Object tracking for device input

Abstract

Object tracking for device input can be improved by utilizing various tracking parameters to correlate objects between analyzed image frames. In some embodiments, relatively low resolution infrared cameras can be used for object tracking, in order to conserve resources on the device. Intensity segmentation can be used to identify potential objects of interest to be analyzed in captured image data. One or more tracking parameters, such as size, shape, and/or distance, can be specified for each of the objects in order to correlate objects between images. The correlations can be ranked by confidence or other such metrics in order to improve overall accuracy. Tracking data can also be stored for a period of time such that objects that are not clearly distinguishable for a while but then reappear can again be correlated with objects from earlier images.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 identifying an object in a first image;   determining a segmentation threshold based on the object; and   identifying the object in a second image based, at least in part, on the segmentation threshold.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein identifying the object further includes:
 analyzing the first image to determine at least one intensity level; and   identifying pixels associated with respective intensity values that meet or exceed the at least one intensity level, wherein the object is represented by the pixels.   
     
     
         3 . The computer-implemented method of  claim 1 , wherein determining the segmentation threshold further includes:
 determining a type of object detection and tracking; and   selecting an initial segmentation threshold based on the type of object detection and tracking.   
     
     
         4 . The computer-implemented method of  claim 3 , comprising:
 updating the initial segmentation threshold based at least in part on identifying the object.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein determining the segmentation threshold further includes:
 analyzing the first image to determine a plurality of intensity levels;   determining a highest intensity level from the plurality of intensity levels; and   setting an initial segmentation threshold to a predetermined percentage of the highest intensity level.   
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 determining a first position of the object in the first image;   determining a value for at least one tracking parameter for the object in the first image;   identifying one or more potential objects represented in the second image;   correlating a potential object in the second image, of the one or more potential objects, with the object based at least in part upon the first position and the value for the at least one tracking parameter; and   providing a second position of the object as determined using the correlated potential object in the second image.   
     
     
         7 . The computer-implemented method of  claim 6 , comprising:
 tracking a motion of the object using a difference between the first position and the second position, the motion capable of corresponding to a determined input to a computing device.   
     
     
         8 . A computing device, comprising:
 at least one processor;   a camera; and   memory including instructions that, when executed by the at least one processor, cause the computing device to:   identify an object in a first image captured using the camera;   determine a segmentation threshold based on the object; and   identify the object in a second image based, at least in part, on the segmentation threshold.   
     
     
         9 . The computing device of  claim 8 , wherein the instructions when executed further cause the computing device to:
 determine a first position of the object in the first image;   determine a value for at least one tracking parameter for the object in the first image;   identify one or more potential objects represented in the second image; and   correlate a potential object in the second image, of the one or more potential objects, with the object based at least in part upon the first position and the value for the at least one tracking parameter.   
     
     
         10 . The computing device of  claim 9 , wherein the instructions when executed further cause the computing device to:
 determine at least one additional tracking parameter for the object and the potential object, the at least one additional tracking parameter including at least one of a size, a shape, a velocity of motion, or a direction of motion,   wherein correlating the potential object with the object is further based at least in part upon matching the at least one additional tracking parameter.   
     
     
         11 . The computing device of  claim 9 , further comprising:
 at least one motion sensor, the instructions when executed further enabling the computing device to account for any change in determined position of at least one of the object or the potential object attributable to motion of the computing device.   
     
     
         12 . The computing device of  claim 9 , wherein the instructions when executed further cause the computing device to:
 eliminate from consideration one or more of regions of the first image, having less than a minimum object size or a shape outside an allowable range of shapes, before determining the first position of the object.   
     
     
         13 . The computing device of  claim 9 , wherein the instructions when executed further cause the computing device to:
 provide a second position of the object as determined using the correlated potential object in the second image.   
     
     
         14 . The computing device of  claim 13 , wherein the instructions when executed further cause the computing device to:
 determine additional data including at least one of a direction, a speed, or a velocity of motion of the object between the first position and the second position; and   use the additional data to correlate the object to a potential object in an additional image captured by the camera of the computing device.   
     
     
         15 . The computing device of  claim 8 , wherein the first image and the second image correspond to infrared light detected by the camera. 
     
     
         16 . A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of a computing device, cause the computing device to:
 identify an object in a first image;   determine a segmentation threshold based on the object; and   identify the object in a second image based, at least in part, on the segmentation threshold.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein the instructions when executed further cause the computing device to:
 determine a first position of the object in the first image;   determine a value for at least one tracking parameter for the object in the first image;   identify one or more potential objects represented in the second image;   correlate a potential object in the second image, of the one or more potential objects, with the object based at least in part upon the first position and the value for the at least one tracking parameter; and   provide a second position of the object as determined using the correlated potential object in the second image.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the instructions when executed further cause the computing device to:
 track a motion of the object using a difference between the first position and the second position, the motion capable of corresponding to a determined input to the computing device.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the instructions when executed further cause the computing device to:
 determine at least one additional tracking parameter for the object and the potential object, the at least one additional tracking parameter including at least one of a size, a shape, a velocity of motion, or a direction of motion,   wherein correlating the potential object with the object is further based at least in part upon matching the at least one additional tracking parameter.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein the instructions when executed further cause the computing device to:
 determine additional data including at least one of a direction, a speed, or a velocity of motion of the object between the first position and the second position; and   use the additional data to correlate the object to a potential object in an additional image captured by a camera of the computing device.