CN102497495A - Target association method for multi-camera monitoring system - Google Patents
Target association method for multi-camera monitoring system Download PDFInfo
- Publication number
- CN102497495A CN102497495A CN2011104332680A CN201110433268A CN102497495A CN 102497495 A CN102497495 A CN 102497495A CN 2011104332680 A CN2011104332680 A CN 2011104332680A CN 201110433268 A CN201110433268 A CN 201110433268A CN 102497495 A CN102497495 A CN 102497495A
- Authority
- CN
- China
- Prior art keywords
- target
- camera
- target association
- control system
- supervisory control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a target association method for a multi-camera monitoring system. The method mainly comprises the following steps that: a minimum cost flow module based on increment realizes real-time tracking of a target object in a multi-camera covering domain; when a target appears in a camera, a target detection module of a computer connected with the camera detects the target, extracts the characteristics of the target, and finally uploads the characteristics to a server; a target tracking module on the computer continually tracks the target inside a single camera scene, extracts the characteristics of the target at the same moment once again at certain time intervals, and uploads the characteristics to the server; and the server only calculates whether target characteristics transmitted by the target detection module include characteristics which can be associated with the target characteristics and are transmitted by the target tracking module and the target tracking module, and returns a result to the computer. The target association method can be widely applied to an intelligent monitoring system in indoor and outdoor scenes, and has a wide market prospect and high application value.
Description
Technical field
The present invention relates to method such as moving object detection, target following in the intelligent video monitoring system, mainly be applicable to the multiple-camera supervisory control system, belong to the technical field of video monitoring, be specifically related to a kind of target association method that is used for the multiple-camera supervisory control system.
Background technology
Along with the acceleration of global urban process, a large amount of video cameras has been installed in the public place.Though exist very big correlation between video camera, related application also only rests on the basis of single video camera related algorithm.At present, work in coordination with the technology of monitoring between multiple-camera and still be in the starting stage.The multiple-camera tracking mainly comprises at present:
1, based on the multiple-camera target tracking algorism of three-dimensional information
If Camera calibration information and three-dimensional environment coordinate information are known; Just can be mapped to these information unifications under the same coordinate system, just can obtain the corresponding relation between the correct multiple-camera by comparatively simple one dimension parameter at last through certain mapping function.But this method needs equipment that higher precision is arranged.
2, the multiple-camera target tracking algorism of based target model
This basic idea is that hypothesis assert that certain characteristic of people is not easy to change along with the change in time and space (like people's gait etc.); These characteristics are set up unified model; When target detection, directly detect this characteristic of target,, draw the identity of target with the model comparison.But the method process is complicated, is difficult to realize real-time.
3, the multiple-camera target tracking algorism that merges based on characteristic
The basic thought of this method is some simple feature of selecting target in the initial period for use, like color, profile, positional information etc., utilizes methods such as statistics or probability to draw last corresponding relation then.
Summary of the invention
The technical problem that the present invention will solve: a kind of target association method that is used for the multiple-camera supervisory control system is provided, and this method adopts the least cost flow model based on increment, makes the raising degree of system effectiveness fairly obvious.
The technical scheme that the present invention solves the problems of the technologies described above: a kind of target association method that is used for the multiple-camera supervisory control system comprises the steps:
Step (1) will be applied to the association between the target in the multiple-camera supervisory control system based on the least cost flow model of increment;
Step (2) is through repeatedly training, and the Adjustment System parameter improves the accuracy of this target association method;
Used similarity measurement when step (3) target association calculates is taken all factors into consideration characteristic that target is detected in the target detection stage and the characteristic several times in time and the target tracking stage afterwards.
Wherein, described least cost flow model based on increment when time target association calculates, does not directly rebulid whole least cost flow model, but makes full use of a preceding target association result calculated, reduces amount of calculation, improves running efficiency of system.
Wherein, described through repeatedly training, utilize repeatedly to train to obtain the reasonable threshold interval of a plurality of systems, these interval logarithmic axis are covered, and number axis is divided into a plurality of intervals, the intermediate value in the interval that coverage is the highest is as the threshold value of system.
