An Efficient Method of Shot Cut Detection
In this paper we present a method of abrupt cut detection with a novel logic of frames- comparison. Actual frame is compared with its motion estimated prediction instead of comparison with successive frame. Four different similarity metrics were employed to estimate the resemblance of compared frames. Obtained results were evaluated by standard used measures of test accuracy and compared with existing approach. Based on the results, we claim the proposed method is more effective and Pearson correlation coefficient obtained the best results among chosen similarity metrics.
Abrupt cut, mutual information, shot cut detection,
Pearson correlation coefficient.
Key Frames Extraction for Sign Language Video Analysis and Recognition
In this paper we proposed a method for finding video
frames representing one sign in the finger alphabet. The method is
based on determining hands location, segmentation and the use of
standard video quality evaluation metrics. Metric calculation is
performed only in regions of interest. Sliding mechanism for finding
local extrema and adaptive threshold based on local averaging is used
for key frames selection. The success rate is evaluated by recall,
precision and F1 measure. The method effectiveness is compared
with metrics applied to all frames. Proposed method is fast, effective
and relatively easy to realize by simple input video preprocessing
and subsequent use of tools designed for video quality measuring.
Key frame, video, quality, metric, MSE, MSAD, SSIM, VQM, sign language, finger alphabet.
Fast Algorithm of Shot Cut Detection
In this paper we present a novel method, which
reduces the computational complexity of abrupt cut detection. We
have proposed fast algorithm, where the similarity of frames within
defined step is evaluated instead of comparing successive frames.
Based on the results of simulation on large video collection, the
proposed fast algorithm is able to achieve 80% reduction of needed
frames comparisons compared to actually used methods without the
shot cut detection accuracy degradation.
Abrupt cut, fast algorithm, shot cut detection,
Pearson correlation coefficient.
An Adaptive ARQ – HARQ Method with Two RS Codes
In this paper we proposed multistage adaptive
ARQ/HARQ/HARQ scheme. This method combines pure ARQ
(Automatic Repeat reQuest) mode in low channel bit error rate and
hybrid ARQ method using two different Reed-Solomon codes in
middle and high error rate conditions. It follows, that our scheme has
three stages. The main goal is to increase number of states in adaptive
HARQ methods and be able to achieve maximum throughput for
every channel bit error rate. We will prove the proposal by
calculation and then with simulations in land mobile satellite channel
environment. Optimization of scheme system parameters is described
in order to maximize the throughput in the whole defined Signal-to-
Noise Ratio (SNR) range in selected channel environment.
Signal-to-noise ratio, throughput, forward error
correction (FEC), pure and hybrid automatic repeat request (ARQ).
Shape Error Concealment for Shape Independent Transform Coding
Arbitrarily shaped video objects are an important
concept in modern video coding methods. The techniques presently
used are not based on image elements but rather video objects having
an arbitrary shape. In this paper, spatial shape error concealment
techniques to be used for object-based image in error-prone
environments are proposed. We consider a geometric shape
representation consisting of the object boundary, which can be
extracted from the α-plane. Three different approaches are used to
replace a missing boundary segment: Bézier interpolation, Bézier
approximation and NURBS approximation. Experimental results on
object shape with different concealment difficulty demonstrate the
performance of the proposed methods. Comparisons with proposed
methods are also presented.
error concealment, shape coding, object-based
image, NURBS, Bézier curves.
Shot Detection Using Modified Dugad Model
In this paper we present a modification to existed model of threshold for shot cut detection, which is able to adapt itself to the sequence statistics and operate in real time, because it use for calculation only previously evaluated frames. The efficiency of proposed modified adaptive threshold scheme was verified through extensive test experiment with several similarity metrics and achieved results were compared to the results reached by the original model. According to results proposed threshold scheme reached higher accuracy than existed original model.
Abrupt cut, shot cut detection, adaptive threshold.
Video Quality Control Using a ROI and Two- Component Weighted Metrics
In this paper we propose a new content-weighted
method for full reference (FR) video quality control using a region of
interest (ROI) and wherein two-component weighted metrics for Deaf
People Video Communication. In our approach, an image is
partitioned into region of interest and into region "dry-as-dust", then
region of interest is partitioned into two parts: edges and background
(smooth regions), while the another methods (metrics) combined and
weighted three or more parts as edges, edges errors, texture, smooth
regions, blur, block distance etc. as we proposed. Using another idea
that different image regions from deaf people video communication
have different perceptual significance relative to quality. Intensity
edges certainly contain considerable image information and are
Video quality assessment, weighted MSE.
