M Tech Dissertations

Permanent URI for this collectionhttp://drsr.daiict.ac.in/handle/123456789/3

Browse

Search Results

Now showing 1 - 4 of 4
  • ItemOpen Access
    Object-background segmentation from video
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2015) Domadiya, Prashant; Mitra, Suman K.
    Fast and accurate algorithms for background-foreground separation are an essential part of

    any video surveillance system. GMM (Gaussian Mixture Models) based object segmentation

    methods give accurate results for background-foreground separation problems but are

    computationally expensive. In contrast, modeling with only single Gaussian improves the

    time complexity with the reduction in the accuracy due to variations in illumination and

    dynamic nature of the background. It is observed that these variations affect only a few

    pixels in an image. Most of the background pixels are unimodal. We propose a method

    to account for the dynamic nature of the background and low lighting conditions. It is an

    adaptive approach where each pixel is modeled as either unimodal Gaussian or multimodal

    Gaussians. The flexibility in terms of number of Gaussians used to model each pixel, along

    with learning when it is required approach reduces the time complexity of the algorithm

    significantly. To resolve problems related to false negative due to the homogeneity of color

    and texture in foreground and background, a spatial smoothing is carried out by K-means,

    which improves the overall accuracy of proposed algorithm. The shadow causes the problem

    in many applications which rely on segmentation results. Shadow cause variation in

    RGB values of pixels, RGB value dependent GMM based method can’t remove shadow

    from detection results. The preprocessing stage involving illumination invariant representation

    takes care of the object shadow as well.

  • ItemOpen Access
    Development of difference detection algorithm for surveillance video compression
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2011) Marvaniya, Hitul D.; Banerjee, Asim
    Video surveillance is widely used tool in today’s era for improving public and residential safety. Here the size of the video data is much higher due to large number of surveillance cameras scattered over large area and data needs to be saved for longer time. Thus various compression schemes needs to be implemented to reduce the size of the data. Currently H.264/AVC is widely used as a compression for video surveillance. The computational complexity of H.264/AVC is higher. So the surveillance system is going to be computationally complex and more time consuming. The difference detection algorithm is working as a preprocessing module before video encoder to reduce the complexity of video compression. As proposed algorithm is completely independent from compression module of H.264, it has high adaptability to work with any existing H.264 video encoder to save the cost of implementation.
  • ItemOpen Access
    Object segmentation in still camera videos
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2010) Pandya, Sweta A.; Mitra, Suman K.
    The goal of object segmentation is to simplify and change the representation of an image into more meaningful so that it can easily analyse. Segmentation is the process of partitioning the digital image into multiple segments (set of pixels). It is the foremost step before performing other operations like recognition, scene understanding, tracking, etc. Main purpose of video segmentation is to extract the objects of interest from a series of consecutive video frames. For example surveillance video requires high-level image understanding and scene interpretation for tracking the special events. Another example is of segmenting flower from an image and video in which there are variety of flowers, the variability within a particular flower, and the variability of the imaging conditions – lighting, pose, etc. There are various approaches for segmenting the object from an image. Some of them are histogram based approach, region based approach and graph partitioning approach. In graph partitioning approach, the image being segmented is modelled as a weighted, undirected graph. Each pixel is represented as a node in the graph, and an edge is formed between every pair of pixels. The weight of an edge is a measure of the similarity between the pixels. Some popular algorithms of graph partitioning category are random walker, minimum mean cut, minimum spanning tree-based algorithm and normalized cut. In graph partitioning approach, the normalized cut algorithm is used to solve the grouping problem. In this algorithm, image is partitioned into disjoint sets by removing the edges connecting the segments. The partition can be done by finding the splitting point. The optimal solution of the splitting point is computed by solving the Eigen value problem. The optimal partitioning of the graph is the one that minimizes the weights of the edges that were removed. A normalized cut criterion measures the dissimilarity between the different groups as well as total similarity within the groups. Here group size doesn’t matter for normalized cut criterion. The normalized cut can be computed using three different splitting points and the result is analysed accordingly. A common approach for detecting the object from a video is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model and then apply the segmentation algorithm to that video. Here background subtraction has been done by frame difference method. In this method previous frame is subtracted from the current frame and difference is compared with the specific threshold value. For experimental purpose, videos of different flowers and movement of the tennis balls have been taken. All the experiments have been performed on both gray scale image and videos in MATLAB.
  • ItemOpen Access
    Video compression using color transfer based on motion estimation
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2008) Reddy, Pandu Ranga M.; Mitra, Suman K.
    Many compression techniques were developed in last decade and are being used in many applications like HDTV, Videoconferencing, Videophone, multimedia work stations and mobile image communications. It is also certain that digital video will have a significant economic impact on the computer, telecommunications, and imaging industries. Compression that is obtained by standard compression schemes for color video can be further increased if we can take the advantage of color information of successive images of a scene. The color of the objects in the present frame will be almost similar to the color of it in previous frame. So color can be applied at decoder, even if the information is not known for all frames of a scene. The main objective of this thesis is to propose schemes for different profiles of MPEG-2 which uses color transfer techniques. The proposed schemes are tested with different sequences and are compared with the MPEG-2 coded sequences.