• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2014 Fiscal Year Final Research Report

Development of robust smoke detection method from video for outside scene

Research Project

  • PDF
Project/Area Number 25870526
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Perceptual information processing
Measurement engineering
Research InstitutionNagasaki University

Principal Investigator

MARUTA Hidenori  長崎大学, 工学研究科, 助教 (00363474)

Project Period (FY) 2013-04-01 – 2015-03-31
Keywords画像認識 / 煙画像解析
Outline of Final Research Achievements

The purpose of this research is to develop the robust detection method of smoke from outside scene with image information. The nature of smoke has dynamical shape structure and transparency and they make it more difficult to detect smoke from image sequence compare to other solid shaped objects. To address such problems, LBP based image feature which are extended to represent such natures of smoke. Additionally, AdaBoost, which is widely used in the field of machine learning area, is combined with the presented image features to obtain more accurate detection results against varying environmental conditions. Evaluation results reveal that the presented method has effective results using real scene data.

Free Research Field

知覚情報処理

URL: 

Published: 2016-06-03  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi