Segmenting objects in multimedia data

1. A method for segmenting a plurality of objects present in a two-dimensional (2D) video having a plurality of 2D frames and depth information, the method comprising:

receiving, by a processor, the 2D video and the depth information corresponding to pixels of the 2D frames in the 2D video;

detecting, by the processor, camera motion in each 2D frame of the plurality of 2D frames of the 2D video;

segregating, by the processor, the plurality of 2D frames into a first set of 2D frames and a second set of 2D frames based upon the detection of the camera motion in the each frame, wherein the first set of 2D frames is detected to be void of the camera motion, and wherein the second set of 2D frames is detected to have the camera motion therein;

determining, by the processor, a plurality of cloud points in each 2D frame of the first set of 2D frames and depth data, wherein each cloud point of the plurality of cloud points stores x, y, z co-ordinates data and color data associated with each pixel of each 2D frame of the first set of 2D frames;

converting, by the processor, each 2D frame and depth data of the first set of 2D frames into a 3D grid, wherein the 3D grid comprises a plurality of voxels, and wherein the 3D grid is indicative of a division of a 3D space, associated with each frame, by a plurality of equidistant planes perpendicular to an x-axis, a y-axis and a z-axis, and wherein each voxel has a definite volume in the 3D grid, and wherein each voxel accommodates one or more cloud points, and wherein each voxel being indicative of the definite volume is surrounded by three pairs of consecutive planes along the x-axis, the y-axis and the z-axis;

determining, by the processor, valid voxels and invalid voxels from the plurality of voxels based upon a number of cloud points present in each voxel of the plurality of voxels;

classifying, by the processor, each voxel of the plurality of the voxels into a first set of voxels and a second set of voxels after traversing each 2D frame of the plurality of the 2D frames in the first set of 2D frames, wherein the first set of voxels are valid voxels, and wherein the second set of voxels are invalid voxels; and

labeling, by the processor, each voxel in the first set of voxels using a 3D connected component labeling technique in order to segment the plurality of objects present in the 2D video and depth data.

2. The method of claim 1 , wherein the camera motion is detected by monitoring a change in color data of each 2D frame of the plurality of 2D frames.

3. The method of claim 1 , wherein each cloud point is representative of a pixel in a frame.

4. The method of claim 1 , wherein the 3D grid is generated along the x-axis, the y-axis, and the z-axis.

5. The method of claim 1 , wherein the camera motion comprises a camera jitter, a change in camera direction, illumination changes in a surrounding environment, or any combination thereof.

6. The method of claim 1 , wherein the valid voxels and the invalid voxels are determined based upon the number of cloud points associated with each voxel of the plurality of voxels in the 3D grid.

7. A segmentation system for segmenting a plurality of objects present in a two-dimensional (2D) video having a plurality of 2D frames and depth information, the system comprising:

a processor; and

a memory coupled to the processor, wherein the processor is capable of executing a plurality of modules stored in the memory, and wherein the plurality of module comprising:

a detection module configured to

receive the 2D video and the depth information corresponding to pixels of the 2D frames in the 2D video;

detect camera motion in each 2D frame of the plurality of 2D frames of the 2D video;

segregate the plurality of 2D frames into a first set of 2D frames and a second set of 2D frames based upon the detection of the camera motion in the each frame, wherein the first set of 2D frames is detected to be void of the camera motion, and wherein the second set of 2D frames is detected to have the camera motion therein;

a cloud point module configured to

a cloud point module configured to determine a plurality of cloud points corresponding to each 2D frame of the first set of 2D frames, wherein each cloud point of the plurality of cloud points stores x, y, z co-ordinates and color data associated with each pixel of each 2D frame of the first set of 2D frames;

a voxelization module configured to

convert each 2D frame using corresponding depth information of the first set of 2D frames into a 3D grid, wherein the 3D grid comprises a plurality of voxels, and wherein each voxel accommodates one or more cloud points;

determine valid voxels and invalid voxels from the plurality of voxels based upon a number of cloud points present in each voxel of the plurality of voxels;

classify each voxel of the plurality of the voxels into a first set of voxels and a second set of voxels after traversing each 2D frame of the plurality of the 2D frames in the first set of 2D frames, wherein the first set of voxels are valid voxels, and wherein the second set of voxels are invalid voxels; and

a voxel labeling module configured to

a voxel labeling module configured to label each voxel in the first set of voxels using a 3D connected component labeling technique in order to segment the plurality of objects present in the 2D video and associated depth information.

8. The segmentation system of claim 7 , wherein the 3D grid is indicative of a division of a 3D space by a plurality of equidistant planes perpendicular to an x-axis, a y-axis and a z-axis, and wherein each voxel has a definite volume in the 3D grid, and wherein each voxel being indicative of the definite volume is surrounded by three pairs of consecutive planes along the x-axis, the y-axis and the z-axis.

9. The segmentation system of claim 7 , wherein the camera motion is detected by monitoring a change in color data of each 2D frame of the plurality of 2D frames.

10. The segmentation system of claim 7 , wherein each cloud point is representative of a smallest entity in 3D space, and wherein each cloud point is equivalent to a pixel in the 2D frame.

11. The segmentation system of claim 8 , wherein the 3D grid is generated along the x-axis, the y-axis, and the z-axis.

12. The segmentation system of claim 7 , wherein the camera motion comprises a camera jitter, a change in camera direction, illumination changes in a surrounding environment, or any combination thereof.

13. The segmentation system of claim 7 , wherein the valid voxels and the invalid voxels are determined based upon the number of cloud points in each voxel of the plurality of voxels in the 3D grid.