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
IMPROVED ACCURACY IN CLASSIFICATION OF MOVING OBJECTS IN REAL TIME VIDEO USING MACHINE LEARNING
Authors Name:
Siva Nagarjuna Madala
, B. Sai Navaneeth Reddy , V. Shashank , G. Sridhar Rao , Mrs. C. Anuradha
Unique Id:
IJSDR2304190
Published In:
Volume 8 Issue 4, April-2023
Abstract:
In this paper, we present a novel method for detecting thrown objects and other free-flying bodies in video se-quences. Our method is designed to be used as a compo-nent in a deployed surveillance system and runs in real-time. We find interesting motion regions that meet certain size, compactness, and speed criteria, and then use the expectation maximization algorithm to find objects on parabolic trajectories over a short time window. In a large test set of indoor and outdoor videos, the system was shown to detect thrown objects of various sizes. In our project, we compared the accuracy of the following algorithms: Histogram of Oriented Gradient (HOG) and Single Shot Multibox Detector (SSMD)
Keywords:
Objects, Real time video, Machine Learning, Histogram of Oriented Gradient, Single Shot Multibox Detector, Moving object detection
Cite Article:
"IMPROVED ACCURACY IN CLASSIFICATION OF MOVING OBJECTS IN REAL TIME VIDEO USING MACHINE LEARNING", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 4, page no.1158 - 1160, April-2023, Available :http://www.ijsdr.org/papers/IJSDR2304190.pdf
Downloads:
000337354
Publication Details:
Published Paper ID: IJSDR2304190
Registration ID:205396
Published In: Volume 8 Issue 4, April-2023
DOI (Digital Object Identifier):
Page No: 1158 - 1160
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn