Claims:
WE CLAIM:
1. A method for detecting regions of interest from images, the method comprising:
creating, by a region detection device, at least one histogram associated with at least one storage area within an image captured for a predetermined location;
identifying, by the region detection device, a plurality of boundaries within the at least one storage area based on the at least one histogram; and
detecting, by the region detecting device, at least one region of interest based on the plurality of boundaries.

2. The method of claim 1 further comprising identifying at least one storage area from the image based on a machine learning model.

3. The method of claim 2, wherein identifying the at least one storage area comprises:
adding a boundary box around the at least one storage area in the image; and
extracting the at least one storage area from the image based on the boundary box.

4. The method of claim 3 further comprising identifying outer edges of the at least one storage area extracted from the image.

5. The method of claim 4, wherein the at least one histogram is plotted for the at least one storage area lying within the outer edges.

6. The method of claim 1, wherein identifying the plurality of boundaries comprises applying a line detection algorithm on the histogram.

7. The method of claim 1, wherein the at least one region of interest is detected based on intersection of the plurality of boundaries.

8. The method of claim 1, wherein the at least one storage area comprises at least one of fixtures, frames, shelves, racks, cabinets, or boxes.
9. The method of claim 1, wherein the at least one histogram comprises at least one of a vertical histogram, a diagonal histogram, or a horizontal histogram.

10. A region detection device for detecting regions of interest from images, the region detection device comprising:
at least one camera
a processor communicatively coupled the at least one camera; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
create at least one histogram associated with at least one storage area within an image captured for a predetermined location;
identify a plurality of boundaries within the at least one storage area based on the at least one histogram; and
detect at least one region of interest based on the plurality of boundaries.

11. The region detection device of claim 10, wherein the processor instructions further cause the processor to identify at least one storage area from the image based on a machine learning model.

12. The region detection device of claim 11, wherein to identify the at least one storage area, the processor instructions further cause the processor to:
add a boundary box around the at least one storage area in the image; and
extract the at least one storage area from the image based on the boundary box.

13. The region detection device of claim 12, wherein the processor instructions further cause the processor to identify outer edges of the at least one storage area extracted from the image.

14. The region detection device of claim 13, wherein the at least one histogram is plotted for the at least one storage area lying within the outer edges.

15. The region detection device of claim 10, wherein to identifying the plurality of boundaries, the processor instructions further cause the processor to apply a line detection algorithm on the histogram.

16. The region detection device of claim 10, wherein the at least one region of interest is detected based on intersection of the plurality of boundaries.

17. The region detection device of claim 10, wherein the at least one storage area comprises at least one of fixtures, frames, shelves, racks, cabinets, or boxes.

18. The region detection device of claim 10, wherein the at least one histogram comprises at least one of a vertical histogram, a diagonal histogram, or a horizontal histogram.

Dated this 19th day of December, 2017

R Ramya Rao
IN/PA-1607
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to detecting region of interest and more particularly to method and device for detecting region of interest based on images.