Object Tracking Using Opencv

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 19

OBJECT TRACKING

USING OPENCV
Guided by:
Prof Jyothis Anwarshahin N K
T7B 14
Electronics and Communication Department 1
 Introduction
 Literature survey
 Open cv
 Design Methodology
 Working
CONTENTS  Feature
 Types of algorithm
 Yolo algorithm
 Conclusion
 Future Scope

2
INTRODUCTION
 OpenCV: OpenCV stands for "Open Source Computer Vision Library."
 Purpose: It's an open-source software library designed for computer vision, image processing, and
machine learning tasks.
 Cross-Platform: Works on various operating systems, including Windows, macOS, Linux, Android,
and iOS.
 Extensive Functionality: Provides a wide range of tools for image analysis, object detection,
tracking, and machine learning.
 Common Use Cases: Used for tasks such as face recognition, object detection, image stitching,
augmented reality, and medical image analysis.

3
LITERATURE REVIEW

RESEARCH PAPER AUTHOR REMARKS

• The proposed method is an


Yanli Yang , Xinlin Wang effective small-sample learning
Recognition of bird nests on method for bird nest detection on
transmission lines based on YOLOv5 transmission lines.
and DETR using small samples,
• More tests are needed on more
datasets to apply the method in
practice.

4
LITERATURE REVIEW

RESEARCH PAPER AUTHOR REMARKS

• Comprehensive overview of recent


Wei Chen , Yan Li , Zijian Tian , advancements in deep learning
2D and 3D object detection Fan Zhang a algorithms for image object
algorithms from images: A Survey detection 2d and 3d

5
OPEN CV
• Open Source: OpenCV is freely available and open-source, allowing developers and
researchers to access its source code, modify it, and contribute to its development.

• Cross-Platform: OpenCV is compatible with various operating systems including Windows,


Linux, macOS, Android, and iOS, making it versatile for different platforms and devices.

• Rich Functionality: OpenCV offers a wide array of functions for image and video analysis,
object detection and tracking, image processing, camera calibration, machine learning, and
deep learning integration.

• Supports Multiple Languages: OpenCV provides interfaces for programming languages


like C++, Python, Java, and more. This language flexibility allows developers to work with
OpenCV in their preferred programming language.

6
DESIGN METHEDOLOGY

7
Fig 1 : Block diagram of open cv
WORKING OF OBJECT TRACKING

• Different features that can be used to track an object, such as color, shape, and texture.
The algorithm will choose the features that are most distinctive for the object being
tracked.

• Once the algorithm has chosen the features to track, it will compare the features in the
current frame to the features in the previous frame. If the features are similar, then the
algorithm will assume that the object is in the same location in the current frame as it was
in the previous frame.

• If the features are not similar, then the algorithm will search for the object in the current
frame..

• Once the object has been found in the current frame, the algorithm will update the object's
track. This is done by recording the object's location, size, and orientation in the current
frame.

• The algorithm will then repeat this process for the next frame in the video sequence.
8
Fig 2- object tracking using open cv

9
 Open-source

 Fast Speed

Features of open cv  Easy to Integrate

 Ease of Coding

 Fast Prototyping

10
MOST POPULAR ALGORITHM FOR OBJECT
TRACKING
• Faster R-CNN
Faster R-CNN is a deep learning algorithm that is used to detect and track objects in image
and videos. It is a very accurate algorithm, but it can be computationally expensive.

• Mask R-CNN:
Mask R-CNN is an extension of Faster R-CNN that can also generate instance masks
for objects. This is useful for applications such as video segmentation and object tracking.

• YOLO: YOLO
is a deep learning algorithm that is designed to be fast and accurate. It is a popular choice for real-time
object tracking applications.
11
YOLO ALGORITHM

• Speed
• Accuracy
• Simplicity
• Flexibility

12
HOW DOES IT WORK

Working of yolo algorithm


13
Analysis of bird nests

14
Conclusion
• Overall, OpenCV is a powerful tool for object tracking. It
provides a variety of accurate and fast algorithms that can be
used in a wide range of applications.

• OpenCV is constantly being updated with new features and


algorithms, making it a valuable tool for researchers and
developers alike.

• OpenCV is well-suited for both commercial and academic


use, making it a versatile and powerful tool for object
tracking.

15
APPLICATION

1 Image and Video Processing:


•Image Filtering and Enhancement
•Object Detection and Tracking
•Face Recognition:

2 Medical Image Analysis:


•Image Segmentation:
•Tumor Detection:
•X-ray and MRI Analysis

3 Robotics:
•Object Detection for Robots:
•Gesture Recognition:.
•Simultaneous Localization and Mapping (SLAM):

4 Industrial Automation
•Quality Control:
•Robotic Vision.
16
FUTURE SCOPE
1.Integration with Deep Learning

2. Real-time Applications and Edge Devices:

3. Augmented Reality (AR) and Virtual Reality (VR):

4. Automated Driving and Robotics:

5. Medical Imaging and Healthcare:

6. AI-powered Content Creation:

7. Robustness and Security:

8. Human-Computer Interaction:

9. Education and Research:

10. Community and Open Source Development: 17


REFERENCES

1. S. Cherian and C. Singh, "Real Time Implementation of Object Tracking Through webcam", Internation Journal
of Research in Engineering and Technology, pp. 128-132, 2014.

2. Z. Zhao, Q. Zheng, P. Xu, S. T and X. Wu, "Object detection with deep learning: A review", IEEE transactions
on neural networks and learning systems, vol. 30, no. 11, pp. 3212-3232, 2019.

3. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection", 2005 IEEE computer society
conference on computer vision and pattern recognition (CVPR'05), vol. 1, pp. 886-893, 2005, June.

4. R. Girshick, J. Donahue, T. Darrell and J. Malik, "Region-based convolutional networks for accurate object
detection and segmentation", IEEE transactions on pattern analysis and machine intelligence, vol. 38, no. 1, pp.
142-158, 2015.

5. X. Wang, A. Shrivastava and A. Gupta, "A-fast-rcnn: Hard positive generation via adversary for object
detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2606-2615,
2017.

6. J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified real-time object
detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016.

18
THANK YOU

19

You might also like