Depth map generation module for foreground object and method thereof

#1. Technical Field

#The present invention relates to a depth map generation module for a foreground object and the method thereof applied in two dimensional (2D) image sequence data, so as to provide 3D image data.

#2. Background

#The objectives and advantages of the present invention are illustrated with the following description and upon reference to the accompanying drawings in which:

#FIG. 1 shows a block diagram of a depth map generation module for a foreground object according to an embodiment of the present invention;

#FIG. 2 is a flow chart of a method for generation of a depth map for a foreground object according to an embodiment of the present invention;

#The embodiments of the present invention will be described in detail with reference to the drawings in the following description. Throughout the description, identical or similar devices are labeled with similar reference numbers.

#In order to explain the generation method of the depth map in the present invention, the following will describe the depth map generation module used as a means of executing the method of the present invention. FIG. 1 shows a block diagram of a depth map generation module for a foreground object 10 according to an embodiment of the present invention. The depth map generation module for a foreground object 10 is configured to receive 2D image sequence data IMG_SEQ, wherein the IMG_SEQ comprises a plurality of image frames. Referring to FIG. 1, the depth map generation module for a foreground object 10 comprises a microprocessor 100 and a storage unit 11. The storage unit 11 is coupled with the microprocessor 100, and is configured to store the data processed by the microprocessor 100. The microprocessor 100 comprises a sequence unit 12, a data providing unit 14, a contour generation unit 16, a segment motion vector generation unit 18, a depth motion unit 20, and a depth repair unit 22. The depth map generation module for a foreground object 10 can selectively operate under three operation modes: forward operation mode, reverse operation mode, and bidirectional operation mode. According to different operation modes, the depth map generation module for a foreground object 10 can automatically generate a depth map of the image sequence data IMG_SEQ, so as to transform the 2D image sequence data IMG_SEQ into a format that can be viewed as a 3D image through a 3D display by viewers.

#FIG. 2 is a flow chart of a depth map generation method for a foreground object according to an embodiment of the present invention, wherein the sequence data corresponds to the same scene. The method comprises: receiving the image sequence data (step S10), wherein the image sequence data comprises a plurality of image frames, and each image frame comprises at least one object; selecting at least one key image frame from the image sequence data (step S20); providing at least one depth indicative information and a contour of a first segment in the at least one key image frame (step S30); generating a segment motion vector, a deformed key image frame, and a contour of the deformed first segment according to color information of the key image frame, color information of the first non-key image frame, and a contour of the first segment in the key image frame (step S40); generating a contour of a second segment in the first non-key image frame according to the segment motion vector, the contour of the first segment, color information of the deformed key image frame, the contour of the deformed first segment, color information of the key image frame, and color information of the first non-key image frame (step S50), wherein the first and second segments correspond to the same object in the key image frame; transferring at least one first depth indicative information in the at least one key image frame to the first non-key image frame according to the segment motion vector so as to generate at least one second depth indicative information in the first non-key image frame (step S60); and compensating the second depth indicative information in the first non-key image frame according to the contour of the second segment, color information of the key image frame, and color information of the first non-key image frame so as to generate at least one third depth indicative information of the second segment in the first non-key image frame (step S70), wherein steps S40 to S70 are executed through a microprocessor. The following describes the details of the depth map generation method as shown in FIG. 1.