REAL TIME OBJECT DETECTION USING

YOLO ALGORITHM

DEPARTMENT OF CSE
CMR ENGINEERING COLLEGE, HYDERABAD

ABSTRACT - The Objective is to detect of objects using You Only Look Once
(YOLO) approach. This method has several advantages as compared to other
object detection algorithms. In other algorithms like Convolutional Neural
Network, Fast Convolutional Neural Network the algorithm will not look at the
image completely but in YOLO the algorithm looks the image completely by
predicting the bounding boxes using convolutional network and the class
probabilities for these boxes and detects the image faster as compared to other
algorithms.This project aims to harness YOLO’s efficiency and accuracy to
address the need for timely and precise object detection in various scenarios

Keywords:
Convolutional Neural Network, Fast-Convolutional Neural Network, Bounding
Boxes, YOLO.

I. INTRODUCTION

The main aim of Object Detection is to detect all the objects that are present
in that particular image. The important thing in object detection is to make
system detect the object by making it to learn how to do that which is
nothing but training the dataset and allowing system to detect the object by
itself. The searching or recognition process in a real time scenario is so
tough. So far, no effective solution has been found. Though there is a lot of
work going on, the methods developed till now aren’t efficient, require long
training time, are not suitable for real time application, and are not scalable
to large numbers of classes. Object detection is relatively simpler if the
machine is looking for detecting one particular object. However, recognizing
all the objects inherently requires the skill to differentiate one object from
the other, though they may be of the same type.
Such a problem is very difficult for machines, if they don’t know about the
various possibilities of objects. When anyone goes to any hospital or to a
Traffic controlling monitor or self driving cars all they do is to detect the
objects for the best performances. For example in a hospital when the
doctor sees the scan report they will be able to tell whether there is a virus
in our body or not. So we decided to make a REAL TIME OBJECT DETECTION
System. Sometime it’s very tough to negotiate between different Object
detection techniques. In image classification we assign the class label to an
image, In Object localization we draw the bounding boxes around the
objects. Detecting the Object is tough because we combine both the tasks
where we include both the bounding box around the each object and then
we assign the class label to an image, all this comes under the category of
Image

II. LITERATURE SURVEY

You Only Look Once: Unified, Real-Time Object Detection, by Joseph

Redmon. Their prior work is on detecting objects using a regression
algorithm. To get high accuracy and good predictions they have proposed
YOLO algorithm in this paper.

Understanding of Object Detection Based on CNN Family and YOLO, by Juan

Du. In this paper, they generally explained about the object detection
families like CNN, R-CNN and compared their efficiency and introduced
YOLO algorithm to increase the efficiency.

In Object detection it first detects the location and scale of an input objects
instance if such things are present in an image. So the objective of the Object
detector is to find any number of the object belongs to particular class
irrespective of class type objects, location, size in the input image

Learning to Localize Objects with Structured Output Regression, by Matthew

B. Blaschko. This paper is about Object Localization. In this, they used the
Bounding box method for localization of the objects to overcome the
drawbacks of the sliding window method
 III. EXISTING SYSTEM
At present there are Automated systems which uses the Object detection
techniques to detect the object, in that object detecting techniques they have
used the CNN older algorithms. But here we are using the Yolo algorithm
which is new algorithm to detect the objects quickly with more accuracy so
that detecting speed will be improved and action will be done quickly.
There were many existing systems/methods that were used for Real-Time
object detection like: Haar Cascades, HOG features, R-CNN and also SSD
these systems often offer good performance.
But they have some limitations.

Limited Functionality: Without object counting, the system can only detect
and draw bounding boxes around objects.

Accuracy and False Positives: SSD, like any object detection model, can have
false positives and false negatives. Without counting and object identification
it's challenging to assess and mitigate these errors effectively.

No Object Identification: The system can detect objects but doesn't identify
them and you won't get information about the specific classes or labels of
detected objects.

IV. PROPOSED SYSTEM

The main objective of object detection is to detect various objects in a video

stream with more accuracy and with less computation time Image
classification involves assigning a class label to an image, whereas object
localization involves drawing a bounding box around one or more objects in
an image. The object detection algorithm YOLO to examine the entire image
in a single instance and predicts the bounding box coordinates and class
probabilities for these boxes. This system uses Yolo algorithm with Darknet
architecture to detect all possible objects in a video stream derived from a
Webcam. From the experimental study, the accuracy of object detection
varies from 37% to 88% The existing algorithms take more time to process
each frame and accuracy is also less. The Intersection over Union will decide
prediction of each object as Good one. The Nonmax suppression technique
will get a sıngle prediction per object. The biggest advantage of using YOLOv3
can process 67 FPS. an image
 SYSTEM ARCHITECTURE

Convolution Layers

V. RESULTS
The image which we passed for input will be divided into the same number
of the grids as in the training dataset. For every grid the output value will be
3x3x19.16 values will be the same as in the prediction model.

Output Image with

Input Image for detection
Object names in it
 VI. CONCLUSION

In this paper, we proposed about YOLO algorithm for the purpose of

detecting objects using a single neural network.This algorithm is generalized,
it outperforms different strategies once generalizing from natural pictures to
different domains. The algorithm is simple to build and can be trained
directly on a complete image.Region proposal strategies limit the classifier to
a particular region. YOLO accesses to the entire image in predicting
boundaries. And also it predicts fewer false positives in background
areas.Comparing to other classifier algorithms this algorithm is much more
efficient and fastest algorithm to use in real time.

VII. FUTURE SCOPE

YOLO is already known for its speed, but there's always room for improving
accuracy. Future work could focus on refining the algorithm to better detect
objects in various conditions such as low light, occlusions, or different
viewpoints. While YOLO is primarily designed for object detection, integrating
it with algorithms for object tracking could enable more sophisticated
applications such as video surveillance, traffic monitoring, and crowd
analysis. Optimizing energy efficiency could extend its applicability to
battery-powered devices. Making YOLO more accurate at recognizing objects,
especially in different situations like when it's dark or when objects are
partially hidden.

VIII. REFERENCES

[1] Joseph Redmon, Santosh Divvala, Ross Girshick, "You Only Look Once:
Unified, Real-Time Object Detection`",The IEEE Conference on Computer
Vision and Pattern Recognition(CVPR), 2016, pp. 779-788

[2] YOLO Juan Dul,'Understanding of Object Detection Based on CNN Family",

New Research, and Development Center of Hisense, Qingdao 266071, China.

[3] Matthew B. Blaschko Christoph H. Lampert, "Learning to Localize Objects

with Structured Output Regression", Published in Computer Vision- ECCV
2008 pp 2-15
[4] Wei Liu, Dragomir Anguelov, Dumitru Erhan, "SSD: Single Shot MultiBox
Detector", Published in Computer Vision- ECCV 2016 pp 21-37.

[5] Lichao Huang, Yi Yang, Yafeng Deng, Yinan Yu DenseBox, "Unifying

Landmark Localization with End to End Object Detection", Published in
Computer Vision and Pattern Recognition (cs.CV).

[6] Dumitru Erhan, Christian Szegedy, Alexander Toshev, "Scalable Object

Detection using DeepNeural Networks", The IEEE Conference on Computer
Vision and Pattern Recognition (CVPR), 2014, pp. 2147-2154.

[7] Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, ""Faster R-CNN:
Towards Real-Time Object Detection with Region Proposal Networks",
Published in Advances in Neural Information Processing Systems 28 (NIPS
2015).

[8] Joseph Redmon, Ali Farhadi,""YOL09000: Better, Faster, Stronger"', The

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017,
pp. 7263-7271.

[9] Jifeng Dai, Yi Li, Kaiming He, Jian Sun, "R-FCN: Object Detection via Region-
based Fully Convolutional Networks", published in: Advances in Neural
Information Processing Systems 29 (NIPS 2016).

[10]Karen Simonyan, Andrew Zisserman, "Very Deep Convolutional Networks

for Large-Scale Image Recognition", published in Computer Vision and
Pattern Recognition (cs.CV).