Tezislər / Theses



Yüklə 17,55 Mb.
Pdf görüntüsü
səhifə166/493
tarix02.10.2023
ölçüsü17,55 Mb.
#151572
1   ...   162   163   164   165   166   167   168   169   ...   493
BHOS Tezisler 2022 17x24sm

THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
175
REAL-TIME OBJECT DETECTION AND COUNTING 
Nazrin Gurbanova, Agamirza Fataliyev, Hasan Isgandarli 
Baku Higher Oil School
Baku, Azerbaijan 
nazrin.gurbanova.std@bhos.edu.az
agamirza.fataliyev.std@bhos.edu.az
hasan.isgandarli.std@bhos.edu.az 
Supervisor: PhD, Associate Professor Leyla Muradkhanli 
Keywords:
Python, OpenCV, Live-detection, Directions, Frame
With this thesis, a program written in the Python programming language, 
using OpenCV library and working on the basis of Single-Shot Detection 
(SSD) via implementing a convolution neural network (CNN) architecture, in 
other words, will be described.
The reason for choosing the Python language as the main language is 
its simplicity of syntax and versatility, which gives it an advantage over other 
languages. The Single-Shot Detection allows us to detect multiple objects 
within the image from one single shot, which in terms is the main reason we 
divide the input/live video into frames and analyze each. 
The utilization of the live-detection became more necessary in recent 
years, as, for example, the spread of the coronavirus and the global 
pandemic are forcing more shopkeepers, malls, restaurants, and other public 
establishments to monitor the number of people in the premises and take the 
necessary measures. The use of the above program makes it easily 
accessible – the only things needed are the surveillance or any other camera 
connected to the computer and the software. The usage of the software lets 
the user select individual settings and update the code to add other features 
later on. As an example, the alert system is included here as well, which is 
triggered and sends the notification to the owner whenever the number of 
people inside exceeds the threshold input.
Coming to the concept of how the 
directions of the objects are identified, the 
principle of calculating the difference of the 
corresponding coordinates of centroids of the 
objects is used and later compared to 0. On the 
right the representation of the frame is provided 
on which the objects are moving: the person 
goes to the right, the car goes to the left, the dog 
goes downwards, and the cat goes upwards. In 
the following section the explanation of the 
direction detection will be given: 



Yüklə 17,55 Mb.

Dostları ilə paylaş:
1   ...   162   163   164   165   166   167   168   169   ...   493




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin