Method and a system for occupancy location

1. A method for occupancy location comprising:

capturing a spatially coded image of a scene,

identifying a region of interest in the image,

generating a pixel plausibility index for each image pixel in the region of interest, and

classifying pixels as relating to occupancy responsive to the pixel plausibility index,

wherein said identifying the region of interest in the image comprises of generating a list of pixels of interest in the image,

wherein said generating the list of pixels of interest in the image further comprises generating said list while considering that an occupant cannot move more than one pixel between two successive frames of the image.

2. The method as claimed in claim 1 , wherein said capturing the spatially coded image comprises computing sensor measurements of a compressive coded aperture camera for a current frame of the image and background sensor measurements of the image.

3. The method as claimed in claim 1 , wherein the region of interest in the image comprises:

all M x ×N x pixels of the image, if all the pixels of the image are to be tested; otherwise

a subset of the all M x ×N x pixels of the image, if only the pixels in the subset region are required to be tested;

where M x ×N x being the dimension of the image.

4. The method as claimed in claim 1 , wherein said generating the list of pixels of interest in the image further comprises generating said list while considering second neighbour pixels of the already occupied pixels in the image.

5. The method as claimed in claim 1 , wherein the list of pixels of interest in the image comprises of following types of pixels:

pixels at the border of the region of interest;

pixels that were occupied in a last frame; and

pixels that are at the boundary of the currently occupied pixels.

6. The method as claimed in claim 1 , wherein said generating pixel plausibility index comprises of computing pixel plausibility index in accordance with a linear relation

y=Φx+η

wherein y being the MyNy×1 vectorized sensor measurement, where My×Ny is an array of photo sensors, Φ being an optical transfer matrix which relate the scene with the sensor measurement, which is an MyNy×MxNx matrix, x being MxNx×1 vectorized form of the scene and η being the noise term accounting for the measurement error and model error.

7. The method as claimed in claim 1 , wherein said classifying pixels as relating to occupancy responsive to the pixel plausibility index comprises of classifying the pixels on the basis of a fixed cut-off threshold of the pixel plausibility index, wherein

pixels with plausibility index above the said fixed cut-off threshold are classified as occupied; and

pixels with plausibility index below the said fixed cut-off threshold are classified as unoccupied.

8. A system for occupancy location, the system comprising:

means for capturing a spatially coded image of a scene,

means for identifying a region of interest in the image,

means for generating a pixel plausibility index for each image pixel in the region of interest, and

means for classifying pixels as relating to occupancy responsive to the pixel plausibility index,

wherein the means for identifying the region of interest in the image configured to generate a list of pixels of interest in the image,

further comprising a list of pixels of interest in the image is generated while considering that an occupant cannot move more than one pixel between two successive frames of the image.

9. The system as claimed in claim 8 , wherein the means for capturing the spatially coded image further comprises of a compressive coded aperture camera.

10. The system as claimed in claim 9 , wherein the means for capturing the spatially coded image configured to compute sensor measurements of the compressive coded aperture camera for a current frame of the image and background sensor measurements of the image.

11. The system as claimed in claim 8 , wherein the region of interest in the image comprises of:

all M x ×N x pixels of the image, if all the pixels of the scene are to be tested; otherwise

a subset of the all M x ×N x pixels of the image, if only the pixels in the subset region are required to be tested;

where M x ×N x being the dimension of the image.

12. The system as claimed in claim 8 , further comprising a list of pixels of interest in the image is generated while considering second neighbour pixels of the already occupied pixels in the image.

13. The system as claimed in claim 8 , wherein the list of pixels of interest in the image comprises of following types of pixels:

pixels at the border of the region of interest;

pixels that were occupied in a last frame; and

pixels that are at the boundary of the currently occupied pixels.

14. The system as claimed in claim 8 , wherein the means for generating the pixel plausibility index configured to compute pixel plausibility index in accordance with a linear relation

y=Φx+η

wherein y being the MyNy×1 vectorized sensor measurement, where My×Ny is an array of photo sensors, Φ being the optical transfer matrix that relate the scene with the sensor measurement, which is an MyNy×MxNx matrix, x being MxNx×1 vectorized form of the scene and η being the noise term accounting for the measurement error and model error.

15. The system as claimed in claim 8 , wherein the means for classifying pixels as relating to occupancy responsive to the pixel plausibility index configured to classify the pixels on the basis of a fixed cut-off threshold of the pixel plausibility index, wherein

pixels with plausibility index above said fixed cut-off threshold are classified as occupied; and

pixels with plausibility index below said fixed cut-off threshold are classified as unoccupied.