M2 further comprise：
Step M21, division of the multiple dimensioned floating window to region is determined, the size of floating window is according to the actual possibility of target
Size is set.For certain specific target, it is assumed that minimum dimension of such target in video image be s × t (for
Target pedestrian, this value is using such as：S=8, t=16；For target vehicle, this value is using such as：S=24,
T=24), then it is s × t that window size is defined on first yardstick, and the window floats in the upper left position in region first, then
The window's position float from left to right, from the top down successively until the lower right corner in region, the displacement floated every time is window size
1/2 (i.e. the span of displacement from left to right is s/2, and the span of displacement is t/2 from the top down), when the location free procedure terminates, i.e.,
The location free procedure of first yardstick terminates；Into the floating of second yardstick, in the floating of this second yardstick, floating frame
Some wide, high wide, high while that be adjusted to floating frame in a yardstick be more than 1 constant times (such as 1.05), so
It is similar afterwards equally to be floated in first yardstick, next one yardstick is entered after terminating until window size has exceeded target
Full-size untill (such as：Two times of minimum dimension are wide, high).All stop places of each of the above yardstick floating window, shape
Into the region division to the region, we can judge to whether there is the specific mesh in each of which position in step below
Mark.So it is exactly to form this region division (region has been partitioned into many window's positions, between these positions that M21 is actual
Mutually may be overlapping)；
Step M22, to calculating HoG features a little in region, the calculating of HoG features, it can directly use OpenCV
Respective function complete；
Step M23, each the window's position come out to M21 region divisions, is carried out based on HoG features in the window
Target identification (carries out pedestrian/vehicle identification) respectively, as the result of identification, each window of region division, is judged
In the window there is target in Yes/No.
Based on the target identification of HoG features, this needs to use step M4 progress machine learning acquisitions decision mechanism (i.e.
Identification model, that is, model data D3).
In order to which step M4 carries out machine learning, a target data Sample Storehouse D2 has been demarcated manually first (for pedestrian, car
It is each to have such set of data samples by oneself, illustrated now just for a certain kind therein), data sample storehouse D2
(such as 32 × 64) are formed by the picture of the identical size of a certain amount of (such as 1000 width), each picture, which has been demarcated, is wherein
Or it is no specific objective (i.e. pedestrian/vehicle) be present, the HoG features of each pixel, which obtain, in each picture (obtains special
Sign)；
Step M4, the identification model data of the target are obtained based on D2 progress machine learning.Due to the size of picture in D2
Fixed, the byte number of the HoG features of each pixel is also fixed in picture, therefore it is exactly to regard one as that each pictures are actual
The individual high dimension vector formed by the HoG features arranged in sequence of all pixels, and whether include specific mesh in this pictures
Mark (0,1) is classification, and this is a very typical classification problem, and we complete this learning process using SVM algorithm
(SVM algorithm is directly carried out using the function in OpenCV), so as to obtain the identification model data D3 of the target；
In M23, we are first adjusted to window size the size of picture in D2, are called then or with SVM algorithm
Model data D3, identification is completed, judges that Yes/No has the specific objective in the window；
Step M24, arrange recognition result.Due to there is largely overlapping between those windows of M21 region divisions,
It is therefore possible to simple target repeatedly to be identified, it is therefore desirable to which it is weight which the simple target for judging to recognize in M23, which wherein has,
Multiple, by arranging, all targets finally arrived in the region detection are obtained, and these targets are added to set OkIn (Fig. 5
Fig. 4 final recognition result, it is seen that come it on moving region two targets of adhesion separate)；
For potential moving region SkIn target truly detection, we research process also carried out with
Lower detection mode：
1) it is the seat of pixel using the first two field picture as initial background, i.e. C (x, y, 1)=T (x, y, k), wherein x, y
Mark, k is frame number number；
2) to present frame T (x, y, k), the calculating of target identification matrix D (x, y, k) is carried out, calculation formula is：
Wherein C (x, y, k) is current background image, and F (k) span is 20-40；
3) each pixel A is countedi,j,kAnd Ai+n,j+m,k+fProbability within the time and space field of pixel to be measured is close
Degree, calculates the value of information gap and test point pixel, and wherein information gap M (x, y, k) is：
In formula, g (Ai,j,k) and g (Ai+n,j+m,k+f) it is respectively pixel Ai,j,kAnd Ai+n,j+m,k+fIn time-domain and spatial domain
Interior probability density function；Value Z (the A of pixeli,j,k) be：Z(Ai,j,k)=g (Ai,j,k)+M (x, y, k)/26, (k >=2)；
4) by the value Z (A of pixeli,j,kThe region of) >=0.02 marks as prospect, labeled as Qq；The value Z of pixel
(Ai,j,kThe region of)≤0.02 is as context marker, labeled as Qb；
5) the multiscale morphological gradient image g of present frame is calculated using Multiscale Morphological method；
6) mark Q more than utilizingqWith QbOptimize：G ,=imimposemin (g, Qq|Qb), then calculated using watershed
Method obtains target image：Contour=watershed (g)；
7) new background, repeat step 2 are established to next frame image update and according to above step M13) -6), until last
One two field picture.
By above detecting step, finally give and step M24 identical particular detection target vehicles and pedestrian.
Step M3, carry out target following.Step M2 have detected target to all potential moving regions of present image, him
Integrate all targets just obtained in present image, it is known that these targets are not isolated existing, it can regarding
Persistently exist in a period of time in frequency sequence, we string together the target between different images, so as to obtain by step 3
Obtain the motion track of target；
Step M31, some obvious undesirable targets are screened out, this is a reservation step, in a variety of causes
Be likely to require and do a preliminary screening, for example, boundary, such as due to wrong report that recognition accuracy deficiency is brought etc.；
Step M32, to present image IkSet O beforek-1In target, to tracking before present frame k is carried out, tracking
Method is specific as follows：
1) initialize first in frame to be tracked with tracking source frame in target location identical position be initial retrieval position p；
2) in frame to be tracked retrieve position p centered on, size and the target equal-sized rectangle frame in source frame is tracked
As potential tracking result, the target in it and tracking source is sought into mean square deviation, if this value is less than threshold value 2, then it is assumed that with
Track is completed, and have found tracking target, algorithm terminates；
3) it is eight positions diamond shaped positions around p if the mean square deviation that previous step obtains is unsatisfactory for condition：It is tiltedly right
Four adjoint points at angle+up and down each every the position of any each calculate respectively as rectangle frame center with tracking target with
Mean square deviation in track source frame, think tracking knot is not present if this eight values exceed the mean square deviation of previous step acquisition
Fruit, algorithm terminate；Otherwise, p is replaced to produce the point of lowest mean square difference；
4) occur to the last time of the target in a range of frame before present frame (such as 25 frames), all use
Method in above step is tracked, and sees whether it occurs, if there is, judge whether be among M24 testing result,
If then both are connected by identifying identical ID, work as if not then it is added to as a newfound target
Preceding goal set OkIn；
Step M33, it would be desirable to which disappearance processing is not made in the target of appearance to some for a long time；Once make disappearance processing,
Then system will forget the target, and any target occurred later will not may make any association with it again, in our realization
In, the target not occurred in some nearest frames (such as 600 frames) is simply made disappearance processing by we.
Thus, the quick detection to moving target in monitor video is completed.
Particular embodiments described above, the purpose of the present invention, technical scheme and beneficial effect are carried out further in detail
Describe in detail it is bright, should be understood that the foregoing is only the present invention specific embodiment, be not intended to limit the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements done etc., it should be included in the guarantor of the present invention
Within the scope of shield.
Claims (4)
1. the quick determination method of moving target in a kind of video surveillance, it is characterised in that comprise the following steps：
Step 1, video V={ I to be measured0,I1,I2,…,Ik, wherein IkIt is the kth frame image in video V, by the 0th of video the
Two field picture is set as initial back-ground model D0, i.e. D0=I0；
Step 2, by calculating Fk=Ik-Dk-1Extraction prospect, and in FkThe set S of the upper potential moving region of extractionk, set SkIn
The initial value O of the set of targetk={ } is empty set；It is the image I that currently will analyzing wherein to extract prospectkWith background model
Dk-1Point-to-point to subtract each other, difference exceedes the point of constant 10 as foreground point, otherwise as background dot；It is point-to-point subtract each other completion after
Using morphology open and close operation, cross noise filtering and make UNICOM region relatively more regular, then obtained wherein using region growing method
As all UNICOM regions of prospect, close region is merged, obtains the set S of potential moving regionk；
Step 3, for step 2 SiIn each potential moving region s, detect s in target to be checked that may be present, Suo Youjian
The target measured adds set OkIn；
Step 4, to Ok-1In all targets, be tracked in kth frame, gained target to be checked is also added to OkIn, and after
Continuous to appear in present frame to the last time of lost target in all short time forward and be tracked, gained target equally adds
To current goal set OkIn；
Step 5, for set OkThe target that middle certain time occurs without makees disappearance processing, by the target from set OkMiddle deletion；
Step 6, update background model；
Step 7, for next two field picture, repeat the above steps and two arrive step 6, until detecting video last frame image
Afterwards, testing result is obtained；
It is multiple dimensioned, floating window and based on HoG feature calculations that mesh calibration method to be checked that may be present in s is detected in step 3
The method of target identification；Target identification based on HoG feature calculations a, it is also necessary to decision mechanism is set, headed by the mechanism
First one target data Sample Storehouse of demarcation, data sample storehouse are made up of the picture of a large amount of identical sizes, all marked per pictures manually
It is determined and whether there is particular detection target, the HoG features of each pixel are acquired in every pictures；Decision mechanism is by obtaining
Take the HoG features of each pixel in every pictures and then form the identification model data for detecting target；Particular detection process
In, first by window to be measured be adjusted to picture identical size in decision mechanism, then treated by identification model data judging
Survey in window and whether there is particular detection target.
2. the quick determination method of moving target in video surveillance according to claim 1, it is characterised in that in step 4
The method of tracking is as follows：
1) initialize first in frame to be tracked with tracking source frame in target location identical position be initial retrieval position p；
2) using centered on retrieving position p in frame to be tracked, size and target in source frame is tracked equal-sized rectangle frame as
Potential tracking result, the target in it and tracking source is sought into mean square deviation, if this value is less than threshold value 2, then it is assumed that tracked
Into have found tracking target, algorithm terminates；
3) it is eight positions diamond shaped positions around p if the mean square deviation that previous step obtains is unsatisfactory for condition：Diagonally opposing corner
Four adjoint points+each each calculated with tracking target in tracking source respectively as rectangle frame center every the position of any up and down
Mean square deviation in frame, think tracking result is not present if this eight values exceed the mean square deviation of previous step acquisition, calculate
Method terminates；Otherwise, p is replaced to produce the point of lowest mean square difference；
4) occur to the last time of the target in a range of frame before present frame, all using the method in above step
It is tracked.
3. the quick determination method of moving target in video surveillance according to claim 1, it is characterised in that in step 6
The point that it is (x, y) to position that renewal background model, which is specially, such as the brightness value in current background model is d, and is schemed currently
Brightness value as in is p, then is updated to D by present image, the value of background modelk=(1- α) × d+ α × p, if position is
The point of (x, y) is determined as background dot in step 2, then α values take 0.1, if being determined as foreground point in step 2, α values take
0.01。
4. the quick determination method of moving target in video surveillance according to claim 2, it is characterised in that in step 4)
A range of frame refers to preceding 25 frame of present frame before present frame.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611069001.7A CN106910203B (en) | 2016-11-28 | 2016-11-28 | The quick determination method of moving target in a kind of video surveillance |
| PCT/CN2017/097647 WO2018095082A1 (en) | 2016-11-28 | 2017-08-16 | Rapid detection method for moving target in video monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611069001.7A CN106910203B (en) | 2016-11-28 | 2016-11-28 | The quick determination method of moving target in a kind of video surveillance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106910203A CN106910203A (en) | 2017-06-30 |
| CN106910203B true CN106910203B (en) | 2018-02-13 |
Family
ID=59206767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611069001.7A Active CN106910203B (en) | 2016-11-28 | 2016-11-28 | The quick determination method of moving target in a kind of video surveillance |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106910203B (en) |
| WO (1) | WO2018095082A1 (en) |
Families Citing this family (58)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910203B (en) * | 2016-11-28 | 2018-02-13 | 江苏东大金智信息***有限公司 | The quick determination method of moving target in a kind of video surveillance |
| CN107578424B (en) * | 2017-08-04 | 2020-09-29 | 中山大学 | Dynamic background difference detection method, system and device based on space-time classification |
| EP3796189A4 (en) | 2018-05-18 | 2022-03-02 | Cambricon Technologies Corporation Limited | Video retrieval method, and method and apparatus for generating video retrieval mapping relationship |
| CN112597341A (en) * | 2018-05-25 | 2021-04-02 | 中科寒武纪科技股份有限公司 | Video retrieval method and video retrieval mapping relation generation method and device |
| CN109188390B (en) * | 2018-08-14 | 2023-05-23 | 苏州大学张家港工业技术研究院 | High-precision detection and tracking method for moving target |
| CN110879951B (en) * | 2018-09-06 | 2022-10-25 | 华为技术有限公司 | Motion foreground detection method and device |
| CN109446901B (en) * | 2018-09-21 | 2020-10-27 | 北京晶品特装科技有限责任公司 | Embedded transplantation real-time humanoid target automatic identification algorithm |
| CN109658440A (en) * | 2018-11-30 | 2019-04-19 | 华南理工大学 | A kind of method for tracking target based on target significant characteristics |
| CN109816650B (en) * | 2019-01-24 | 2022-11-25 | 强联智创（北京）科技有限公司 | Target area identification method and system based on two-dimensional DSA image |
| CN109862263B (en) * | 2019-01-25 | 2021-07-30 | 桂林长海发展有限责任公司 | Moving target automatic tracking method based on image multi-dimensional feature recognition |
| CN111833375B (en) * | 2019-04-23 | 2024-04-05 | 舟山诚创电子科技有限责任公司 | Method and system for tracking animal group track |
| JPWO2020261333A1 (en) * | 2019-06-24 | 2020-12-30 | ||
| CN110288051B (en) * | 2019-07-03 | 2022-04-22 | 电子科技大学 | Multi-camera multi-target matching method based on distance |
| CN110427844B (en) * | 2019-07-19 | 2022-11-22 | 宁波工程学院 | Behavior anomaly video detection method based on convolutional neural network |
| CN111753609B (en) * | 2019-08-02 | 2023-12-26 | 杭州海康威视数字技术股份有限公司 | Target identification method and device and camera |
| CN112419362B (en) * | 2019-08-21 | 2023-07-07 | 中国人民解放***箭军工程大学 | Moving target tracking method based on priori information feature learning |
| CN110738686B (en) * | 2019-10-12 | 2022-12-02 | 四川航天神坤科技有限公司 | Static and dynamic combined video man-vehicle detection method and system |
| CN112784651A (en) * | 2019-11-11 | 2021-05-11 | 北京君正集成电路股份有限公司 | System for realizing efficient target detection |
| CN111161304B (en) * | 2019-12-16 | 2023-06-30 | 北京空间机电研究所 | Remote sensing video target track tracking method for rapid background estimation |
| CN111191576B (en) * | 2019-12-27 | 2023-04-25 | 长安大学 | Personnel behavior target detection model construction method, intelligent analysis method and system |
| CN113111681B (en) * | 2020-01-09 | 2024-05-03 | 北京君正集成电路股份有限公司 | Method for reducing false alarm of detection of upper body of humanoid form |
| CN111047625B (en) * | 2020-02-18 | 2023-04-07 | 神思电子技术股份有限公司 | Semi-automatic dish video sample marking method |
| CN111310689B (en) * | 2020-02-25 | 2023-04-07 | 陕西科技大学 | Method for recognizing human body behaviors in potential information fusion home security system |
| CN111369591A (en) * | 2020-03-05 | 2020-07-03 | 杭州晨鹰军泰科技有限公司 | Method, device and equipment for tracking moving object |
| CN111259907B (en) * | 2020-03-12 | 2024-03-12 | Oppo广东移动通信有限公司 | Content identification method and device and electronic equipment |
| CN111553255B (en) * | 2020-04-26 | 2023-04-07 | 上海天诚比集科技有限公司 | High-altitude parabolic wall monitoring area positioning method based on gradient algorithm |
| CN111723654B (en) * | 2020-05-12 | 2023-04-07 | 中国电子***技术有限公司 | High-altitude parabolic detection method and device based on background modeling, YOLOv3 and self-optimization |
| CN111639578B (en) * | 2020-05-25 | 2023-09-19 | 上海中通吉网络技术有限公司 | Method, device, equipment and storage medium for intelligently identifying illegal parabolic objects |
| CN111738108B (en) * | 2020-06-08 | 2024-01-16 | 中国电信集团工会上海市委员会 | Method and system for detecting head of video stream |
| CN111931575A (en) * | 2020-07-01 | 2020-11-13 | 南京工业大学 | Method for detecting and tracking steering of mixing drum of concrete mixer truck based on classifier integration |
| CN111898511A (en) * | 2020-07-23 | 2020-11-06 | 北京以萨技术股份有限公司 | High-altitude parabolic detection method, device and medium based on deep learning |
| CN112016440B (en) * | 2020-08-26 | 2024-02-20 | 杭州云栖智慧视通科技有限公司 | Target pushing method based on multi-target tracking |
| CN112183252A (en) * | 2020-09-15 | 2021-01-05 | 珠海格力电器股份有限公司 | Video motion recognition method and device, computer equipment and storage medium |
| CN112215870B (en) * | 2020-09-17 | 2022-07-12 | 武汉联影医疗科技有限公司 | Liquid flow track overrun detection method, device and system |
| CN112288767A (en) * | 2020-11-04 | 2021-01-29 | 成都寰蓉光电科技有限公司 | Automatic detection and tracking method based on target adaptive projection |
| CN112508998A (en) * | 2020-11-11 | 2021-03-16 | 北京工业大学 | Visual target alignment method based on global motion |
| CN112435280A (en) * | 2020-11-13 | 2021-03-02 | 桂林电子科技大学 | Moving target detection and tracking method for unmanned aerial vehicle video |
| CN112528843A (en) * | 2020-12-07 | 2021-03-19 | 湖南警察学院 | Motor vehicle driver fatigue detection method fusing facial features |
| CN112489086A (en) * | 2020-12-11 | 2021-03-12 | 北京澎思科技有限公司 | Target tracking method, target tracking device, electronic device, and storage medium |
| CN112686921B (en) * | 2021-01-08 | 2023-12-01 | 西安羚控电子科技有限公司 | Multi-interference unmanned aerial vehicle detection tracking method based on track characteristics |
| CN112784738B (en) * | 2021-01-21 | 2023-09-19 | 上海云从汇临人工智能科技有限公司 | Moving object detection alarm method, moving object detection alarm device and computer readable storage medium |
| CN112835010B (en) * | 2021-03-17 | 2022-06-17 | 中国人民解放军海军潜艇学院 | Weak and small target detection and combination method based on interframe accumulation |
| CN113052878B (en) * | 2021-03-30 | 2024-01-02 | 北京中科通量科技有限公司 | Multipath high-altitude parabolic detection method and system for edge equipment in security system |
| CN113255737B (en) * | 2021-04-30 | 2023-08-08 | 超节点创新科技(深圳)有限公司 | Method for sorting baggage in folded package on civil aviation sorting line, electronic equipment and storage medium |
| CN113223059B (en) * | 2021-05-17 | 2022-10-21 | 浙江大学 | Weak and small airspace target detection method based on super-resolution feature enhancement |
| CN113297950B (en) * | 2021-05-20 | 2023-02-17 | 首都师范大学 | Dynamic target detection method |
| CN113569770B (en) * | 2021-07-30 | 2024-06-11 | 北京市商汤科技开发有限公司 | Video detection method and device, electronic equipment and storage medium |
| CN113807250B (en) * | 2021-09-17 | 2024-02-02 | 沈阳航空航天大学 | Anti-shielding and scale-adaptive low-altitude airspace flight target tracking method |
| CN113554683A (en) * | 2021-09-22 | 2021-10-26 | 成都考拉悠然科技有限公司 | Feature tracking method based on video analysis and object detection |
| CN113723364A (en) * | 2021-09-28 | 2021-11-30 | 中国农业银行股份有限公司 | Moving object identification method and device |
| CN113989357A (en) * | 2021-11-10 | 2022-01-28 | 广东粤海珠三角供水有限公司 | Shield slag-tapping gradation rapid estimation method based on monitoring video |
| CN114743154B (en) * | 2022-06-14 | 2022-09-20 | 广州英码信息科技有限公司 | Work clothes identification method based on registration form and computer readable medium |
| CN115273138B (en) * | 2022-06-29 | 2023-04-11 | 珠海视熙科技有限公司 | Human body detection system and passenger flow camera |
| CN115170535A (en) * | 2022-07-20 | 2022-10-11 | 水电水利规划设计总院有限公司 | Hydroelectric engineering fishway fish passing counting method and system based on image recognition |
| CN116205914B (en) * | 2023-04-28 | 2023-07-21 | 山东中胜涂料有限公司 | Waterproof coating production intelligent monitoring system |
| CN117292321A (en) * | 2023-09-27 | 2023-12-26 | 深圳市正通荣耀通信科技有限公司 | Motion detection method and device based on video monitoring and computer equipment |
| CN117537929A (en) * | 2023-10-27 | 2024-02-09 | 大湾区大学(筹) | Unmanned aerial vehicle detection method, system, equipment and medium based on infrared thermal imaging |
| CN117834942A (en) * | 2023-12-15 | 2024-04-05 | 山东爱特云翔信息技术有限公司 | Mobile detection video recording method based on ViBe algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
| CN101739551A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for identifying moving objects |
| CN101739550A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting moving objects |
| CN101916447A (en) * | 2010-07-29 | 2010-12-15 | 江苏大学 | Robust motion target detecting and tracking image processing system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201001338A (en) * | 2008-06-16 | 2010-01-01 | Huper Lab Co Ltd | Method of detecting moving objects |
| CN101739686B (en) * | 2009-02-11 | 2012-05-30 | 北京智安邦科技有限公司 | Moving object tracking method and system thereof |
| CN101854467B (en) * | 2010-05-24 | 2012-01-04 | 北京航空航天大学 | Method for adaptively detecting and eliminating shadow in video segmentation |
| CN106910203B (en) * | 2016-11-28 | 2018-02-13 | 江苏东大金智信息***有限公司 | The quick determination method of moving target in a kind of video surveillance |
-
2016
- 2016-11-28 CN CN201611069001.7A patent/CN106910203B/en active Active
-
2017
- 2017-08-16 WO PCT/CN2017/097647 patent/WO2018095082A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
| CN101739551A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for identifying moving objects |
| CN101739550A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting moving objects |
| CN101916447A (en) * | 2010-07-29 | 2010-12-15 | 江苏大学 | Robust motion target detecting and tracking image processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018095082A1 (en) | 2018-05-31 |
| CN106910203A (en) | 2017-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910203B (en) | The quick determination method of moving target in a kind of video surveillance | |
| CN106203274B (en) | Real-time pedestrian detection system and method in video monitoring | |
| CN101739686B (en) | Moving object tracking method and system thereof | |
| CN102136059B (en) | Video- analysis-base smoke detecting method | |
| CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
| CN107622258A (en) | A kind of rapid pedestrian detection method of combination static state low-level image feature and movable information | |
| CN100545867C (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN106204640A (en) | A kind of moving object detection system and method | |
| CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN106845364B (en) | Rapid automatic target detection method | |
| CN107392885A (en) | A kind of method for detecting infrared puniness target of view-based access control model contrast mechanism | |
| CN105404857A (en) | Infrared-based night intelligent vehicle front pedestrian detection method | |
| CN106128022A (en) | A kind of wisdom gold eyeball identification violent action alarm method and device | |
| CN105160297A (en) | Masked man event automatic detection method based on skin color characteristics | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN108765453B (en) | Expressway agglomerate fog identification method based on video stream data | |
| CN106548131A (en) | A kind of workmen's safety helmet real-time detection method based on pedestrian detection | |
| CN106570440A (en) | People counting method and people counting device based on image analysis | |
| CN104267209B (en) | Method and system for expressway video speed measurement based on virtual coils | |
| CN109215059A (en) | Local data's correlating method of moving vehicle tracking in a kind of video of taking photo by plane | |
| CN117636268A (en) | Unmanned aerial vehicle aerial natural driving data set construction method oriented to ice and snow environment | |
| CN116503912A (en) | Security check early warning method based on electronic graph bag | |
| CN107240111B (en) | Edge communication segmentation passenger flow statistical method | |
| CN108198422A (en) | A kind of road ponding extraction system and method based on video 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |