Time filter

Source Type

Purushothaman A.,Coimbarote | Shankar Kumar K.R.,Coimbarote | Rangarajan R.,VSB Engineering College Karur | Kandasawamy A.,PSGCT Coimbatore
European Journal of Scientific Research | Year: 2011

Real-time object tracking is recently becoming more important in the field of video analysis and processing. Applications like traffic-control, user-computer interaction, online video processing and production and video surveillance need reliable and economically affordable video tracking tools. This paper presents a new method for object tracking with improved efficiency by reducing the number of computations. The video frames are captured and smoothed by a low pass filter. Another group of algorithms deals with object tracking using adaptive particle filters, kalman filter. The captured RGB space color frame is transformed to YCbCr space. The Y component of YCbCr is subjected to Continuous Wavelets Transform (CWT) by dividing into 8×8 blocks, and then the Wavelets coefficients are extracted and are used for detecting moving objects. This method reduces the number of computations and computation time. In addition the noises in the signals are suppressed automatically. © EuroJournals Publishing, Inc. 2011. Source

Purushothaman A.,SREC | Shankar Kumar K.R.,SREC | Rangarajan R.,VSB Engineering College Karur | Kandasawamy A.,Bio Medical Engineering
European Journal of Scientific Research | Year: 2011

Block artifact is one of the visually annoying problems that usually exist in low-bitrate compression images and videos. In this paper, we propose a simple but effective method to reduce block artifact based on pixel classification in spatial domain and frequency domain corrupted with impulses, Gaussian noises, artifacts,(Blocking, Ringing, blur,etc..). In traditional methodology, linear filters are not effective in removal of multiplicative noises, impulses noises, and artifacts (Blocking, Ringing, blur,). And also it is large in amplitude; hence it dominates characterizations of the signals based on secondorder statistics such as correlation and spectral analysis. This project aims to design a non linear adaptive based algorithm, smooth region and edge region (low pass filter is performed for image smoothening) by using a binary edge map from the edge detection process, for removing the artifacts (Blocking, Ringing, blurred,) also preserve edges and fine details in images and videos. This algorithm includes detection of corrupted pixels and the estimation of values for replacing the corrupted pixels and adaptive offset smoothing with the binary edge map is applied to reduce grid noise at block boundaries,( Edge detection: edge detection is performed using sobel edge detector.) Moreover extra edge-preserved filters used to remove block artifacts at edge region. And main advantage of the proposed algorithm is the uncorrupted pixels are unaltered and produced in the output. The appropriate filter is used based on the variance of the filter window, for estimating the value for replacing the corrupted value. This leads to reduced artifacts and high fine detail preservation at low bit rate compression image and videos. © EuroJournals Publishing, Inc. 2011. Source

Discover hidden collaborations