CU4073 Image Processing and Video Analytics Syllabus:

CU4073 Image Processing and Video Analytics Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 To comprehend the relation between human visual system and machine perception and processing of digital images
 To provide a detailed approach towards image processing applications like enhancement, segmentation, and compression.
 To also explore the integration principles of communication system working with different sampling rates.
 To analysis the fundamentals of digital image processing, image and video analysis
 To present the mathematics and algorithms that underlie image analysis techniques.

UNIT I INTRODUCTION AND DIGITAL IMAGE FUNDAMENTALS

Introduction: Introduction & Applications, Elements of visual perception, Image sensing and acquisition, simple image formation, Image sampling and Quantization, Representing digital pixels, Image quality, Introduction to colour image – RGB and HSI Models. Image enhancement in Spatial domain: Introduction to image enhancement, basic grey level transforms, Histogram, Histogram-processing equalization, Matching & colour histogram, Enhancement using arithmetic/logic operations, spatial filtering, Smoothing spatial filtering, Sharpening spatial filtering.

UNIT II IMAGE PROCESSING TECHNIQUES

Image Enhancement: Spatial Domain methods: Histogram Processing, Fundamentals of Spatial Filtering, Smoothing Spatial filters, Sharpening Spatial filters Frequency Domain methods: Basics of filtering in frequency domain, image smoothing, image sharpening, selective filtering Image Segmentation: Segmentation concepts, point, line and Edge detection, Thresholding, region based segmentation

UNIT III VIDEO PROCESSING AND MOTION ESTIMATION

Analog video, Digital Video, Time varying Image Formation models : 3D motion models, Geometric Image formation , Photometric Image formation, sampling of video signals, filtering operations 2-D Motion Estimation: Optical flow, general methodologies, pixel based motion estimation, Block matching algorithm, Mesh based motion Estimation, global Motion Estimation, Region based motion estimation, multi resolution motion estimation. Waveform based coding, Block based transform coding, predictive coding, Application of motion estimation in video coding.

UNIT IV INTRODUCTION: VIDEO ANALYTICS

Computer Vision: Challenges- Spatial Domain Processing – Frequency Domain Processing Background Modeling-Shadow Detection-Eigen Faces – Object Detection -Local Features-Mean Shift: Clustering, Tracking – Object Tracking using Active Contours – Tracking & Video Analysis Kalman filters, condensation, particle, Bayesian filters, hidden Markov models, change detection and model based tracking

UNIT V MOTION UNDERSTANDING

Motion estimation and Compensation-Block Matching Method, Motion Segmentation -Thresholding for Change Detection, Estimation of Model parameters – Optical Flow Segmentation-Modified Hough Transform Method- Segmentation for Layered Video Representation-Bayesian Segmentation -Simultaneous Estimation and Segmentation-Motion Field Model – Action Recognition – Low Level Image Processing for Action Recognition

TOTAL: 45 PERIODS

PRACTICAL EXERCISES: 30 PERIODS

1. Perform basic operations on images like addition, subtraction etc.
2. Plot the histogram of an image and perform histogram equalization
3. Implement segmentation algorithms
4. Perform video enhancement
5. Perform video segmentation
6. Perform image compression using lossy technique
7. Perform image compression using lossless technique
8. Perform image restoration
9. Convert a colour model into another
10. Calculate boundary features of an image
11. Calculate regional features of an image
12. Detect an object in an image/video using template matching/Bayes classifier

COURSE OUTCOMES:

Upon completion of the course, the students will be able to
CO1: Explore of the limitations of the computational methods on digital images.
CO2: Implement the spatial and frequency domain image transforms on enhancement and restoration of images
CO3: Define the need for compression and evaluate the basic compression algorithms
CO4: Study the techniques to recover the desired signal parameters and information from the signal corrupted by noisy channel
CO5:Understand the algorithms available for performing analysis on video data and address the challenges
CO6: Understand the approaches for identifying and tracking objects and person with motion based algorithms.

TOTAL:45+30=75 PERIODS

REFERENCES

1. Digital Image Processing – Rafael C. Gonzalez, Richard E. Woods, 3rd Edition, Pearson, 2008
2. John J. Proakis, Dimitris G. Manolakis, “Digital Signal Processing”, Pearson Education, 2002.
3. Digital Image Processing and Analysis-Human and Computer Vision Application with using CVIP Tools – Scotte Umbaugh, 2nd Ed, CRC Press, 2011
4. John C. Russ, F. Brent Neal-The Image Processing Handbook, Seventh Edition, The Kindle edition (2016), CRC Press,Taylor & Francis Group.
5. John G. Proakis, Masoud Salehi, “Communication Systems Engineering”, Prentice Hall, 1994.
6. Richard Szeliski, “Computer Vision: Algorithms and Applications”, Springer, 2011.
7. Yao Wang, JornOstermann and Ya-Qin Zhang, “Video Processing and Communications”, Prentice Hall, 2001.