CN115865965A - Moving target detection method, system and equipment based on hierarchical perception - Google Patents
Moving target detection method, system and equipment based on hierarchical perception Download PDFInfo
- Publication number
- CN115865965A CN115865965A CN202211465364.8A CN202211465364A CN115865965A CN 115865965 A CN115865965 A CN 115865965A CN 202211465364 A CN202211465364 A CN 202211465364A CN 115865965 A CN115865965 A CN 115865965A
- Authority
- CN
- China
- Prior art keywords
- detection
- node
- target
- period
- network
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 536
- 230000008447 perception Effects 0.000 title claims abstract description 48
- 230000008859 change Effects 0.000 claims abstract description 152
- 239000003016 pheromone Substances 0.000 claims description 33
- 239000000523 sample Substances 0.000 claims description 30
- 230000004927 fusion Effects 0.000 claims description 21
- 238000005259 measurement Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 22
- 238000005265 energy consumption Methods 0.000 abstract description 20
- 238000000034 method Methods 0.000 abstract description 18
- 238000013178 mathematical model Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a moving target detection method, a system and equipment based on hierarchical perception, which determine a network detection period based on detection demand variation, and then determine respective node detection periods in the network detection period according to the variation condition of each detection node relative to a target and the detection effect of each detection node. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. The method of the embodiment of the invention reflects the self-adaptive adjustment effect of the network level and the node level, takes the change of the network and the node into consideration, and can obtain better detection precision and energy consumption by matching from the two levels.
Description
Technical Field
The invention relates to the technical field of target tracking detection, in particular to a moving target detection method, a system and equipment based on hierarchical perception.
Background
Target tracking or target detection techniques are one of the key inputs to many military or civilian scenarios, and tasks such as underwater, ground or aerial surveillance, reconnaissance, exploration, search and rescue, active target striking, etc. must be based on high-precision target detection. In order to break through the limitation of the traditional technology in space and time, a mode of deploying a plurality of detection platforms is needed to obtain multi-source real-time data with different dimensions and complementary information, and real-time detection and continuous tracking of a moving target are achieved through real-time sharing and fusion of the multi-source information. Target tracking and detecting methods based on an underwater sensor network or an unmanned aerial vehicle cluster and the like try to utilize the capability of a mobile self-organizing network to realize the improvement of tracking and detecting precision. Due to the energy consumption limitation of the detection node and the mobile ad hoc network, and the movement of the detection target and the change of the mobile ad hoc network, how to efficiently match the dynamics and realize the self-adaptive adjustment of the tracking detection parameters faces huge challenges.
One of the key factors affecting the accuracy of target tracking detection is the size of the detection period. The smaller the detection period, the more frequent the detection, the more the obtained target information, the greater the detection precision, but the greater the detection energy consumption; conversely, the smaller the detection accuracy and the detection energy consumption. Therefore, how to adaptively adjust the size of the detection period to obtain a good compromise between the detection accuracy and the detection energy consumption is an urgent problem to be solved.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a moving target detection method based on hierarchical perception, and solves the problem that the prior art is difficult to consider low detection energy consumption under the condition of obtaining good detection precision.
The invention also provides a moving target detection system based on hierarchical perception and a moving target detection device based on hierarchical perception.
The moving target detection method based on hierarchical perception according to the embodiment of the first aspect of the invention comprises the following steps:
determining the detection demand variation degree based on the detection data in the current detection period, wherein the detection data is obtained by detecting a target by a detection node;
updating a detection period based on the detection demand variation degree to obtain a network detection period;
determining node detection mutual information, wherein the detection mutual information represents mutual information between measurement data of a detection node and a target state;
determining a node movement variation degree which represents the movement variation between the detection node and the target;
determining a node detection period based on the node detection mutual information, the node movement variation degree and the network detection period;
and based on the node detection period, the detection node performs target detection.
The moving target detection method based on hierarchical perception provided by the embodiment of the invention at least has the following beneficial effects:
the network detection period is determined based on the detection demand change degree, and then in the network detection period, the respective node detection period is determined according to the change condition of each detection node relative to the target and the detection effect of each detection node. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. The moving target detection method based on level perception of the embodiment of the invention reflects the self-adaptive adjustment effect of the network level and the node level, gives consideration to the change of the network and the node, and can obtain better detection precision and energy consumption by matching from the two levels.
According to some embodiments of the present invention, the determining the detection demand variation degree based on the current detection period includes the following steps:
acquiring a plurality of first detection data, wherein the plurality of first detection data are obtained by respectively carrying out target detection on a plurality of detection nodes in a current detection period, and the first detection data comprise detection values of target positions and target motion vectors;
fusing the first detection data to obtain a target direction change degree and a target speed change degree;
determining a target change degree according to the target direction change degree and the target speed change degree;
acquiring a network change degree, wherein the network change degree is determined by network topology of a last detection period and a current detection period;
and determining the detection demand variation degree according to the target variation degree and the network variation degree.
According to some embodiments of the present invention, the updating the probe period to obtain the network probe period based on the probe demand variation degree includes:
acquiring an initial value of the pheromone based on the detection demand variation degree;
iteratively updating the pheromone based on a pheromone updating formula until the value of the pheromone meets a set threshold value, and stopping updating;
and taking the number of times of the iterative updating as the network detection period.
According to some embodiments of the invention, the determining node probes mutual information, comprising the steps of:
acquiring entropy of measured data of the detection node, wherein the measured data is obtained by quantization processing of the detection data;
acquiring a conditional entropy of measurement data of a detection node in a target state;
and obtaining mutual information between the measured data of the detection node and the target state according to the entropy and the conditional entropy so as to determine the node detection mutual information.
According to some embodiments of the invention, the determining the degree of change of the node movement comprises:
acquiring the distance between a detection node and a target in the last detection period and the current detection period;
acquiring a movement direction included angle between a detection node and a target in a last detection period and a current detection period;
acquiring the relative rates between the detection nodes and the target in the last detection period and the current detection period;
and determining the node movement change degree according to the distance, the movement direction included angle and the relative speed.
According to some embodiments of the present invention, the determining a node probing period based on the node probing mutual information, the node mobility change degree, and the network probing period comprises:
if the node detection mutual information is smaller than a set threshold value or the change of the node detection mutual information is not increased, determining the node detection period as the network detection period;
if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is increased, determining that the node detection period is 1/M of the network detection period, wherein M is an integer larger than 1;
and if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is not increased, determining that the node detection period is 1/N of the network detection period, wherein N is an integer which is larger than 1 and smaller than M.
According to some embodiments of the present invention, the probing node performs target probing based on the node probing period, including the following steps:
based on the node detection period, the detection node detects the target for multiple times to obtain multiple second detection data;
and carrying out averaging processing and quantification processing on the plurality of second detection data to obtain optimized measurement data, wherein the optimized measurement data is used for adaptively adjusting the network detection period.
The moving object detection system based on hierarchical perception according to the second aspect of the invention comprises:
the detection demand change degree determining unit is used for determining the detection demand change degree based on detection data in the current detection period, wherein the detection data are obtained by detecting a target by a detection node;
a network detection period obtaining unit, configured to update a detection period to obtain a network detection period based on the detection demand variation degree;
a node detection mutual information determination unit, configured to determine node detection mutual information, where the node detection mutual information represents mutual information between measurement data of a detection node and a target state;
a node movement change degree determination unit for determining a node movement change degree indicating a movement change between the probe node and the target;
a node detection period determination unit, configured to determine a node detection period based on the node detection mutual information, the node movement variation degree, and the network detection period;
and the target detection unit is used for detecting the target by the nodes based on the node detection period.
The moving target detection system based on hierarchical perception provided by the embodiment of the invention at least has the following beneficial effects:
by executing the corresponding method in the moving target detection system based on the hierarchical perception, the network detection period is determined based on the detection requirement change degree, and then the respective node detection period is determined according to the change condition of each detection node relative to the target and the detection effect of each detection node in the network detection period. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. For the moving target detection system based on level perception, the embodiment of the invention reflects the self-adaptive adjustment effect of the network level and the node level, gives consideration to the change of the network and the node, and can obtain better detection precision and energy consumption by matching from the two levels.
The moving object detection device based on the hierarchical perception according to the third aspect of the present invention includes a data fusion center and a plurality of detection nodes, where the data fusion center and the plurality of detection nodes jointly execute the moving object detection method based on the hierarchical perception according to any one of the embodiments of the first aspect of the present invention.
The moving target detection equipment based on hierarchical perception according to the embodiment of the invention at least has the following beneficial effects:
the detection nodes are used for detecting, and the data fusion center processes the detection data, so that the network detection period is determined based on the detection requirement change degree, and then in the network detection period, the respective node detection period is determined according to the change condition of each detection node relative to the target and the detection effect of the detection node per se, and the respective node detection period is applied to each detection node. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. The moving target detection equipment based on the level perception of the embodiment of the invention embodies the self-adaptive adjustment effect of the network level and the node level, considers the change of the network and the node, and performs matching from the two levels to finally obtain better detection precision and energy consumption.
According to some embodiments of the present invention, each of the probe nodes is configured to report respective probe data to the data fusion center; the data fusion center is used for feeding back detection strategy information to each detection node, the detection strategy information comprises a network detection period obtained by updating and a node detection period mark, and the node detection period mark is used for enabling each detection node to determine a respective node detection period.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a moving object detection method based on hierarchical perception according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a moving object detection system based on hierarchical perception according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a moving object detection device based on hierarchical perception according to an embodiment of the present invention.
Reference numerals:
a detection demand variation degree determination unit 100;
a network detection period acquisition unit 200;
a node probe mutual information determination unit 300;
a node movement change degree determination unit 400;
a node detection period determination unit 500;
an object detection unit 600;
a data fusion center 700;
the node 800 is probed.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, if there are first, second, etc. described, it is only for the purpose of distinguishing technical features, and it is not understood that relative importance is indicated or implied or that the number of indicated technical features is implicitly indicated or that the precedence of the indicated technical features is implicitly indicated.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to, for example, the upper, lower, etc., is indicated based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, but does not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly defined, terms such as setup, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention by combining the detailed contents of the technical solutions.
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the embodiments described below are some, but not all embodiments of the present invention.
Referring to fig. 1, a flowchart of a moving object detection method based on hierarchical perception according to the present invention is shown, and the method includes the following steps:
determining a detection demand change degree based on the detection data in the current detection period, wherein the detection demand change degree comprises a target change degree and a network change degree, and the target change degree comprises a target direction change degree and a target speed change degree;
determining the detection demand variation degree based on the detection data in the current detection period, wherein the detection data is obtained by performing target detection on the detection nodes;
updating the detection period based on the detection demand variation degree to obtain a network detection period;
determining node detection mutual information, wherein the detection mutual information represents mutual information between measurement data of a detection node and a target state;
determining a node movement change degree, wherein the node movement change degree represents the movement change between a detection node and a target;
determining a node detection period based on node detection mutual information, a node movement change degree and a network detection period;
and based on the node detection period, the detection node performs target detection.
Specifically, as shown in fig. 1, in the current probing period, a plurality of probing nodes will probe to obtain a plurality of probing data, and according to the processing of the plurality of probing data, a target change degree and a network change degree can be determined, and finally a probing demand change degree is determined; then based on the detection requirement change degree, the detection period can be updated to determine and obtain a network detection period, and the node detection mutual information and the node movement change degree are continuously determined, so that the node detection period is determined and obtained from the network detection period according to the change conditions of the node detection mutual information and the node movement change degree; and finally, the node detection period can be applied to the corresponding detection node so as to carry out the next target detection.
In this embodiment, a network probing period is determined based on the probing requirement variation degree, and then, in the network probing period, respective node probing periods are determined according to the variation of each probing node with respect to the target and the probing effect of each probing node. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. The moving target detection method based on level perception of the embodiment of the invention reflects the self-adaptive adjustment effect of the network level and the node level, gives consideration to the change of the network and the node, and can obtain better detection precision and energy consumption by matching from the two levels.
In some embodiments, determining the detection demand variation degree based on the current detection period includes the following steps:
acquiring a plurality of first detection data, wherein the plurality of first detection data are obtained by respectively carrying out target detection on a plurality of detection nodes in a current detection period, and the first detection data comprise detection values of target positions and target motion vectors;
fusing the plurality of first detection data to obtain a target direction change degree and a target speed change degree;
determining a target change degree according to the target direction change degree and the target speed change degree;
acquiring a network change degree, wherein the network change degree is determined by network topology of a last detection period and a current detection period;
and determining the detection demand variation degree according to the target variation degree and the network variation degree.
Specifically, it can be understood that, in the current detection period, each detection node detects a target to obtain a target position and a target motion vector, that is, obtain first detection data; further, the first detection data of each detection node is fused, and a target direction change degree and a target speed change degree can be obtained, wherein the target direction change degree and the target speed change degree are respectively constrained by the following mathematical models:
wherein, theta o (T, T + T) represents a target direction change degree; v. of o (T, T + T) represents a target rate change degree;
and &>
Respectively representing the target motion vectors detected at time T and time T + T; />
And &>
Respectively representing the moving speed of the target detected at the time T and the time T + T; t denotes a detection period.
Therefore, the target change degree can be calculated according to the target direction change degree and the target speed change degree, and is constrained by the following mathematical model:
OCD(t,t+T)＝θ o (t,t+T)+v o (t,t+T)，
wherein OCD (T, T + T) represents a target degree of change; theta o (T, T + T) represents a target direction change degree; v. of o (T, T + T) represents the target rate change degree.
It can be understood that the larger the target change degree is, the larger the target change is, and the sensing needs to be more frequent for the network.
Further, the degree of network variation is constrained by the following mathematical model:
wherein, delta tp Representing the degree of network change; i E t ∪E t+T I represents the network topology G at time t t (V t ,E t ) And network topology G at time T + T t+T (V t+T ,E t+T ) The number of total edges; w is a t (u, v) and w t+T (u, v) each represents G t (V t ,E t ) And G t+T (V t+T ,E t+T And the weights of the links of the middle network node u and the network node v are specifically represented by the distance between the network nodes.
It can be understood that the larger the network change degree is, the larger the network topology change is, and the perception needs to be more frequent for the network.
And finally, determining the detection demand variation degree according to the target variation degree and the network variation degree, wherein the detection demand variation degree is specifically constrained by the following mathematical model:
S o (t,t+T)＝OCD(t,t+T)+Δ tp ，
wherein S is o (T, T + T) represents the detection demand variation degree; OCD (T, T + T) represents a target degree of change; delta tp Indicating the degree of network change.
It will be appreciated that the larger the target changes, or the larger the network changes, the more frequent the target detection is.
In some embodiments, updating the probing period to obtain the network probing period based on the probing requirement variation degree includes the following steps:
acquiring an initial value of the pheromone based on the detection demand variation degree;
iteratively updating the pheromone based on a pheromone updating formula until the value of the pheromone meets a set threshold value, and stopping updating;
and taking the number of times of iterative updating as a network detection period.
It is understood that the detection period needs to be adaptively changed as the target moves or the network changes. The detection requirement change degree is increased, and the detection period is required to be shortened so as to detect the target information in time; otherwise, the detection period needs to be increased so as to save energy consumption. The process of acquiring the detection demand variation degree is equal to the process of acquiring the pheromone in the ant colony algorithm, the value of the detection demand variation degree is equal to the value of the pheromone, and the target detection updating period T is set as the volatilization time of the pheromone. The detection requirement changes quickly, the pheromone volatilizes quickly, the T value is small, and the detection interval is short; if the detection requirement changes slowly, the pheromone volatilizes slowly, the T value is relatively large, and the detection interval is lengthened. When the pheromone is volatilized to be small enough, the pheromone is considered to be volatilized, and the next target detection can be carried out.
Specifically, an initial value of the pheromone is first acquired. Initial value Q of pheromone 0 (T + T) is the detection demand variation degree S obtained by the last sensing o (T, T + T) and the value Q of the last pheromone 0 (t) is equal to the last detection demand variation degree S o (t) of (d). The method comprises the following specific steps:
Q 0 (t+T)＝S o (t,t+T)，
further, the pheromone is iteratively updated based on the pheromone update formula. The value of the pheromone is reduced after each updating of the pheromone, and the iteration is repeated until all pheromones are volatilized. The information volatilization speed depends on the volatilization coefficient rho, and the pheromone Q obtained at this time 0 Value of (T + T) and last pheromoneValue of Q 0 (t) the result of the comparison. Specifically, the pheromone update formula is as follows:
Q k (t+T)＝(1-ρ) k Q 0 (t+T)，
wherein the volatility coefficient ρ is obtained by the following formula:
wherein, it can be understood that the detection requirement has small change, is relatively stable, the volatilization time can be slightly longer, and rho 1 May be slightly smaller; detecting moderate change in demand, ρ 2 Can be set to the ratio ρ 1 Slightly larger; large variation in detection demand, ρ 3 Can be set to the ratio ρ 2 And larger. The value interval of alpha is (0, 1).
Finally when Q is k ≈0.0001×Q 0 When the value of the pheromone is small enough and meets the set threshold value, the pheromone is considered to be volatilized completely, iteration updating is stopped, the iteration number k at the moment is taken as a new detection period, and the network detection period T is obtained 0 . In particular, the network probing period T 0 Consists of the following:
wherein Q is k Value, Q, representing the currently updated pheromone 0 Denotes the initial value of the pheromone, and ρ denotes the volatilization coefficient.
In some embodiments, determining the node probe mutual information comprises:
acquiring entropy of measurement data of the detection node, wherein the measurement data is obtained by quantization processing of the detection data;
acquiring a conditional entropy of measurement data of a detection node in a target state;
and obtaining mutual information between the measured data of the detection node and the target state according to the entropy and the conditional entropy so as to determine node detection mutual information.
Specifically, the entropy of the measured data of the probe node is obtained first. Entropy of the metrology data H (Z) k+1 ) Constrained by the following mathematical model:
wherein the set of quantization thresholds γ = [ γ ] 0 ,γ 1 ,…,γ L ]From a number of quantization levels L =2 m And (6) determining. Thus, the distribution p (z) is quantized k+1 ) Comprises the following steps:
p(z k+1 )＝∫p(z k+1 |x k+1 )p(x k+1 )dx k+1 ，
a priori distribution p (x) of target states k+1 ) Sampling is carried out, and sampling particles in a target state can be used for approximately obtaining:
wherein the content of the first and second substances,
representing the predicted particles from the last time target estimation state, and N represents the total number of particles.
Therefore, the entropy H (Z) of the measured data can be approximated according to the following formula k+1 )：
Further, the conditional entropy of the measured data of the detection node in the target state is obtained. Specifically, target state x k+1 Conditional entropy of H (z) k+1 |x k+1 ) Constrained by the following mathematical model:
H(z k+1,q |x k+1 )＝∫p(z k+1 ,x k+1 )log p(z k+1 |x k+1 )dx k+1 ，
wherein p (z) is distributed jointly k+1 ,x k+1 ) Comprises the following steps:
p(z k+1 ,x k+1 )＝p(z k+1 |x k+1 )p(x k+1 )，
thereby, it is possible to obtain:
H(z k+1,q |x k+1 )＝∫p(z k+1 |x k+1 )log p(z k+1 |x k+1 )p(x k+1 )dx k+1 ，
therefore, the target state x can be approximated according to the following formula k+1 Conditional entropy of H (z) k+1 |x k+1 )：
It can be understood that, in general, the closer to the target, the more accurate the target information, i.e., the metrology data, is obtained by the probing node. Measured data z of probe node k+1 And target state x k+1 The mutual information between them can be determined by the following formula:
I(x k+1 ,z k+1 )＝H(z k+1 )-H(z k+1 |x k+1 )，
wherein, the measurement data of the detection node is as follows:
thus, the metrology data z of the probe nodes is determined k+1 And target state x k+1 The mutual information between the nodes, namely the node detection mutual information is determined.
In some embodiments, determining the degree of change in node mobility comprises:
acquiring the distance between a detection node and a target in a last detection period and a current detection period;
acquiring a movement direction included angle between a detection node and a target in a last detection period and a current detection period;
acquiring the relative rates between the detection nodes and the target in the last detection period and the current detection period;
and determining the node movement change degree according to the distance, the movement direction included angle and the relative speed.
In particular, it can be understood that the degree of change in node movement is constrained by the following mathematical model:
wherein the content of the first and second substances,
and &>
Respectively representing the distance between the detection node i and the target o in the last detection period and the current detection period; />
And &>
Respectively representing the motion direction included angles between the detection node i and the target o in the last detection period and the current detection period; />
And &>
The relative rates between the probing node i and the target o in the last probing period and the current probing period are respectively shown.
In particular, the amount of the solvent to be used,
and &>
Is easy to obtain by distance measurement; angle of movement directionAnd the relative rates are determined by the following equations, respectively:
wherein the content of the first and second substances,
and &>
Respectively representing the target motion vectors of the detection node i and the target o in the current detection period.
Thus, by obtaining separately
And &>
And &>
And &>
The node movement change degree MCD (T, T + T) can be finally determined.
In some embodiments, determining the node probing period based on the node probing mutual information, the node movement change degree and the network probing period comprises the following steps:
if the node detection mutual information is smaller than a set threshold value or the change of the node detection mutual information is not increased, determining the node detection period as a network detection period;
if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is increased, determining that the node detection period is 1/M of the network detection period, wherein M is an integer larger than 1;
and if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is not increased, determining that the node detection period is 1/N of the network detection period, wherein N is an integer which is larger than 1 and smaller than M.
Specifically, for important detection nodes, a node detection period is set according to the detection effect and the movement change degree, multiple detections can be performed in the network detection period, and the detection precision under the target change can be further improved. It can be understood that, in practice, the network probing period is divided into a plurality of node probing periods, that is, the probing node can perform multiple probing within the network probing period.
In some embodiments, the probing node performs target probing based on a node probing period, including the steps of:
based on the node detection period, the detection node detects the target for multiple times to obtain multiple second detection data;
and carrying out average processing and quantification processing on the plurality of second detection data to obtain optimized measurement data, wherein the optimized measurement data is used for adaptively adjusting the network detection period.
Specifically, it can be understood that after the current node probing period is obtained, the probing node can perform corresponding probing, optimize the probing data for multiple times to obtain optimized measurement data, and use the optimized measurement data as a condition for obtaining a next probing requirement variation degree, that is, the method is circulated to the first step of the method of the embodiment of the present invention, and actually determines the next probing requirement variation degree based on the second probing data, and finally obtains the next network probing period, so that the method embodies adaptive adjustment of the network probing period.
In addition, referring to fig. 2, a moving object detection system based on hierarchical perception provided for an embodiment of the present invention includes: the node movement detection method includes a detection requirement change degree determining unit 100, a network detection period acquiring unit 200, a node detection mutual information determining unit 300, a node movement change degree determining unit 400, a node detection period determining unit 500 and an object detecting unit 600. The detection demand change degree determining unit 100 is configured to determine a detection demand change degree based on detection data in the current detection period, where the detection data is obtained by performing target detection by a detection node; the network probing period obtaining unit 200 is configured to update a probing period based on the probing requirement variation degree to obtain a network probing period; the node detection mutual information determination 300 unit is configured to determine node detection mutual information, where the detection mutual information represents mutual information between measurement data of a detection node and a target state; the node movement change degree determining unit 400 is configured to determine a node movement change degree, where the node movement change degree represents a movement change between a probe node and a target; the node detection period determining unit 500 is configured to determine a node detection period based on the node detection mutual information, the node movement variation degree, and the network detection period; the target detection unit 600 is configured to detect a target by a node based on a node detection period.
Specifically, with reference to fig. 1 and fig. 2, it can be understood that the moving target detection system based on hierarchical perception in the embodiment of the present application is used to implement the moving target detection method based on hierarchical perception, the moving target detection system based on hierarchical perception in the embodiment of the present application corresponds to the moving target detection method based on hierarchical perception, and a specific processing procedure refers to the moving target detection method based on hierarchical perception, which is not described herein again.
It can be understood that, by executing the corresponding method in the moving object detection system based on hierarchical perception according to the embodiment of the present invention, a network detection period is determined based on a detection requirement variation degree, and then, in the network detection period, respective node detection periods are determined according to a variation condition of each detection node with respect to an object and a detection effect of each detection node. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple times of detection can be performed in the network detection period, and the detection precision under the target change is further improved. The moving target detection system based on the hierarchical perception of the embodiment of the invention embodies the self-adaptive adjustment effect of the network hierarchy and the node hierarchy, considers the change of the network and the node, and performs matching from the two hierarchies to finally obtain better detection precision and energy consumption.
In addition, referring to fig. 3, an embodiment of the present invention further provides a moving object detection device based on hierarchical perception, including a data fusion center 700 and a plurality of detection nodes 800, where the data fusion center 700 and the plurality of detection nodes 800 jointly execute any one of the moving object detection methods based on hierarchical perception according to the embodiments of the present invention.
Specifically, referring to fig. 3, the plurality of probe nodes 800 perform target probing respectively to obtain current probe data, and report the current probe data to the data fusion center 700, and the data fusion center 700 processes the current probe data, that is, executes the moving target probing method based on hierarchical perception according to the embodiment of the present invention, so as to obtain a network probing period through adaptive adjustment. The data fusion center 700 sends the detection policy information including the network detection period and the node detection period flag to the plurality of detection nodes 800, and the plurality of detection nodes 800 determine respective node detection periods according to the detection policy information. Specifically, if the probing period flag of a certain probing node 800 is 0, the node probing period is set as the network probing period; otherwise, the probe node 800 executes the moving object detection method based on hierarchical perception according to the embodiment of the present invention, that is, the node detection period of the probe node 800 is determined based on the node detection mutual information, the node movement variation degree, and the network detection period. Finally, each probing node 800 can perform multiple corresponding probing in the network probing period.
It can be understood that, by using the probing nodes 800 to perform probing and processing the probing data by the data fusion center 700, a network probing period is determined based on the degree of change of the probing requirement, and then, in the network probing period, according to the change of each probing node with respect to the target and the probing effect of each probing node, a respective node probing period is determined and applied to each probing node 800. Therefore, the network detection period can be matched with the target change and the network change through self-adaptive adjustment, and meanwhile, the detection precision and the network energy consumption performance are guaranteed. For important detection nodes, the node detection period is adaptively set according to the detection effect and the movement change degree, so that multiple detections can be performed in the network detection period, and the detection precision under the target change is further improved. The moving target detection equipment based on level perception of the embodiment of the invention embodies the self-adaptive adjustment effect of the network level and the node level, gives consideration to the change of the network and the node, and can obtain better detection precision and energy consumption by matching from the two levels.
In some embodiments, as shown in fig. 3, each probe node 800 is configured to report respective probe data to the data fusion center 700; the data fusion center 700 is configured to feed back detection policy information to each detection node 800, where the detection policy information includes an updated network detection period and a node detection period flag, and the node detection period flag is used to enable each detection node 800 to determine a respective node detection period.
Specifically, referring to fig. 3, it can be understood that each probe node 800 transmits its respective probe data to the data fusion center 700; the data fusion center 700 performs processing to obtain a network detection period through adaptive updating, and generates detection strategy information to feed back to each detection node 800; each probe node 800 processes the probe policy information received by itself, specifically, determines a node probe period flag to determine a node probe period for performing multiple subsequent target probes.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A moving target detection method based on hierarchical perception is characterized by comprising the following steps:
determining the detection demand variation degree based on the detection data in the current detection period, wherein the detection data is obtained by detecting a target by a detection node;
updating a detection period based on the detection demand variation degree to obtain a network detection period;
determining node detection mutual information, wherein the detection mutual information represents mutual information between measurement data of a detection node and a target state;
determining a node movement variation degree which represents the movement variation between the detection node and the target;
determining a node detection period based on the node detection mutual information, the node movement variation degree and the network detection period;
and based on the node detection period, the detection node performs target detection.
2. The moving object detection method based on hierarchical perception according to claim 1, wherein the determining of the detection demand variation degree based on the detection data in the current detection period includes the following steps:
acquiring a plurality of first detection data, wherein the plurality of first detection data are obtained by respectively carrying out target detection on a plurality of detection nodes in a current detection period, and the first detection data comprise detection values of target positions and target motion vectors;
fusing the first detection data to obtain a target direction change degree and a target speed change degree;
determining a target change degree according to the target direction change degree and the target speed change degree;
acquiring a network change degree, wherein the network change degree is determined by network topology of a last detection period and a current detection period;
and determining the detection demand variation degree according to the target variation degree and the network variation degree.
3. The moving object detection method based on hierarchical perception according to claim 2, wherein the step of updating a detection period based on the detection demand variation degree to obtain a network detection period comprises the following steps:
acquiring an initial value of the pheromone based on the detection demand variation degree;
iteratively updating the pheromone based on a pheromone updating formula until the value of the pheromone meets a set threshold value, and stopping updating;
and taking the number of times of the iterative updating as the network detection period.
4. The moving object detection method based on hierarchical perception according to claim 3, wherein the determining node detects mutual information, comprising the steps of:
acquiring entropy of measured data of the detection node, wherein the measured data is obtained by quantization processing of the detection data;
acquiring a conditional entropy of measurement data of a detection node in a target state;
and obtaining mutual information between the measured data of the detection node and the target state according to the entropy and the conditional entropy so as to determine the node detection mutual information.
5. The moving object detection method based on hierarchical perception according to claim 4, wherein the determining the degree of change of node movement includes the following steps:
acquiring the distance between a detection node and a target in the last detection period and the current detection period;
acquiring a movement direction included angle between a detection node and a target in a last detection period and a current detection period;
acquiring the relative rates between the detection nodes and the target in the last detection period and the current detection period;
and determining the node movement change degree according to the distance, the movement direction included angle and the relative speed.
6. The moving object detection method based on hierarchical perception according to claim 5, wherein the determining a node detection period based on the node detection mutual information, the node movement variation degree and the network detection period includes:
if the node detection mutual information is smaller than a set threshold value or the change of the node detection mutual information is not increased, determining the node detection period as the network detection period;
if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is increased, determining that the node detection period is 1/M of the network detection period, wherein M is an integer larger than 1;
and if the node detection mutual information is larger than the set threshold value, the change of the node detection mutual information is increased, and the node movement change degree is not increased, determining that the node detection period is 1/N of the network detection period, wherein N is an integer which is larger than 1 and smaller than M.
7. The moving object detection method based on hierarchical perception according to claim 6, wherein the detecting nodes perform object detection based on the node detection period, including the following steps:
based on the node detection period, the detection node detects the target for multiple times to obtain multiple second detection data;
and carrying out averaging processing and quantification processing on the plurality of second detection data to obtain optimized measurement data, wherein the optimized measurement data is used for adaptively adjusting the network detection period.
8. A moving object detection system based on hierarchical perception is characterized by comprising:
the detection demand change degree determining unit is used for determining the detection demand change degree based on detection data in the current detection period, wherein the detection data are obtained by detecting a target by a detection node;
a network detection period obtaining unit, configured to update a detection period to obtain a network detection period based on the detection demand variation degree;
a node detection mutual information determination unit, configured to determine node detection mutual information, where the node detection mutual information represents mutual information between measurement data of a detection node and a target state;
a node movement change degree determination unit for determining a node movement change degree indicating a movement change between the probe node and the target;
a node probing period determining unit, configured to determine a node probing period based on the node probing mutual information, the node mobility change degree, and the network probing period;
and the target detection unit is used for detecting the target of the nodes based on the node detection period.
9. A moving object detection device based on hierarchical perception is characterized by comprising a data fusion center and a plurality of detection nodes, wherein the data fusion center and the plurality of detection nodes jointly execute the moving object detection method based on hierarchical perception according to any one of claims 1 to 7.
10. The moving-target detection device based on hierarchical perception according to claim 9, wherein each of the detection nodes is configured to report respective detection data to the data fusion center; the data fusion center is used for feeding back detection strategy information to each detection node, the detection strategy information comprises a network detection period obtained by updating and a node detection period mark, and the node detection period mark is used for enabling each detection node to determine a respective node detection period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211465364.8A CN115865965B (en) | 2022-11-22 | 2022-11-22 | Method, system and equipment for detecting moving target based on hierarchical perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211465364.8A CN115865965B (en) | 2022-11-22 | 2022-11-22 | Method, system and equipment for detecting moving target based on hierarchical perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115865965A true CN115865965A (en) | 2023-03-28 |
| CN115865965B CN115865965B (en) | 2023-12-19 |
Family
ID=85664854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211465364.8A Active CN115865965B (en) | 2022-11-22 | 2022-11-22 | Method, system and equipment for detecting moving target based on hierarchical perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115865965B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104113896A (en) * | 2013-04-16 | 2014-10-22 | 华为技术有限公司 | Detection frequency adjusting method of sensor node, detection frequency adjusting system of sensor node, and sensor |
| CN109523011A (en) * | 2018-11-06 | 2019-03-26 | 哈尔滨工业大学（深圳） | A kind of multisensor adaptive management method towards multiple no-manned plane collaboration detection |
| CN110719223A (en) * | 2019-09-16 | 2020-01-21 | 清华大学 | Detection period cooperative self-adaptive adjustment method and system |
| CN113344473A (en) * | 2021-08-04 | 2021-09-03 | 北京邮电大学 | Optimization method and device for ocean target cooperative detection device |
| US20220041255A1 (en) * | 2020-06-01 | 2022-02-10 | Chuan Qin | Layered data acquisition system applied to marine information network and method thereof |
-
2022
- 2022-11-22 CN CN202211465364.8A patent/CN115865965B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104113896A (en) * | 2013-04-16 | 2014-10-22 | 华为技术有限公司 | Detection frequency adjusting method of sensor node, detection frequency adjusting system of sensor node, and sensor |
| CN109523011A (en) * | 2018-11-06 | 2019-03-26 | 哈尔滨工业大学（深圳） | A kind of multisensor adaptive management method towards multiple no-manned plane collaboration detection |
| CN110719223A (en) * | 2019-09-16 | 2020-01-21 | 清华大学 | Detection period cooperative self-adaptive adjustment method and system |
| US20220041255A1 (en) * | 2020-06-01 | 2022-02-10 | Chuan Qin | Layered data acquisition system applied to marine information network and method thereof |
| CN113344473A (en) * | 2021-08-04 | 2021-09-03 | 北京邮电大学 | Optimization method and device for ocean target cooperative detection device |
Non-Patent Citations (3)
| Title |
|---|
| LINGHUA ZHAO: "A Moving Object Detection Method Using Deep Learning-Based Wireless Sensor Networks", 《COMPLEXITY》 * |
| 张立韬;周赤非;: "一种支撑反导精度链需求的多传感器资源调度方法", 军事运筹与系统工程, no. 01 * |
| 陈延军;潘泉;王征;: "无线传感器网络目标跟踪性能优化及仿真", 传感技术学报, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115865965B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9594150B2 (en) | Determining device locations using movement, signal strength | |
| Wang et al. | Robust device-free wireless localization based on differential RSS measurements | |
| KR20220103808A (en) | Systems and methods for calibrating unstable sensors | |
| CN107659989B (en) | Distributed measurement dormancy and target tracking method for wireless sensor network nodes | |
| CN105791143B (en) | A kind of self-adaptive quadtree method of mobility and DSRC/WAVE network relevant feedback | |
| Zhao et al. | GraphIPS: Calibration-free and map-free indoor positioning using smartphone crowdsourced data | |
| CN109379780A (en) | Wireless sensor network locating method based on adaptive differential evolution algorithm | |
| CN111427019A (en) | Roadside radar self-adaptive correction method and system | |
| CN107422326B (en) | Underwater target tracking method based on Bayesian estimation | |
| CN112714397B (en) | WSN node positioning method based on ranging optimization and improved sparrow search algorithm | |
| CN114281101A (en) | Unmanned aerial vehicle and holder interference source joint search method based on reinforcement learning | |
| CN115865965B (en) | Method, system and equipment for detecting moving target based on hierarchical perception | |
| Farahmand et al. | Tracking target signal strengths on a grid using sparsity | |
| CN115494450B (en) | High-precision ultra-wideband indoor positioning tracking and control method and device | |
| CN109769206B (en) | Indoor positioning fusion method and device, storage medium and terminal equipment | |
| CN114894222B (en) | External parameter calibration method of IMU-GNSS antenna and related method and equipment | |
| WO2014079245A1 (en) | Positioning method, device and system | |
| JPWO2020004448A1 (en) | Aircraft control device | |
| KR101445800B1 (en) | Range free localization scheme and apparatus in irregular wireless sensor networks | |
| Zhou et al. | DV-Hop node localization algorithm based on improved particle swarm optimization | |
| CN107590509B (en) | Cherenov fusion method based on maximum expectation approximation | |
| CN111328015A (en) | Wireless sensor network target tracking method based on Fisher information distance | |
| Li et al. | Fingerprint-based BLE indoor position methods to improve localization accuracy by particle filters | |
| CN108322888A (en) | A kind of indoor orientation method of mobile terminal | |
| KR102408488B1 (en) | Apparatus and method for estimating location |
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 |