Object detection device, object detection method, and recording medium

Abstract

Provided is an object detection device for efficiently and simply selecting an image for creating instructor data on the basis of the number of detected objects. The object detection device is provided with: a detection unit for detecting an object from each of a plurality of input images using a dictionary; an acceptance unit for displaying, on a display device, a graph indicating the relationship between the input images and the number of subregions in which the objects are detected, and displaying, on the display device, in order to create instructor data, one input image among the plurality of input images in accordance with a position on the graph accepted by operation of an input device; a generation unit for generating the instructor data from the input image; and a learning unit for learning a dictionary from the instructor data.

1 . A system comprising:
 a storage configured to store a program; and   one or more processors, wherein the one or more processors are configured to execute the program to perform:
 displaying a first frame indicating a first region of a detected object from an input image, 
 accepting an input of a second frame indicating a second region including an object in the input image displaying the first frame, and accepting an input of a first class indicating a type of object corresponding to the second frame, and 
 accepting an input of a second class corresponding to the first frame when the first region of the first frame and the second region of the second frame overlap, the second class indicating a type of object different from the first class. 
   
     
     
         2 . The system according to  claim 1 , wherein the one or more processors are further configured to execute the program to perform:
 determining whether at least part of the first region of the first frame and the second region of the second frame overlap.   
     
     
         3 . The system according to  claim 1 , wherein the one or more processors are further configured to execute the program to perform:
 accepting the input of the second frame by accepting an operation of an input device by a user.   
     
     
         4 . A method comprising:
 displaying a first frame indicating a first region of a detected object from an input image;   accepting an input of a second frame indicating a second region including an object in the input image displaying the first frame, and accepting an input of a first class indicating a type of object corresponding to the second frame; and   accepting an input of a second class corresponding to the first frame when the first region of the first frame and the second region of the second frame overlap, the second class indicating type of object different from the first class.   
     
     
         5 . The method according to  claim 4 , further comprising:
 determining whether at least part of the first region of the first frame and the second region of the second frame overlap.   
     
     
         6 . The method according to  claim 4 , further comprising:
 accepting the input of the second frame by accepting an operation of an input device by a user.   
     
     
         7 . A non-transitory computer-readable storage medium in which a program is stored, the program configured to cause a computer to execute:
 displaying a first frame indicating a first region of a detected object from an input image;   accepting an input of a second frame indicating a second region including an object in the input image displaying the first frame, and accepting an input of a first class indicating a type of object corresponding to the second frame; and   accepting an input of a second class corresponding to the first frame when the first region of the first frame and the second region of the second frame overlap, the second class indicating a type of object different from the first class.   
     
     
         8 . The non-transitory computer-readable storage medium according to  claim 7 , wherein the program is further configured to cause the computer to execute:
 determining whether at least part of the first region of the first frame and the second region of the second frame overlap.   
     
     
         9 . The non-transitory computer-readable storage medium according to  claim 7 , wherein the program is further configured to cause the computer to execute:
 accepting the input of the second frame by accepting an operation of an input device by a user.