Salient features tracking apparatus and methods using visual initialization

Abstract

Apparatus and methods for detecting and utilizing saliency in digital images. In one implementation, salient objects may be detected based on analysis of pixel characteristics. Least frequently occurring pixel values may be deemed as salient. Pixel values in an image may be compared to a reference. Color distance may be determined based on a difference between reference color and pixel color. Individual image channels may be scaled when determining saliency in a multi-channel image. Areas of high saliency may be analyzed to determine object position, shape, and/or color. Multiple saliency maps may be additively or multiplicative combined in order to improve detection performance (e.g., reduce number of false positives). Methodologies described herein may enable robust tracking of objects utilizing fewer determination resources. Efficient implementation of the methods described below may allow them to be used for example on board a robot (or autonomous vehicle) or a mobile determining platform.

What is claimed is: 
     
         1 . A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions being executable by a processing apparatus to perform a method of providing a tracking indication, the method comprising:
 for an image comprising a plurality of pixels, individual ones of the pixels characterized by one or more pixel characteristics, determining a pixel occurrence statistics parameter based at least on analysis of the one or more pixel characteristics;   determining a spatial saliency distribution of the based on the at least one pixel occurrence statistics parameter;   determining a location of a salient area in an image corresponding to saliency; and   providing the tracking indication configured to convey information related to the salient area to a tracking apparatus in communication with the non-transitory computer-readable storage medium.   
     
     
         2 . The computer readable medium of  claim 1 , wherein:
 the image comprises a representation of an object; and   the providing the tracking indication comprises providing the tracking indication so as to enable tracking of the object throughout a plurality of images occurring subsequent to the image, individual ones of the plurality of images comprising representations of the object.   
     
     
         3 . The computer readable medium of  claim 1 , wherein:
 the image comprises one or more channels, individual ones of the more or more channels being characterized by the one or more pixel characteristics; and   the one or more pixel characteristics are selected from the group consisting of pixel color and pixel luminance.   
     
     
         4 . The computer readable medium of  claim 3 , wherein the pixel occurrence statistics parameter is configured based on determining likelihood of occurrence of a value of a pixel characteristic within the image. 
     
     
         5 . The computer readable medium of  claim 4 , wherein:
 the determination of the likelihood is configured based at least on determining a histogram of a plurality of values of a pixel characteristic, the histogram comprising a plurality of bins, individual ones of the plurality of bins being characterized by a characteristic value range;   a value of a given bin of the plurality of bins being determined based at least on a comparison between a value of a pixel characteristic and the value range for the given bin;   the determination of the likelihood is configured based at least on determining a histogram of a plurality of values of a pixel characteristic, the histogram comprising a plurality of bins, individual ones of the plurality of bins being characterized by a characteristic value range; and   a value of the threshold is determined based at least on an evaluation of the histogram.   
     
     
         6 . The computer readable medium of  claim 1 , wherein:
 the location of the salient area is determined based at least on the saliency distribution meeting or exceeding a threshold; the at least one pixel parameter is configured based at least on determining a distribution of pixel values within the image, the distribution characterized by a parameter; and   the saliency determination is configured based at least on an evaluation of the at least one pixel parameter relative to the threshold.   
     
     
         7 . The computer readable medium of  claim 6 , wherein a value of the threshold is determined based at least on a determination of saliency associated with another image preceding the image 
     
     
         8 . The computer readable medium of  claim 6 , wherein a value of the threshold is determined based at least on a success rate of detecting the object in one or more images preceding the image. 
     
     
         9 . The computer readable medium of  claim 2 , wherein:
 the image is characterized by a color space comprising at least one dimension; and   the at least one pixel characteristic is configured to convey information related to the at least one dimension.   
     
     
         10 . The computer readable medium of  claim 9 , wherein:
 the salient area is characterized by a first rate of pixel occurrence;   the spatial saliency distribution comprises a background area characterized by a second rate of pixel occurrence, the second rate of pixel occurrence being greater than the first rate of pixel occurrence; and   the pixel occurrence statistics parameter is configured to provide a reference within the color space.   
     
     
         11 . The computer readable medium of  claim 10 , wherein:
 the at least one dimension comprises a chromaticity dimension; and   the reference comprises a reference chromaticity.   
     
     
         12 . The computer readable medium of  claim 11 , wherein the method further comprises determining a distance measure between chromaticity of individual pixels within the image and the reference chromaticity; and
 wherein determination of the reference chromaticity based on the pixel occurrence statistics parameter is configured to increase discriminability between distance measure associated with pixels corresponding to the salient area of the image and distance measure corresponding to the background area of the image.   
     
     
         13 . The computer readable medium of  claim 12 , wherein the increased discriminability is based at least on a greater difference between (i) the distance measure associated with pixels corresponding to the salient area of the image, and (ii) the distance measure corresponding to the background area of the image when compared to respective distance measures determined based on another reference chromaticity, the another reference chromaticity determined based at least on pixels disposed outside the salient area of the image. 
     
     
         14 . The computer readable medium of  claim 12 , wherein:
 the tracking of the object comprises detecting the object in the image; and   use of the reference chromaticity is configured to improve the detection of the object, the improvement of the detection characterized by fewer false positives of object detection compared to object detection effectuated absent determination of the reference chromaticity based on the pixel occurrence statistics parameter.   
     
     
         15 . A computer implemented method of tracking an object in a sequence of digital images each comprised of pixels, the method comprising:
 for an image of the sequence of images, determining at least one distribution of orientations in the image;   evaluating the at least one distribution to determine salient orientation information;   determining a location of at least one salient area in the image based on the salient orientation information; and   tracking the object based on the location of the at least one salient area, the tracking of the object comprising determining an occurrence of a salient orientation in an area proximate to the location, the determined occurrence of the salient orientation being in a subsequent image of the sequence of images.   
     
     
         16 . The method of  claim 15 , wherein:
 individual pixels of the image are characterized by one or more channels; and   the determining of at least one distribution of orientations in the image is configured based on analysis of pixel values for individual ones of the one or more channels   
     
     
         17 . The method of  claim 16 , wherein:
 the one or more channels comprise pixel chromaticity; and   the analysis comprises determining a chromaticity distance measure between pixel chromaticity and a reference chromaticity.   
     
     
         18 . The method of  claim 16 , wherein:
 the image comprises an object portion characterized by pixel chromaticity values occurring in a first range, and a background portion characterized by pixel chromaticity values occurring in a second range, the second range non overlapping with the first range; and   the chromaticity distance determination is configured to increase likelihood of the object being present at the location relative location determination effectuated in absence of the chromaticity distance determination.   
     
     
         19 . The method of  claim 15 , wherein:
 individual pixels of the image are characterized by a chromaticity parameter; and   the method further comprises determining a chromaticity distance measure between chromaticity of pixels of the image within the salient area and a reference chromaticity.