US Patent Application 18215573. OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDIUM simplified abstract

From WikiPatents
Jump to navigation Jump to search

OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDIUM

Organization Name

NEC Corporation


Inventor(s)

Tetsuo Inoshita of Tokyo (JP)


OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDIUM - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 18215573 Titled 'OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDIUM'

Simplified Explanation

The abstract describes an object detection device that efficiently selects an image for creating instructor data based on the number of detected objects. The device includes a detection unit that uses a dictionary to detect objects in multiple input images. It also has an acceptance unit that displays a graph showing the relationship between the input images and the number of subregions where objects are detected. The acceptance unit allows the user to select an input image from the graph using an input device. The device further includes a generation unit that creates instructor data from the selected image, and a learning unit that learns a dictionary from the instructor data.


Original Abstract Submitted

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.