INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
The secure helmet wearing detection is very needed in power substation. At first, the ViBe background modelling algorithm is used to detect the moving object under a view of fix surveillant camera in power substation. After that obtaining the movement region of interest, the Histogram of Oriented Gradient (HOG) feature is used to relate inner human. And then, based on the result of HOG quality selection, the Support Vector Machine (SVM) is developed to classify pedestrians. Finally, the safety helmet detection will be executed by colour feature identification. gripping experimental results indicated the accuracy and effectiveness of our proposed method .The U.S. construction industry suffers from the large amount of fatalities among all factories, that is, one of five workman expires in private factories were in power substation. Large amount of loss has occurred to the workers family members, the factory, and the countries. Considering the highest and increasing number of substation projects that are being handled in the U.S., there is a highest necessity of developing innovative methods to automatically monitor the safety for the workers at power substation.
Keywords:
ViBe, Histogram of oriented gradient, Support vector machine,Color feature recognition
Cite Article:
"Secure helmet wearing detection by using image processing and machine learnig.", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.3, Issue 5, page no.643 - 644, May-2018, Available :http://www.ijsdr.org/papers/IJSDR1805097.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR1805097
Registration ID:180345
Published In: Volume 3 Issue 5, May-2018
DOI (Digital Object Identifier):
Page No: 643 - 644
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn