R. K. Kulkarni

Learn More
Video-surveillance and traffic analysis systems can be heavily improved using vision-based techniques to extract, manage and track objects in the scene. However, problems arise due to shadows. In particular, moving shadows can affect the correct localization, measurements and detection of moving objects. This work aims to present a technique for shadow(More)
3D Television enhances viewing experience by adding visual impact to any scene. Generating stereoscopic content from the vast collection of already existing 2D material is less expensive and less time consuming than creating 3D material using stereoscopic cameras. Depth Image Based Rendering (DIBR) is one of the various approaches for 2D to 3D video(More)
In this paper a novel method for effectively denoising the extremely corrupted image by fixed value impulse noise using robust estimation based filter is proposed. The proposed algorithm classifies the pixels of localized window in to “corrupted” or “uncorrupted” and removes only corrupted pixels by robust estimation or by mean of the processed neighboring(More)
In this paper, the algorithm is developed by combining advantages of the median filters for filtration of noisy pixels with noise detection step. The algorithm works well for suppressing impulse noise with noise density ranging from 10 to 70% while preserving image details. The proposed algorithm is based on the two schemes:- 1) Impulse noise detection(More)
Moving objects detection is a fundamental step in many vision based applications. Background subtraction is the typical method. Many background models have been introduced to deal with different problems. The method based on mixture of Gaussians is a good balance between accuracy and complexity, and is used frequently by many researchers. But it still(More)
Image segmentation is about splitting the whole image into segments. In case of image analysis, image processing one of the crucial steps is segmentation of the image. Segmentation of image concern about dividing the entire image in sub parts that may be similar or dissimilar with respect to features. Output of image segmentation has consequence on analysis(More)
For removing impulse noise, basic median filter is used. The median filters are not able to retain edges and fine details of images at high density noise. A new algorithm is proposed to overcome the limitations of existing methods. This algorithm is categorized into two stages. First stage is detection of impulse pixel depends on threshold values and second(More)