CN104469875A - Prediction-based target tracking method and system in wireless sensor network - Google Patents
Prediction-based target tracking method and system in wireless sensor network Download PDFInfo
- Publication number
- CN104469875A CN104469875A CN201410693468.3A CN201410693468A CN104469875A CN 104469875 A CN104469875 A CN 104469875A CN 201410693468 A CN201410693468 A CN 201410693468A CN 104469875 A CN104469875 A CN 104469875A
- Authority
- CN
- China
- Prior art keywords
- sensor node
- node
- tracking
- prediction
- mobile object
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/18—Communication route or path selection, e.g. power-based or shortest path routing based on predicted events
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
- H04W40/248—Connectivity information update
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to a prediction-based target tracking method and system in the wireless sensor network. The method comprises the steps that S1, all sensor nodes in the wireless sensor network are clustered; S2, all the clustered sensor nodes are arranged to be in an active state, and historical movement path information of a movable object is collected; S3, backward dependency sequences of all the sensor nodes are built according to the historical movement path information and are stored in corresponding cluster head nodes; S4, the states of the sensor nodes are controlled according to the backward dependency sequences in the clusters to track the movable object. By the mode of clustering the sensor nodes, long-distance communication between the sensor nodes and a base station is reduced, and part of prediction information is updated. In addition, in the tracking process, prediction is performed according to the backward dependency mode, time complexity is reduced greatly, tracking accuracy is improved, and multiple types of objects can be tracked at the same time.
Description
Technical field
The present invention relates to technology of wireless sensing network field, particularly relate in a kind of radio sensing network based on the method for tracking target of prediction and system thereof.
Background technology
In numerous application of radio sensing network, target following Sensor Network (OTSN) is one of application of consuming energy most, OTSN is mainly used to follow the tracks of mobile object and report latest position, and this dynamic process expends a lot of Internet resources, and the power supply energy of transducer is extremely limited.Have the approach solution transducer energy consumption problem that two kinds main at present, one is the hardware designs by improving transducer, optimizes the energy consumption that physical structure reduces sensing node; Two is undertaken energy-conservation by controlling sensor states, make idle transducer keep resting state as far as possible, these class methods are divided into again two kinds, a kind of is not based on the method for prediction, periodically transducer is set to active and resting state, another kind of is method based on prediction, by carrying out law-analysing to path log information, selectively allows sensor node keep the resting state of maximum duration.
Scheme 1: paper " An Energy Efficient Technique for Object Tracking in Wireless Sensor Networks " (ICC, 2011:1-5) proposes PTSP method and carries out articles path tracking.The method, mainly according to history mobile route, generates before and after all sensor nodes and relies on sequence, then selects the stronger sequence of dependence according to sequence-dependent frequency size, predicts the mobile route of object based on these sequences.The method relies in sequence process in generation, and need node before and after each sensor node traversal on path, complexity is higher.In addition, select dependence sequence can not describe object moving direction completely, and even some sensor node does not have stronger front and back to rely on sequence, and will cause and cannot judge down hop sensor node, Loss Rate is higher.
Scheme 2: paper " An object tracking scheme for wireless sensor networks using data mining mechanism " (NOMS IEEE, 2012:526-529), application Apriori method is based on historical path information excavating correlation rule, the method progressively Mining Frequent access sensor node, each step increase sensor node, delete the sensor sequence that supporting rate is less than threshold value, stop until sensor node can not be increased.Finally obtain the longest dependence sequence of transducer, control sensor node state according to this dependence sequence and carry out path trace.The method, when often walking the sensor node of Mining Frequent access, all needs traversal All Paths information once.The mobile route amount of information of object is comparatively large, therefore the method complexity is higher.In addition, the final the longest dependence sequence excavated can not ensure to comprise all the sensors node, for the sensor node not in the longest dependence sequence, cannot judge next hop information.
Scheme 3: patent No. ZL 200710164468.4 1 kinds is based on the wireless sensor network target tracking method of prediction, and the method comprises following steps: A. is according to the motion feature of the current measurement data of target travel or historical measurement data determination target; B. the Future Positions of the information prediction target such as current location, speed, the direction of motion of combining target and next monitor node wake the moment up; C., when target prodiction failure, network starts prediction of failure recovery process step by step according to the motion history record of target and priori.The present invention is according to the motion feature of the statistics determination target of target travel, and the Future movement of target of prediction accordingly.This invention the Future Positions of target of prediction, next monitor node wake up moment and prediction of failure recover time, all need the priori such as target maximum speed, peak acceleration, maximum angular rate, maximum angular acceleration extreme sport parameter, sensor node need be consumed calculating that more energy carries out priori.Though this invention has some superiority in prediction accuracy, but power consumption is larger.
The method for tracking target of scheme 4 a: patent No. ZL200810103125.1 wireless sensor network, comprise the following steps: steps A, utilize history target status information and current time observation data, carry out importance sampling, obtain particle state estimated information, calculate track SI and residue measured value; Step B, determines whether stop this track according to track SI, and upgrades track set; Step C, uses the particle after resampling, and the current state obtaining target complete track is estimated, i.e. the current location of moving target and movement velocity, realize target locating and tracking.This invention uses the particle after resampling, and the current state obtaining target complete track is estimated, i.e. the current location of moving target and movement velocity, and realize target locating and tracking, this requires that all the sensors node must be in time synchronized state, and complexity is higher.
Scheme 5: patent No. ZL 200810225565.4 1 kinds of wireless sensor network target localization and tracking methods, described method mainly comprises: locating the moment arbitrarily, according to sensor node metrical information pre-estimation target location, set up the learning region comprising target pre-estimation position, the location point of any amount is chosen in learning region, utilize Polynomial kernel function and Ε-support vector regression to approach location point and obtain decision function to the mapping relations of sensor node distance vector and location point coordinate, sensor node is obtained target location estimated value to object ranging vector input decision function, target location estimated value is sent to base station, base station is carried out matching to object location history data and is upgraded target trajectory, realize target is followed the tracks of.This invention is by obtaining target location estimated value by sensor node to object ranging vector input decision function, target location estimated value is sent to base station, base station is carried out matching to object location history data and is upgraded target trajectory, realize target is followed the tracks of, target trajectory is not had to the situation of any curve law, this invention there will be larger predicated error in fit procedure, and then causes Loss Rate higher.
Summary of the invention
Based on the problems referred to above, the invention provides in a kind of radio sensing network based on the method for tracking target of prediction and system thereof, by the mode by sensor node sub-clustering, decrease the long haul communication between sensor node and base station, realize information of forecasting local updating.And in tracing process, predict according to backward dependence mode, greatly reduce time complexity, and improve tracking precision.
According to above-mentioned purpose, the invention provides the method for tracking target based on prediction in a kind of radio sensing network, described method comprises:
S1, sub-clustering is carried out to all the sensors node in radio sensing network;
S2, all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of mobile object;
S3, set up the backward dependence sequence of all described sensor nodes according to described history mobile route information, and described backward dependence sequence is stored into corresponding leader cluster node;
S4, in each bunch, control to relying on sequence the tracking that the state of sensor node carries out described mobile object afterwards according to described.
Wherein, described step S1 specifically comprises: utilize K-means algorithm to carry out sub-clustering to described sensor node.
Wherein, described step S2 also comprises: the information classification of described history mobile route stored.
Wherein, described step S4 specifically comprises:
The confidence level of the destination node of each sensor node in S41, compute cluster, and become one-dimension array according to confidence level descending;
S42, is stored in corresponding sensor node using the content of described one-dimension array as information of forecasting;
S43, when carrying out mobile object and following the tracks of, the described information of forecasting that current sensor node stores according to this node activates next sensor node, realizes mobile object and follows the tracks of.
Wherein, described step S43 specifically comprises:
S431, after described current sensor node is activated, start to monitor in tracking area whether there is mobile object;
S432, when tracing into mobile object in tracking time section, then tracking results is reported to a upper sensor node;
S433, in preset time period, predict next sensor node according to the information of forecasting stored, and active information is sent to the next sensor node of prediction;
S434, described next sensor node perform step S431, and described current sensor node enters resting state after the tracking results receiving described next sensor node, otherwise performs next step;
When S435, described current sensor do not receive the tracking results of next sensor node, then described mobile object is followed the tracks of unsuccessfully, starts Restoration Mechanism, recovers the tracking of described mobile object.
Wherein, described step S435 specifically comprises:
Calculate the Loss Rate in described mobile object tracing process, when described Loss Rate is less than threshold value, described prediction of failure information is sent to corresponding leader cluster node by described current sensor, then activate objective sensor node all in the backward dependence sequence of described current sensor node, then enter resting state;
If described objective sensor node traces into described mobile object, then the sensor node tracing into described mobile object sends confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431;
Wherein, described step S435 also comprises:
If when all described objective sensor node all do not trace into described mobile object, then with the sensor node that described leader cluster node is all for source node activates, carry out the tracking of mobile object;
The sensor node tracing into described object is sent confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431;
Wherein, described step S435 also comprises:
When described Loss Rate is greater than threshold value, the backward dependence sequence upgraded is sent to corresponding sensor node by described leader cluster node, each corresponding sensor node upgrades the backward dependence sequence of oneself according to the backward dependence sequence received, and then performs step S41.
According to a further aspect in the invention, provide the Target Tracking System based on prediction in a kind of radio sensing network, described system comprises:
Sub-clustering unit, for carrying out sub-clustering to all the sensors node in radio sensing network;
History mobile message collector unit, for all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of moving target;
Backward dependence sequence sets up unit, for setting up the backward dependence sequence of all described sensor nodes according to described history mobile route information, and described backward dependence sequence is stored into corresponding leader cluster node;
Object tracking unit, for carrying out the tracking of described mobile object in each described bunch according to the described rear state to relying on sequence control sensor node.
Based on the method for tracking target of prediction and system thereof in radio sensing network of the present invention, only need can carry out object tracking based on backward dependence, greatly reduce time complexity, and improve in accuracy; Simultaneously, the long haul communication between sensor node and base station is reduced by sub-clustering, and will predict the outcome and be stored in sensor node, what decrease between transducer and bunch head is mutual, when path rule changes locally, sub-clustering mechanism can be predicted again not affecting realization fast and convenient under the prerequisite of other parts; In addition, when following the tracks of unsuccessfully, restoration methods of the present invention is not simple flooding mechanism, but first recovers according to the path rule having excavated out, if or failure, then carry out overall inundation.By this method, simply can realize fast recovering, significantly reduce tracking Loss Rate; In addition, the method supports that multiclass object is followed the tracks of simultaneously.
Accompanying drawing explanation
Can understanding the features and advantages of the present invention clearly by reference to accompanying drawing, accompanying drawing is schematic and should not be construed as and carry out any restriction to the present invention, in the accompanying drawings:
Fig. 1 shows the flow chart based on the method for tracking target of prediction in radio sensing network of the present invention.
Fig. 2 shows the detailed process schematic diagram based on the method for tracking target of prediction in radio sensing network of the present invention.
Fig. 3 shows the structured flowchart based on the Target Tracking System of prediction in radio sensing network of the present invention.
Fig. 4 shows in radio sensing network of the present invention based on the method for tracking target of prediction and the comparison diagram of existing method in total energy consumption;
Fig. 5 shows in radio sensing network of the present invention based on the method for tracking target of prediction and the comparison diagram of existing method in Loss Rate;
Fig. 6 shows in radio sensing network of the present invention and is participating in the comparison diagram of quantitative aspects of the sensor node recovered based on the method for tracking target of prediction and existing method;
Embodiment
Below in conjunction with accompanying drawing, embodiments of the present invention is described in detail.
Fig. 1 shows the flow chart based on the method for tracking target of prediction in radio sensing network of the present invention.
Fig. 2 shows the detailed process schematic diagram based on the method for tracking target of prediction in radio sensing network of the present invention.
See figures.1.and.2, the invention provides the method for tracking target based on prediction in a kind of radio sensing network, the method comprises:
S1, sub-clustering is carried out to all the sensors node in radio sensing network;
In the present embodiment, utilize K-means algorithm to carry out sub-clustering to described sensor node, after sub-clustering, in object tracking process, sensor node only need carry out short-range communication with leader cluster node.
S2, all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of moving target;
In the present embodiment, the surrounding of OTSN, some combinations for the transducer or multiple sensors of distinguishing kind of object can be arranged, then the sensor node distinguishing kind of object and the sensor node that is used for mobile tracking are all placed in active state, collect the routing information of moving target and distinguish classification and store.
This enforcement is a large amount of log informations collected based on sink node, by the regularity of analytical behavior data, under the prerequisite allowing certain Loss Rate, forms the information of forecasting of next sensor node.
S3, set up the backward dependence sequence seq [now of all described sensor nodes according to described history mobile route information, des], wherein, now represents the information of current sensor node, des represents the information of objective sensor node, i.e. the information of next sensor node.
Rear in dependence sequence process of establishing, trace information is sent to leader cluster node by the sensor node in bunch, leader cluster node is responsible for tracking data to be sent to base station, object Move Mode is excavated in base station, backward dependence sequence is set up according to history mobile route information, and rear to the dependence sequence meeting of transmission leader cluster node by what set up, backward dependence sequence is sent to corresponding sensor node by leader cluster node.Meanwhile, in tracing process, when bunch in the movement law of mobile object change time, only need current cluster head node again to excavate the Move Mode of mobile object, upgrade backward dependence sequence, and other bunch be unaffected.It can thus be appreciated that, only need each leader cluster node and base station to carry out long haul communication after sub-clustering, and when one of them bunch upgrades, other bunch is unaffected, thus decreases the complexity of calculating, save the time.
S4, in each described bunch, carry out mobile object tracking according to the described rear state to relying on sequence and control sensor node.
Step S4 specifically comprises:
The confidence level of the destination node of each sensor node in S41, compute cluster, and according to confidence level descending become one-dimension array SN (SN_NUM) (type)=des}, wherein, SN_NUM is the quantity of array, respective sensor number, type is the type of array;
S42, by content (objective sensor node collection (des1, des2, the des3 of descending of one-dimension array ... )) be stored in corresponding sensor node as information of forecasting;
S43, when carrying out mobile object and following the tracks of, the described information of forecasting that current sensor node stores according to this node activates next sensor node, realizes mobile object and follows the tracks of.
With reference to Fig. 2, step S43 specifically comprises:
After S431, current sensor node are activated, start to monitor in tracking area whether there is object;
S432, when tracing into object in tracking time section, then tracking results is reported to a upper sensor node;
S433, in preset time period, predict next sensor node according to the information of forecasting stored, and active information is sent to the next sensor node of prediction;
S434, next sensor node perform step S431, and described current sensor node enters resting state after the tracking results receiving described next sensor node, otherwise performs next step;
When S435, described current sensor do not receive the tracking results of next sensor node, then described mobile object is followed the tracks of unsuccessfully, starts Restoration Mechanism, recovers the tracking of described mobile object.
Particularly, above-mentioned steps S43 is described in detail by following specific embodiment.
As shown in the figure, within first T-X time, current sensor is in resting state, after the T-X moment is activated, starts to monitor in tracking area whether there is object, and the X moment report tracking results ACK on a sensor node; Then within second T-X time period, current sensor node predicts next sensor node according to this information of forecasting, sends active information to next sensor node after the T-X moment; And within second X time period, current sensor node and next sensor node are all in active state, next sensor node, after tracing into object, sends tracking results ACK to current sensor node, now indicates the correctness of prediction.Current sensor node, after receiving ACK, is transformed into resting state by active state, and next transducer proceeds to follow the tracks of as current sensor.
If current sensor does not receive ACK within second X time period, then prediction of failure is described, starts Restoration Mechanism, prediction of failure information is sent to leader cluster node by current sensor node simultaneously.
The process starting Restoration Mechanism comprises the following steps:
Calculate the Loss Rate in described mobile object tracing process, when described Loss Rate is less than threshold value, described prediction of failure information is sent to corresponding leader cluster node by described current sensor, then activate objective sensor node all in the backward dependence sequence of described current sensor node, then enter resting state;
If described objective sensor node traces into described mobile object, then the sensor node tracing into described mobile object sends confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431;
If when all described objective sensor node all do not trace into described mobile object, then start flooding mechanism, namely with the sensor node that described leader cluster node is all for source node activates, carry out the tracking of mobile object;
The sensor node tracing into described object is sent confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431;
In addition, when described Loss Rate is greater than threshold value, namely when Loss Rate is higher, the backward dependence sequence upgraded is sent to corresponding sensor node by described leader cluster node, each corresponding sensor node upgrades the backward dependence sequence of oneself according to the backward dependence sequence received, and then performs step S41.
Fig. 3 shows the structured flowchart based on the Target Tracking System of prediction in radio sensing network of the present invention.
With reference to Fig. 3, according to another aspect of the present invention, provide the Target Tracking System based on prediction in a kind of radio sensing network, this is stated system and comprises:
Sub-clustering unit 10, for carrying out sub-clustering to all the sensors node in radio sensing network;
History mobile message collector unit 20, for all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of moving target;
Backward dependence sequence sets up unit 30, for setting up the backward dependence sequence of all described sensor nodes according to described history mobile route information, and described backward dependence sequence is stored into corresponding leader cluster node;
Object tracking unit 40, for carrying out the tracking of mobile object in each described bunch according to the described rear state to relying on sequence control sensor node.
Following table utilizes method of the present invention to carry out following the tracks of the comparison information table with existing method to object.
| Method name | Complexity | Whether support that multiclass is followed the tracks of | Whether time correlation |
| PTSP | O(3N) | No | No |
| Apriori | O(N 2) | No | No |
| MLS | O(N 2) | No | No |
| MOTA | Influencing factor is many, and complexity is high | Be | No |
| TMP-Mine | O(N 2) | Be | Be |
| ASM | O(N 2) | Be | Be |
| Method of the present invention | O(N+n) | Be | No |
In upper table, PSPT (Prediction-based Tracking Technique using Sequential Patterns) is the sequence pattern tracking technique based on prediction;
MLS (multi-level structure) is sandwich construction tracking;
((Multi-model based Object Tracking Architecture) is the multi-mode tracking method based on tracking structure to MOTA;
TMP-Mine (Temporal Movement Patterns-Mine) is real-time mobile patterns mining method;
ASM (adaptive schedule monitoring): be adaptive tracking method;
Find out by table, compared to other congenic method, method overall energy of the present invention consumes less, follow the tracks of Loss Rate less, and complexity is lower, supports that multiclass is followed the tracks of, and does not rely on the time that object is traced to.
In order to verify the performance of institute of the present invention method, the present invention and existing method are compared by number of sensors three aspect recovered from total energy consumption, tracking Loss Rate, participation by emulation experiment.
Existing method is as follows:
IMP (improved-Mining Patterns) is the method for tracking target based on prediction of the present invention.
OTDM (object tracking using data mining mechanism) is the object tracking methods based on data mining.
The major experimental environment of the present embodiment is Visual Studio and MATLAB, wherein the number order of magnitude of sensing node is 100-700, be uniformly distributed in bulk portion, be divided into Cn bunch, the communication between sensor node and leader cluster node is based on multi-hop shortest-path method.The communication range of sensor node is 20m, T=1s average time that object stops on each sensing node.Rockwell WINS is adopted to emulate energy resource consumption.Design parameter arranges as follows:
Fig. 4 shows in radio sensing network of the present invention based on the method for tracking target of prediction and the comparison diagram of existing method in total energy consumption;
As shown in Figure 4, method IMP energy consumption of the present invention is all less compared with PTSP, OTDM, MLS.Wherein PTSP and OTDM is Forecasting Methodology, does not have Restoration Mechanism, and acquiescence uses flooding mechanism.PTSP method prediction of failure rate is higher, starts flooding method often, so PTSP method energy consumption is higher.In OTDM method, restoration methods uses flooding mechanism, thus energy consumption comparatively IMP is high a lot.Transducer is carried out layering by MLS method, and carry out predicting and recovering according to hierarchical relationship, energy consumption is lower, but also higher than IMP.The inventive method IMP decreases communication energy consumption by sub-clustering mechanism, and recover first according to the dependence excavated out, next utilizes flooding method to ensure zero loss, therefore energy consumption is lower.
Fig. 5 shows in radio sensing network of the present invention based on the method for tracking target of prediction and the comparison diagram of existing method in Loss Rate;
As shown in Figure 5, method IMP Loss Rate of the present invention is suitable with OTDM, is all less than other two methods.PTSP method mainly relies on according to front and back the prediction that sequence carries out down hop, but but the identical forward direction of some backward dependence of transducer possibility is different, now will cause prediction of failure, so PTSP method Loss Rate is higher.The final Result of OTDM method is identical with the present invention, therefore Loss Rate is almost identical with IMP.Transducer is carried out layering by MLS method, predicts according to hierarchical relationship, and Loss Rate is lower, but also higher than IMP.IMP of the present invention utilizes backward dependence quick and precisely to realize prediction, and Loss Rate is lower.
Fig. 6 shows in radio sensing network of the present invention and is participating in the comparison diagram of quantitative aspects of the sensor node recovered based on the method for tracking target of prediction and existing method;
As shown in Figure 6, as can be seen from the sensor node number that the present invention and other three kinds of methods participate in recovery process, the number of sensors that the present invention participates in is minimum, PTSP and OTDM is because directly using flooding mechanism, each all sensors that all needs participates in recovering, therefore the sensor node number participated in is maximum.
Based on the method for tracking target of prediction and system thereof in radio sensing network of the present invention, only need can carry out object tracking based on backward dependence, greatly reduce time complexity, and improve in accuracy; Simultaneously, the long haul communication between sensor node and base station is reduced by sub-clustering, and will predict the outcome and be stored in sensor node, what decrease between transducer and bunch head is mutual, when path rule changes locally, sub-clustering mechanism can be predicted again not affecting realization fast and convenient under the prerequisite of other parts; In addition, when following the tracks of unsuccessfully, restoration methods of the present invention is not simple flooding mechanism, but first recovers according to the path rule having excavated out, if or failure, then carry out overall inundation.By this method, simply can realize fast recovering, significantly reduce tracking Loss Rate; In addition, the method supports that multiclass object is followed the tracks of simultaneously.
Although describe embodiments of the present invention by reference to the accompanying drawings, but those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, such amendment and modification all fall into by within claims limited range.
Claims (9)
1. in radio sensing network based on prediction a method for tracking target, it is characterized in that, described method comprises:
S1, sub-clustering is carried out to all the sensors node in radio sensing network;
S2, all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of mobile object;
S3, set up the backward dependence sequence of all described sensor nodes according to described history mobile route information, and described backward dependence sequence is stored into corresponding leader cluster node;
S4, in each bunch, control to relying on sequence the tracking that the state of sensor node carries out described mobile object afterwards according to described.
2. in a kind of radio sensing network according to claim 1 based on prediction method for tracking target, it is characterized in that, described step S1 specifically comprises: utilize K-means algorithm to carry out sub-clustering to described sensor node.
3. in a kind of radio sensing network according to claim 2 based on the method for tracking target of prediction, it is characterized in that, described step S2 also comprises: the information classification of described history mobile route stored.
4. in a kind of radio sensing network according to claim 1 based on prediction method for tracking target, it is characterized in that, described step S4 specifically comprises:
The confidence level of the destination node of each sensor node in S41, compute cluster, and become one-dimension array according to confidence level descending;
S42, is stored in corresponding sensor node using the content of described one-dimension array as information of forecasting;
S43, when carrying out mobile object and following the tracks of, the described information of forecasting that current sensor node stores according to this node activates next sensor node, realizes mobile object and follows the tracks of.
5. in a kind of radio sensing network according to claim 4 based on prediction method for tracking target, it is characterized in that, described step S43 specifically comprises:
S431, after described current sensor node is activated, start to monitor in tracking area whether there is mobile object;
S432, when tracing into mobile object in tracking time section, then tracking results is reported to a upper sensor node;
S433, in preset time period, predict next sensor node according to the information of forecasting stored, and active information is sent to the next sensor node of prediction;
S434, described next sensor node perform step S431, and described current sensor node enters resting state after the tracking results receiving described next sensor node, otherwise performs next step;
When S435, described current sensor do not receive the tracking results of next sensor node, then described mobile object is followed the tracks of unsuccessfully, starts Restoration Mechanism, recovers the tracking of described mobile object.
6. in a kind of radio sensing network according to claim 5 based on prediction method for tracking target, it is characterized in that, described step S435 specifically comprises:
Calculate the Loss Rate in described mobile object tracing process, when described Loss Rate is less than threshold value, described prediction of failure information is sent to corresponding leader cluster node by described current sensor, then activate objective sensor node all in the backward dependence sequence of described current sensor node, then enter resting state;
If described objective sensor node traces into described mobile object, then the sensor node tracing into described mobile object sends confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431.
7. in a kind of radio sensing network according to claim 6 based on prediction method for tracking target, it is characterized in that, described step S435 also comprises:
If when all described objective sensor node all do not trace into described mobile object, then with the sensor node that described leader cluster node is all for source node activates, carry out the tracking of mobile object;
The sensor node tracing into described object is sent confirmation to described leader cluster node;
Described leader cluster node upgrades after receiving described confirmation follows the tracks of the rear to dependence sequence of failed sensor node;
According to the backward dependence sequence after upgrading, using the described sensor node tracing into described object as present node, perform step S431;
8. in a kind of radio sensing network according to claim 7 based on prediction method for tracking target, it is characterized in that, described step S435 also comprises:
When described Loss Rate is greater than threshold value, the backward dependence sequence upgraded is sent to corresponding sensor node by described leader cluster node, each corresponding sensor node upgrades the backward dependence sequence of oneself according to the backward dependence sequence received, and then performs step S41.
9. in radio sensing network based on prediction a Target Tracking System, it is characterized in that, described system comprises:
Sub-clustering unit, for carrying out sub-clustering to all the sensors node in radio sensing network;
History mobile message collector unit, for all the sensors node after sub-clustering is placed in active state, collects the history mobile route information of moving target;
Backward dependence sequence sets up unit, for setting up the backward dependence sequence of all described sensor nodes according to described history mobile route information, and described backward dependence sequence is stored into corresponding leader cluster node;
Object tracking unit, for carrying out the tracking of described mobile object in each described bunch according to the described rear state to relying on sequence control sensor node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410693468.3A CN104469875B (en) | 2014-11-26 | 2014-11-26 | Method for tracking target and its system based on prediction in radio sensing network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410693468.3A CN104469875B (en) | 2014-11-26 | 2014-11-26 | Method for tracking target and its system based on prediction in radio sensing network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104469875A true CN104469875A (en) | 2015-03-25 |
| CN104469875B CN104469875B (en) | 2018-01-12 |
Family
ID=52915063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410693468.3A Active CN104469875B (en) | 2014-11-26 | 2014-11-26 | Method for tracking target and its system based on prediction in radio sensing network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104469875B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105451182A (en) * | 2016-01-04 | 2016-03-30 | 北京科技大学 | Object identification tracking system and method |
| CN105629225A (en) * | 2015-12-30 | 2016-06-01 | 中国人民解放军信息工程大学 | Multi-hypothesis target tracking method based on improved K shortest paths |
| CN107205255A (en) * | 2017-05-15 | 2017-09-26 | 中国科学院上海微系统与信息技术研究所 | Towards the method for tracking target of the wireless sensor network based on imaging sensor |
| CN108152790A (en) * | 2018-01-05 | 2018-06-12 | 燕山大学 | A kind of non-cooperation multi-target traces projectional technique based on distributed structure/architecture |
| CN109219118A (en) * | 2018-11-27 | 2019-01-15 | 上海交通大学 | A kind of distributed consistent state estimation method based on sequence wake-up mechanism |
| CN109890002A (en) * | 2019-01-04 | 2019-06-14 | 中国电子科技集团公司电子科学研究院 | A kind of method and device of the prediction Risk Degree of Maneuvering Environment of knowledge-based inference |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251593A (en) * | 2008-03-31 | 2008-08-27 | 中国科学院计算技术研究所 | Method for tracking target of wireless sensor network |
| CN101644758A (en) * | 2009-02-24 | 2010-02-10 | 中国科学院声学研究所 | Target localization and tracking system and method |
| US8805008B1 (en) * | 2011-11-02 | 2014-08-12 | The Boeing Company | Tracking closely spaced objects in images |
-
2014
- 2014-11-26 CN CN201410693468.3A patent/CN104469875B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251593A (en) * | 2008-03-31 | 2008-08-27 | 中国科学院计算技术研究所 | Method for tracking target of wireless sensor network |
| CN101644758A (en) * | 2009-02-24 | 2010-02-10 | 中国科学院声学研究所 | Target localization and tracking system and method |
| US8805008B1 (en) * | 2011-11-02 | 2014-08-12 | The Boeing Company | Tracking closely spaced objects in images |
Non-Patent Citations (2)
| Title |
|---|
| THANGARAJAN ET. AL.: "An Energy Efficient Technique for Object Tracking in Wireless Sensor Networks", 《COMMUNICATION SYSTEMS AND NETWORK TECHNOLOGIES(CSNT)》 * |
| 周伟: "基于无线传感器网络的定位跟踪技术研究", 《中国博士学位论文全文数据库信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105629225A (en) * | 2015-12-30 | 2016-06-01 | 中国人民解放军信息工程大学 | Multi-hypothesis target tracking method based on improved K shortest paths |
| CN105629225B (en) * | 2015-12-30 | 2018-05-11 | 中国人民解放军信息工程大学 | A kind of more hypothesis method for tracking target based on improvement K shortest paths |
| CN105451182A (en) * | 2016-01-04 | 2016-03-30 | 北京科技大学 | Object identification tracking system and method |
| CN105451182B (en) * | 2016-01-04 | 2018-11-27 | 北京科技大学 | A kind of target identification tracking system and method |
| CN107205255A (en) * | 2017-05-15 | 2017-09-26 | 中国科学院上海微系统与信息技术研究所 | Towards the method for tracking target of the wireless sensor network based on imaging sensor |
| CN108152790A (en) * | 2018-01-05 | 2018-06-12 | 燕山大学 | A kind of non-cooperation multi-target traces projectional technique based on distributed structure/architecture |
| CN109219118A (en) * | 2018-11-27 | 2019-01-15 | 上海交通大学 | A kind of distributed consistent state estimation method based on sequence wake-up mechanism |
| CN109219118B (en) * | 2018-11-27 | 2021-08-24 | 上海交通大学 | Distributed consistent state estimation method based on sequence awakening mechanism |
| CN109890002A (en) * | 2019-01-04 | 2019-06-14 | 中国电子科技集团公司电子科学研究院 | A kind of method and device of the prediction Risk Degree of Maneuvering Environment of knowledge-based inference |
| CN109890002B (en) * | 2019-01-04 | 2022-08-16 | 中国电子科技集团公司电子科学研究院 | Method and device for predicting environmental risk based on knowledge reasoning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104469875B (en) | 2018-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104469875A (en) | Prediction-based target tracking method and system in wireless sensor network | |
| Tashtarian et al. | On maximizing the lifetime of wireless sensor networks in event-driven applications with mobile sinks | |
| Torkestani | Mobility prediction in mobile wireless networks | |
| Yeow et al. | Energy efficient multiple target tracking in wireless sensor networks | |
| Xu et al. | Dual prediction-based reporting for object tracking sensor networks | |
| CN101505532B (en) | Wireless sensor network target tracking method based on distributed processing | |
| CN101251593B (en) | Method for tracking target of wireless sensor network | |
| CN103354642B (en) | A kind of method improving mobile sensor network coverage rate | |
| Keally et al. | Watchdog: Confident event detection in heterogeneous sensor networks | |
| Tashtarian et al. | ODT: optimal deadline-based trajectory for mobile sinks in WSN: a decision tree and dynamic programming approach | |
| CN113469325A (en) | Layered federated learning method, computer equipment and storage medium for edge aggregation interval adaptive control | |
| Mansouri et al. | Secure and robust clustering for quantized target tracking in wireless sensor networks | |
| CN102883429A (en) | Method and device for tracking move object in sensor network based on directional antenna | |
| Pino-Povedano et al. | Selective forwarding for energy-efficient target tracking in sensor networks | |
| Ahmad et al. | EEAC: An energy efficient adaptive cluster based target tracking in wireless sensor networks | |
| CN103702384B (en) | Application-oriented clustering routing method of wireless sensor network | |
| Onel et al. | Information content-based sensor selection and transmission power adjustment for collaborative target tracking | |
| Fernandes et al. | A machine learning-based dynamic link power control in wearable sensing devices | |
| Liu et al. | Joint trajectory and scheduling optimization for age of synchronization minimization in uav-assisted networks with random updates | |
| Cao et al. | An efficient moving object tracking framework for WSNs using sequence-to-sequence learning model | |
| Wei et al. | An energy-efficient partition-based framework with continuous ant colony optimization for target tracking in mobile sensor networks | |
| Lv et al. | A node coverage algorithm for a wireless-sensor-network-based water resources monitoring system | |
| CN105376707A (en) | Mobile node positioning method and device based on invisible anchor nodes | |
| Guo et al. | A clustering-based improved Grey-Markov target tracking algorithm in wireless sensor networks | |
| Wagner et al. | Power control for target tracking in sensor networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |