CN103702413A - Real-time following and positioning system of indoor camera based on Zigbee network - Google Patents

Abstract

A real-time following and positioning system of an indoor camera based on a Zigbee network comprises a positioning RFID (Radio Frequency Identification) tag for marking a target, an RFID reader-writer module connected with the positioning RFID tag, a Zigbee network environment for wireless positioning, and a camera holder for controlling camera following, wherein the RFID reader-writer module comprises an antenna, an RFID chip, a microcontroller and a Zigbee signal transmit-receive module; the Zigbee network environment comprises the Zigbee network and a positioning mater controller; the Zigbee network comprises a Zigbee wireless network consisting of a Zigbee network coordinator and Zigbee network nodes; the positioning mater controller comprises a communication interface module for receiving a Zigbee network environment signal, an embedded information processing platform and a camera holder executing mechanism control module; and the embedded information processing platform integrates an echo state network positioning algorithm based on an RSSI (Received Signal Strength Indicator) model. The system can solve the problems of lack of a special positioning system, a large positioning error, difficult real-time positioning and the like of the existing indoor camera.

Description

Live pick up head based on Zigbee network is followed navigation system in real time

Technical field

The invention belongs to wireless sensor network positioning technical field, specifically a kind of live pick up head based on Zigbee network is followed navigation system in real time.

Background technology

Live pick up head location has the real-time following feature of stronger application background, especially camera.At present, at live pick up head, following in real time positioning field does not also have a set of complete feasible system and scheme, is more to rely on human assistance to realize.Also have at present people's reference GPS (Global Position System) localization method, the method is located by embedded GPS module.But the positioning equipment of embedded GPS module often exists because indoor signal is easily lost, or the mobile problem limited normally to work of powering, make GPS implement tracing and positioning and lost efficacy.Meanwhile, when live pick up head adopts GPS module, also have that application cost is higher, integrated complex degree is high, among a small circle in the problems such as the limited and real-time of precision is not high.

Summary of the invention

Technical problem to be solved by this invention is just to provide a kind of live pick up head based on Zigbee network and follows in real time navigation system, can solve existing live pick up head and lack the problems such as proprietary navigation system, large, the real-time location difficulty of position error.

For solving the problems of the technologies described above, a kind of live pick up head based on Zigbee network provided by the invention is followed navigation system in real time, comprise for indicating the location RFID label of target, the rfid interrogator module being attached thereto, for carrying out the Zigbee network environment of wireless location and controlling camera and follow mobile camera The Cloud Terrace, described rfid interrogator module comprises antenna, RFID chip, microcontroller and Zigbee signal transmitting and receiving module, described Zigbee network environment comprises Zigbee network and location main controller, described Zigbee network comprises the Zigbee wireless network consisting of Zigbee network telegon and Zigbee network node, described location main controller comprises for receiving the communication interface modules of Zigbee network ambient signal, the embedded information processing platform and camera The Cloud Terrace actuating mechanism controls module,

The described embedded information processing platform the is integrated echo state network location algorithm based on RSSI model, wireless signal strength while moving under Zigbee network environment according to location RFID label, merge, by network training mode, reduce to locate mean square error, thereby accurately locate RFID label; Meanwhile, camera The Cloud Terrace actuating mechanism controls module, according to locator data information, is sent instruction and is dynamically adjusted The Cloud Terrace steering wheel; ;

Described RSSI model is:

$\mathrm{PL}\left(d\right)=\mathrm{PL}\left(d_0\right)-10\mathrm{nlg}\left(\frac{d}{d_0}\right)+\mathrm{\ϵ}---\left(1\right)$

In formula (1), d is the distance that calculative unknown node arrives beaconing nodes, and n is path loss index, depends on Zigbee network environment, the signal strength signal intensity that PL (d) receives for unknown node, PL (d ₀) be reference distance d ₀the signal strength signal intensity at place, d ₀for the distance of reference node to beaconing nodes, ε is position error;

Described echo state network location algorithm comprises the following steps:

1) sample phase: the Zigbee network telegon of some or Zigbee network node are set in indoor positioning region as with reference to node, after Zigbee network telegon and Zigbee network node networking complete, the positional information of these nodes is all known, measure mutual decay intensity RSSI value, build W _out, described W _outfor deposit pond DR(Dynamic Reservior) be that input and output are for the connection weight matrix of output; Zigbee network telegon sends to register control via UART by these data; Location RFID label is moved into the initial condition that is defined as network in Zigbee network, and the initial condition of network is 0, i.e. x (0)=0, training location sample (u (n), n=1,2 ... P) through input connection weight matrix W _inbe added in deposit pond DR, successively completion system state and error output

calculating and collection; Calculate output connection weight matrix W _out, Zigbee network telegon starts to collect internal state variable from a certain moment m, and with vector (x ₁(i), x ₂(i) ..., x _n(i)) (i=m, m+1 ..., P) for row forms matrix Β (P-m+1, N), simultaneously corresponding sample locator data ε (n) is also collected, and forms a column vector Τ (P-m+1,1);

2) weights calculation stages: according to collecting navigation system state matrix in sample phase and locating RFID label and move sample data, calculate output connection weight matrix W _out; Due to state variable x (n) and output

between be linear relationship, and the target need realizing is to utilize the actual output of echo state network

approach desired output ε (n),

$\mathrm{\ϵ}\left(n\right)\≈\widehat{\mathrm{\ϵ}}\left(n\right)={\mathrm{\Σ}}_{i=1}^t{w}_i^{\mathrm{out}}{x}_i\left(n\right)---\left(2\right)$

Namely wish to calculate weights

(

for matrix W _outelement), meet network positions mean square deviation minimum, that is:

$\min \frac{1}{P-m+1}\underset{n=m}{\overset{P}{\mathrm{\Σ}}}{(\mathrm{\ϵ}\left(n\right)-{\mathrm{\Σ}}_{i=1}^L{w}_i^{\mathrm{out}}{x}_i\left(n\right))}^2---\left(3\right)$

Can be in the hope of the inverse matrix of matrix Β, i.e. W according to formula (3) _out=Β ^-1Τ, so far, ESNs network training completes, and what the network training can be directly used in location RFID label follows location in real time.

In technique scheme, the core wireless module of described Zigbee network telegon and Zigbee network node all adopts CC2530 chip.

In technique scheme, described camera The Cloud Terrace actuating mechanism controls module, turns to by regulating PWM mode to control The Cloud Terrace.

In technique scheme, described Zigbee signal transmitting and receiving module and Zigbee network environment adopt 2.4GHz radiofrequency signal.

In technique scheme, described location main controller adopts two ARM kernel processes unit, and described communication interface modules adopts asynchronous receiving-transmitting transmitter.

Compared with prior art, beneficial effect of the present invention is: 1) cost performance of the present invention is high, and Zigbee chip is all more cheap with respect to bluetooth, wifi and GPS chip; 2) node of the network environment that the present invention builds based on Zigbee chip, all there are two kinds of functions of route and main frame, adopt low complex degree and MANET mode, can respond fast the topologies change of existing network, and the new network topology structure of the reconstruct of precise and high efficiency; 3) energy-conserving and environment-protective of the present invention, have feature low in energy consumption, in No. 5 powered battery situations of two joints, and the sustainable work several months long of Zigbee chip; 4) reliability of the present invention is strong, and network environment is stable, safe; 5) the present invention, at the environment based on Zigbee network, adopts radio-frequency (RF) identification (RFID) technology, and adopts the echo state network location algorithm based on RSSI model, has overcome traditional RSSI location algorithm and has had larger measure error, the shortcoming that real-time response is slow.

Accompanying drawing explanation

Fig. 1 is the structural representation that a kind of live pick up head of the present invention is followed navigation system in real time;

Fig. 2 is the structured flowchart of rfid interrogator module;

Fig. 3 is the structured flowchart of Zigbee network environment;

Fig. 4 is the structured flowchart of camera The Cloud Terrace actuator module;

Fig. 5 is the schematic diagram of the echo state network location algorithm based on RSSI model.

Embodiment

Below in conjunction with accompanying drawing, specific embodiments of the invention are described in further detail:

As shown in Figure 1, a kind of live pick up head based on Zigbee network of the present invention is followed navigation system in real time, comprise the location RFID label for indicating target, the rfid interrogator module being attached thereto, for carrying out the Zigbee network environment of wireless location and controlling camera and follow mobile camera The Cloud Terrace.Zigbee network environment comprises Zigbee network and location main controller.As shown in Figure 2, rfid interrogator module comprises antenna, RFID chip, microcontroller and Zigbee signal transmitting and receiving module.

As shown in Figure 3, Zigbee network comprises the Zigbee wireless network consisting of Zigbee network telegon and Zigbee network node.Network environment based on Zigbee of the present invention networking in the following manner: the network sensing node based on Zigbee chip 1 forms this network environment by several (>=4), and its function is equivalent to the terminal in network.According to concrete applied environment and requirement, Zigbee network sensor node is evenly positioned over to indoor environment.Zigbee network routing node 2 is set, and its function is equivalent to the router of network.Zigbee network telegon 3 is set, its function is equivalent to the gateway node of network, in following navigation system in real time, serve as the hardware of communicating by letter with location main controller, network coordinator forms the network of fully connected topology with network sensor node, all Zigbee nodes all send to Zigbee network telegon in real time by the RFID label position information collecting.In actual applications, Zigbee network routing node 2 can be same node with Zigbee network telegon 3, just different on inner parameter arranges.

For stable signal transmission, the core wireless module of above-mentioned Zigbee network telegon and Zigbee network node all adopts CC2530 chip, and Zigbee signal transmitting and receiving module and Zigbee network environment adopt 2.4GHz radiofrequency signal.

As shown in Figure 4, location main controller comprises the communication interface modules for receiving Zigbee network ambient signal, the embedded information processing platform and camera The Cloud Terrace actuating mechanism controls module.First, the RFID label real-time position information transmitting by communication interface modules; Secondly, via intelligent location algorithm, determine orientation regulated quantity; Finally, camera The Cloud Terrace actuating mechanism controls module regulates the orientation angle in length and breadth of external camera The Cloud Terrace, thereby adjusts camera focus direction, reaches and follows in real time location.For the ease of regulating, camera The Cloud Terrace actuating mechanism controls module, turns to by regulating PWM mode to control The Cloud Terrace.Location main controller preferably adopts two ARM kernel processes unit, and operation android4.2 operating system, can combine wireless telecommunications, multimedia application, remote monitoring, distributed task scheduling processing etc.Location main controller is connected to Zigbee network telegon by universal asynchronous receiving-transmitting transmitter (UART).

The above-mentioned embedded information processing platform the is integrated echo state network location algorithm based on RSSI model, wireless signal strength while moving under Zigbee network environment according to location RFID label, merge, by network training mode, reduce to locate mean square error, thereby accurately locate RFID label; Meanwhile, camera The Cloud Terrace actuating mechanism controls module, according to locator data information, is sent instruction and is dynamically adjusted The Cloud Terrace steering wheel; ;

Described RSSI model is:

$\mathrm{PL}\left(d\right)=\mathrm{PL}\left(d_0\right)-10\mathrm{nlg}\left(\frac{d}{d_0}\right)+\mathrm{\ϵ}---\left(1\right)$

In formula (1), d is the distance that calculative unknown node arrives beaconing nodes, and n is path loss index, depends on Zigbee network environment, the signal strength signal intensity that PL (d) receives for unknown node, PL (d ₀) be reference distance d ₀the signal strength signal intensity at place, d ₀for the distance of reference node to beaconing nodes, ε is position error;

Described echo state network location algorithm comprises the following steps:

1) sample phase: the Zigbee network telegon of some or Zigbee network node are set in indoor positioning region as with reference to node, after Zigbee network telegon and Zigbee network node networking complete, the positional information of these nodes is all known, measure mutual decay intensity RSSI value, build W _out, described W _outfor deposit pond DR(Dynamic Reservior) be that input and output are for the connection weight matrix of output; Zigbee network telegon sends to register control via UART by these data; Location RFID label is moved into the initial condition that is defined as network in Zigbee network, and the initial condition of network is 0, i.e. x (0)=0, training location sample (u (n), n=1,2 ... P) through input connection weight matrix W _inbe added in deposit pond DR, successively completion system state and error output

calculating and collection; Calculate output connection weight matrix W _out, Zigbee network telegon starts to collect internal state variable from a certain moment m, and with vector (x ₁(i), x ₂(i) ..., x _n(i)) (i=m, m+1 ..., P) for row forms matrix Β (P-m+1, N), simultaneously corresponding sample locator data ε (n) is also collected, and forms a column vector Τ (P-m+1,1);

2) weights calculation stages: according to collecting navigation system state matrix in sample phase and locating RFID label and move sample data, calculate output connection weight matrix W _out; Due to state variable x (n) and output between be linear relationship, and the target need realizing is to utilize the actual output of echo state network

approach desired output ε (n),

$\mathrm{\ϵ}\left(n\right)\≈\widehat{\mathrm{\ϵ}}\left(n\right)={\mathrm{\Σ}}_{i=1}^t{w}_i^{\mathrm{out}}{x}_i\left(n\right)---\left(2\right)$

Namely wish to calculate weights

(

for matrix W _outelement), meet network positions mean square deviation minimum, that is:

$\min \frac{1}{P-m+1}\underset{n=m}{\overset{P}{\mathrm{\Σ}}}{(\mathrm{\ϵ}\left(n\right)-{\mathrm{\Σ}}_{i=1}^L{w}_i^{\mathrm{out}}{x}_i\left(n\right))}^2---\left(3\right)$

Can be in the hope of the inverse matrix of matrix Β, i.e. W according to formula (3) _out=Β ^-1Τ, so far, ESNs network training completes, and what the network training can be directly used in location RFID label follows location in real time, has very high location efficiency and precision.

Claims (5)

1. the live pick up head based on Zigbee network is followed navigation system in real time, comprise for indicating the location RFID label of target, the rfid interrogator module being attached thereto, for carrying out the Zigbee network environment of wireless location and controlling camera and follow mobile camera The Cloud Terrace, described rfid interrogator module comprises antenna, RFID chip, microcontroller and Zigbee signal transmitting and receiving module, it is characterized in that: described Zigbee network environment comprises Zigbee network and location main controller, described Zigbee network comprises the Zigbee wireless network consisting of Zigbee network telegon and Zigbee network node, described location main controller comprises for receiving the communication interface modules of Zigbee network ambient signal, the embedded information processing platform and camera The Cloud Terrace actuating mechanism controls module,

The described embedded information processing platform the is integrated echo state network location algorithm based on RSSI model, wireless signal strength while moving under Zigbee network environment according to location RFID label, merge, by network training mode, reduce to locate mean square error, thereby accurately locate RFID label; Meanwhile, camera The Cloud Terrace actuating mechanism controls module, according to locator data information, is sent instruction and is dynamically adjusted The Cloud Terrace steering wheel; ;

Described RSSI model is:

$\mathrm{PL}\left(d\right)=\mathrm{PL}\left(d_0\right)-10\mathrm{nlg}\left(\frac{d}{d_0}\right)+\mathrm{\ϵ}---\left(1\right)$

In formula (1), d is the distance that calculative unknown node arrives beaconing nodes, and n is path loss index, depends on Zigbee network environment, the signal strength signal intensity that PL (d) receives for unknown node, PL (d ₀) be reference distance d ₀the signal strength signal intensity at place, d ₀for the distance of reference node to beaconing nodes, ε is position error;

Described echo state network location algorithm comprises the following steps:

1) sample phase: the Zigbee network telegon of some or Zigbee network node are set in indoor positioning region as with reference to node, after Zigbee network telegon and Zigbee network node networking complete, the positional information of these nodes is all known, measure mutual decay intensity RSSI value, build W _out, described W _outfor deposit pond DR(Dynamic Reservior) be that input and output are for the connection weight matrix of output; Zigbee network telegon sends to register control via UART by these data; Location RFID label is moved into the initial condition that is defined as network in Zigbee network, and the initial condition of network is 0, i.e. x (0)=0, training location sample (u (n), n=1,2 ... P) through input connection weight matrix W _inbe added in deposit pond DR, successively completion system state and error output calculating and collection; Calculate output connection weight matrix W _out, Zigbee network telegon starts to collect internal state variable from a certain moment m, and with vector (x ₁(i), x ₂(i) ..., x _n(i)) (i=m, m+1 ..., P) for row forms matrix Β (P-m+1, N), simultaneously corresponding sample locator data ε (n) is also collected, and forms a column vector Τ (P-m+1,1);

2) weights calculation stages: according to collecting navigation system state matrix in sample phase and locating RFID label and move sample data, calculate output connection weight matrix W _out; Due to state variable x (n) and output

between be linear relationship, and the target need realizing is to utilize the actual output of echo state network

approach desired output ε (n),

$\mathrm{\ϵ}\left(n\right)\≈\widehat{\mathrm{\ϵ}}\left(n\right)={\mathrm{\Σ}}_{i=1}^t{w}_i^{\mathrm{out}}{x}_i\left(n\right)---\left(2\right)$

Namely wish to calculate weights

(

for matrix W _outelement), meet network positions mean square deviation minimum, that is:

$\min \frac{1}{P-m+1}\underset{n=m}{\overset{P}{\mathrm{\Σ}}}{(\mathrm{\ϵ}\left(n\right)-{\mathrm{\Σ}}_{i=1}^L{w}_i^{\mathrm{out}}{x}_i\left(n\right))}^2---\left(3\right)$

Can be in the hope of the inverse matrix of matrix Β, i.e. W according to formula (3) _out=Β ^-1Τ, so far, ESNs network training completes, and what the network training can be directly used in location RFID label follows location in real time.

2. the live pick up head based on Zigbee network according to claim 1 is followed navigation system in real time, it is characterized in that: the core wireless module of described Zigbee network telegon and Zigbee network node all adopts CC2530 chip.

3. the live pick up head based on Zigbee network according to claim 1 and 2 is followed navigation system in real time, it is characterized in that: described camera The Cloud Terrace actuating mechanism controls module, turns to by regulating PWM mode to control The Cloud Terrace.

4. the live pick up head based on Zigbee network according to claim 1 and 2 is followed navigation system in real time, it is characterized in that: described Zigbee signal transmitting and receiving module and Zigbee network environment adopt 2.4GHz radiofrequency signal.

5. the live pick up head based on Zigbee network according to claim 1 and 2 is followed navigation system in real time, it is characterized in that: described location main controller adopts two ARM kernel processes unit, and described communication interface modules adopts asynchronous receiving-transmitting transmitter.

Images