Systems and methods for real-time conversion of video into three-dimensions

Abstract

Disclosed herein are systems and methods for enhancing a sequence of video images to add depth and presenting the enhanced images to the user through a lenticular lens arrangement on a display screen for viewing the enhanced images in three-dimensions (3D). The embodiments include the application of image enhancing algorithms which measure spatial and temporal differences between sequential images in an input video stream in order to measure depth within the images and produce one or more interleaved images with depth. Multiple sequential interleaved images may then be created in real-time as the images from the video stream are received, and the sequence of interleaved images may then be presented immediately as a video stream on a display fitted with a lenticular lens to effectively display a 3D video to the user.

What is claimed is: 
     
         1 . A method of converting two-dimensional images to three-dimensional images, comprising:
 determining a depth map from at least one image of a sequence of images based on temporal and spatial changes between the at least one image and one or more prior images in the sequence of images;   creating n-number of unique views from the depth map for two or more left and right image pairs of the image scene at a same instance of time, each unique view providing a different camera perspective of the image scene, wherein n is greater than or equal to two;   forming an interleaved image pattern from the n-number of unique views based on a physical geometry of a lenticular lens and a display screen;   interpolating the two or more left and right image pairs across each lenticule of a plurality of lenticules of the lenticular lens; and   displaying the interleaved image pattern as an auto-stereoscopic video sequence on the display screen.   
     
     
         2 . The method of  claim 1  further comprising receiving the sequence of images from an image capture device. 
     
     
         3 . The method of  claim 2 , wherein the image capture device is one of a light intensifying device, an infrared camera and a thermal imaging camera. 
     
     
         4 . The method of  claim 1  further comprising receiving the sequence of images from an image database. 
     
     
         5 . The method of  claim 1 , wherein the determining the depth map, the creating n-number of unique views, the forming an interleaved image pattern, the interpolating the two or more left and right image pairs, and the displaying of the at least one interleaved image pattern are performed in real-time. 
     
     
         6 . The method of  claim 1 , further comprising displaying the wherein the at least one interleaved image pattern is displayed as a video on the display screen. 
     
     
         7 . The method of  claim 1 , wherein the lenticular lens is configured to match the dimensions of a pixel pattern of the display screen. 
     
     
         8 . A system for converting two-dimensional images to three-dimensional images, comprising:
 a display screen having a lenticular lens; and   an image processing unit configured to
 determine a depth map from at least one image of a sequence of images based on temporal and spatial changes between the at least one image and one or more prior images in the sequence of images; 
 create n-number of unique views from the depth map for two or more left and right image pairs of the image scene at a same instance of time, each unique view providing a different camera perspective of the image scene, wherein n is greater than or equal to two; 
 form an interleaved image pattern from the n-number of unique views based on a physical geometry of the lenticular lens; 
 interpolate the two or more left and right image pairs across each lenticule of a plurality of lenticules of the lenticular lens; and 
 display the interleaved image pattern as an auto-stereoscopic video sequence on the display screen. 
   
     
     
         9 . The system of  claim 8 , wherein the sequence of images is received from an image capture device. 
     
     
         10 . The system of  claim 9 , wherein the image capture device is one of a light intensifying device, an infrared camera, and a thermal imaging camera 
     
     
         11 . The system of  claim 8 , wherein the sequence of images is received from an image database. 
     
     
         12 . The system of  claim 8 , wherein the determining the depth map, the creating n-number of unique views, the forming an interleaved image pattern, the interpolating the two or more left and right image pairs, and the displaying of the at least one interleaved image pattern are performed in real-time. 
     
     
         13 . The system of  claim 12 , wherein the at least one interleaved image pattern is displayed as a video on the display screen. 
     
     
         14 . The system of  claim 8 , wherein the lenticular lens is configured to match the dimensions of a pixel pattern of the display screen. 
     
     
         15 . A non-transitory computer readable medium containing instructions which, when executed by a computer with a processor and a memory, perform a process comprising:
 determining a depth map from at least one image of a sequence of images based on temporal and spatial changes between the at least one image and one or more prior images in the sequence of images;   creating n-number of unique views from the depth map for two or more left and right image pairs of the image scene at a same instance of time, each unique view providing a different camera perspective of the image scene, wherein n is greater than or equal to two;   forming an interleaved image pattern from the n-number of unique views based on a physical geometry of a lenticular lens and a display screen;   interpolating the two or more left and right image pairs across each lenticule of a plurality of lenticules of the lenticular lens; and   displaying the interleaved image pattern as an auto-stereoscopic video sequence on the display screen.   
     
     
         16 . The computer readable medium of  claim 15 , wherein the sequence of images is received from an image capture device. 
     
     
         17 . The computer readable medium of  claim 16 , wherein the image capture device is one of a light intensifying device, an infrared camera and a thermal imaging camera. 
     
     
         18 . The computer readable medium of  claim 15 , wherein the sequence of images is received from an image database. 
     
     
         19 . The computer readable medium of  claim 15 , wherein the processing of the at least one image, the creating a plurality of unique views, the producing of the at least one interleaved image pattern and the displaying of the at least one interleaved image pattern are performed in real-time. 
     
     
         20 . The computer readable medium of  claim 15 , wherein the at least one interleaved image pattern is displayed as a video on the display screen.