Showing 5 results for Kasaei
H. Mahdavi-Nasab, Shohreh Kasaei,
Volume 1, Issue 2 (April 2005)
Abstract
Motion estimation and compensation is an essential part of existing video coding
systems. The mesh-based motion estimation (MME) produces smoother motion field, better
subjective quality (free from blocking artifacts), and higher peak signal-to-noise ratio
(PSNR) in many cases, especially at low bitrate video communications, compared to the
conventional block matching algorithm (BMA). However, the iterative refinement process
of MME is computationally much costly and makes the method impractical in real- (or near
real-) time systems. Also, eliminating the iterative refinement step deteriorates the motion
estimation result. In this paper, we propose motion adaptive interpolation schemes for noniterative
MME, which use BMA to compute the motion vectors (MVs) of mesh nodes. The
proposed algorithm aims at compromising the MME and BMA by modifying the
interpolation patterns (IPPs) of the MME in an adaptive manner, based on the MVs of
mesh nodes. Experimental results show notable rate-distortion improvement over both
BMA and conventional non-iterative MME, with acceptable visual quality and system
complexity, especially when applied to sequences with medium to high motion activities.
A. Abadpour, S. Kasaei,
Volume 1, Issue 3 (July 2005)
Abstract
A robust skin detector is the primary need of many fields of computer vision,
including face detection, gesture recognition, and pornography filtering. Less than 10 years
ago, the first paper on automatic pornography filtering was published. Since then, different
researchers claim different color spaces to be the best choice for skin detection in
pornography filtering. Unfortunately, no comprehensive work is performed on evaluating
different color spaces and their performance for detecting naked persons. As such,
researchers usualy refer to the results of skin detection based on the work doen for face
detection, which underlies different imaging conditions. In this paper, we examine 21 color
spaces in all their possible representations for pixel-based skin detection in pornographic
images. Consequently, this paper holds a large investigation in the field of skin detection,
and a specific run on the pornographic images.
Sh. Mahmoudi-Barmas, Sh. Kasaei,
Volume 4, Issue 1 (April 2008)
Abstract
Image registration is a crucial step in most image processing tasks for which the
final result is achieved from a combination of various resources. In general, the majority of
registration methods consist of the following four steps: feature extraction, feature
matching, transform modeling, and finally image resampling. As the accuracy of a
registration process is highly dependent to the feature extraction and matching methods, in
this paper, we have proposed a new method for extracting salient edges from satellite
images. Due to the efficiency of multiresolution data representation, we have considered
four state-of-the-art multiresolution transforms –namely, wavelet, curvelet, complex
wavelet and contourlet transform- in the feature extraction step of the proposed image
registration method. Experimental results and performance comparison among these
transformations showed the high performance of the contourlet transform in extracting
efficient edges from satellite images. Obtaining salient, stable and distinguishable features
increased the accuracy of the proposed registration process.
Sh. Kasaei, E. Shabani Nia,
Volume 7, Issue 3 (September 2011)
Abstract
Multicamera vehicle tracking is a necessary part of any video-based intelligent transportation system for extracting different traffic parameters such as link travel times and origin/destination counts. In many applications, it is needed to locate traffic cameras disjoint from each other to cover a wide area. This paper presents a method for tracking moving vehicles in such camera networks. The proposed method introduces a new method for handling inter-object occlusions as the most challenging part of the single camera tracking phase. This approach is based on coding the silhouette of moving objects before and after occlusion and separating occluded vehicles by computing the longest common substring of the related chain codes. In addition, to improve the accuracy of the tracking method in the multicamera phase, a new feature based on the relationships among surrounding vehicles is formulated. The proposed feature can efficiently improve the efficiency of the appearance (or space-time) features when they cannot discriminate between correspondent and non-correspondent vehicles due to noise or dynamic condition of traffic scenes. A graph-based approach is then used to track vehicles in the camera network. Experimental results show the efficiency of the proposed methods.
S. M. Marvasti Zadeh, H. Ghanei Yakhdan, Sh. Kasaei,
Volume 10, Issue 3 (September 2014)
Abstract
Sending compressed video data in error-prone environments (like the Internet and wireless networks) might cause data degradation. Error concealment techniques try to conceal the received data in the decoder side. In this paper, an adaptive boundary matching algorithm is presented for recovering the damaged motion vectors (MVs). This algorithm uses an outer boundary matching or directional temporal boundary matching method to compare every boundary of candidate macroblocks (MBs), adaptively. It gives a specific weight according to the accuracy of each boundary of the damaged MB. Moreover, if each of the adjacent MBs is already concealed, different weights are given to the boundaries. Finally, the MV with minimum adaptive boundary distortion is selected as the MV of the damaged MB. Experimental results show that the proposed algorithm can improve both objective and subjective quality of reconstructed frames without any considerable computational complexity The average PSNR in some frames of test sequences increases about 4.59, 4.44, 3.57, and 2.98 dB compared to classic boundary matching, directional boundary matching, directional temporal boundary matching, and outer boundary matching algorithm, respectively.