Field of the Invention

The present invention generally relates to Wireless Sensor Networks (WNS) and more particularly, to a system and method for detecting any intrusion by eliminating false alarming arising from the presence of Wind-Blown Vegetation in a pre-marked geographical area.

Background of the Invention

Passive Infra-Red sensor (PIR sensor) is an electronic device that measures infrared (IR) light radiating from objects in its field of view. PIR sensors are often used in the construction of PIR-based motion detectors. Apparent motion is detected when an infrared source with one temperature, such as a human, passes in front of an infrared source with another temperature, such as a wall. All objects emit what is known as black body radiation. It is usually infrared radiation that is invisible to the human eye but can be detected by electronic devices designed for such a purpose. The PIR device does not emit an infrared beam but merely passively accepts incoming infrared radiation.

Passive Infra-red based intrusion detection systems are commonly deployed in home security systems. However, in these systems, manufacturers recommend careful placement of their PIR detectors to prevent false alarms resulting from vegetation, air currents, etc. as well as exposure to direct sunlight. In these systems however, false alarms are of a lesser concern as typically motion is used to trigger a light which is then switched off after a pre-determined interval. Also, these algorithms employed in these devices are designed for operation on the mains and not on batteries.

Moreover, PIR signal is first high-pass filtered to remove the low frequency components resulting from slow environment changes and then the signal energy is compared against an adaptive threshold. In particular, use of an unsupervised adaptation technique to adjust the energy threshold for target detection. Most other works either use simple thresholding on the PIR signal or thresholding on the energy computed in a window in declaring detection. The short-coming of the existing technology are due to high-complexity nature of the technique results in the reduction of network lifetime, secondly, no control of false alarms caused by wind-blown vegetation and also lack in the device performance.

For the reasons stated above, which will become apparent to those skilled in the art upon reading and understanding the specification, there is a need in the art for a system and method for detecting any intrusion by eliminating false alarming arising from the presence of Wind-Blown Vegetation in a pre-marked geographical area.

Brief description of the drawings
Figure 1 illustrates functional block diagram an intrusion detection system to prevent false alarming arising due to clutter windblown vegetation in a graphical region according to one embodiment of the present invention.
Figure 2 shows a flow chart of an intrusion detection method to prevent false alarming arising due to clutter windblown vegetation in a graphical region according to one embodiment of the present invention.

Figure 3 shows frequency bins corresponding to the 8-point Haar matrix.

Figure 4 shows geometry used for modeling intruder signature and illustration of to and
dmin.

Figure 5 shows comparison graph of analytical and actual signals for an intruder signature.

Figure 6 shows three sensors platform and the wireless trip-wire.

Figure 7 shows the placement of the sensor platform as shown in figure 5.

Detail description of the invention

In the following detailed description of the preferred embodiments, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the invention may be practiced. It is understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the present invention.

The leading digit(s) of reference numbers appearing in the Figures generally corresponds to the Figure number in which that component is first introduced, such that the same reference number is used throughout to refer to an identical component which appears in multiple Figures.

The features, structures, or characteristics of the invention described throughout this specification may be combined in any suitable manner in one or more embodiments. For example, reference throughout this specification to "certain embodiments," "some embodiments," or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases "in certain embodiments," "in demonstrative embodiments," "in some embodiment," "in other embodiments," or similar language throughout this specification do not necessarily all refer to the same group of embodiments and the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Assumption has been made in the present description as an example that the intruder to be a human traveling in the vicinity of the sensor and use the term clutter to describe the sensor's output as a result of the wind-blown vegetation caused by the wind.

Figure 1 illustrates functional block diagram an intrusion detection system to prevent
false alarming arising due to clutter windblown vegetation in a graphical region according to
one embodiment of the present invention. The system includes a sensor (not shown in figure 1)
to detect intruder or clutter arising from any disturbances including but not limited to wind
blow vegetation. The sensor is a PIR sensor which is a high-pass filter to remove the low
frequency components. The preferred sensor for the present invention is the analog sensor to the digital PIR sensor as it was easier to distinguish between the spectrum of intruder and clutter from the output of the analog sensor. The PIR sensors are extremely sensitive and can detect any small object or clutter in its range.
A sampling frequency (fs) of 12.5 HZ is chosen based on the frequency content of intruder and clutter. The sampling frequency is passed into sliding window protocol, the sliding window protocol is used here because it transmits packet switched data in data link layer and the delivery of packets is very reliable.

The system further including a Haar Transformation (HT) Unit 110 which is capable of receiving the transmitted packets. A block of 128(N) consecutive samples is transformed by HT unit. The Haar transform is wavelet based, because of the same coefficients are designed to provide both frequency and time localization in-formation. As a result the breakdowns of 128 Haar coefficients are as follows: one coefficient assigned to frequency 0, i.e. the DC component and 2k coefficients attached to signals of frequency 2k 0 < k < 6. Thus, there are a total of log (N) +1 = 8 frequencies in all. The system collects together the energy in each of these 8 frequency "bins". The Haar signals associated with an example N = 8 sample transform are shown separately in Figure 3. The time localization information allows reuse of most of the components of the last transformed vector for the current window if there is overlap of the current window with the previous window.

For the purpose of maximizing battery life, the use of HT for computing the spectrum of
Intruder and clutter signals in preference to the computationally more complex Discrete Fourier
Transform as only additions and subtractions suffice to compute the HT. HT was preferred as it is less complex compared to other transform (e.g. Walsh Hadamard Transform (WHT)), HT has ability to reuse past computed HT coefficients for the next window and can potentially be used to yield time-frequency localization information. A sampling frequency (fs) of 12:5Hz was chosen based on the frequency content of intruder and clutter waveforms (as shown in Figure 1).

The resultant binned vector is passed on to a classifier 130 (obtained by offline Support Vector Machine (SVM) training) which classify it as either intruder or clutter. This entire process is repeated every 16 (/.) samples.
Figure 2 shows a flow chart of an intrusion detection method to prevent false alarming arising due to clutter windblown vegetation in a graphical region according to one embodiment of the present invention. The method 200, at step 210 detecting a reflected signal from a predefined graphical region. At step 220, the method transforms the detected signal to generate block of transformed sampled consecutive components, wherein the generated sample coefficients of consecutive samples are capable of providing both frequency and time localization information. Further, the transforming the detected signal includes a support vector machine (SVM) learning technique for classifying the detected signal into two labeled sets of signals and to maximize the margin between them.

At step 230, the method bins the transformed consecutive components into frequency bins. The energy in each of these transformed components is binned into 8 frequency bins.

At step 240, the method classifies the resultant binned vector with one or more predetermined thresholds in order to identify the actual intrusion. The classifying step includes comparing the resultant binned vector with a predetermined value representing an intrusion threshold to give a first digital signal whose states changes if the latter threshold is exceeded.

At step 250, the method decides and inform about intrusion detection by, if the first digital signal is less than zero then the method classified as clutter and if the signal is more than or equal to zero then the method classified as intruder.

ANALYTICAL MODEL FOR INTRUDER SIGNATURE

The Panasonic PIR sensor has a quad of sensing elements and a multilens which creates a virtual pixel array (VPA) in its field of vision. When an intruder cuts across the virtual beams, the infra-red signal incident on the sensing element can be modeled as a triangular waveform whose period is inversely proportional to the angular velocity w of the intruder. The sensing element acts upon this infrared signal as a band pass filter which we will assume filters out all but the fundamental frequency component, whose frequency is thus proportional to w. Let K denote the proportionality constant. The intruder is assumed to walk with a uniform velocity along a straight line path in the vicinity of the sensor. Reasonable assumption has been made as the sensing range of the sensor is around 6m. Let v be the speed of the intruder walking along a straight line making an angle ^ with the sensor's axis and at a distance of d from the sensor (as shown in figure 4(a)). Let 29 be the horizontal angular coverage of the sensor equal to 110° in for the sensor under study. The sensor responds to the intrusion for t > 0. The duration of the signal is limited either by the sensing range or by the angular coverage of the sensor. The instantaneous frequency/(t) of the intruder signature from ΔOSC is given by.

Using ΔSOAB we can substitute for r{t) to get
Let λ = λ = and cot (Φ+ θ) = -λto Thus 0 < λ <°° when u>0, d>0 and 0< <Φ< π. Also,
dmin is the distance of the closest approach of the intruder to the sensor (see figure 4(b)), The equation can be rewritten as
Note that the maximum frequency fmax = KΛ occurs at to =. The intruder signature
is thus given by,

Figure 5 shows comparison graph of analytical and actual signals for an intruder signature. The constant K corresponds to the density of the beams in the plane of the intruder motion. Hence the analytical expression naturally extends to other differential PIR sensors in general as K abstracts the lens. A contains all the information required to track the intruder but λ for different triplets of (u, d, φ) can be the same. So do track the intruder, many sensor nodes spaced apart will be required.

Tracking

The goal in this section is to determine an optimal locationing of multiple sensor nodes, having coordinates (xj, yi) respectively, that will enable them to reliably estimate the velocity and direction of motion of the intruder. Setting ni = 1/λ and assuming on the basis of equation (3) that the ith sensor node reliably estimates ni.

(a) Minimum Number of Nodes Required
Let the intruder path equation be ax+by+c = 0, which with r = and α = arctan
can be rewritten as xrsin a+ yrcos a+l=0. Note that where dmin, i is the distance from
the ith node to the straight-line path of the intruder. With this, obtaining the system equations is
the 2 unknowns r, a and u.
After some work, it can be shown that 3 sensing nodes will suffice in estimating r, a and v and thus in reliably tracking the intruder.

(b) Optimal Positioning of the Sensor Nodes
Tracking involves the transformation: (n1,n2, n3)-> (r, α, u). The impact of error in the estimates of on ni's on r, α and u should be kept minimum for reliable tracking. Thus, our interest is in maximizing the Jacobian of the transformation carrying out the mapping: (r, α, v) -> (n1, n2, n3). Without loss of generality, we assume a coordinate system whose origin is equidistant from the three sensors. Thus we may assume that each sensor is at a constant distance R from the origin. We change variables by writing Xi = Rcos (βi), yi = Rsin (βi), whereβi = arctan. With this, (4) becomes
After some work, it can be shown that the Jacobian is given by

The value of J is clearly maximized when β3-β2=β1-β3=β2-β1 made as large as possible. This suggests that the nodes should be arranged in an equilateral triangle with R as large as possible, subject to the desired node density.
In the field tests, three sensors were mounted onto a single node each with an angular spacing of 120°. When combined with the approximately 110° angular field of view of each sensor, this essentially gave each node an omni-directional sensing range (see Fig. 6 and 7) and (b)). Data emanating from the 3 sensors were fed to the 3 ADC channels of the TelosB motes. The initial decision was to deploy the sensor nodes in the form of a linear array with inter-node spacing chosen to maximize the area covered by a single node while ensuring that every point in the sensing range was covered by at least 3 nodes. The idea here was that the sensing nodes would serve as a wireless trip wire (see Fig. 6 and 7). Larger areas can be covered by interlacing many such wireless trip wires. It was found that a single linear array would on occasion, fail to detect intruder moving at high-speeds, possibly because at high speeds, the intruder was in the field of view for only a very short duration. With this In mind, the decision was made to create a double array comprising of two identical, linear and parallel arrays spaced apart by 5m (which is just Im under the maximum sensing radius of 6m). Decisions were made locally as follows: If a node detected an intruder in its vicinity using the HT-cum- SVM based algorithm outlined earlier, it would broadcast its local detection (via the Zigbee protocol available on TelosB motes) to all of its neighbors. A node was permitted to declare a confirmed detection if In addition to making a local detection, it also received news of local detection from any other node within a distance of twice the sensing range of each sensor. The confirmed detection was then relayed back to the base station using an appropriately designed network routing algorithm. At the base station, a graphical user interface (GUI) would display the information regarding the nodes that detected and the route of the confirmed detection. This algorithm is scalable as the detection of an intruder results from the consensus of a few neighboring nodes. When tested over a period of several hours across the week, the network performed flawlessly by detecting every intrusion at speeds ranging from that of a slow crawl to a sprint at 5m/sec. There were also no false alarms in the period over which testing was conducted.

Advantages:

• Reduction of false alarms caused by wind-blown vegetation.

• The ability to incorporate training data to fine-tune the device to improve
performance over a particular terrain.

• Employs a low-complexity algorithm that will tend to extend battery life.

The present disclosure may be implemented with a variety of combination of hardware and software. If implemented as a computer-implemented apparatus, the present disclosure is implemented using means for performing all of the steps and functions described above.

The present disclosure can be included in an article of manufacture (e.g., one or more computer program products) having, for instance, computer usable media. The media has embodied therein, for instance, computer readable program code means for providing and facilitating the mechanisms of the present invention. The article of manufacture can be included as part of a computer system or sold separately.

FIGS. 1-7 are merely representational and are not drawn to scale. Certain portions thereof may be exaggerated, while others may be minimized.

FIGS. 1-7 illustrate various embodiments of the disclosed invention that can be understood and appropriately carried out by those of ordinary skill in the art.

In the foregoing detailed description of embodiments of the invention, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure.

We claim

1. An improved intrusion detection method to prevent false alarming arising due to clutter
windblown vegetation in a graphical region, the method comprising:
detecting a reflected signal from a predefined graphical region;
transforming the detected signal to generate block of transformed sampled consecutive components, wherein the generated sample coefficients of consecutive samples are capable of providing both frequency and time localization information;
binning the transformed consecutive components into frequency bins; and
classifying the resultant binned vector with one or more predetermined thresholds In order to identify the actual intrusion.

2. The method of claim 1, wherein the step of classifying further including:
comparing the resultant binned vector with a predetermined value representing an intrusion threshold to give a first digital signal whose states changes if the latter threshold is exceeded.

3. The method of claim 2, wherein if the first digital signal is less than zero is classified as clutter and if the signal is more than or equal to zero is classified as intruder.

4. The method of claim 1, wherein the transforming step includes a support vector machine (SVM) learning technique for classifying the detected signal into two labeled sets of signals and to maximize the margin between them.

5. An intrusion detection system to prevent false alarming due to clutter arising from
windblown vegetation in a graphical region, the system comprising:
a plurality of node including at least three sensors, wherein sensors are positioned with an angular spacing of 120°, and wherein each node having an Omni-directional sensing range; wherein each node is configured for
detecting a reflected signal from a predefined graphical region; transforming the detected signal to generate block of transformed sampled consecutive components, wherein the generated sample coefficients of consecutive samples are capable of providing both frequency and time localization information; binning the transformed consecutive components into frequency bins; and classifying the resultant binned vector with one or more predetermined thresholds in order to identify the actual intrusion, at least one communication network; and
at least one server including a database capable of receiving signals from each nodes to determine clutter arising from windblown vegetation.

6. The system of claim 5, wherein the sensors are Passive Infra-Red sensors.

7. The system of claim 5, wherein the communication network is a Wireless Sensing Network (WSN).

8. The system of claim 5, wherein the server includes a processor, a memory and a display, wherein the processor is capable of displaying in a Graphical User Interface (GUI) about the information of the location of the nodes to confirm the geographical location.

9. An improved intrusion detection method to prevent false alarming arising due to clutter windblown vegetation in a graphical region substantially as herein described with reference to description and the accompanying drawings.

10. An intrusion detection system to prevent false alarming due to clutter arising from windblown vegetation in a graphical region substantially as herein described with reference to description and the accompanying drawings.