DETECTION OF UNAUTHORISED PERSONS THROUGH SMART CAMERAS BY USING DEEP LEARNING

Authors:

G. DIVYA TEJA, E. NAVEEN REDDY, A. PAVAN SAI KALYAN, B. VINOD , D. RAJESH

Page No: 744-753

Abstract:

Computational vision-based Person detection has drawn significant attention in the past decade with camera surveillance systems becoming ubiquitous. Signal and image processing methods are developed for the detection of person in open and large spaces with a range of up to 30m to the camera in visible-range (IR) video. By using Artificial Intelligence, through face detection, we will store a dataset with faces of family and relatives. If it is unauthorized person then we will set an alert and also send an email notification or message to the owner or apartment watchman. Previously, SVM algorithm is used in the existing system. Now in the proposed work Convolutional Neural network and along with SVM. Convolutional Neural Network (CNN/ConvNet) is a class of deep neural networks, most commonly applied to analyze visual imagery

Description:

Vision,Convolutional Neural Network(CNN),Support vector Machine(SVM),Person Detection.

Volume & Issue

Volume-12,ISSUE-3

Keywords

.