Object Detection by Stereo Vision Images

OBJECT DETECTION BY STEREO VISION IMAGES

SINCE BOTH THEORETICAL AND PRACTICAL ASPECTS OF THE DEVELOPMENTS IN THIS FIELD OF RESEARCH ARE EXPLORED, INCLUDING RECENT STATE-OF-THE-ART TECHNOLOGIES AND RESEARCH OPPORTUNITIES IN THE AREA OF OBJECT DETECTION, THIS BOOK WILL ACT AS A GOOD REFERENCE FOR PRACTITIONERS, STUDENTS, AND RESEARCHERS.Current state-of-the-art technologies have opened up new opportunities in research in the areas of object detection and recognition of digital images and videos, robotics, neural networks, machine learning, stereo vision matching algorithms, soft computing, customer prediction, social media analysis, recommendation systems, and stereo vision. This book has been designed to provide directions for those interested in researching and developing intelligent applications to detect an object and estimate depth. In addition to focusing on the performance of the system using high-performance computing techniques, a technical overview of certain tools, languages, libraries, frameworks, and APIs for developing applications is also given. More specifically, detection using stereo vision images/video from its developmental stage up till today, its possible applications, and general research problems relating to it are covered. Also presented are techniques and algorithms that satisfy the peculiar needs of stereo vision images along with emerging research opportunities through analysis of modern techniques being applied to intelligent systems. AUDIENCEResearchers in information technology looking at robotics, deep learning, machine learning, big data analytics, neural networks, pattern & data mining, and image and object recognition. Industrial sectors include automotive electronics, security and surveillance systems, and online retailers. R. AROKIA PRIYA, PHD, is Head of Electronics & Telecommunication Department at Dr. D Y Patil Institute of Engineering, Management and Research, Pune, India. She has 20 years of experience in this field as well as more than 40 publications, one patent and two copyrights to her credit.

ANUPAMA V PATIL, PHD, is the Principal at Dr. D Y Patil Institute of Engineering, Management and Research, Pune, India. She has more than 30 years of experience in this field as well as more than 40 publications and 1 patent to her credit. MANISHA BHENDE, PHD, is a professor at the Marathwada Mitra Mandals Institute of Technology, Pune, India. She has 23 years of experience in this field as well as 39 research papers in international and national conferences and journals, and has published five patents and four copyrights to her credit. ANURADHA THAKARE, PHD, is a professor in the Department of Computer Engineering at Pimpri Chinchwad College of Engineering, Pune, India. She has 20 years of experience in academics and research, with 78 research publications and eight IPR’s (Patents and Copyrights) to her credit. SANJEEV WAGH, PHD, is a Professor in the Department of Information Technology at Govt. College of Engineering, Karad, India. He has 71 research papers to his credit. Preface xiii

1 DATA CONDITIONING FOR MEDICAL IMAGING 1

Shahzia Sayyad, Deepti Nikumbh, Dhruvi Lalit Jain, Prachi Dhiren Khatri, Alok Saratchandra Panda and Rupesh Ravindra Joshi

1.1 Introduction 2

1.2 Importance of Image Preprocessing 2

1.3 Introduction to Digital Medical Imaging 3

1.3.1 Types of Medical Images for Screening 4

1.3.1.1 X-rays 4

1.3.1.2 Computed Tomography (CT) Scan 4

1.3.1.3 Ultrasound 4

1.3.1.4 Magnetic Resonance Imaging (MRI) 5

1.3.1.5 Positron Emission Tomography (PET) Scan 5

1.3.1.6 Mammogram 5

1.3.1.7 Fluoroscopy 5

1.3.1.8 Infrared Thermography 6

1.4 Preprocessing Techniques of Medical Imaging Using Python 6

1.4.1 Medical Image Preprocessing 6

1.4.1.1 Reading the Image 7

1.4.1.2 Resizing the Image 7

1.4.1.3 Noise Removal 8

1.4.1.4 Filtering and Smoothing 9

1.4.1.5 Image Segmentation 11

1.5 Medical Image Processing Using Python 13

1.5.1 Medical Image Processing Methods 16

1.5.1.1 Image Formation 17

1.5.1.2 Image Enhancement 19

1.5.1.3 Image Analysis 19

1.5.1.4 Image Visualization 19

1.5.1.5 Image Management 19

1.6 Feature Extraction Using Python 20

1.7 Case Study on Throat Cancer 24

1.7.1 Introduction 24

1.7.1.1 HSI System 25

1.7.1.2 The Adaptive Deep Learning Method Proposed 25

1.7.2 Results and Findings 27

1.7.3 Discussion 28

1.7.4 Conclusion 29

1.8 Conclusion 29

References 30

Additional Reading 31

Key Terms and Definition 32

2 DETECTION OF PNEUMONIA USING MACHINE LEARNING AND DEEP LEARNING TECHNIQUES: AN ANALYTICAL STUDY 33

Shravani Nimbolkar, Anuradha Thakare, Subhradeep Mitra, Omkar Biranje and Anant Sutar

2.1 Introduction 33

2.2 Literature Review 35

2.3 Learning Methods 41

2.3.1 Machine Learning 41

2.3.2 Deep Learning 42

2.3.3 Transfer Learning 42

2.4 Detection of Lung Diseases Using Machine Learning and Deep Learning Techniques 43

2.4.1 Dataset Description 43

2.4.2 Evaluation Platform 44

2.4.3 Training Process 44

2.4.4 Model Evaluation of CNN Classifier 46

2.4.5 Mathematical Model 47

2.4.6 Parameter Optimization 47

2.4.7 Performance Metrics 50

2.5 Conclusion 52

References 53

3 CONTAMINATION MONITORING SYSTEM USING IOT AND GIS 57

Kavita R. Singh, Ravi Wasalwar, Ajit Dharmik and Deepshikha Tiwari

3.1 Introduction 58

3.2 Literature Survey 58

3.3 Proposed Work 60

3.4 Experimentation and Results 61

3.4.1 Experimental Setup 61

3.5 Results 64

3.6 Conclusion 70

Acknowledgement 71

References 71

4 VIDEO ERROR CONCEALMENT USING PARTICLE SWARM OPTIMIZATION 73

Rajani P. K. and Arti Khaparde

4.1 Introduction 74

4.2 Proposed Research Work Overview 75

4.3 Error Detection 75

4.4 Frame Replacement Video Error Concealment Algorithm 77

4.5 Research Methodology 77

4.5.1 Particle Swarm Optimization 78

4.5.2 Spatio-Temporal Video Error Concealment Method 78

4.5.3 Proposed Modified Particle Swarm Optimization Algorithm 79

4.6 Results and Analysis 83

4.6.1 Single Frame With Block Error Analysis 85

4.6.2 Single Frame With Random Error Analysis 86

4.6.3 Multiple Frame Error Analysis 88

4.6.4 Sequential Frame Error Analysis 91

4.6.5 Subjective Video Quality Analysis for Color Videos 93

4.6.6 Scene Change of Videos 94

4.7 Conclusion 95

4.8 Future Scope 97

References 97

5 ENHANCED IMAGE FUSION WITH GUIDED FILTERS 99

Nalini Jagtap and Sudeep D. Thepade

5.1 Introduction 100

5.2 Related Works 100

5.3 Proposed Methodology 102

5.3.1 System Model 102

5.3.2 Steps of the Proposed Methodology 104

5.4 Experimental Results 104

5.4.1 Entropy 104

5.4.2 Peak Signal-to-Noise Ratio 105

5.4.3 Root Mean Square Error 107

5.4.3.1 Qab/f 108

5.5 Conclusion 108

References 109

6 DEEPFAKE DETECTION USING LSTM-BASED NEURAL NETWORK 111

Tejaswini Yesugade, Shrikant Kokate, Sarjana Patil, Ritik Varma and Sejal Pawar

6.1 Introduction 111

6.2 Related Work 112

6.2.1 Deepfake Generation 112

6.2.2 LSTM and CNN 112

6.3 Existing System 113

6.3.1 AI-Generated Fake Face Videos by Detecting Eye Blinking 113

6.3.2 Detection Using Inconsistence in Head Pose 113

6.3.3 Exploiting Visual Artifacts 113

6.4 Proposed System 114

6.4.1 Dataset 114

6.4.2 Preprocessing 114

6.4.3 Model 115

6.5 Results 117

6.6 Limitations 119

6.7 Application 119

6.8 Conclusion 119

References 119

7 CLASSIFICATION OF FETAL BRAIN ABNORMALITIES WITH MRI IMAGES: A SURVEY 121

Kavita Shinde and Anuradha Thakare

7.1 Introduction 121

7.2 Related Work 123

7.3 Evaluation of Related Research 129

7.4 General Framework for Fetal Brain Abnormality Classification 129

7.4.1 Image Acquisition 130

7.4.2 Image Pre-Processing 130

7.4.2.1 Image Thresholding 130

7.4.2.2 Morphological Operations 131

7.4.2.3 Hole Filling and Mask Generation 131

7.4.2.4 MRI Segmentation for Fetal Brain Extraction 132

7.4.3 Feature Extraction 132

7.4.3.1 Gray-Level Co-Occurrence Matrix 133

7.4.3.2 Discrete Wavelet Transformation 133

7.4.3.3 Gabor Filters 134

7.4.3.4 Discrete Statistical Descriptive Features 134

7.4.4 Feature Reduction 134

7.4.4.1 Principal Component Analysis 135

7.4.4.2 Linear Discriminant Analysis 136

7.4.4.3 Non-Linear Dimensionality Reduction Techniques 137

7.4.5 Classification by Using Machine Learning Classifiers 137

7.4.5.1 Support Vector Machine 138

7.4.5.2 K-Nearest Neighbors 138

7.4.5.3 Random Forest 139

7.4.5.4 Linear Discriminant Analysis 139

7.4.5.5 Naïve Bayes 139

7.4.5.6 Decision Tree (DT) 140

7.4.5.7 Convolutional Neural Network 140

7.5 Performance Metrics for Research in Fetal Brain Analysis 141

7.6 Challenges 142

7.7 Conclusion and Future Works 142

References 143

8 ANALYSIS OF COVID-19 DATA USING MACHINE LEARNING ALGORITHM 147

Chinnaiah Kotadi, Mithun Chakravarthi K., Srihari Chintha and Kapil Gupta

8.1 Introduction 147

8.2 Pre-Processing 148

8.3 Selecting Features 149

8.4 Analysis of COVID-19–Confirmed Cases in India 152

8.4.1 Analysis to Highest COVID-19–Confirmed Case States in India 153

8.4.2 Analysis to Highest COVID-19 Death Rate States in India 153

8.4.3 Analysis to Highest COVID-19 Cured Case States in India 154

8.4.4 Analysis of Daily COVID-19 Cases in Maharashtra State 155

8.5 Linear Regression Used for Predicting Daily Wise COVID- 19

Cases in Maharashtra 156

8.6 Conclusion 157

References 157

9 INTELLIGENT RECOMMENDATION SYSTEM TO EVALUATE TEACHING FACULTY PERFORMANCE USING ADAPTIVE COLLABORATIVE FILTERING 159

Manish Sharma and Rutuja Deshmukh

9.1 Introduction 160

9.2 Related Work 162

9.3 Recommender Systems and Collaborative Filtering 164

9.4 Proposed Methodology 165

9.5 Experiment Analysis 167

9.6 Conclusion 168

References 168

10 VIRTUAL MORATORIUM SYSTEM 171

Manisha Bhende, Muzasarali Badger, Pranish Kumbhar, Vedanti Bhatkar and Payal Chavan

10.1 Introduction 172

10.1.1 Objectives 172

10.2 Literature Survey 172

10.2.1 Virtual Assistant—BLU 172

10.2.2 HDFC Ask EVA 173

10.3 Methodologies of Problem Solving 173

10.4 Modules 174

10.4.1 Chatbot 174

10.4.2 Android Application 175

10.4.3 Web Application 175

10.5 Detailed Flow of Proposed Work 176

10.5.1 System Architecture 176

10.5.2 DFD Level 1 177

10.6 Architecture Design 178

10.6.1 Main Server 178

10.6.2 Chatbot 178

10.6.3 Database Architecture 180

10.6.4 Web Scraper 180

10.7 Algorithms Used 181

10.7.1 AES-256 Algorithm 181

10.7.2 Rasa NLU 181

10.8 Results 182

10.9 Discussions 183

10.9.1 Applications 183

10.9.2 Future Work 183

10.9.3 Conclusion 183

References 183

11 EFFICIENT LAND COVER CLASSIFICATION FOR URBAN PLANNING 185

Vandana Tulshidas Chavan and Sanjeev J. Wagh

11.1 Introduction 185

11.2 Literature Survey 189

11.3 Proposed Methodology 191

11.4 Conclusion 192

References 192

12 DATA-DRIVEN APPROCHES FOR FAKE NEWS DETECTION ON SOCIAL MEDIA PLATFORMS: REVIEW 195

Pradnya Patil and Sanjeev J. Wagh

12.1 Introduction 196

12.2 Literature Survey 196

12.3 Problem Statement and Objectives 201

12.3.1 Problem Statement 201

12.3.2 Objectives 201

12.4 Proposed Methodology 202

12.4.1 Pre-Processing 202

12.4.2 Feature Extraction 203

12.4.3 Classification 203

12.5 Conclusion 204

References 204

13 DISTANCE MEASUREMENT FOR OBJECT DETECTION FOR AUTOMOTIVE APPLICATIONS USING 3D DENSITY-BASED CLUSTERING 207

Anupama Patil, Manisha Bhende, Suvarna Patil and P. P. Shevatekar

13.1 Introduction 208

13.2 Related Work 210

13.3 Distance Measurement Using Stereo Vision 213

13.3.1 Calibration of the Camera 215

13.3.2 Stereo Image Rectification 215

13.3.3 Disparity Estimation and Stereo Matching 216

13.3.4 Measurement of Distance 217

13.4 Object Segmentation in Depth Map 218

13.4.1 Formation of Depth Map 218

13.4.2 Density-Based in 3D Object Grouping Clustering 218

13.4.3 Layered Images Object Segmentation 219

13.4.3.1 Image Layer Formation 221

13.4.3.2 Determination of Object Boundaries 222

13.5 Conclusion 223

References 224

14 REAL-TIME DEPTH ESTIMATION USING BLOB DETECTION/ CONTOUR DETECTION 227

Arokia Priya Charles, Anupama V. Patil and Sunil Dambhare

14.1 Introduction 227

14.2 Estimation of Depth Using Blob Detection 229

14.2.1 Grayscale Conversion 230

14.2.2 Thresholding 231

14.2.3 Image Subtraction in Case of Input with Background 232

14.2.3.1 Preliminaries 233

14.2.3.2 Computing Time 234

14.3 Blob 234

14.3.1 BLOB Extraction 234

14.3.2 Blob Classification 235

14.3.2.1 Image Moments 236

14.3.2.2 Centroid Using Image Moments 238

14.3.2.3 Central Moments 238

14.4 Challenges 241

14.5 Experimental Results 241

14.6 Conclusion 251

References 255

Index 257