Systems and methods for detecting and tracking movable objects

Abstract

A method for supporting visual tracking includes receiving a plurality of image signals indicative of a plurality of image frames captured by an imaging device over a period of time while the imaging device is in motion. Each image frame includes a plurality of pixels. The method further includes obtaining motion characteristics of the imaging device based on a plurality of motion signals, and analyzing the plurality of image signals based on the motion characteristics of the imaging device, so as to compute movement characteristics associated with the plurality of pixels.

What is claimed is: 
     
         1 . A method for supporting visual tracking, the method comprising:
 receiving a plurality of image signals indicative of a plurality of image frames captured by an imaging device over a period of time while the imaging device is in motion, wherein each image frame comprises a plurality of pixels;   obtaining motion characteristics of the imaging device based on a plurality of motion signals; and   analyzing the plurality of image signals based on the motion characteristics of the imaging device, so as to compute movement characteristics associated with the plurality of pixels.   
     
     
         2 . The method of  claim 1 , wherein analyzing the plurality of image signals based on the motion characteristics of the imaging device comprises:
 obtaining a correlation between the movement characteristics associated with the plurality of pixels and the motion characteristics of the imaging device.   
     
     
         3 . The method of  claim 1 , wherein the plurality of pixels are associated with a plurality of feature points, each feature point associated with a background feature or a tracking feature. 
     
     
         4 . The method of  claim 3 , wherein the background feature is associated with a first set of pixels having a first movement characteristic and the tracking feature is associated with a second set of pixels having a second movement characteristic that is different from the first movement characteristic. 
     
     
         5 . The method of  claim 3 , further comprising:
 adjusting movement of the imaging device to position a group of feature points associated with the tracking feature in a target region of a subsequent image frame captured by the imaging device.   
     
     
         6 . The method of  claim 3 , further comprising:
 selecting a subset of feature points associated with the tracking feature based on size, shape, movement characteristics of the feature points associated with the tracking feature; and   using the subset of feature points to track the tracking feature.   
     
     
         7 . The method of  claim 1 , wherein analyzing the plurality of image signals based on the motion characteristics of the imaging device comprises:
 identifying a background feature of each image frame based on the motion characteristics of the imaging device; and   identifying a tracking feature relative to the background feature.   
     
     
         8 . The method of  claim 7 , wherein identifying the background feature of each image based on the motion characteristics of the imaging device comprises:
 identifying feature points that move across the image frames at a speed that is scaled in proportion to a speed of the imaging device to identify the background feature.   
     
     
         9 . The method of  claim 7 , wherein identifying the background feature of each image based on the motion characteristics of the imaging device comprises:
 identifying feature points that move across the image frames at a movement direction that is opposite to a movement direction of the imaging device to identify the background feature.   
     
     
         10 . The method of  claim 7 , wherein identifying the tracking feature relative to the background feature comprises:
 identifying features points that move across the image frames at a speed that is different from a speed of feature points associated with the background feature to identify the tracking feature.   
     
     
         11 . The method of  claim 7 , wherein identifying the tracking feature relative to the background feature comprises:
 identifying features points that move across the image frames at a movement direction that is different from a movement direction of feature points associated with the background feature to identify the tracking feature.   
     
     
         12 . The method of  claim 1 , wherein the movement characteristics associated with the plurality of pixels comprise at least one of a velocity or an acceleration of each of the plurality of pixels as measured across the plurality of image frames. 
     
     
         13 . The method of  claim 1 , wherein the motion characteristics of the imaging device comprise at least one of an attitude, an instantaneous position, a velocity, or an acceleration of the imaging device. 
     
     
         14 . The method of  claim 13 , further comprising:
 determining the instantaneous position of the imaging device using a range-finding and/or locating device.   
     
     
         15 . The method of  claim 13 , wherein the instantaneous position of the imaging device is determined relative to a physical location of a background feature. 
     
     
         16 . The method of  claim 15 , further comprises:
 calculating a scaling factor based on the instantaneous position of the imaging device and the physical location of the background feature; and   computing the movement characteristic of each of the plurality of pixels using the motion characteristics of the imaging device and the scaling factor.   
     
     
         17 . The method of  claim 1 , wherein the motion characteristics of the imaging device are determined using an inertial measurement sensor. 
     
     
         18 . An apparatus for supporting visual tracking, the apparatus comprising one or more processors that are, individually or collectively, configured to:
 receive a plurality of image signals indicative of a plurality of image frames captured by an imaging device over a period of time while the imaging device is in motion, wherein each image frame comprises a plurality of pixels;   obtain motion characteristics of the imaging device based on a plurality of motion signals; and   analyze the plurality of image signals based on the motion characteristics of the imaging device, so as to compute movement characteristics associated with the plurality of pixels.   
     
     
         19 . The apparatus of  claim 18 , wherein the apparatus is an unmanned aerial vehicle (UAV). 
     
     
         20 . A non-transitory computer-readable medium storing instructions that, when executed, cause a computer to perform a method for supporting visual tracking, the method comprising:
 receiving a plurality of image signals indicative of a plurality of image frames captured by an imaging device over a period of time while the imaging device is in motion, wherein each image frame comprises a plurality of pixels;   obtaining motion characteristics of the imaging device based on a plurality of motion signals; and   analyzing the plurality of image signals based on the motion characteristics of the imaging device, so as to compute movement characteristics associated with the plurality of pixels.