New refinement schemes for voice conversion are proposed in this paper. We take mel-frequency cepstral coefficients (MFCC) as the basic feature and adopt cepstral mean subtraction to compensate the channel effects. We propose S/U/V (Silence/Unvoiced/Voiced) decision rule such that two sets of codebooks are used to capture the difference between unvoiced and voiced segments of the source speaker...

We present an approach to tracking multiple human subjects within a camera network. A particle filter framework is used in which we combine foreground-background subtraction with a novel approach to texture learning and likelihood computation based on an ellipsoid model. As there are inevitable problems with multiple subjects due to occlusion and crossing, we include a robust method to suppress...

Today, security of human being is the most active research area. In this paper, we review the two different techniques of video surveillance system based on motion segmentation and tracking. The first system is based on dual frame differencing method followed by the morphological operations & Kalman filtering. The second technique is the use of visual background subtraction combined with illumi...

This paper presents a novel approach to detect traffic congestion on roads in a natural open world scene observed from TV cameras placed on poles or buildings. In this system, three algorithms are proposed to estimate the road status. They are based on background subtraction, frame differencing and time-spatial image respectively. The experimental results on real road traffic congestion estimat...

Kinematic dipole signal originates from the motion of the Sun with respect to the CMB rest frame. It is a remarkable signal, two orders of magnitude larger than the observed pattern of CMB anisotropies. Therefore the dipole subtraction from the main beam is of primary importance. But what happens to the dipole signal entering the main spillover (i.e. the most relevant far antenna pattern featur...

This paper presents a multiple target tracking system through a fixed video camera, based on approaches found in literature. The proposed system is composed of three steps: foreground identification through background subtraction techniques; object association through color, area and centroid position matching, by using the Kalman filter to estimate the object’s position in the next frame; obje...

We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparity information is calculated in an initialization step so that only disparities of moving object regions are updated in the main process. We propose a real-time segmentation technique using background subtraction and inter-frame ...

Background maintenance is a frequent element of video surveillance systems. We develop Wallflower, a threecomponent system for background maintenance: the pixellevel component performs Wiener filtering to make probabilistic predictions of the expected background; the region-level component fills in homogeneous regions of foreground objects; and the frame-level component detects sudden, global c...

This paper describes the SFU entry for the TRECVid 2009 event detection challenge. We attempted to detect events involving either one or two individuals, and present algorithms for “running”, “embrace”, and “pointing” event detection. The system has three stages. First, preprocessing is performed to extract candidate space-time regions using background subtraction and photogrammetric context. T...

BACKGROUND AND PURPOSE We sought to evaluate the diagnostic accuracy of ultrasound criteria for recanalization during real-time transcranial Doppler monitoring of intra-arterial reperfusion procedures in acute ischemic stroke patients in an international, multicenter study. METHODS Consecutive acute ischemic stroke patients with proximal intracranial occlusions underwent intra-arterial reperf...