Filters








11,033 Hits in 4.8 sec

Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks [article]

Jae Shin Yoon, Francois Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
<span title="2017-08-17">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel video object segmentation algorithm based on pixel-level matching using Convolutional Neural Networks (CNN).  ...  in its appearance through a video sequence.  ...  Video Object Segmentation Initial frame fine-tuning In order to generate the finetuning data, we use only the first frame of a new video (not utilized for training).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.05137v1">arXiv:1708.05137v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xyllllgcdjczzb3mtvbhmnirce">fatcat:xyllllgcdjczzb3mtvbhmnirce</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015215111/https://arxiv.org/pdf/1708.05137v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/72/0072bde48a516f1b9a1ec11914dcdc976c676a43.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.05137v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Adaptive temporal compressive sensing for video

Xin Yuan, Jianbo Yang, Patrick Llull, Xuejun Liao, Guillermo Sapiro, David J. Brady, Lawrence Carin
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2013 IEEE International Conference on Image Processing</a> </i> &nbsp;
We propose a CS algorithm to adapt the compression ratio based on the scene's temporal complexity, computed from the compressed data, without compromising the quality of the reconstructed video.  ...  This paper introduces the concept of adaptive temporal compressive sensing (CS) for video.  ...  Fig. 8 8 implements adaptive N F on video data captured in front of a shop [30].  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2013.6738004">doi:10.1109/icip.2013.6738004</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/YuanYLLSBC13.html">dblp:conf/icip/YuanYLLSBC13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mqe75yri5feu3i3w3f4xjdmp4e">fatcat:mqe75yri5feu3i3w3f4xjdmp4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171130021351/https://core.ac.uk/download/pdf/37750105.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6b/4d/6b4d046262c7d67640382d7eefcf0bdc1cd1e858.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2013.6738004"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

An error resilient coding scheme for JPEG image transmission based on data embedding and side-match vector quantization

Li-Wei Kang, Jin-Jang Leou
<span title="">2006</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kekp3nlexfexzm4yg4msrqoove" style="color: black;">Journal of Visual Communication and Image Representation</a> </i> &nbsp;
In this study, an error resilient coding scheme for JPEG image transmission based on data embedding and side-match vector quantization (VQ) is proposed.  ...  At the encoder, the important data (the codebook index) for each Y (U or V) block in a JPEG image are extracted and embedded into another "masking" Y (U or V) block in the image by the odd-even data embedding  ...  six data units (four Y blocks, one U block, and one V block), just like a GOB in the H.263 video compression standard [6] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jvcir.2005.08.003">doi:10.1016/j.jvcir.2005.08.003</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/frt65264tbgufh6qlbronceeaa">fatcat:frt65264tbgufh6qlbronceeaa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060924105635/http://www.iis.sinica.edu.tw/papers/lwkang/2003-F.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/c8/dcc800324272c50e9f60d2a7784fb9b2585ff63a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jvcir.2005.08.003"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

WCAM: smart encoding for wireless surveillance

Jerome Meessen, C. Parisot, C. Le Barz, Didier Nicholson, Jean-Francois Delaigle, Amir Said, John G. Apostolopoulos
<span title="2005-03-14">2005</span> <i title="SPIE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ls4q4x7rdzeuhlbun5ks7yr7aq" style="color: black;">Image and Video Communications and Processing 2005</a> </i> &nbsp;
First the system performs a real-time unsupervised segmentation of mobiles in each frame of the video.  ...  In this paper, we present an integrated system for smart encoding in video surveillance.  ...  The video sequence used for the results presented in this document (speedway test sequence) have been generated by Université catholique de Louvain, in the context of the past ACTS project MODEST.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.585468">doi:10.1117/12.585468</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/eiivcp/MeessenPBND05.html">dblp:conf/eiivcp/MeessenPBND05</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tfvzoxsvsnernkpsvyiowht55a">fatcat:tfvzoxsvsnernkpsvyiowht55a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060209035511/http://www.multitel.be:80/~meessejer/PDF/Meessen_Spie05_SmartCoding.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/49/20/4920247b9ce86c5bd30fd82153c37000f420a449.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.585468"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Compressing Piecewise Smooth Images with the Mumford-Shah Cartoon Model [article]

Ferdinand Jost, Pascal Peter, Joachim Weickert
<span title="2020-06-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Compressing piecewise smooth images is important for many data types such as depth maps in 3D videos or optic flow fields for motion compensation.  ...  However, current approaches rely on ad hoc segmentations that lack a clean interpretation in terms of energy minimisation.  ...  This work acted as a blueprint for a series of depth map compression approaches [2] - [4] that rely on the same basic principle.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.05206v2">arXiv:2003.05206v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/txkxqzwhabgpfg7hmq27qaffcu">fatcat:txkxqzwhabgpfg7hmq27qaffcu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200619001634/https://arxiv.org/pdf/2003.05206v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.05206v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Evaluation of Video Coding for Machines without Ground Truth [article]

