Camera configuration on movable objects

Abstract

A method for controlling a movable object includes receiving, at one or more processors, a plurality of images from a plurality of imaging devices carried by the movable object; determining, with aid of the one or more processors, an environment type of an environment surrounding the movable object; identifying a target based on the plurality of images and the environment type; determining information of the target based on the plurality of images; and controlling the movable object to avoid the target based on the information of the target. The plurality of imaging devices includes a first imaging device arranged at an upper surface of a body of the movable object and a second imaging device arranged at a lower surface of the body. Each of the first imaging device and the second imaging device has a field of view greater than 150 degrees.

What is claimed is: 
     
         1 . A method for controlling a movable object comprising:
 receiving, at one or more processors, a plurality of images from a plurality of imaging devices carried by the movable object, the plurality of imaging devices including a first imaging device arranged at an upper surface of a body of the movable object and a second imaging device arranged at a lower surface of the body, each of the first imaging device and the second imaging device having a field of view greater than 150 degrees;   determining, with aid of the one or more processors, an environment type of an environment surrounding the movable object;   identifying, with aid of the one or more processors, a target based on the plurality of images and the environment type;   determining, with aid of the one or more processors, information of the target based on the plurality of images; and   controlling the movable object to avoid the target based on the information of the target.   
     
     
         2 . The method of  claim 1 , further comprising:
 receiving, at the one or more processors, sensing data from one or more sensors of the movable object;   wherein determining the environment type includes determining the environment type according to the sensing data.   
     
     
         3 . The method of  claim 2 , wherein determining the environment type includes:
 determining, with aid of the one or more processors according to the sensing data, the environment type from a plurality of types including a first type and a second type different from the first type.   
     
     
         4 . The method of  claim 3 , wherein identifying the target based on the plurality of images and the environment type includes:
 identifying, with aid of the one or more processors, the target based on the plurality of images using a first method in response to determining that the environment type is the first type or using a second method different from the first method in response to determining that the environment type is the second type.   
     
     
         5 . The method of  claim 4 , wherein the first type includes an outdoor environment and the first method includes distinguishing the target from a background using a color-based image segmentation algorithm. 
     
     
         6 . The method of  claim 5 , wherein the color-based image segmentation algorithm includes a K-Means clustering algorithm. 
     
     
         7 . The method of  claim 4 , wherein the second type includes an indoor environment and the second method includes distinguishing the target from a background using a corner detection algorithm. 
     
     
         8 . The method of  claim 1 , wherein the plurality of images include a first image taken by one of the plurality of imaging devices at a first location and a second image taken by the one of the plurality of imaging devices after the movable object travelled from the first location to a second location. 
     
     
         9 . The method of  claim 8 , further comprising:
 measuring, with aid of the one or more processors according to sensing data received from one or more sensors of the movable object, a distance between the first location and the second location.   
     
     
         10 . The method of  claim 9 , wherein determining the information of the target includes:
 determining, with aid of the one or more processors, the information of the target based on the first image, the second image, and the distance between the first location and the second location.   
     
     
         11 . The method of  claim 1 , further comprising:
 determining state information of the movable object;   wherein controlling the movable object to avoid the target includes controlling the movable object to avoid the target based on the information of the target and the state information of the movable object.   
     
     
         12 . The method of  claim 1 , wherein the information of the target includes a distance between the movable object and the target. 
     
     
         13 . The method of  claim 12 , wherein controlling the movable object to avoid the target includes, in response to the distance being within a threshold range:
 initiating an obstacle avoidance program; and   generating a warning signal.   
     
     
         14 . The method of  claim 13 , wherein the warning signal includes at least one of a haptic signal, a visual signal, or an auditory warning. 
     
     
         15 . The method of  claim 12 , wherein:
 the target is positioned at a side of the movable object; and   determining the information of the target includes calculating the distance based on an angle of view of the target within each of the plurality of images.   
     
     
         16 . The method of  claim 1 , wherein determining the information of the target includes:
 detecting feature points in the plurality of images;   determining changes in the feature points between the plurality of images; and   determining the information of the target based on the changes.   
     
     
         17 . The method of  claim 1 , wherein at least one of the first imaging device or the second imaging device is coupled to the movable object via a coupling that permits rotational movement of the at least one of the first imaging device or the second imaging device relative to the movable object. 
     
     
         18 . The method of  claim 17 , wherein the rotational movement of the at least one of the first imaging device or the second imaging device is controlled remotely by user input. 
     
     
         19 . The method of  claim 17 , wherein the rotational movement of the at least one of the first imaging device or the second imaging device is controlled autonomously. 
     
     
         20 . A system for controlling a movable object comprising:
 a plurality of imaging devices carried by the movable object and configured to obtain a plurality of images, the plurality of imaging devices including a first imaging device arranged at an upper surface of a body of the movable object and a second imaging device arranged at a lower surface of the body, each of the first imaging device and the second imaging device having a field of view greater than 150 degrees; and   one or more processors individually or collectively configured to:
 receive the plurality of images from the plurality of imaging devices; 
 determine an environment type of an environment surrounding the movable object; 
 identify a target based on the plurality of images and the environment type; 
 determine information of the target based on the plurality of images; and 
 control the movable object to avoid the target based on the information of the target.