HW3_sol - CS556 HW #3 Ali Torkamani 1 Introduction This...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
CS556 HW #3 Ali Torkamani 1 Introduction This homework is about segmenting the image in each video frame. In other words it is on spa- tiotemporal segmentation. A set of video frames when stacked together can be viewed as forming a space-time (2D+t) volume. As segmentation partitions an image into regions, spatiotemporal seg- mentation partitions a 2D+t volume into subvolumes, or 2D+t tubes. There are multiple ways to conduct spatiotemporal segmentation. In this homework I have implemented two popular methods in Problem 1 and Problem 2 on the given sequence of frames. In the first problem the Ncuts algo- rithm is implemented to cluster all pixels from all video frames. The resulting Ncut clusters represent the tubes. In the second problem the Meanshift algorithm on every individual video frame. 2 Literature Review The goal of segmentation is to simplify and change the representation of an image into something that is more meaningful and easier to analyze [1] [2] [3]. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics [1]. There are many used methods for segmentation of an image, there are some works on segmentation of color images and some only have focused on gray scale ones [4] [5]. Some of this methods are: Clustering methods like K-means which iteratively partitions an image into K clusters [6], Histogram-based methods which very efficient when compared to other image segmentation methods because they typically require only one pass through the pixels [7]. In this techniques, a histogram is computed from all of the pixels in the image, and the peaks and valleys in the histogram are used to locate the clusters in the image, Edge detection methods that are a well-developed field on its own within image processing. Region boundaries and edges are closely related, since there is often a sharp adjustment in intensity at the region boundaries. Edge detection techniques have therefore been used as the base of another segmentation technique.The edges identified by edge detection are often disconnected. To segment an object from an image however, one needs closed region boundaries. Region growing methods, The first region growing method was the seeded region growing method. This method takes a set of seeds as input along with the image. The seeds mark each of the objects to be segmented. The regions are iteratively grown by comparing all unallocated neighboring pixels to the regions. Level set methods,Curve propagation is a popular technique in image analysis for object extraction, object tracking, stereo reconstruction, etc. The central idea behind such an approach is to evolve a curve towards the lowest potential of a cost function, where its definition reflects the task to be addressed and imposes certain smoothness constraints. Lagrangian techniques are based on parameterizing the contour
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 5

HW3_sol - CS556 HW #3 Ali Torkamani 1 Introduction This...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online