Marco Cagnazzo | Associate Professor

@conference{	11577_3469673,

title = {ROI-based rate control using tiles for an HEVC encoded video stream over a lossy network},

author = { M. Meddeb and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICIP.2015.7351028},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

pages = {1389--1393},

publisher = {IEEE Computer Society},

abstract = {The growth in the use of high definition (HD) and above video resolutions streams has outstripped the rate at which network infrastructure has been deployed. Video streaming applications require appropriate rate control techniques that make use of the specific characteristics of the video content, such as the regions of interest (ROI). With the introduction of high efficiency video coding (HEVC) streams, we consider new coding features to make a novel ROI-based rate control (RC) algorithm. The proposed approach introduces tiling in a ROI-based rate control scheme. It aims at enhancing the quality of important regions (i.e. faces for a videoconferencing system) considering independently coded regions lying within an ROI and helps evaluating the ROI quality under poor channel conditions. Our work consists of two major steps. First, we designed a RC algorithm based on an independent processing of tiles of different regions. Second, we investigate the effect of ROI- and tile-based rate control algorithm on the decoded quality of the stream transmitted over a lossy channel.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469681,

title = {Depth coding and perceived quality for 3D video},

author = { M. Calemme and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/QoMEX.2015.7148116},

isbn = {978-1-4799-8958-4},

year  = {2015},

date = {2015-01-01},

booktitle = {2015 7th International Workshop on Quality of Multimedia Experience, QoMEX 2015},

pages = {1--2},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Multi-view video plus depth is emerging as the most flexible format for 3D video representation, as witnessed by the current standardization efforts by ISO and ITU. The depth information allows synthesizing virtual view points, and for its compression various techniques have been proposed. We make a preliminary investigation of the effects on the synthesized views of two different approaches: object-based and block-based, from a perceptual point of view.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469670,

title = {Improved view synthesis by motion warping and temporal hole filling},

author = { A. I. Purica and E. G. Mora and B. Pesquet-Popescu and M. Cagnazzo and B. Ionescu},

doi = {10.1109/ICASSP.2015.7178158},

year  = {2015},

date = {2015-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

volume = {2015-},

pages = {1191--1195},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {View synthesis received increasing attention over the last years, as it offers a wide range of practical applications like Free Viewpoint Television, 3D video, video gaming, etc. The main issues in view synthesis are the filling of disoccluded areas and the warping of real views. In this paper we propose a new hole filling method, it uses temporal correlations in the real views to extract information on disoccluded areas from different time instants in the synthetic view. We also propose a sub-pixel warping technique that takes into account depth and can be used for both the warping of the real view as well as for motion compensation. Our method is proved to bring gains of up to 0.31dB in average over several multiview test sequences.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469513,

title = {Shannon-Kotelnikov mappings for softcast-based joint source-channel video coding},

author = { M. Cagnazzo and M. Kieffer},

doi = {10.1109/ICIP.2015.7350967},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

volume = {2015-},

pages = {1085--1089},

publisher = {IEEE Computer Society},

abstract = {This paper introduces Shannon-Kotelnikov (SK) mapping in the SoftCast joint source-channel video coding scheme. On bandwidth constrained channels, the performance of SoftCast saturates, due to the large amount of data (chunks) dropped to match the bandwidth requirements. Using SK mapping, it is possible to increase the number of chunks that may be transmitted without increasing the bandwidth requirements. The resulting scheme has an increased number of design parameters for which we present a transmission-power constrained optimization. This extends range of channel SNRs over which the PSNR gracefully increases and improves the end-to-end performance at medium to high SNRs. The price to be paid is a performance degradation at low SNRs.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469680,

title = {Integral images compression scheme based on view extraction},

author = { A. Dricot and J. Jung and M. Cagnazzo and B. Pesquet and F. Dufaux},

doi = {10.1109/EUSIPCO.2015.7362353},

isbn = {978-0-9928-6263-3},

year  = {2015},

date = {2015-01-01},

booktitle = {2015 23rd European Signal Processing Conference, EUSIPCO 2015},

pages = {101--105},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Integral imaging is a glasses-free 3D video technology that captures a light-field representation of a scene. This representation eliminates many of the limitations of current stereoscopic and autostereoscopic techniques. However, integral images have a large resolution and a structure based on microimages which is challenging to encode. In this paper a compression scheme for integral images based on view extraction is proposed. Average BD-rate gains of 15.7% and up to 31.3% are reported over HEVC. Parameters of the proposed coding scheme can take a large range of values. Results are first provided with an exhaustive search of the best configuration. Then an RD criterion is proposed to avoid exhaustive search methods, saving runtime while preserving the gains. Finally, additional runtime savings are reported by exploring how the different parameters interact.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469674,

title = {A convex-optimization framework for frame-level optimal rate allocation in predictive video coding},

author = { A. Fiengo and G. Chierchia and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICASSP.2014.6855023},

isbn = {978-1-4799-2893-4},

year  = {2014},

date = {2014-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

pages = {7328--7332},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Optimal rate allocation is among the most challenging tasks to perform in the context of predictive video coding, because of the dependencies between frames induced by motion compensation. In this paper, we derive an analytical rate-distortion model that explicitly takes into account the dependencies between frames. The proposed approach allows us to formulate the frame-level optimal rate allocation as a convex optimization problem. Within this framework, we are able to achieve the exact solution in limited time (even for large-size problems), thanks to the flexibility offered by recent convex optimization techniques. Experiments on standard sequences demonstrate the interest of considering the proposed rate-distortion model and confirm that the optimal rate allocation ensures a better distribution of the total bit budget, with superior results (in the rate-distortion sense) with respect to the standard H.264/AVC rate control. © 2014 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469677,

title = {Full parallax super multi-view video coding},

author = { A. Dricot and J. Jung and M. Cagnazzo and B. Pesquet and F. Dufaux},

doi = {10.1109/ICIP.2014.7025026},

isbn = {978-1-4799-5751-4},

year  = {2014},

date = {2014-01-01},

booktitle = {2014 IEEE International Conference on Image Processing, ICIP 2014},

pages = {135--139},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {Super Multi-View (SMV) video is a key enabler for future 3D video services that allows a glasses-free visualization and eliminates many causes of discomfort existing in current available 3D video technologies. SMV video content is composed of tens or hundreds of views, that can be aligned in horizontal only or both horizontal and vertical directions, providing respectively horizontal parallax or full parallax. This paper compares several coding schemes and coding orders, and proposes a coding structure that exploits inter-view correlations in the two directions, providing BD-rate gains up to 29.1% when compared to a basic anchor structure. Additionally, Neighboring Block Disparity Vector (NBDV) and Inter-View Motion Prediction (IVMP) coding tools are further improved to efficiently exploit coding structures in two dimensions, with BD-rate gains up to 4.2% reported over the reference 3D-HEVC encoder.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469683,

title = {Modification of the disparity vector derivation process in 3D-HEVC},

author = { E. G. Mora and J. Jung and B. Pesquet-Popescu and M. Cagnazzo},

doi = {10.1109/MMSP.2013.6659289},

isbn = {978-1-4799-0125-8},

year  = {2013},

date = {2013-01-01},

booktitle = {2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013},

pages = {206--211},

abstract = {The up-and-coming extension of HEVC for 3D video (3D-HEVC) includes various tools to exploit different redundancies in a 3D video signal. Inter-view redundancies are in particular exploited using Inter-View Motion Prediction (IVMP) and Inter-View Residual Prediction (IVRP). Both of these tools compensate disparity-wise the current prediction unit (PU) in order to find its corresponding PU in a base view, from which some prediction information for the current PU is retrieved. The disparity vector (DV) used for disparity compensation is currently derived using a neighboring search process (NBDV) for a DV across spatial and temporal neighbors. The first DV found is selected as the final DV used in IVMP and IVRP, with no guarantee of optimality. In this paper, the NBDV derivation process is changed: all found DVs from different neighbors are stored in a list. Redundant vectors in this list are removed, and a median computation on the remaining vectors is performed. The resulting DV is set as the DV used for IVMP. Average bitrate reductions of 0.6% and 0.8% for the two dependent views and 0.2% on synthesized views are reported with only a slight increase in encoder and decoder runtimes. © 2013 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469676,

title = {Versatile multiview layered video based on distributed source coding},

author = { G. Petrazzuoli and C. Macovei and I. -E. Nicolae and M. Cagnazzo and F. Dufaux and B. Pesquet-Popescu},

doi = {10.1109/WIAMIS.2013.6616157},

isbn = {978-1-4799-0833-2},

year  = {2013},

date = {2013-01-01},

booktitle = {International Workshop on Image Analysis for Multimedia Interactive Services},

