Title:
OBJECT DETECTION METHOD, OBJECT DETECTION DEVICE, AND COMPUTER PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/031423
Kind Code:
A1
Abstract:
An object detection method that detects an object included in a captured image, wherein the object is detected according to a first system that can detect the location and type of the object included in the captured image, the object is detected according to a second system that can, for an object of indeterminate type, detect the location of said object, the success or failure of the object detection according to the first system is determined on the basis of the object detection results according to the first system and the object detection results according to the second system, and if it is determined that the object detection according to the first system has failed, an object detection method according to the first system is subjected to machine learning.
Inventors:
IVANDER (JP)
MIURA KATSUSHI (JP)
KAMI YOSHITAKA (JP)
NOMURA YASUSHI (JP)
KAKII TOSHIAKI (JP)
MIURA KATSUSHI (JP)
KAMI YOSHITAKA (JP)
NOMURA YASUSHI (JP)
KAKII TOSHIAKI (JP)
Application Number:
PCT/JP2019/013135
Publication Date:
February 13, 2020
Filing Date:
March 27, 2019
Export Citation:
Assignee:
SUMITOMO ELECTRIC INDUSTRIES (JP)
International Classes:
G06T7/00
Domestic Patent References:
| WO2018135246A1 | 2018-07-26 |
Other References:
OKATANI TAKAYUKI: "Research trend in deep learning for visual recognition : Advances of convolutional neural networks and their use", JOURNAL OF THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, vol. 31, no. 2, 2016, pages 169 - 179, ISSN: 2188-2266
Attorney, Agent or Firm:
SUNCREST PATENT AND TRADEMARK ATTORNEYS (JP)
Download PDF:
Previous Patent: OBJECT DETECTION METHOD, OBJECT DETECTION DEVICE, AND COMPUTER PROGRAM
Next Patent: SOLID-STATE BATTERY
Next Patent: SOLID-STATE BATTERY