Methods and apparatus for adaptive object classification

Abstract

The present disclosure relates to methods and apparatus for image processing. The apparatus can generate object mask information for one or more objects in a first image of a plurality of images in a scene. In some aspects, the first image can be at least one of a downscaled image, a down-sampled image, or a low resolution image. The apparatus can also determine one or more object classifications of the first image based on the generated object mask information. Additionally, the apparatus can identify a modification to at least one of the one or more object classifications based on a second image of the plurality of images in the scene. In some aspects, the apparatus can adjust or maintain the one or more object classifications based on the identified modification to at least one of the one or more object classifications.

What is claimed is: 
     
         1 . A method of image processing, comprising:
 generating object mask information for one or more objects in a first image of a plurality of images in a scene by determining a skin plot, a non-skin plot, and a skin detection range from a hue, saturation, and value (HSV) distribution of the first image, wherein the first image is at least one of a downscaled image, a down-sampled image, or a low resolution image;   determining one or more object classifications of the first image based on the generated object mask information; and   identifying a modification to at least one of the one or more object classifications based on a second image of the plurality of images in the scene.   
     
     
         2 . The method of  claim 1 , further comprising:
 adjusting or maintaining the one or more object classifications based on the identified modification to at least one of the one or more object classifications.   
     
     
         3 . The method of  claim 2 , wherein the one or more object classifications are adjusted or maintained based on one or more trapezoidal regions of the one or more object classifications. 
     
     
         4 . The method of  claim 1 , further comprising:
 adjusting or maintaining the object mask information based on the identified modification to at least one of the one or more object classifications.   
     
     
         5 . The method of  claim 1 , further comprising:
 identifying at least one of a first object classification or one or more second object classifications of the first image based on the determined one or more object classifications.   
     
     
         6 . The method of  claim 5 , wherein the first object classification includes memory color content and the one or more second object classifications include non-memory color content. 
     
     
         7 . The method of  claim 5 , further comprising:
 modifying at least one of the first object classification or the one or more second object classifications of the first image.   
     
     
         8 . The method of  claim 7 , wherein at least one of the first object classification or the one or more second object classifications is sharpened, smoothened, de-noised, or enhanced. 
     
     
         9 . The method of  claim 1 , further comprising:
 mapping the one or more object classifications of the first image to a histogram, wherein the one or more object classifications include one or more trapezoidal regions.   
     
     
         10 . The method of  claim 1 , wherein the one or more object classifications are determined via an object detector or a color detector. 
     
     
         11 . The method of  claim 10 , further comprising:
 configuring the object detector or the color detector based on the identified modification to at least one of the one or more object classifications.   
     
     
         12 . The method of  claim 1 , further comprising:
 downscaling or down-sampling the first image in the scene.   
     
     
         13 . The method of  claim 1 , wherein the one or more object classifications include at least one of a color classification, a memory color classification, a pixel classification, object content, color content, memory color content, or pixel content. 
     
     
         14 . The method of  claim 1 , wherein the object mask information includes memory color mask information. 
     
     
         15 . The method of  claim 1 , wherein each of the one or more object classifications includes a plurality of pixels. 
     
     
         16 . An apparatus for image processing, comprising:
 a memory; and   at least one processor coupled to the memory and configured to:
 generate object mask information for one or more objects in a first image of a plurality of images in a scene by determining a skin plot, a non-skin plot, and a skin detection range from a hue, saturation, and value (HSV) distribution of the first image, wherein the first image is at least one of a downscaled image, a down-sampled image, or a low resolution image;
 determine one or more object classifications of the first image based on the generated object mask information; and 
 identify a modification to at least one of the one or more object classifications based on a second image of the plurality of images in the scene. 
 
   
     
     
         17 . The apparatus of  claim 16 , wherein the at least one processor is further configured to: adjust or maintain the one or more object classifications based on the identified modification to at least one of the one or more object classifications. 
     
     
         18 . The apparatus of  claim 17 , wherein the one or more object classifications are adjusted or maintained based on one or more trapezoidal regions of the one or more object classifications. 
     
     
         19 . The apparatus of  claim 16 , wherein the at least one processor is further configured to:
 adjust or maintain the object mask information based on the identified modification to at least one of the one or more object classifications.   
     
     
         20 . The apparatus of  claim 16 , wherein the at least one processor is further configured to:
 identify at least one of a first object classification or one or more second object classifications of the first image based on the determined one or more object classifications.   
     
     
         21 . The apparatus of  claim 20 , wherein the first object classification includes memory color content and the one or more second object classifications include non-memory color content. 
     
     
         22 . The apparatus of  claim 20 , wherein the at least one processor is further configured to:
 modify at least one of the first object classification or the one or more second object classifications of the first image.   
     
     
         23 . The apparatus of  claim 22 , wherein at least one of the first object classification or the one or more second object classifications is sharpened, smoothened, de-noised, or enhanced. 
     
     
         24 . The apparatus of  claim 16 , wherein the at least one processor is further configured to:
 map the one or more object classifications of the first image to a histogram, wherein the one or more object classifications include one or more trapezoidal regions.   
     
     
         25 . The apparatus of  claim 16 , wherein the one or more object classifications are determined via an object detector or a color detector. 
     
     
         26 . The apparatus of  claim 25 , wherein the at least one processor is further configured to:
 configure the object detector or the color detector based on the identified modification to at least one of the one or more object classifications.   
     
     
         27 . The apparatus of  claim 16 , wherein the at least one processor is further configured to:
 downscale or down-sample the first image in the scene.   
     
     
         28 . The apparatus of  claim 16 , wherein the one or more object classifications include at least one of a color classification, a memory color classification, a pixel classification, object content, color content, memory color content, or pixel content. 
     
     
         29 . An apparatus for image processing, comprising:
 means for generating object mask information for one or more objects in a first image of a plurality of images in a scene by determining a skin plot, a non-skin plot, and a skin detection range from a hue, saturation, and value (HSV) distribution of the first image, wherein the first image is at least one of a downscaled image, a down- sampled image, or a low resolution image;   means for determining one or more object classifications of the first image based on the generated object mask information; and   means for identifying a modification to at least one of the one or more object classifications based on a second image of the plurality of images in the scene.   
     
     
         30 . A non-transitory computer-readable medium storing computer executable code for image processing, comprising code to:
 generate object mask information for one or more objects in a first image of a plurality of images in a scene by determining a skin plot, a non-skin plot, and a skin detection range from a hue, saturation, and value (HSV) distribution of the first image, wherein the first image is at least one of a downscaled image, a down-sampled image, or a low resolution image;
 determine one or more object classifications of the first image based on the generated object mask information; and 
   identify a modification to at least one of the one or more object classifications   based on a second image of the plurality of images in the scene.