2. INTRODUCTION
Image compression is a type of data
compression applied to digital images.
It is used to reduce their cost
for storage or transmission.
Algorithms may take advantage of visual perception.
Types of Compressions are:
Lossy image Compression
Lossless image compression
3. IMAGE COMPRESSION STANDARDS
International Standards
Binary image compression standards
CCITT Group 3 Standard (G3)
CCITT Group 4 Standard (G4)
Continuous one image and video compression standards
JPEG, JPEG 2000
MPEG-1, MPEG-2, MPEG-4
ITU-T H.261, H.263
4. THE JPEG STANDARD
JPEG is an image compression standard.
It was developed by “Joint Photographic Experts
Group”.
JPEG is a lossy image compression method.
It employs transform coding method using the DCT
(Discrete Cosine Transform).
JPEG was formally accepted as an international standard
in 1992.
6. MAIN STEPS IN JPEG IMAGE
COMPRESSION
Transform RGB to YIQ or YUV and subsample color.
DCT on image blocks.
Quantization.
Zig- zag ordering and run-length encoding.
Entropy coding.
7. FOUR COMMONLY USED JPEG MODES
Sequential Mode
It is the default JPEG mode
Each gray level image or color image
component is encoded in a single left-to-right,
top-to-bottom scan.
Progressive Mode
Hierarchical Mode
Lossless Mode
JPEG-LS
8. HIERARCHICAL MODE
The encoded image at the lowest resolution is a
compressed low-pass filtered image.
The higher resolutions provide additional details.
Progressive JPEG, the Hierarchical JPEG images can be
transmitted in multiple passes progressively by
improving the quality.
10. USE OF MOTION IN SEGMENTATION
Stationary camera
Background modeling
Human tracking & extraction
Moving camera
3D Reconstruction
Moving target detecting
11. MOTION SEGMENTATION
Segmenting the images is based on common motion.
Gestalt insight: grouping forms the basis of human
perception
12. APPLICATIONS OF MOTION SEGMENTATION
Object detection
pedestrian detection
Tracking
vehicle tracking
Robotics
Surveillance Vechicle Tracking
Image and video compression
Scene reconstruction
Video manipulation / editing
video matting
video annotation
motion magnification Video Editing
13. CHALLENGES: SHORT TERM
1. statue
2. wall
4. grass
3. trees
5. biker
6. pedestrian
Computation of motion Number of objects
Initialization of motion parameters Description of complex motions
20. Joint feature tracking
Incorporation of neighboring feature motion
Improved performance in areas of low-texture or repetitive texture
Detection of articulated motion
Motion based approach for learning high-level human motion models
Segment and track human motion in varying pose, scale, and lighting
conditions
View invariant pose estimation
Iris segmentation
Graph cuts based dense segmentation using texture and intensity
Combines appearance and eye geometry
Handles non-ideal iris image with occlusion, illumination changes, and eye
rotation
CONCLUSION