Scribd
Upload
962 views

Object Detection ppt-1

Object detection

Uploaded by

Deeksha gowda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
962 views

Object Detection ppt-1

Object detection

Uploaded by

Deeksha gowda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

C.

BYREGOWDA INSTITUTE OF TECHNOLOGY


Srinivaspur Road, Kolar - 563101
2023 - 2024

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING


Technical Seminar Presentation
On
“OBJECT DETECTION TECHNOLOGY ”

Presented by
Under the guidance of
D EEKSHA C N
Prof. MANJUNATH SINGH. H
(1CK20CS013)
Dept of CSE – CBIT
Dept of CSE – CBIT
KOLAR
KOLAR
AGENDA
1. What is Object
Detection?
2. Introduction
3. Need of Object
Detection
4. Working
5.Advantages 6.
Applications 7.
Conclusion 8.References

Dept. of CSE, CBIT 2


1.WHAT IS OBJECT DETECTION ?
• Object Detection is one of computer vision and image understanding technology . It
detects the object by using the convolutional neural network ( CNN ) model of deep
learning.

• Object Detection refers to the task of identifying and localizing objects. First it will
detect the presence of object and then determine their precise location of the object.

• It is used to detect the object and this technology is very helpful for the visually
impaired people to known where the object is and even in self driving cars .

Dept. of CSE, CBIT 3


2. INTRODUCTION
• Object detection technology mainly uses deep learning algorithms such as
convolutional neural network.This algorithm is trained on large datasets to learn
patterns and features that represent different objects.
• A CNN is a feed forward neural network that is generally used to analyze visual
images by processing data. It is also known as a ConvNet.
• CNN includes layers like input layer, many hidden layers and output layer.

• This technology is very good assistive system of obstacle detection and the
surrounding environment depiction to help blind people using deep learning
techniques.
Dept. of CSE, CBIT 4
INTRODUCTION(Contd…)

• The CNN model is trained with different datasets such as PASCAL VOC,MS-COCO,
open images.

• The model or network is pretrained with more than a million images from the
database of the datasets. By this it can easily detect the object.

• The openCV captures real-time images and CNN performs convolution operations
on images and it will detect the object.

Dept. of CSE, CBIT 5


3.NEED of Object Detection
• To classify image objects and also to determine the objects positions we use two
different methods object classification and localization in the same time.
• Humans can easily detect and identify objects present in an image but for visually
impaired people it is difficult to detect the object. So object detection technology is
very important.
• This technology is very essential to identify the obstacles for self driving cars.
• It is very essential for video surveillance and analytics , enabling efficient search and
analysis of large amount video footage.

Dept. of CSE, CBIT 6


4. WORKING

Fig: CNN Architecture.

Dept. of CSE, CBIT 7


WORKING (contd..)
• There are different CNN architectures such as AlexNet, ZFNet,VGGNet. Among
these VGGNet is the best and recent architecture that detect the object very
acuurately.

• The VGGNet (Visual Geometry Group Network) consists of 16 to 19 layers to


classify or to detect the image.

• The convolution layer will extract the features from an image and the ReLU will
perform element wise operation and sets all the negative pixels to zero.

• The pooling is a down sampling operation that will identify the different parts of the
image like edges, corners, body (dimensionality of the feature map).
Dept. of CSE, CBIT 8
WORKING (contd..)
• The flattening is used to convert all the resultant 2D array into a single linear vector.
• The fully connected layer is also known as dense layer. This layer will classify the
image.
• The softmax activation function transforms the raw output of the neural network
into a
vector of probabilities (probability distribution over the input classes).

Dept. of CSE, CBIT 9


Fig: Detecting Objects.

Dept. of CSE, CBIT 10


5.ADVANTAGES
 Highly accurate at image recognition and classification.
 They also help to identify the dimensions of the object.
 They have the ability to perform automatic feature extraction.
 Object detection is versatile and can be applied to various domains
including autonomous vehicles, robotics, security system .
 It can detect multiple objects simultaneously , even in complex
scenes with overlapping objects.

Dept. of CSE, CBIT 11


6.APPLICATION AND SOCIAL BENEFITS
1) FACIAL RECOGNITION

The deep learning facial recognition system developed to identify human faces in a
digital image. Google also has its own facial recognition system in Google Photos,
which automatically separates all the photos according to the person in the image.

2) SELF DRIVING CARS

Self-driving is the future most promising technology to be used, but the working behind
can be very complex as it combines a variety of techniques to perceive their
surroundings, including radar, laser light, GPS, odometer, and computer vision.
Advanced control systems interpret sensory info to allow navigation methods to work,
as well as obstacles.
Dept. of CSE, CBIT 12
3) SECURITY

Object Detection plays a vital role in the field of Security; it takes part in major fields
such as face ID or the retina scan used in all the mobiles. Government also widely
use this application to access the security feed and match it with their existing
database to find any criminals.

Dept. of CSE, CBIT 13


7.CONCLUSION
Object detection technology is a very powerful and useful technology it involves
detecting objects from multiple visual sources such as images and videos, enabling
more comprehensive and accurate object detection in complex scenarios. Multi-
modal detection can be helpful in applications such as autonomous driving. Tiny
objects can also be detected through this method. By the use of CNN model it
increases the speed of computing the data and giving the accurate result.

Dept. of CSE, CBIT 14


8.REFERENCES
[1] J. Ni, K. Shen, Y. Chen, W. Cao, and S. X. Yang, ‘‘An improved deep network-based scene classification method for
self-driving cars,’’ IEEE Trans. Instrum. Meas., vol. 71, pp. 1–14, 2022, doi: 10.1109/TIM.2022.3146923.
[2] W. Liu, I. Hasan, and S. Liao, ‘‘Center and scale prediction: Anchor-free approach for pedestrian and face detection,’’
Pattern Recognition., vol. 135, Mar. 2023, Art. no. 109071, doi: 10.1016/j.patcog.2022.109071.
[3] Z. Sun, Q. Ke, H. Rahmani, M. Bennamoun, G. Wang, and J. Liu, ‘‘Human action recognition from various data
modalities: A review,’’ IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 3, pp. 3200–3225, Mar. 2022, doi: 10.1109/
TPAMI.2022.3183112.
[4] A. B. Nassif, M. A. Talib, Q. Nasir, Y. Afadar, and O. Elgendy, ‘‘Breast cancer detection using artificial intelligence
techniques: A systematic literature review,’’ Artif. Intell. Med., vol. 127, May 2022, Art. no. 102276, doi: 10.1016/j.
artmed.2022.102276.
[5] Z. Zhou, L. Li, A. Fürsterling, H. J. Durocher, J. Mouridsen, and X. Zhang, ‘‘Learning-based object detection and
localization for a mobile robot manipulator in SME production,’’ Robot. Comput.-Integr. Manuf., vol. 73, Feb. 2022, Art.
no. 102229, doi: 10.1016/j.rcim.2021.102229.
.
Dept. of CSE, CBIT 15
Dept. of CSE, CBIT 16

You might also like