Wherein, used similarity measurement when described target association calculates, the utility function in target association calculates in conjunction with module of target detection in the supervisory control system and target tracking module, extracts characteristic simultaneously in two modules, improve the related accuracy of calculating.
Wherein, Utility function during described target association calculates, target signature similarity are calculated and are got the characteristic that first object appearing is partly sampled in target detection stage and target tracking stage on the characteristic in target detection stage and time preface of back object appearing on the time preface and carry out similarity measurement.
Principle of the present invention is:
The target association method based on the least cost flow model of increment that adopts in this method is new object observing to occur; When server end will carry out target association calculating; Directly on the remaining network of the least cost flow network that last once target association calculates, add two nodes and a spot of limit, carrying out iteration then, to look for weights be positive ring.After finding positive ring, the remaining network of direct modification.When do not exist just encircle after, finish based on the part of increment.Constantly look for least cost road augmentation afterwards, after certain augmentation, the threshold value that the added value of expense is obtained by the training stage less than system.The expense of least cost flow network top, the characteristics determined of extracting by the target of target detection and target tracking module mark.
The present invention's advantage compared with prior art is:
In multiple-camera relay tracking research field; The thought of Combinatorial Optimization is used for the association between a plurality of targets; It is method relatively more commonly used; Wherein the least cost flow model is a kind of simple, intuitive and comparatively ripe a kind of target association method, but each efficient of directly using the least cost flow model to carry out target association calculating is too low.And the minimum cost flow simulated target correlating method that is based on increment that uses in this patent has made full use of last target association result calculated, thereby makes computational efficiency be greatly improved.
Description of drawings
Fig. 1 is system software module figure;
Fig. 2 is the system hardware Organization Chart;
Fig. 3 is the client-side program flow chart;
Fig. 4 is based on the target association method flow diagram of increment;
Fig. 5 is effective threshold interval sketch map.
Embodiment
Below in conjunction with accompanying drawing and specific embodiment the present invention is elaborated.
As shown in Figure 1, the native system software module comprises: target association module and data transmission module are arranged on the server end, image capture module, module of target detection, target tracking module and data transmission module are arranged on the client.
As shown in Figure 2, the native system hardware device comprises: a station server, multiple cameras and the computer that links to each other with every video camera.
In system; Work as a new target appears in the video camera at every turn; The module of target detection of the computer that links to each other with this video camera will detect this target and it is extracted characteristic; The rectangular area mark at detected target place is come out, color histogram is obtained in this rectangular area, characteristic uploads onto the server the most at last.Because the rectangular area of each observation size is also inequality, thus need be to color histogram normalization, to the data of each dimension of characteristic, divided by data on all dimensions with, its meaning accounts for the proportion of all data for the data on this one dimension.To in i video camera, detected a target O of target detection stage
I, aColor histogram be designated as f
I, a, 0, the time is designated as t
I, aAnd the g of color histogram characteristic dimension is designated as f
I, a, 0, g
Then; Target tracking module can carry out continuing in the single camera to follow the tracks of to the target that is detected; In tracing process, sampled in the rectangular area at this target place at regular intervals, and obtain the color histogram after the normalization of this new rectangular area again.To in i video camera, detected a target O of target detection stage
I, aThe color histogram that obtains in the h time sampling of target tracking stage afterwards is designated as f
I, a, h(h＞0), and this color histogram characteristic g dimension be designated as f
I, a, h, gLike this, this object observing just has the characteristic f of many group color histograms in this video camera
I, a, 0, f
I, a, 1, f
I, a, 2..., f
I, a, h
The characteristic that server only transmits module of target detection; Through the target association algorithm in the target association module based on the least cost flow model of increment; Whether have comprise the characteristic that target detection and target tracking module transmit of with it association, and the result is returned to computer if calculating this target signature.As a new target O
J, bAppear in another video camera, ask target O this moment
J, bWith target O
I, aAssociation
Effectiveness
Be that this association is twice continuous possibility that occurs of the same target in the real world, adopt current object observing O
J, bColor histogram characteristic f
J, b, 0With object observing O
I, aThe characteristic f of q+1 color histogram
I, a, 0, f
I, a, 1, f
I, a, 2..., f
I, a, qAsk Euclidean distance respectively, and the Euclidean distance that these are tried to achieve is got minimum value as object observing O
J, bWith object observing O
I, aSimilarity distance between the color histogram characteristic, that is:
In system; Between per two video cameras that directly can reach a parameter is set and is called the mean transferred time, promptly under the photographed scene of a video camera without the scene of the 3rd video camera and directly arrive the expectation of the photographed scene required time of another video camera.In utility function, the mean transferred time is only done the accessibility judgement,, if the mean transferred time is more than 10 times of two time differences between the observation, thinks that then this association is infeasible that is.
The characteristic of the final color histogram of in system, tieing up for q+1 r, the utility function of target association algorithm adopts:
ξ wherein
I, j=1 represents between two video cameras and directly can reach ξ
I, j=0 represents between two video cameras and directly can not reach τ
I, jIt is two mean transferred times between the video camera that directly can reach.
If do not satisfy condition t
J, b＞t
I, a, and ξ
I, j=1, and
Be in the formula " otherwise " situation; On behalf of this association, this can not in system, need not consider this association for the continuous appearance of the same target in the real world, so will
Value is-∞.
The software of native system is divided into server end and client.Server software operates on the server, on the computer that client software operates in video camera links to each other.Client-side program flow chart such as Fig. 3, the client-side program flow process is following:
Step 1 is extracted view data, and this step is accomplished by image capture module.
Step 2, target detection utilizes the aims of systems detection module to carrying out target detection in certain zone, and detected fresh target is sent clarification of objective give server end.
Step 3, target following utilizes the aims of systems module that detected target in the step 2 is carried out the lasting tracking in the multiple-camera scope, and after at set intervals, sends the current characteristic of tracking target and give server end.
Server is embodied as; When receiving clarification of objective that a computer is sent; Judge at first whether this characteristic is by the detected fresh target of module of target detection; If fresh target just like Fig. 4, uses the minimum cost flow simulated target correlating method based on increment to carry out a target association calculating.
The target association method modeling pattern of least cost flow model is: on the fee flows network, increase by two node s, t is as source point and meeting point.To each target O
I, a, on the fee flows network, increase by two nodes
Add the limit
Expense is 0, and flow restriction is 1.For each utility
is not - ∞ association
add edges
cost
traffic is limited to one.This flow network is constantly asked the shortest augmenting path, and after certain augmentation, flow is that incidence number is increased to m+1 from m; Expense be relevant effectiveness and be increased to w (m+1) from w (m), and effective increment function w (m+1)-w (m) is less than threshold value, at this moment; Flow m before the augmentation is the optimal relevance number; Be real related number in the real world, the stream before the augmentation, the institute that flows through tangible as
The limit, represent target O
I, aWith O
J, bRelated.
Minimum cost flow simulated target correlating method flow process based on increment is following:
Step 1 increases corresponding node and the limit of current newly-increased target on the remaining network that last once target association calculates.
Step 2 is positive ring if there is not cost metric in the residual network, forwards step 4 to, goes on foot rapid 3 otherwise change.
Step 3 is positive ring augmentation along the cost metric that finds, and changes step 2.
Step 4: on current network, continue to look for the shortest augmenting path,, then finish if can not find the shortest augmenting path or effective increment less than threshold value.Otherwise forward step 4 to.
At this moment, the same as the method for non-increment, the flow m before the last augmentation is the optimal relevance number, the stream before the augmentation, the institute that flows through tangible as
The limit, represent target O
I, aWith O
J, bRelated.
The reasonable selection of threshold of system utility increment is adopted training method, and flow process is following: at first each group sample is carried out the calculating of effective increment function w (m) in the training, count M according to the true optimal relevance of sample, can obtain two value w (M) and w (M+1).W (M+1)＜w (M)≤1 wherein must be arranged.As shown in Figure 5, so just obtained one to the effective threshold interval of this group sample (w (M+1), w (M)).
This interval meaning is: the threshold value t of effective increment function gets this interval interior any number, can both make this group sample after the algorithm operation, obtain a correct incidence number.
Each group sample is all calculated its effective threshold interval (w
i(M+1), w
i(M)), and then try to achieve an interval (p, q) make satisfied
Interval quantity maximum.Then the meaning directly perceived that threshold value t gets
to be done like this that obtains of training is that the threshold value of the effective increment function selected is can make algorithm on sample set, move the time; The sample of many as far as possible groups is arranged, and what its optimal relevance number obtained is correct value.
The flow process in the interval that concrete judgement degree of covering is maximum is following:
Step 1 is marked at the coordinate that occurs in all effective threshold intervals on the reference axis X axle, thereby the X axle is divided into a plurality of intervals, and with these intervals counter of each auto correlation all, initial value all is made as 0.
Step 2, for each effective threshold interval, the Counter Value that the interval that the X axle that it is covered splits is associated with all adds 1.
Step 3 is found out the maximum interval of counter values, calculate this interval left and right sides end points and half threshold value as system.
The part that the present invention does not set forth in detail belongs to techniques well known.
Claims (5)
1. a target association method that is used for the multiple-camera supervisory control system is characterized in that: comprise the steps:
Step (1) will be applied to the association between the target in the multiple-camera supervisory control system based on the least cost flow model of increment;
Step (2) is through repeatedly training, and the Adjustment System parameter improves the accuracy of this target association method;
Used similarity measurement when step (3) target association calculates is taken all factors into consideration characteristic that target is detected in the target detection stage and the characteristic several times in time and the target tracking stage afterwards.
2. a kind of target association method that is used for the multiple-camera supervisory control system according to claim 1; It is characterized in that: described least cost flow model based on increment; When time target association calculates, directly do not rebulid whole least cost flow model, but make full use of a preceding target association result calculated; Reduce amount of calculation, improve running efficiency of system.
3. a kind of target association method that is used for the multiple-camera supervisory control system according to claim 1; It is characterized in that: described through repeatedly training; Utilizing repeatedly, training obtains the reasonable threshold interval of a plurality of systems; These interval logarithmic axis are covered, and number axis is divided into a plurality of intervals, the intermediate value in the interval that coverage is the highest is as the threshold value of system.
4. a kind of target association method that is used for the multiple-camera supervisory control system according to claim 1; It is characterized in that: used similarity measurement when described target association calculates; Utility function in target association calculates; In conjunction with module of target detection in the supervisory control system and target tracking module, in two modules, extract characteristic simultaneously, improve the related accuracy of calculating.
5. a kind of target association method that is used for the multiple-camera supervisory control system according to claim 4; It is characterized in that: the utility function during described target association calculates, target signature similarity are calculated and are got the characteristic that first object appearing is partly sampled in target detection stage and target tracking stage on the characteristic in target detection stage and time preface of back object appearing on the time preface and carry out similarity measurement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110433268 CN102497495B (en) | 2011-12-21 | 2011-12-21 | Target association method for multi-camera monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110433268 CN102497495B (en) | 2011-12-21 | 2011-12-21 | Target association method for multi-camera monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102497495A true CN102497495A (en) | 2012-06-13 |
| CN102497495B CN102497495B (en) | 2013-10-09 |
Family
ID=46189279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110433268 Expired - Fee Related CN102497495B (en) | 2011-12-21 | 2011-12-21 | Target association method for multi-camera monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102497495B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679560A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Data transmission method, device, mobile terminal and computer-readable recording medium |
| CN109541593A (en) * | 2018-10-30 | 2019-03-29 | 北京航空航天大学 | A kind of improved minimum cost flow InSAR phase unwrapping method |
| CN110717474A (en) * | 2019-10-18 | 2020-01-21 | 北京百度网讯科技有限公司 | Target association calculation method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731762A (en) * | 2005-08-05 | 2006-02-08 | 武汉理工大学 | QoS restricting multicast routing method based on Steiner |
| CN101237469A (en) * | 2008-02-27 | 2008-08-06 | 中山大学 | Method for optimizing multi-QoS grid workflow based on ant group algorithm |
| US20100100414A1 (en) * | 2008-10-17 | 2010-04-22 | Yahoo! Inc. | Optimization of allocation of online advertisement inventory |
| US20100306006A1 (en) * | 2009-05-29 | 2010-12-02 | Elan Pavlov | Truthful Optimal Welfare Keyword Auctions |
-
2011
- 2011-12-21 CN CN 201110433268 patent/CN102497495B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731762A (en) * | 2005-08-05 | 2006-02-08 | 武汉理工大学 | QoS restricting multicast routing method based on Steiner |
| CN101237469A (en) * | 2008-02-27 | 2008-08-06 | 中山大学 | Method for optimizing multi-QoS grid workflow based on ant group algorithm |
| US20100100414A1 (en) * | 2008-10-17 | 2010-04-22 | Yahoo! Inc. | Optimization of allocation of online advertisement inventory |
| US20100306006A1 (en) * | 2009-05-29 | 2010-12-02 | Elan Pavlov | Truthful Optimal Welfare Keyword Auctions |
Non-Patent Citations (1)
| Title |
|---|
| 刘少华,赖世铭,张茂军: "基于最小费用流模型的无重叠视域多摄像机目标关联算法", 《自动化学报》, vol. 36, no. 10, 31 October 2010 (2010-10-31) * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679560A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Data transmission method, device, mobile terminal and computer-readable recording medium |
| CN107679560B (en) * | 2017-09-15 | 2021-07-09 | Oppo广东移动通信有限公司 | Data transmission method and device, mobile terminal and computer readable storage medium |
| CN109541593A (en) * | 2018-10-30 | 2019-03-29 | 北京航空航天大学 | A kind of improved minimum cost flow InSAR phase unwrapping method |
| CN110717474A (en) * | 2019-10-18 | 2020-01-21 | 北京百度网讯科技有限公司 | Target association calculation method, device, equipment and medium |
| CN110717474B (en) * | 2019-10-18 | 2022-07-26 | 阿波罗智能技术(北京)有限公司 | Target association calculation method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102497495B (en) | 2013-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106303442B (en) | Tracking path topological structure establishing method, target object tracking method and target object tracking equipment | |
| CN101950426B (en) | Vehicle relay tracking method in multi-camera scene | |
| CN105336171B (en) | A kind of camera position scaling method and device | |
| CN103546726B (en) | Method for automatically discovering illegal land use | |
| CN104751486A (en) | Moving object relay tracing algorithm of multiple PTZ (pan/tilt/zoom) cameras | |
| CN105225482A (en) | Based on vehicle detecting system and the method for binocular stereo vision | |
| CN103854292B (en) | A kind of number and the computational methods and device in crowd movement direction | |
| CN110955288B (en) | Environment supervision system based on big data | |
| CN104517095B (en) | A kind of number of people dividing method based on depth image | |
| CN107301369A (en) | Road traffic congestion analysis method based on Aerial Images | |
| CN102592288B (en) | Method for matching pursuit of pedestrian target under illumination environment change condition | |
| CN102779410B (en) | Parallel implementation method of multi-source heterogeneous traffic data fusion | |
| CN106127137A (en) | A kind of target detection recognizer based on 3D trajectory analysis | |
| CN104517289B (en) | A kind of indoor scene localization method based on hybrid camera | |
| CN103400379B (en) | The detection of a kind of icing based on image and thickness method of estimation | |
| CN103279791A (en) | Pedestrian counting method based on multiple features | |
| CN110060299A (en) | Danger source identifies and positions method in passway for transmitting electricity based on binocular vision technology | |
| CN110688922A (en) | Deep learning-based traffic jam detection system and detection method | |
| CN101179707A (en) | Wireless network video image multi-visual angle cooperation target tracking measurement method | |
| CN108270999A (en) | A kind of object detection method, image recognition server and system | |
| WO2022247045A1 (en) | Laser radar information-based mobile robot location re-identification method | |
| CN102497495B (en) | Target association method for multi-camera monitoring system | |
| CN112261719B (en) | Area positioning method combining SLAM technology with deep learning | |
| CN111666823A (en) | Pedestrian re-identification method based on individual walking motion space-time law collaborative identification | |
| CN104199006B (en) | A kind of random set trackings based on more hypothesis Joint Distribution wave filters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131009 Termination date: 20181221 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |