System and method for identifying target objects

Abstract

A method, system, article of manufacture, and UAV configured to identify a target object shown in an image, such as shown in a perspective view that is a two-dimensional image or frame of video. The method comprises: identifying and track the position of a target object shown in a sequence of images or video, even when the target object may be traveling at high speeds, detecting the target object within an image based on one or more of the object's physical characteristics, such as its color, shape, size, chrominance, luminance, brightness, lightness, darkness, and/or other characteristics. Thus, in this context a target object may be anything having one or more detectable physical characteristics. The method also providing an improved and more intuitive user interface that enables a user to select a target object for tracking. As a result, the method and system improve the accuracy, usability, and robustness of the system.

1 .- 34 . (canceled) 
     
     
         35 . A controller configured to identify a target object in an image, the controller comprising:
 a memory storing executable instructions; and   a communication interface configured to receive the image;   a user input device configured to receive a user identification of a position of the target object in the image; and   at least one processor configured to execute the stored instructions to:
 define a first area surrounding the user identified position based on the user identification and a second area surrounding the first area, wherein the first and second areas are concentric; and 
 compare image characteristics of the first area and the second area to identify the target object in the image. 
   
     
     
         36 . The controller of  claim 35 , wherein the controller is coupled to a display device configured to display the image to a user. 
     
     
         37 . The controller of  claim 36 , wherein the display device is integrated into the controller. 
     
     
         38 . The controller of  claim 36 , wherein the display device is a touchscreen device. 
     
     
         39 . The controller of  claim 36 , wherein the display device is an external display device that is connected to the controller. 
     
     
         40 . The controller of  claim 35 , wherein the controller is implemented in a smartphone. 
     
     
         41 . The controller of  claim 35 , wherein the communication interface is configured to receive the image from an unmanned aerial vehicle. 
     
     
         42 . The controller of  claim 35 , wherein the image characteristics include at least one of color, intensity, chrominance, luminance, brightness, lightness, or darkness. 
     
     
         43 . The controller of  claim 35 , wherein the user identified position is a user-selected point in the image. 
     
     
         44 . The controller of  claim 35 , wherein the user identified position is a user-selected area in the image. 
     
     
         45 . The controller of  claim 35 , wherein the at least one processor is further configured to execute the stored instructions to:
 generate a first histogram representing the image characteristics in the first area and a second histogram representing the image characteristics in the second area;   determine a third histogram by combining the first and second histograms using a predetermined function; and   apply the third histogram to an area of interest, the area of interest comprising the first and second areas.   
     
     
         46 . The controller of  claim 45 , wherein the predetermined function determines, for each image characteristic, a ratio of a value for that image characteristic in the first area divided by a value for that image characteristic in both the first and second areas. 
     
     
         47 . The controller of  claim 45 , wherein the at least one processor is further configured to execute the stored instructions to:
 redefine the first and second areas based on probabilities that a plurality of points in the area of interest contain the target object;   generate a new first histogram representing the image characteristics in the redefined first area and a new second histogram representing the image characteristics in the redefined second area; and   determine a new third histogram by combining the new first and second histograms using a second predetermined function.   
     
     
         48 . The controller of  claim 47 , wherein the same predetermined function is used to determine the third histogram and the new third histogram. 
     
     
         49 . The controller of  claim 47 , wherein the at least one processor is further configured to execute the stored instructions to:
 apply the new third histogram to the area of interest to create a back-projected image.   
     
     
         50 . The controller of  claim 49 , wherein the at least one processor is further configured to execute the stored instructions to repeat each of the redefining the first and second areas, generating a new first histogram and new second histogram, determining a new third histogram, and applying the new third histogram to the area of interest. 
     
     
         51 . The controller of  claim 35 , wherein the first area is a foreground area and the second area is a background area surrounding the foreground area. 
     
     
         52 . The controller of  claim 35 , wherein the at least one processor is further configured to execute the stored instructions to identify likely contours of the target object. 
     
     
         53 . The controller of  claim 35 , wherein the at least one processor is further configured to execute the stored instructions to use the identified target object to track the target object's position. 
     
     
         54 . The controller of  claim 35 , wherein comparing image characteristics comprises:
 determining a representation of a first physical meaning based on the image characteristics in the first area;   determining a representation of a second physical meaning based on the image characteristics in the second area; and   comparing the representations of the first and second physical meanings to identify the target object in the image.   
     
     
         55 .- 59 . (canceled)