Kristian Fischer, Markus Hofbauer, Christopher Kuhn, Eckehard Steinbach, André Kaup
<span title="2022-05-13">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Thus, current methods have to either evaluate their codecs on still images or on already compressed data.  ...  To mitigate this problem, we propose an evaluation method based on pseudo ground-truth data from the field of semantic segmentation to the evaluation of video coding for machines.  ...  For instance segmentation, we use Mask R-CNN [30] with the weights from [31] . For object detection with Faster R-CNN, we trained a model similar to [7] on Cityscapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.06519v1">arXiv:2205.06519v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zf6dbeevcjhfpiuo4ntp77ypsy">fatcat:zf6dbeevcjhfpiuo4ntp77ypsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220518091128/https://arxiv.org/pdf/2205.06519v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/09/8a/098ae4b4b1380bfe9a4b06b3a386bd3f4b53a26a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.06519v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Compressing Flow Fields with Edge-aware Homogeneous Diffusion Inpainting [article]

Ferdinand Jost, Pascal Peter, Joachim Weickert
<span title="2020-04-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our paper addresses this problem by proposing the first lossy diffusion-based codec for this purpose. It keeps only a few flow vectors on a coarse grid.  ...  In spite of the fact that efficient compression methods for dense two-dimensional flow fields would be very useful for modern video codecs, hardly any research has been performed in this area so far.  ...  Most modern video codecs such as HEVC [1] use block matching algorithms to compute motion vectors for coarse blocks of pixels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.12263v3">arXiv:1906.12263v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6eukwfqovbamjpypky73fgqzsi">fatcat:6eukwfqovbamjpypky73fgqzsi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200913190714/https://arxiv.org/pdf/1906.12263v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bc/62/bc62d67dd7cc9497326104b8f83c518c829fd9c0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.12263v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SwiftNet: Real-time Video Object Segmentation [article]

Haochen Wang, Xiaolong Jiang, Haibing Ren, Yao Hu, Song Bai
<span title="2021-04-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work we present SwiftNet for real-time semisupervised video object segmentation (one-shot VOS), which reports 77.8% J &F and 70 FPS on DAVIS 2017 validation dataset, leading all present solutions  ...  Spatially, PAM selectively performs memory update and match on dynamic pixels while ignoring the static ones, significantly reducing redundant computations wasted on segmentation-irrelevant pixels.  ...  Given a test video accompanied by its first frame annotated mask, at inference time we frame-by-frame segment the video using SwiftNet.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.04604v2">arXiv:2102.04604v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ecn4dmx3yneg7egxtsokvy67sa">fatcat:ecn4dmx3yneg7egxtsokvy67sa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210213001610/https://arxiv.org/pdf/2102.04604v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/65/03/65035090ee8f28676eeacc70f1e3f3c1f75d1ada.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.04604v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Accelerating Video Object Segmentation with Compressed Video [article]

Kai Xu, Angela Yao
<span title="2022-04-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our approach is flexible and can be added on top of several existing video object segmentation algorithms.  ...  We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream.  ...  This research is supported by the National Research Foundation, Singapore under its NRF Fellowship for AI (NRF-NRFFAI1-2019-0001).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.12192v3">arXiv:2107.12192v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qbw4qaxorvgoffucx4iilhk7g4">fatcat:qbw4qaxorvgoffucx4iilhk7g4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220520093537/https://arxiv.org/pdf/2107.12192v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a2/59/a25955091564eb7ca69123dbea5d9f064851f95a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.12192v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Video Object Segmentation: A Compressed Domain Approach

R.V. Babu, K.R. Ramakrishnan, S.H. Srinivasan
<span title="">2004</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jqw2pm7kwvhchpdxpcm5ryoic4" style="color: black;">IEEE transactions on circuits and systems for video technology (Print)</a> </i> &nbsp;
This paper addresses the problem of extracting video objects from MPEG compressed video. The only cues used for object segmentation are the motion vectors which are sparse in MPEG.  ...  A block-based affine clustering method is proposed for determining the number of appropriate motion models to be used for the EM step and the segmented objects are temporally tracked to obtain the video  ...  The approach taken by the MPEG-4 group in coding of video for multimedia applications relies on the content-based visual data representation of scenes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2004.825536">doi:10.1109/tcsvt.2004.825536</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t4xwnsdcmfg5zhje6vgfi3tvgm">fatcat:t4xwnsdcmfg5zhje6vgfi3tvgm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829165149/http://www.serc.iisc.ernet.in/~venky/Papers/rvb_csvt04.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7b/8e/7b8ec72b6795d7b6b55458df74f4c890ceffc34b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2004.825536"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Novel Object Segmentation Method for Silhouette Tracker in Video Surveillance Application

Tao Luo, Ronald H. Y. Chung, K. P. Chow
<span title="">2014</span> <i title="IEEE"> 2014 International Conference on Computational Science and Computational Intelligence </i> &nbsp;
In this paper, we present a novel block based object mask segmentation method for silhouette tracker initialization.  ...  On one hand, a simple bounding box contains too much irrelevant background objects, while a manually specified mask could provide accurate silhouette but this also requires lots of interactive which greatly  ...  As for block-wise segmentation, it is a natural evolution of block-based video encoding because most, if not all, IP cameras compress video with block-based compression framework such as mpeg2, mpeg4 or  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/csci.2014.24">doi:10.1109/csci.2014.24</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dpkz4ppl65d5vcwtu4kuxcuhje">fatcat:dpkz4ppl65d5vcwtu4kuxcuhje</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171130065938/https://core.ac.uk/download/pdf/38056401.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ea/1c/ea1cbc81cfb10f52e810401973dae7930a8f7bf7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/csci.2014.24"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces [article]

Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner
<span title="2018-03-24">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In fact, distinguishing between original and manipulated video can be a challenge for humans and computers alike, especially when the videos are compressed or have low resolution, as it often happens on  ...  Using our new dataset, we introduce benchmarks for classical image forensic tasks, including classification and segmentation, considering videos compressed at various quality levels.  ...  Forgery segmentation examples on easy-compressed videos. For each frame, we show the heatmaps for the original video (first row) and the manipulated one (second row).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.09179v1">arXiv:1803.09179v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zyvej5n46bc63jhai4ilzfexy4">fatcat:zyvej5n46bc63jhai4ilzfexy4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902125941/https://arxiv.org/pdf/1803.09179v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/69/2a/692aecba13add2b8c1d82db303f5b2ec743ceb44.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.09179v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Hybrid Person Detection and Tracking in H.264/AVC Video Streams

Philipp Wojaczek, Marcus Laumer, Peter Amon, Andreas Hutter, André Kaup
<span title="">2015</span> <i title="SCITEPRESS - Science and and Technology Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tyl5kfigejfehnouax7r3tii24" style="color: black;">Proceedings of the 10th International Conference on Computer Vision Theory and Applications</a> </i> &nbsp;
This results in a coarse binary mask segmenting the frame into foreground and background.  ...  In this paper we present a new hybrid framework for detecting and tracking persons in surveillance video streams compressed according to the H.264/AVC video coding standard.  ...  An algorithm analyzing the compressed video stream is used as a preselection step to provide a binary mask, which segments the regions of an image into foreground and background.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0005296704780485">doi:10.5220/0005296704780485</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/visapp/WojaczekLAHK15.html">dblp:conf/visapp/WojaczekLAHK15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/flxx7ddw7fg5nhzdg4js7fuqv4">fatcat:flxx7ddw7fg5nhzdg4js7fuqv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220191452/http://pdfs.semanticscholar.org/26cd/b9b6d94c1d6c6a01792fee3c176585f594ac.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/26/cd/26cdb9b6d94c1d6c6a01792fee3c176585f594ac.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0005296704780485"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Design of Wireless Vision Sensor Network for Smart Home

Tsung-Han Tsai, Chih-Chi Huang, Chih-Hao Chang, Muhammad Awais Hussain
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
For video analysis, foreground segmentation, object labeling, and object tracking have been performed.  ...  An efficient binary data compression technique has been proposed to compress the information during the labeling process.  ...  the data by using a proper video coding technique.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982438">doi:10.1109/access.2020.2982438</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ty6zsqulynbxxmj7azld5gssz4">fatcat:ty6zsqulynbxxmj7azld5gssz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108085849/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09044291.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e0/79/e07944001829bd139f63bf9ac9cb326819469a73.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982438"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Spatial error concealment: A novel exemplar-based approach using segmentation

Mani Ranjbar, Shohreh Kasaei
<span title="">2009</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fj5ycmjsdvfz7njycwowhlfiwq" style="color: black;">Computers &amp; electrical engineering</a> </i> &nbsp;
For splitting the erroneous block to different patches, a novel context-dependent exemplar-based algorithm based on a previously proposed segmentation method is proposed.  ...  In this paper, the problem of spatial error concealment for real-time applications is addressed. The proposed method can be categorized in exemplar-based error concealment approaches.  ...  Acknowledgement This work was in part supported by a grant from Iran Telecommunication Research Center (ITRC).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.compeleceng.2008.08.002">doi:10.1016/j.compeleceng.2008.08.002</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pthbq4xi5bglbb6p4itaai5a4y">fatcat:pthbq4xi5bglbb6p4itaai5a4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808191502/http://sina.sharif.ac.ir/~skasaei/Papers/Els_08_MR.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f4/05/f405842607d8109898847e35f654730353bd2ba7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.compeleceng.2008.08.002"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 11,033 results