Adaptive Group of Pictures Structure Based On the Positions of Video Cuts
In this paper we propose a method which improves the efficiency of video coding. Our method combines an adaptive GOP (group of pictures) structure and the shot cut detection. We have analyzed different approaches for shot cut detection with aim to choose the most appropriate one. The next step is to situate N frames to the positions of detected cuts during the process of video encoding. Finally the efficiency of the proposed method is confirmed by simulations and the obtained results are compared with fixed GOP structures of sizes 4, 8, 12, 16, 32, 64, 128 and GOP structure with length of entire video. Proposed method achieved the gain in bit rate from 0.37% to 50.59%, while providing PSNR (Peak Signal-to-Noise Ratio) gain from 1.33% to 0.26% in comparison to simulated fixed GOP structures.
Adaptive GOP structure, video coding, video
content, shot cut detection.
The Content Based Objective Metrics for Video Quality Evaluation
In this paper we proposed comparison of four content based objective metrics with results of subjective tests from 80 video sequences. We also include two objective metrics VQM and SSIM to our comparison to serve as “reference” objective metrics because their pros and cons have already been published. Each of the video sequence was preprocessed by the region recognition algorithm and then the particular objective video quality metric were calculated i.e. mutual information, angular distance, moment of angle and normalized cross-correlation measure. The Pearson coefficient was calculated to express metrics relationship to accuracy of the model and the Spearman rank order correlation coefficient to represent the metrics relationship to monotonicity. The results show that model with the mutual information as objective metric provides best result and it is suitable for evaluating quality of video sequences.
Objective quality metrics, mutual information, region recognition, content based metrics
Face Image Coding Using Face Prototyping
In this paper we present a novel approach for face image coding. The proposed method makes a use of the features of video encoders like motion prediction. At first encoder selects appropriate prototype from the database and warps it according to features of encoding face. Warped prototype is placed as first I frame. Encoding face is placed as second frame as P frame type. Information about features positions, color change, selected prototype and data flow of P frame will be sent to decoder. The condition is both encoder and decoder own the same database of prototypes. We have run experiment with H.264 video encoder and obtained results were compared to results achieved by JPEG and JPEG2000. Obtained results show that our approach is able to achieve 3 times lower bitrate and two times higher PSNR in comparison with JPEG. According to comparison with JPEG2000 the bitrate was very similar, but subjective quality achieved by proposed method is better.
Triangulation, H.264, Model-based coding, Average
Video Quality Assessment using Visual Attention Approach for Sign Language
Visual information is very important in human perception
of surrounding world. Video is one of the most common ways to
capture visual information. The video capability has many benefits
and can be used in various applications. For the most part, the
video information is used to bring entertainment and help to relax,
moreover, it can improve the quality of life of deaf people. Visual
information is crucial for hearing impaired people, it allows them to
communicate personally, using the sign language; some parts of the
person being spoken to, are more important than others (e.g. hands,
face). Therefore, the information about visually relevant parts of the
image, allows us to design objective metric for this specific case. In
this paper, we present an example of an objective metric based on
human visual attention and detection of salient object in the observed
sign language, objective video quality, visual attention,
A Generator from Cascade Markov Model for Packet Loss and Subsequent Bit Error Description
In this paper we present a novel error model for
packet loss and subsequent error description. The proposed model
simulates the error performance of wireless communication link. The
model is designed as two independent Markov chains, where the first
one is used for packet generation and the second one generates
correctly and incorrectly transmitted bits for received packets from
the first chain. The statistical analyses of real communication on the
wireless link are used for determination of model-s parameters. Using
the obtained parameters and the implementation of the generator, we
collected generated traffic. The obtained results generated by
proposed model are compared with the real data collection.
Wireless channel, error model, Markov chain, Elliot
model, Gilbert model, generator, IEEE 802.11.
A Content-Based Optimization of Data Stream Television Multiplex
The television multiplex has reserved capacity and therefore we can use only limited number of videos for propagation of it. Appropriate composition of the multiplex has a major impact on how many videos is spread by multiplex. Therefore in this paper is designed a simple algorithm to optimize capacity utilization multiplex. Significant impact on the number of programs in the multiplex has also the fact from which programs is composed. Content of multiplex can be movies, news, sport, animated stories, documentaries, etc. These types have their own specific characteristics that affect their resulting data stream. In this paper is also done an impact analysis of the composition of the multiplex to use its capacity by video content.
Multiplex, content, group of pictures, frame, capacity.