BUILDING AREA

FIELD OF INVENTION

The invention generally relates to a system and method for identifying Carbon-dioxide (C0 ₂ ) le vel inside a building and particularly system and method for detecting Carbon -dioxide (CO?) level inside a building through an imaging device.

BACKGROUND

Identification of Carbon dioxide (C0 ₂ ) level is critical and important function of a Heating-A entifation/Air-conditioriing (HVAC) duct system. Typically, for measuring carbon dioxide (CO2) level, carbon dioxide (CO ) detectors/sensors are employed in the building. Based on reading from the carbon dioxide (C0 ₂ ) detectors/sensors, the flow of fresh air can be increased or reduced into particular part of the building.

Generally, C0 ₂ sensors for ventilation control are of two type i.e. photometric and photoacousiic. The photometric sensors have a sample compartment that contains a photodetector, a light source and a optical filter. The light source emits light in the infrared range and the optical filter ensures tha only wavelengths in the absorbing spectrum of CO? enter the compartment containing the air sample- The photodetector measures the light intensity at a wavelength that may be absorbed by C0 ₂ . The higher the CO? concentration in the sample air, the lower the measured light intensity.

^' The photoacousiic sensors have a sample compartment that contains a microphone and a iight source for emitting infrared energy. The Ci¾ molecules in the compartment absorb the infrared energy, whic in turn increases the molecular vibration and generates an acoustic field. The microphone picks up the acoustic field and converts it to an electronic signal identifying the C0 concentration.

However, known CO2 detectors face one or more issues such as interference from other gases (e.g. water vapor), accuracy and drift that may affect the sensor performance. Moreover, C0 ₂ detectors are very costly, require periodic maintenance and are not very accurate. Therefore, there continues to be a need for maintenance free, cost effective and more accurate system and method for detecting CO? in a building.

The present invention is directed to overcoming one or more of the problems as set forth above.

SUMMARY OF THE INVENTION

According to embodiments of the invention, a system and method for identifying CO? concentration in a building area using an imaging device is disclosed. The disclosed method and system includes identifying the number of living beings present in a particular area of the building by processing images obtained from the imaging device; identifying the active state of the living beings and categorizing the active state as per predefined criteria; and identifying the CO? concentration based on the size of the building area, total number of living beings present in the building area and the active state of the living beings. The method may further include controlling the flow of fresh air by a HVAC system based on the C0 ₂ concentration.

The invention further discloses a system for identifying. CO? concentration in a building area using an imaging device. The system may include a counting arrangement for counting number of living beings present in the building area by processing images obtained from an imaging device from the building area. The system may further Include an activity analyses arrangement for identifying the active state of the living beings and categorizing the active state as per predefined criteria and a processor for calculating the CC¾ concentration iri the building area based on the total number of living beings present in the building area and the active state of the living being at a given point of time.

BRIEF DESCRIPTION OF DRAWINGS

Other objects, features, and advantages of the invention will be apparent from the following description when read with reference to the accompanying drawings. In the drawings, wherein like reference numerals denote corresponding parts throughout the several views: Figure 1 illustrates .an exemplary flow chart for a method for identifying CO ₂ concentration in a building area according to an embodiment of the invention; and

Figure 2 illustrates an exemplary system for identifying CO? concentration in a buildmg area according to another embodiment of the invention.

DETAILED DESCRIPTION OF DRAWINGS

According to an embodiment Of the invention, a method for detecting C(¾ in a building area using an imaging device is disclosed. The imaging device may be selected from a group comprising digital camera, web cam, overhead camera, security camera, spy camera etc. Figure 1 illustrates an exemplary flow chart for a method 100 for identifying C ⁽ ¾ concentration in a building area according to an embodiment of the invention. As illustrated at step 102 the method 100 includes procuring the volume of the buildmg area where the concentration of CO? is required to be identified. According to a exemplary embodiment, the volume may be retrieved from a repository. According to yet another embodiment, the volume may he computed based dimensions of the building area.

A step 104, the method includes identifying number of living beings present in the given area. According to an embodiment, the number of living beings may be identified by keeping a count of incoming and outgoin living beings in th building area using live video feed from the imaging device. According to another embodiment, the number of living beings may be identified by analysing the images of the living beings in the area on real time basts.

According to yet another embodiment, the imaging device may perform a background modelling to eliminate noises due to illumination for effectively counting living beings in the building area. The background modelling involves detecting foreground objects and presenting the detected foreground object to a binary classifier to distinguish the presence of living beings. According to an embodiment, the background modelling may be performed using any known methods for objec detection such as but not limited to HAAR- Wavelet Transform, Gabor- Wavelet Transform, HAAJR-Like Features, Histogram of Oriented Gradients etc.

According to an exemplary embodiment, to detect living being, either in static images or in videos, a frame may be identified. Once the frame is identified, the process of living being identification may be divided into two parts i.e. Feature Extraction and Classification. The feature extraction includes extracting unique feature from the captured image or video. According to an exemplary embodiment, any known technique fo feature extraction such as, but not limited to, Haar- Wavelet Transform, Viola-Jones Haar-Uke Features, Histogram of oriented Gradients, Haar- Wavelet Transform may be used. The ciassiOcatson step may use classifiers. According to an embodiment of the invention, two types of classifiers may be used Neural Networks and/or Support Vector machine (SVM).

At step 106, the method includes identifying the active state of the living beings in. the area. According to an embodiment, the active state of the living beings may be identified by processing the video images captured b the imaging device on real time basis. According another embodiment, the identified active state of the living beings may be categorized as mild such as, but not limited to, sitting, sleeping etc., moderate such as, but not limited to, walking, eating etc., intensive such as, but not limited to, playing, jumping, running etc. The invention is not restricted to disclosed three categories and the categories may vary and may be predefined a system administrator without going beyond the scope of invention.

According to an exemplary embodiment, the process of identifying the active state of the living beings includes, corner detection, optical flow and velocity thresholds. The corner detection ineludes identification of significant points in an image where gradient magn itude in both X & Y directions is significant or greater than a threshold. According yet another embodiment, any of the known corner detection algorithms may be used such as Harris Comer Detector, SIFT, SURF etc. The corners identified from the corner detection algorithms may include living beings, object of interest and static background scene. To distinguish or filter moving objects corners from static background corners an Optical Flow algorithm may be employed. The optical flow is the partem of apparent motion of objects, surfaces, and edges in a visual scene caused by the relative motion between an observer (an eye or a camera) and the scene. Using the optical flow algorithm, the direction and speed of moving objects from one image to another image may be measured i terms of velocity vectors. A predefined velocit threshold may be employed to separate moving objects corners from rest of the corners (corners of slow moving background objects like tree branches, Static Object corners and false velocity measures caused by illumination effects) i the consecutive frames. To classify actions as mild, moderate or intensive the velocity of each corner in an image or fram may be identified. The velocity of the corners may be compared with the predefined velocity threshold. Based on the comparison, the motion of the objects may be categorised as still, mild, moderate or intensi e. According to. an embodiment, the amount of C(¾ generation by the living beings may vary based on the activit classification. According to another embodiment, the activity classification may be predefined in the system or may be procure on a real time basis through a network such as internet, intranet etc.

Table 1 below illustrate exemplary relation between carbon dioxide emission from persons and their activity:

Table 1

Carbon Dioxide Emission per

Respiration per Person

Activity Person

(m h)

{m ³ /h)

Sleep 0.3 0.013

\ Restin or Sow activity work 0.5 0.02

Normal work 2 - 3 0.08 - 0.13

Hard work 7 - 8 0.33 - 0.38

At step 108, the method calculates C<¾ concentration as a function of volume of the area, number of living beings present in the area and activities of the living beings present in the area as illustrated below:

Where N _p is the number of living beings present in the area, A _P is the active state of the living beings present in the area and V _r is the volume of the area.

Exemplary considering, imaging device identify N number of living being in a building area having volume V. On processing images from the imaging device, it is identified that out of N number of living being N 1 living beings are engaged in mild activity, N2 living beings are engaged in moderate activities and N3 living beings are engaged in intensive activities.

Np^ N1+ N2+ N3 The total activity factor for the total number of people in the room Λτΐρ may be calculated as:

An _p - Nl * x + N2 * y + N3 * z

Where x, y and z are predefined constant, for mild, moderate or intensive activities respectively. According yet another embodiment, the number of predefined activity constant is equal to the number of predefined active states. According yet another embodiment, the total activity factor An _p indicates the total C ⁽ ¾ generated by the living beings present in the building area per hour. The amount of C0 ₂ generated in ppm per minute may be calculated using following equation:

An _p * 60 * 10*

According' to another embodiment, for calculating the total concentration of CO? in the building area, apart from CO? generated, ventilation rate and CO? concentration outside building area may also be considered.

According to yet another embodiment based on CO? concentration the air circulation system of a HVAC system may be controlled.

According to an embodiment, the method steps may be performed in any sequence without going beyond the essence of the invention. According to another embodiment, the method may process ail the functions simultaneously.

Figure 2 illustrates an exemplary block diagram of the system 200 for identifying CO? concentration in a building area according to an embodiment of the invention. The system 200 may be configured to receive images from an imaging device 10. The imaging device 10 may be any apparatus for capturing images such as but not limited to a digital video camera, web cam, overhead camera, spy cam etc. The system 200 may include a counting module 202 for counting number of living beings present in the building area, According to an embodiment, the counting module 202 may identify the number of living beings by processing images obtained from the imaging device. According to another embodiment, the images received from the imaging device 10 may be stored in an image repository 204 for further processing. The images may include still images and/or video images. According to an embodiment, the counting module 202 may identify the number of living beings b processing the images to count the number of incoming and outgoing living beings from the building area. According to yet another embodiment, the counting module 202 may identif the number of living beings by analysing the images of the living beings in the area on real time basis.

The system 200 may have a volume identification module 206 for procuring the volume of the building where the concentration of CO ₂ is required to be detected. According to an embodiment, the volume ma h retrieved from a repository. According to yet another embodiment, the volume may be computed based on dimensions of the area procured from the images.

The system 200 may further include an activity analyses module 208 for identifying the active state of the living beings present in the building area. The acti vity analyses module 208 may further categorize the active state of the living beings as per predefined criteria. According to an embodiment, the activity analyses module 208 may identify the active state of the living being by processing the images captured by the imaging device 10 on real time basis. According to another embodiment, the identified active state of the living beings may be categorized as mild, moderate or intensive by the activity analyses module 208. According to yet another embodiment, the invention is not restricted to disclosed three categories id it may vary without going beyond the scope of invention.

The system 200 may further have a module 210 for identifying the CO? concentration in the building area. The module 210 may iden tify CO^ concentration as a function of volume of the area V _r , number of living beings present in the area N _p and the activities of the living beings present in the area.

According to an embodiment, the system 200 may have an inbuilt imaging device 10. According to another embodiment, the counting module 202, the volume identification module 206, the activity analyses module 208 and the (X); concentration calculation module 210 may reside in different processor. According to yet another embodiment, the counting module 202, the volume identification module 206, the activity analyses module 208 and the CO2 concentration calculation module 210 may reside in a single processor. 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. This metho of disclosure is not to be interpreted as reflecting an intention thai the claimed embodiments of the invention require more features tha are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description of embodiments of the invention, with each claim standing on its own as a separate embodiment. it is. understood that the above description is intended to be illustrative, and not restrictive, it is intended to cover all alternatives, modifications and equivalents as may be included within the spirit and scope of the invention as defined in the appended claims. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description. The scope of the invention should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. In the appended claims, the terms "including ^' " and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein," respectively.