Search results for: J. Polec
16 Fast Algorithm of Shot Cut Detection
Authors: Lenka Krulikovská, Jaroslav Polec, Tomáš Hirner
Abstract: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.
Keywords: Abrupt cut, fast algorithm, shot cut detection, Pearson correlation coefficient.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1645
15 Shot Detection Using Modified Dugad Model
Authors: Lenka Krulikovská, Jaroslav Polec
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.
Keywords: Abrupt cut, shot cut detection, adaptive threshold.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1427
14 An Efficient Method of Shot Cut Detection
Authors: Lenka Krulikovská, Jaroslav Polec
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.
Keywords: Abrupt cut, mutual information, shot cut detection, Pearson correlation coefficient.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1826
13 A Content-Based Optimization of Data Stream Television Multiplex
Authors: Jaroslav Polec, Martin Šimek, Michal Martinovič, Elena Šikudová
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.
Keywords: Multiplex, content, group of pictures, frame, capacity.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1286
12 Video Quality Assessment using Visual Attention Approach for Sign Language
Authors: Julia Kucerova, Jaroslav Polec, Darina Tarcsiova
Abstract: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 scene.
Keywords: sign language, objective video quality, visual attention, saliencyProcedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1436
11 Key Frames Extraction for Sign Language Video Analysis and Recognition
Authors: Jaroslav Polec, Petra Heribanová, Tomáš Hirner
Abstract: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.
Keywords: Key frame, video, quality, metric, MSE, MSAD, SSIM, VQM, sign language, finger alphabet.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1916
10 A Generator from Cascade Markov Model for Packet Loss and Subsequent Bit Error Description
Authors: Jaroslav Polec, Viliam Hirner, Michal Martinovič, Kvetoslava Kotuliaková
Abstract: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.
Keywords: Wireless channel, error model, Markov chain, Elliot model, Gilbert model, generator, IEEE 802.11.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1897
9 Intelligibility of Cued Speech in Video
Authors: P. Heribanová, J. Polec, S. Ondrušová, M. Hosťovecký
Abstract:This paper discusses the cued speech recognition methods in videoconference. Cued speech is a specific gesture language that is used for communication between deaf people. We define the criteria for sentence intelligibility according to answers of testing subjects (deaf people). In our tests we use 30 sample videos coded by H.264 codec with various bit-rates and various speed of cued speech. Additionally, we define the criteria for consonant sign recognizability in single-handed finger alphabet (dactyl) analogically to acoustics. We use another 12 sample videos coded by H.264 codec with various bit-rates in four different video formats. To interpret the results we apply the standard scale for subjective video quality evaluation and the percentual evaluation of intelligibility as in acoustics. From the results we construct the minimum coded bit-rate recommendations for every spatial resolution.
Keywords: cued speech, inteligibility, logatom, videoProcedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1386
8 Unequal Error Protection for Region of Interest with Embedded Zerotree Wavelet
Abstract:This paper describes a new method of unequal error protection (UEP) for region of interest (ROI) with embedded zerotree wavelet algorithm (EZW). ROI technique is important in applications with different parts of importance. In ROI coding, a chosen ROI is encoded with higher quality than the background (BG). Unequal error protection of image is provided by different coding techniques. In our proposed method, image is divided into two parts (ROI, BG) that consist of more important bytes (MIB) and less important bytes (LIB). The experimental results verify effectiveness of the design. The results of our method demonstrate the comparison of the unequal error protection (UEP) of image transmission with defined ROI and the equal error protection (EEP) over multiple noisy channels.
Keywords: embedded zerotree wavelet (EZW), equal error protection (EEP), region of interest (ROI), RS code, unequal error protection (UEP)Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1296
7 Shape Error Concealment for Shape Independent Transform Coding
Authors: Sandra Ondrušová, Jaroslav Polec
Abstract: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.
Keywords: error concealment, shape coding, object-based image, NURBS, Bézier curves.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1160
6 Video Quality Control Using a ROI and Two- Component Weighted Metrics
Authors: Petra Heribanová, Jaroslav Polec, Michal Martinovič
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 perceptually significant.
Keywords: Video quality assessment, weighted MSE.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1849
5 Adaptive Group of Pictures Structure Based On the Positions of Video Cuts
Authors: Lenka Krulikovská, Jaroslav Polec, Michal Martinovič
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.
Keywords: Adaptive GOP structure, video coding, video content, shot cut detection.Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2169
4 An Adaptive ARQ – HARQ Method with Two RS Codes
Authors: Michal Martinovič, Jaroslav Polec, Kvetoslava Kotuliaková
Abstract: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.
Keywords: Signal-to-noise ratio, throughput, forward error correction (FEC), pure and hybrid automatic repeat request (ARQ).Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1853
3 The Content Based Objective Metrics for Video Quality Evaluation
Authors: Michal Mardiak, Jaroslav Polec
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.
Keywords: Objective quality metrics, mutual information, region recognition, content based metricsProcedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1350
2 Face Image Coding Using Face Prototyping
Authors: Jaroslav Polec, Lenka Krulikovská, Natália Helešová, Tomáš Hirner
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.
Keywords: Triangulation, H.264, Model-based coding, Average faceProcedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1616
1 Unequal Error Protection of Facial Features for Personal ID Images Coding
Abstract:This paper presents an approach for an unequal error protection of facial features of personal ID images coding. We consider unequal error protection (UEP) strategies for the efficient progressive transmission of embedded image codes over noisy channels. This new method is based on the progressive image compression embedded zerotree wavelet (EZW) algorithm and UEP technique with defined region of interest (ROI). In this case is ROI equal facial features within personal ID image. ROI technique is important in applications with different parts of importance. In ROI coding, a chosen ROI is encoded with higher quality than the background (BG). Unequal error protection of image is provided by different coding techniques and encoding LL band separately. In our proposed method, image is divided into two parts (ROI, BG) that consist of more important bytes (MIB) and less important bytes (LIB). The proposed unequal error protection of image transmission has shown to be more appropriate to low bit rate applications, producing better quality output for ROI of the compresses image. The experimental results verify effectiveness of the design. The results of our method demonstrate the comparison of the UEP of image transmission with defined ROI with facial features and the equal error protection (EEP) over additive white gaussian noise (AWGN) channel.
Keywords: Embedded zerotree wavelet (EZW), equal error protection (EEP), facial features, personal ID images, region of interest (ROI), unequal error protection (UEP)Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1380