pages = {1--4},

abstract = {Video content constitutes today a large part of the data traffic on the Internet. This is allowed by the capillary spreading of video codec technologies: nowadays, every computer, tablet and smart phone is equipped with video encoding and decoding technologies. As a matter of fact, the video content often exists in different formats, that, even though they can be incompatible to each other, still have a significant mutual redun-dancy. The incompatibility prevents an efficient exploitation of the scalability, which on the other hand is a very important characteristic when it comes to efficient network use. An interesting alternative to classical scalable video is to use distributed video coding (DVC) for the enhancement layers. In the envisaged scenario, clients have different decoders for the base layer, adapted to the characteristics of their de-vice. However they can share the same enhancement layer, since DVC allows encoding frames independently from the reference that will be employed at the decoder. This approach has been considered in the past in order to improve temporal and spatial scalability. In this work we review the existing approaches, improve them using more recent DVC techniques and perform a new analysis for the emerging multi-view applications. © 2013 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471522,

title = {On a practical approach to source separation over finite fields for network coding applications},

author = { I. Nemoianu and C. Greco and M. Castella and B. Pesquet-Popescu and M. Cagnazzo},

doi = {10.1109/ICASSP.2013.6637868},

isbn = {978-1-4799-0356-6},

year  = {2013},

date = {2013-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

pages = {1335--1339},

abstract = {In Blind Source Separation, or BSS, a set of source signals are recovered from a set of mixed observations without knowledge of the mixing parameters. Originated for real signals, BSS has recently been applied to finite fields, enabling more practical applications. However, classical entropy-based techniques do not perform well in finite fields. Here, we propose a non-linear encoding of the sources to increase the discriminating power of the separation methods. Our results show that the encoding improves the success rate of the separation for sources with few samples in large finite fields, both conditions met in practical networking applications. Our results open new possibilities in the context of network coding-wherein linear combinations of packets are sent in order to maximize throughput and increase loss immunity- by relieving the nodes from the need to send the combination coefficients, thus reducing the overhead cost. © 2013 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471465,

title = {Modification of the merge candidate list for dependent views in 3D-HEVC},

author = { E. -G. Mora and J. Jung and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICIP.2013.6738352},

isbn = {978-1-4799-2341-0},

year  = {2013},

date = {2013-01-01},

booktitle = {2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings},

pages = {1709--1713},

publisher = {IEEE Computer Society},

abstract = {A test model for an HEVC-based 3D video coding standard (3D-HEVC) has recently been drafted. 3D-HEVC exploits inter-view redundancies by including disparity-compensated prediction (DCP) for efficient dependent view coding. It also uses the Merge coding mode to reduce the cost of motion / disparity parameters. However, the candidates in the Merge list are mostly temporal motion vectors. DCP does not often benefit from accurate predictors and is thus costly. Consequently, motion-compensated prediction (MCP) remains largely preferred. In this paper, we propose to reduce the cost of DCP by modifying the Merge candidate list to always include a disparity vector candidate. Two methods are proposed: the new candidate is either added in the secondary or in the primary list of candidates. The latter method, which achieves average bitrate reductions of 0.6% for dependent views, and 0.2% for coded and synthesized views, was adopted in both the 3D-HEVC working draft and software. © 2013 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471469,

title = {A distributed video coding system for multi view video plus depth},

author = { G. Petrazzuoli and T. Maugey and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ACSSC.2013.6810373},

isbn = {978-1-4799-2388-5},

year  = {2013},

date = {2013-01-01},

booktitle = {Conference Record - Asilomar Conference on Signals, Systems and Computers},

pages = {699--703},

publisher = {IEEE Computer Society},

abstract = {Multi-view video plus depth (MVD) is gathering huge attention, as witnessed by the recent standardization activity, since its rich information about the geometry of the scene allows high-quality synthesis of virtual viewpoints. Distributed video coding of such kind of content is a challenging problem whose solution could enable new services as interactive multi-view streaming. In this work we propose to exploit the geometrical information of the MVD format in order to estimate inter-view occlusions without communication among cameras. Experimental results show a bit rate reduction up to 77% for low bit rate w.r.t. state-of-the-art architectures. © 2013 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469693,

title = {Fusion of global and local side information using Support Vector Machine in transform-domain DVC},

author = { A. Abou-Elailah and F. Dufaux and J. Farah and M. Cagnazzo},

year  = {2012},

date = {2012-01-01},

booktitle = {European Signal Processing Conference},

pages = {574--578},

abstract = {Side information has a strong impact on the performance of Distributed Video Coding. Commonly, side information is generated using motion compensated temporal interpolation. In this paper, we propose a new method for the fusion of global and local side information using Support Vector Machine. The global side information is generated at the decoder using global motion parameters estimated at the encoder using the Scale-Invariant Feature Transform. Experimental results show that the proposed approach can achieve a PSNR improvement of up to 1.7 dB for a GOP size of 2 and up to 3.78 dB for larger GOP sizes, with respect to the reference DISCOVER codec. © 2012 EURASIP.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471539,

title = {Side Information improvement in transform-domain distributed video coding},

author = { A. Abou-Elailah and G. Petrazzuoli and J. Farah and M. Cagnazzo and B. Pesquet-Popescu and F. Dufaux},

doi = {10.1117/12.930620},

year  = {2012},

date = {2012-01-01},

booktitle = {Proceedings of SPIE - The International Society for Optical Engineering},

volume = {8499},

abstract = {Side Information (SI) has a strong impact on the rate-distortion performance in distributed video coding. The quality of the SI can be impaired when the temporal distance between the neighboring reference frames increases. In this paper, we introduce two novel methods that allow improving the quality of the SI. In the first approach, we propose a new estimation method for the initial SI using backward and forward motion estimation. The second one consists in re-estimating the SI after decoding all WZFs within the current Group of Pictures (GOP). For this purpose, the SI is first successively refined after each decoded DCT band. Then, after decoding all WZFs within the GOP, we adapt the search area to the motion content. Finally, each already decoded WZF is used, along with the neighboring ones, to estimate a new SI closer to the original WZF. This new SI is then used to reconstruct again the WZF with better quality. The experimental results show that, compared to the DISCOVER codec, the proposed method reaches an improvement of up to 3.53 dB in rate-distortion performance (measured with the Bjontegaard metric) for a GOP size of 8. © 2012 SPIE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469697,

title = {A network coding scheduling for Multiple Description video streaming over wireless networks},

author = { C. Greco and I. Delia Nemoianu and M. Cagnazzo and B. Pesquet-Popescu},

year  = {2012},

date = {2012-01-01},

booktitle = {European Signal Processing Conference},

pages = {1915--1919},

abstract = {Network coding (NC) can achieve the maximum information flow in a network by allowing nodes to combine received packets before retransmission. Several works have shown NC to be beneficial in wireless networks, but the delay introduced by buffering before decoding raises a problem in real-time streaming applications. Here, we propose a framework for video delivery in wireless networks that combines Expanding Window Network Coding (EWNC), Multiple Description Coding (MDC), and a novel Rate-Distortion Optimised (RDO) scheduling algorithm that optimises the order in which the video packets are included in the coding window at the current sending opportunity. Results show that our approach consistently outperforms both EWNC applied on single description coding (SDC) and EWNC applied to MDC when a trivial scheduling is used. © 2012 EURASIP.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471542,

title = {Cedar: An optimized network-aware solution for P2P video multicast},

author = { E. G. Mora and C. Greco and B. Pesquet-Popescu and M. Cagnazzo and J. Farah},

doi = {10.1109/ICTEL.2012.6221262},

isbn = {978-1-4673-0746-8},

year  = {2012},

date = {2012-01-01},

booktitle = {2012 19th International Conference on Telecommunications, ICT 2012},

pages = {1--6},

abstract = {Video multicast is an important application for P2P networks, which can benefit from the load repartitioning and large scale distribution properties they offer. In this context, the Orchard algorithm was developed in 2007, with an aim to build a P2P system meeting video multicast requirements. However, Orchard suffers from a slow overlay construction and a potentially high end-to-end delay. In this work, we propose a new algorithm that we call Cedar. Based on Orchard, it integrates original functionalities to speed-up the tree construction and builds a topologically-aware overlay network in order to minimize end-to-end delay. Simulation results showed that Cedar fulfilled its requirements, as the tree construction speed was increased by at least 64%, and the end-to-end delays reduced from around 20 seconds to a maximum of 5 seconds. The Network Awareness functionality also reduced end-to-end delays by 33%. © 2012 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469694,

title = {Motion prediction of depth video for depth-image-based rendering using don't care regions},

author = { G. Valenzise and G. Cheung and R. Galvao and M. Cagnazzo and B. Pesquet-Popescu and A. Ortega},

doi = {10.1109/PCS.2012.6213294},

isbn = {978-1-4577-2048-2},

year  = {2012},

date = {2012-01-01},

booktitle = {2012 Picture Coding Symposium, PCS 2012, Proceedings},

pages = {93--96},

abstract = {To enable synthesis of any desired intermediate view between two captured views at decoder via depth-image-based rendering (DIBR), both texture and depth maps from the captured viewpoints must be encoded and transmitted in a format known as texture-plus-depth. In this paper, we focus on the compression of depth maps across time to lower the overall bitrate in texture-plus-depth format. We observe that depth maps are not directly viewed, but are only used to provide geometric information of the captured scene for view synthesis at decoder. Thus, as long as the resulting geometric error does not lead to unacceptable synthesized view quality, each depth pixel only needs to be reconstructed at the decoder coarsely within a tolerable range. We first formalize the notion of tolerable range per depth pixel as don't care region (DCR), by studying the synthesized view distortion sensitivity to the pixel value a sensitive depth pixel will have a narrow DCR, and vice versa. Given per-pixel DCRs, we then modify inter-prediction modes during motion prediction to search for a predictor block matching per-pixel DCRs in a target block (rather than the fixed ground truth depth signal in a target block), in order to lower the energy of the prediction residual for the block. We implemented our DCR-based motion prediction scheme inside H.264; our encoded bitstreams remain 100% standard compliant. We show experimentally that our proposed encoding scheme can reduce the bitrate of depth maps coded with baseline H.264 by over 28%. © 2012 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469879,

title = {Multi-view video streaming over wireless networks with RD-optimized scheduling of network coded packets},

author = { I. Delia Nemoianu and C. Greco and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/VCIP.2012.6410748},

isbn = {978-1-4673-4406-7},

year  = {2012},

date = {2012-01-01},

booktitle = {2012 IEEE Visual Communications and Image Processing, VCIP 2012},

pages = {1--6},

abstract = {Multi-view video streaming is an emerging video paradigm that enables new interactive services, such as free viewpoint television and immersive teleconferencing. However, it comes with a high bandwidth cost, as the equivalent of many single-view streams has to be transmitted. Network coding (NC) can improve the performance of the network by allowing nodes to combine received packets before retransmission. Several works have shown NC to be beneficiai in wireless networks, but the delay introduced by buffering before decoding raises a problem in real-time streaming applications. Here, we propose to use Expanding Window NC (EWNC) for multi-view streaming to allow immediate decoding of the received packets. The order in which the packets are included in the coding window is chosen via RD-optimization for the current sending opportunity. Results show that our approach consistently outperforms both classical NC applied on each view independently and transmission without NC. © 2012 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471540,

title = {A framework for joint multiple description coding and network coding over wireless ad-hoc networks},

author = { I. D. Nemoianu and C. Greco and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICASSP.2012.6288376},

isbn = {978-1-4673-0044-5},

year  = {2012},

date = {2012-01-01},

booktitle = {ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},

pages = {2309--2312},

abstract = {Network coding (NC) can achieve the maximum information flow in the network by allowing nodes to combine received packets before retransmission. Several papers have shown NC to be beneficial in mobile ad-hoc networks, but the delay introduced by buffered decoding raises a problem in real-time streaming applications. Here we propose to use NC jointly with multiple description coding (MDC) to allow instant decoding of the received packets. The optimal encoding coefficients are chosen via distributed optimisation of the expected video quality. Nodes receive up-to-date information about the network topology through a recently proposed protocol, originally designed for real-time streaming of MDC video. Results show that, due to the limitations imposed by instant decoding to the coding window size, our approach consistently outperforms the popular technique of random linear network coding. © 2012 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3471474,

title = {Successive refinement of side information using adaptive search area for long duration GOPs in distributed video coding},

author = { A. Abou-Elailah and F. Dufaux and M. Cagnazzo and B. Pesquet-Popescu and J. Farah},

doi = {10.1109/ICTEL.2012.6221275},

isbn = {978-1-4673-0746-8},

year  = {2012},

date = {2012-01-01},

booktitle = {2012 19th International Conference on Telecommunications, ICT 2012},

pages = {1--6},

abstract = {In distributed video coding, the reference frames are used to generate a side information at the decoder in order to decode the Wyner-Ziv frame. The quality of side information has a strong impact on the coding efficiency of distributed video coding. The estimation of the side information becomes less accurate when the temporal distance between the neighboring reference frames increases or when the sequence contains fast motion. In this paper, we propose a new method based on successive refinement of the side information by adapting the motion search area after decoding the first DCT band. More specifically, different search areas are initially set, according to the temporal distance between the neighboring reference frames. Furthermore, the size of the search area is adapted to the motion content after decoding the first DCT band by using the partially decoded Wyner-Ziv frame. This adapted search area is used in order to refine the side information after decoding each remaining DCT band. The experimental results show that the proposed technique allows an improvement in rate distortion performance that can reach 0.7 dB for a GOP size of 8, compared to the method where a constant search area is used, and a significant gain up to 3.23 dB, with respect to DISCOVER codec. The improvement in the quality of the final side information reaches 5.6 dB for some frames, compared to constant search area. Moreover, the proposed method reduces significantly the decoding time for all test sequences. © 2012 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469686,

title = {Wyner-Ziv coding for depth maps in multiview video-plus-depth},

author = { G. Petrazzuoli and M. Cagnazzo and F. Dufaux and B. Pesquet-Popescu},

doi = {10.1109/ICIP.2011.6115817},

isbn = {978-1-4577-1302-6},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

pages = {1817--1820},

abstract = {Three dimensional digital video services are gathering a lot of attention in recent years, thanks to the introduction of new and efficient acquisition and rendering devices. In particular, 3D video is often represented by a single view and a so called depth map, which gives information about the distance between the point of view and the objects. This representation can be extended to multiple views, each with its own depth map. Efficient compression of this kind of data is of course a very important topic in sight of a massive deployment of services such as 3D-TV and FTV (free viewpoint TV). In this paper we consider the application of distributed coding techniques to the coding of depth maps, in order to reduce the complexity of single view or multi view encoders and to enhance interactive multiview video streaming. We start from state-of-the-art distributed video coding techniques and we improve them by using high order motion interpolation and by exploiting texture motion information to encode the depth maps. The experiments reported here show that the proposed method achieves a rate reduction up to 11.06% compared to state-of-the-art distributed video coding technique. © 2011 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469811,

title = {Successive refinement of motion compensated interpolation for transform-domain distributed video coding},

author = { A. Abou-Elailah and F. Dufaux and J. Farah and M. Cagnazzo and B. Pesquet-Popescu},

year  = {2011},

date = {2011-01-01},

booktitle = {European Signal Processing Conference},

pages = {11--15},

abstract = {In distributed video coding, the estimation of the side information at the decoder plays a key role in the final ratedistortion performance of the codec. The side information is commonly generated by motion-compensated temporal interpolation of the neighboring reference frames. In this paper, we propose a successive refinement after the decoding of each DCT subband to improve the accuracy of motion compensation between reference frames, in order to obtain a new side information estimation closer to the originalWyner-Ziv frame. The experimental results show that the proposed scheme can achieve up to 0.9 dB of improvement in ratedistortion performance for a GOP size of 2 and 2.4 dB for a GOP size of 8 for sequences containing high motion with respect to state-of-the-art techniques. © EURASIP, 2011.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469809,

title = {Depth map coding by dense disparity estimation for MVD compression},

author = { M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/ICDSP.2011.6005011},

isbn = {978-1-4577-0273-0},

year  = {2011},

date = {2011-01-01},

booktitle = {17th DSP 2011 International Conference on Digital Signal Processing, Proceedings},

pages = {1--6},

abstract = {In multiview video representation, one of the most popular format is the so-called multiple view video plus depth. This representation is made up of N image sequences, each accompanied by a sequence of depth maps, telling the distance of each represented pixel from the observing camera. The depth maps are needed at the decoder side in order to generate intermediate views and therefore to enrich the user experience. This format is very flexible but also very demanding, in terms of storage space or and transmission bandwidth. Therefore, compression is needed. At this end, one of the key steps is an efficient representation of depth maps. In this work we build over a proposed method for multiple view video coding, based on dense disparity estimation between views. This allows us to obtain a compact and high-quality depthmap representation. In particular we explore the complex relationship between estimation and encoding parameters, showing that an optimal parameter set exist, that allows a fine-tuning of the estimation phase and an adaption of its results to the subsequent compression phase. Experiments are encouraging, showing remarkable gain over simple methods such as H.264/AVC simulcast, and even some gain with respect to more sophisticated techniques such as MVC. © 2011 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469695,

title = {Using distributed source coding and depth image based rendering to improve interactive multiview video access},

author = { G. Petrazzuoli and M. Cagnazzo and F. Dufaux and B. Pesquet-Popescu},

doi = {10.1109/ICIP.2011.6116620},

isbn = {978-1-4577-1302-6},

year  = {2011},

date = {2011-01-01},

booktitle = {Proceedings - International Conference on Image Processing, ICIP},

pages = {597--600},

abstract = {Multiple-views video is commonly believed to be the next significant achievement in video communications, since it enables new exciting interactive services such as free viewpoint television and immersive teleconferencing. However the interactivity requirement (i.e. allowing the user to change the viewpoint during video streaming) involves a trade-off between storage and bandwidth costs. Several solutions have been proposed in the literature, using redundant predictive frames, Wyner-Ziv frames, or a combination of them. In this paper, we adopt distributed video coding for interactive multiview video plus depth (MVD), taking advantage of depth image based rendering (DIBR) and depth-aided inpainting to fill the occlusion areas. To the authors' best knowledge, very few works in interactive MVD consider the problem of continuity of the playback during the switching among streams. Therefore we survey the existing solutions, we propose a set of techniques for MVD coding and we compare them. As main results, we observe that DIBR can help in rate reduction (up to 13.36% for the texture video and up to 8.67% for the depth map, wrt the case where DIBR is not used), and we also note that the optimal strategy to combine DIBR and distributed video coding depends on the position of the switching time into the group of pictures. Choosing the best technique on a frame-to-frame basis can further reduce the rate from 1% to 6%. © 2011 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469687,

title = {Improved side information generation for distributed video coding},

author = { A. Abou-Elailah and J. Farah and M. Cagnazzo and B. Pesquet-Popescu and F. Dufaux},

doi = {10.1109/EuVIP.2011.6045553},

isbn = {978-1-4577-0072-9},

year  = {2011},

date = {2011-01-01},

booktitle = {3rd European Workshop on Visual Information Processing, EUVIP 2011 - Final Program},

pages = {42--49},

abstract = {In distributed video coding, the side information is commonly generated by motion-compensated temporal interpolation of the neighboring reference frames at the decoder side. The side information quality has a strong impact on the final rate-distortion performance of the codec. In this paper, we propose a successive refinement after the decoding of each DCT subband to improve the accuracy of motion compensation between reference frames, in order to obtain a new side information estimation closer to the original Wyner-Ziv frame. Here, we propose two different algorithms in the refinement process of the side information. The experimental results show that the proposed techniques allow an improvement in rate-distortion performance that can reach 1.15 dB for GOP size of 2 and 3.2 dB for longer GOP size, with respect to state-of-the-art techniques, for sequences containing high motion. © 2011 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{	11577_3469685,

title = {An MDC-based video streaming architecture for mobile networks},

author = { C. Greco and G. Petrazzuoli and M. Cagnazzo and B. Pesquet-Popescu},

doi = {10.1109/MMSP.2011.6093829},

isbn = {978-1-4577-1433-7},

year  = {2011},

date = {2011-01-01},

booktitle = {MMSP 2011 - IEEE International Workshop on Multimedia Signal Processing},

pages = {1--6},

abstract = {Multiple description coding (MDC) is a framework designed to improve the robustness of video content transmission in lossy environments. In this work, we propose an MDC technique using a legacy coder to produce two descriptions, based on separation of even and odd frames. If only one description is received, the missing frames are reconstructed using temporal high-order motion interpolation (HOMI), a technique originally proposed for distributed video coding. If both descriptions are received, the frames are reconstructed as a block-wise linear combination of the two descriptions, with the coefficient computed at the encoder in a RD-optimised fashion, encoded with a context-adaptive arithmetic coder, and sent as side information. We integrated the proposed technique in a mobile ad-hoc streaming protocol, and tested it using a group mobility model. The results show a non-negligible gain for the expected video quality, with respect to the reference technique. © 2011 IEEE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}