Generation of an image that is devoid of a person from images that include the person

Abstract

Certain embodiments disclosed herein generate an image that is devoid of a person. Such an embodiment can includes using a camera to obtain a first image of a scene while a person is at a first location within the FOV of the camera, obtaining a second image of the scene while the person is at a second location within the FOV of the camera, and generating, based on the first and second images, a third image of the scene, such that the third image of the scene is devoid of the person and includes portions of the scene that were blocked by the person in the first and second images. Other embodiments disclosed herein determine spatial information for one or more items of interest within a graphical representation of a region generated based on one or more images of the region captured using a camera of a mobile device.

What is claimed: 
     
         1 . A method for use with a camera having a field of view (FOV), the method comprising:
 obtaining a first image (A) of a scene within the FOV of the camera while a person is at a first location within the FOV of the camera, and thus, the person appears in a first portion of the first image (A);   obtaining a second image (B) of the scene within the FOV of the camera while the person is at a second location within the FOV of the camera that differs from the first location, and thus, the person appears in a second portion of the second image (B) that differs from the first portion of the first image (A); and   generating, based on the first and second images (A and B), a third image (C) of the scene, such that the third image (C) of the scene is devoid of the person and includes portions of the scene that were blocked by the person in the first and second images (A and B), wherein the generating is performing using one or more processors.   
     
     
         2 . The method of  claim 1 , wherein the generating the third image (C) of the scene comprises:
 using computer vision to identify the person within each of the first and second images (A and B); and   combining a portion of the first image (A) that is devoid of the person with a portion of the second image (B) that is devoid of the person to produce the third image (C) of the scene that is devoid of the person and includes the portions of the scene that were blocked by the person in the first and second images.   
     
     
         3 . The method of  claim 1 , wherein the generating the third image (C) of the scene comprises:
 identifying first and second portions (A1, A2) of the first image (A) that differ from the second image (B);   identifying first and second portions (B1, B2) of the second image (B) that differ from the first image (A);   determining a first metric of similarity (a1) indicative of similarity between the first portion (A1) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a second metric of similarity (a2) indicative of similarity between the second portion (A2) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a third metric of similarity (b1) indicative of similarity between the first portion (B1) of the second image (B) that differs from the first image (A) and a remaining portion of the second image (B);   determining a fourth metric of similarity (b2) indicative of similarity between the second portion (B2) of the second image (B) that differs from the first image (A) and a remaining portion of the first image (A); and   determining, based on the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C).   
     
     
         4 . The method of  claim 3 , wherein the determining, based on the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C), comprises:
 comparing a sum of the first and fourth metrics (a1+b2) to a sum of the second and third metrics (a2+b3); and   determining, based on results of the comparing, which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C).   
     
     
         5 . The method of  claim 4 , wherein the comparing the sum of the first and fourth metrics (a1+b2) to the sum of the second and third metrics (a2+b3) comprises determining whether or not the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3). 
     
     
         6 . The method of  claim 4 , wherein:
 for each of the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), a lower magnitude is indicative of higher similarity, and higher magnitude is indicative of a lower similarity;   the comparing comprises determining whether the sum of the first and fourth metrics (a1+b2) is less than or greater than the sum of the second and third metrics (a2+b3); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3), determining that the first portion (A1) of the first image (A) and the second portion (B2) of the second image (B) are to be included in the third image (C); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is greater than the sum of the second and third metrics (a2+b3), determining that the second portion (A2) of the first image (A) and the first portion (B1) of the second image (B) are to be included in the third image (C).   
     
     
         7 . The method of  claim 4 , wherein:
 for each of the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), a lower magnitude is indicative of lower similarity, and higher magnitude is indicative of a higher similarity;   the comparing comprises determining whether the sum of the first and fourth metrics (a1+b2) is less than or greater than the sum of the second and third metrics (a2+b3); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is greater than the sum of the second and third metrics (a2+b3), determining that the first portion (A1) of the first image (A) and the second portion (B2) of the second image (B) are to be included in the third image (C); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3), determining that the second portion (A2) of the first image (A) and the first portion (B1) of the second image (B) are to be included in the third image (C).   
     
     
         8 . The method of  claim 1 , wherein the camera has a 360-degree FOV. 
     
     
         9 . The method of  claim 1 , wherein the first and second images (A and B) are captured using a 360-degree camera that is being controlled by a mobile computing device that is in wireless communication with the 360-degree camera, and the mobile computing device comprises one of a smartphone or a tablet type of mobile computing device. 
     
     
         10 . One or more processor readable storage devices having instructions encoded thereon which when executed cause one or more processors to perform a method for use with a camera having a field of view (FOV), the method comprising:
 obtaining a first image (A) of a scene within the FOV of the camera while a person is at a first location within the FOV of the camera, and thus, the person appears in a first portion of the first image (A);   obtaining a second image (B) of the scene within the FOV of the camera while the person is at a second location within the FOV of the camera that differs from the first location, and thus, the person appears in a second portion of the second image (B) that differs from the first portion of the first image (A); and   generating, based on the first and second images (A and B), a third image (C) of the scene, such that the third image (C) of the scene is devoid of the person and includes portions of the scene that were blocked by the person in the first and second images (A and B).   
     
     
         11 . The one or more processor readable storage devices of  claim 10 , wherein the generating the third image (C) of the scene comprises:
 using computer vision to identify the person within each of the first and second images (A and B); and   combining a portion of the first image (A) that is devoid of the person with a portion of the second image (B) that is devoid of the person to produce the third image (C) of the scene that is devoid of the person and includes the portions of the scene that were blocked by the person in the first and second images.   
     
     
         12 . The one or more processor readable storage devices of  claim 10 , wherein the generating the third image (C) of the scene comprises:
 identifying first and second portions (A1, A2) of the first image (A) that differ from the second image (B);   identifying first and second portions (B1, B2) of the second image (B) that differ from the first image (A);   determining a first metric of similarity (a1) indicative of similarity between the first portion (A1) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a second metric of similarity (a2) indicative of similarity between the second portion (A2) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a third metric of similarity (b1) indicative of similarity between the first portion (B1) of the second image (B) that differs from the first image (A) and a remaining portion of the second image (B);   determining a fourth metric of similarity (b2) indicative of similarity between the second portion (B2) of the second image (B) that differs from the first image (A) and a remaining portion of the first image (A); and   determining, based on the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C).   
     
     
         13 . The one or more processor readable storage devices of  claim 12 , wherein the determining, based on the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C), comprises:
 comparing a sum of the first and fourth metrics (a1+b2) to a sum of the second and third metrics (a2+b3); and   determining, based on results of the comparing, which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C).   
     
     
         14 . The one or more processor readable storage devices of  claim 13 , wherein the comparing the sum of the first and fourth metrics (a1+b2) to the sum of the second and third metrics (a2+b3) comprises determining whether or not the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3). 
     
     
         15 . The one or more processor readable storage devices of  claim 14 , wherein:
 for each of the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), a lower magnitude is indicative of higher similarity, and higher magnitude is indicative of a lower similarity;   the comparing comprises determining whether the sum of the first and fourth metrics (a1+b2) is less than or greater than the sum of the second and third metrics (a2+b3); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3), determining that the first portion (A1) of the first image (A) and the second portion (B2) of the second image (B) are to be included in the third image (C); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is greater than the sum of the second and third metrics (a2+b3), determining that the second portion (A2) of the first image (A) and the first portion (B1) of the second image (B) are to be included in the third image (C).   
     
     
         16 . The one or more processor readable storage devices of  claim 14 , wherein:
 for each of the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), a lower magnitude is indicative of lower similarity, and higher magnitude is indicative of a higher similarity;   the comparing comprises determining whether the sum of the first and fourth metrics (a1+b2) is less than or greater than the sum of the second and third metrics (a2+b3); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is greater than the sum of the second and third metrics (a2+b3), determining that the first portion (A1) of the first image (A) and the second portion (B2) of the second image (B) are to be included in the third image (C); and   in response to determining that the sum of the first and fourth metrics (a1+b2) is less than the sum of the second and third metrics (a2+b3), determining that the second portion (A2) of the first image (A) and the first portion (B1) of the second image (B) are to be included in the third image (C).   
     
     
         17 . A system for use with a camera having a field of view (FOV), the system comprising one or more processors configured to:
 obtain a first image (A) of a scene within the FOV of the camera while a person is at a first location within the FOV of the camera, and thus, the person appears in a first portion of the first image (A);   obtain a second image (B) of the scene within the FOV of the camera while the person is at a second location within the FOV of the camera that differs from the first location, and thus, the person appears in a second portion of the second image (B) that differs from the first portion of the first image (A); and   generate, based on the first and second images (A and B), a third image (C) of the scene, such that the third image (C) of the scene is devoid of the person and includes portions of the scene that were blocked by the person in the first and second images (A and B).   
     
     
         18 . The system of  claim 17 , wherein the one or more processors is/are configured to generate the third image (C) of the scene by:
 using computer vision to identify the person within each of the first and second images (A and B); and   combining a portion of the first image (A) that is devoid of the person with a portion of the second image (B) that is devoid of the person to produce the third image (C) of the scene that is devoid of the person and includes the portions of the scene that were blocked by the person in the first and second images.   
     
     
         19 . The system of  claim 17 , wherein the one or more processors is/are configured to generate the third image (C) of the scene by:
 identifying first and second portions (A1, A2) of the first image (A) that differ from the second image (B);   identifying first and second portions (B1, B2) of the second image (B) that differ from the first image (A);   determining a first metric of similarity (a1) indicative of similarity between the first portion (A1) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a second metric of similarity (a2) indicative of similarity between the second portion (A2) of the first image (A) that differs from the second image (B) and a remaining portion of the first image (A);   determining a third metric of similarity (b1) indicative of similarity between the first portion (B1) of the second image (B) that differs from the first image (A) and a remaining portion of the second image (B);   determining a fourth metric of similarity (b2) indicative of similarity between the second portion (B2) of the second image (B) that differs from the first image (A) and a remaining portion of the first image (A); and   determining, based on the first, second, third, and fourth metrics of similarity (a1, a2, b1, b2), which one of the first portion (A1) of the first image (A) and the first portion (B1) of the second image (B) is to be included the third image (C), and which one of the second portion (A2) of the first image (A) and the second portion (B2) of the second image (B) is to be included the third image (C).   
     
     
         20 . The system of  claim 17 , wherein the one or more processors is/are further configured to use the third image (C) of the scene, which is devoid of the person, to generate a schematic, blueprint or other graphical representation of a room.