Filters








8,872 Hits in 4.2 sec

Unsupervised Feature Learning for RGB-D Image Classification [chapter]

I-Hong Jhuo, Shenghua Gao, Liansheng Zhuang, D. T. Lee, Yi Ma
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Experimental results on three publicly available RGB-D datasets demonstrate that the proposed method consistently outperforms the state-of-the-art conventional, manually designed RGB-D image representation  ...  Motivated by the success of Deep Neural Networks in computer vision, we propose a deep Regularized Reconstruction Independent Component Analysis network (R 2 ICA) for RGB-D image classification.  ...  It is worth noting that the indoor segmentation scene dataset contains various objects in one scene, this makes the dataset very challenging to scene classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16865-4_18">doi:10.1007/978-3-319-16865-4_18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zukahvjhenfsnfson4y3bpbrem">fatcat:zukahvjhenfsnfson4y3bpbrem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829061659/http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ACCV_2014/pages/PDF/128.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/2a/34/2a34389c700cd3638a6f8c5df257cce955bf28aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16865-4_18"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Exploiting local and global patch rarities for saliency detection

A. Borji, L. Itti
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2012 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
The second one is based on our observation that for different images, one of the RGB and Lab color spaces outperforms the other in saliency detection.  ...  We introduce a saliency model based on two key ideas. The first one is considering local and global image patch rarities as two complementary processes.  ...  Note that the global operator is not affected by this parameter.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2012.6247711">doi:10.1109/cvpr.2012.6247711</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/BorjiI12.html">dblp:conf/cvpr/BorjiI12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ytcw2clah5e6hebkg2njgttl7q">fatcat:ytcw2clah5e6hebkg2njgttl7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130108025155/http://ilab.usc.edu/publications/doc/Borji_Itti12cvpr.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/69/56/6956e3aa1d2f1b65e5397df2711ba94899879e1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2012.6247711"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Occlusion Edge Detection in RGB-D Frames using Deep Convolutional Networks [article]

Soumik Sarkar, Vivek Venugopalan, Kishore Reddy, Michael Giering, Julian Ryde, Navdeep Jaitly
<span title="2015-07-08">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We trained a deep convolutional neural network (CNN) to identify occlusion edges in images and videos with both RGB-D and RGB inputs.  ...  Occlusion edges in images which correspond to range discontinuity in the scene from the point of view of the observer are an important prerequisite for many vision and mobile robot tasks.  ...  RGB-D and RGB frames lie on the two ends of the spectrum of input data information content.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.7007v3">arXiv:1412.7007v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4hqjh3vot5b5hgsxy6npzhoc54">fatcat:4hqjh3vot5b5hgsxy6npzhoc54</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015033903/https://arxiv.org/pdf/1412.7007v3.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/28/d3/28d34408f934e5e228cf821cf5f6f9196dacd161.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.7007v3" 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>

Covid-19 Images and Video Denoising Algorithms Based on Convolutional Neural Network CNNs

Zoubeida Messali, Salsabil SAAD SAOUD, Amira LAMRECHE
<span title="2021-06-30">2021</span> <i title="Signals and Systems Laboratory, University Mhamed Bougara of Boumerdes"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/szdvrzv5ffdolbh7ay6fcxrzuu" style="color: black;">Algerian journal of signals and systems</a> </i> &nbsp;
Much attention is given to the latest DVDNet and FastDVDNet algorithms, which are based on CNN.  ...  Two assessments are adapted; the first is a qualitative comparison based on the qualityof the images / videos and the second is quantitative in terms of PSNR and running time criteria.  ...  We should note that collaborative filtering consists on using several types of filtering for the same algorithm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51485/ajss.v6i2.126">doi:10.51485/ajss.v6i2.126</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/shuzatdhtjcg5aj7pp3tqarnpa">fatcat:shuzatdhtjcg5aj7pp3tqarnpa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220618132722/https://ajss.dz/index.php/ajss/article/download/126/118" 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/d0/31/d031929e893853e3adf942a4911fedb704bce76c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51485/ajss.v6i2.126"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

AN EFFICIENT WEED DETECTION PROCEDURE USING LOW-COST UAV IMAGERY SYSTEM FOR PRECISION AGRICULTURE APPLICATIONS

M. Hassanein, N. El-Sheimy
<span title="2018-09-26">2018</span> <i title="Copernicus GmbH"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/i74shj7anreaxjo327fokng66m" style="color: black;">The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences</a> </i> &nbsp;
The achieved results showed the potential of the proposed methodology to use low-cost UAV imagery system equipped with low-cost RGB imagery sensor for detecting weed patches in different cropped agriculture  ...  The proposed methodology adopts detecting the high-density vegetation spots as indication for weed patches spots.  ...  Moreover, the authors would like to thank Darren Nikkel from Nikkel farms for his help through providing the needed fields that were used for the data acquisition process.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5194/isprs-archives-xlii-1-181-2018">doi:10.5194/isprs-archives-xlii-1-181-2018</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wgdikovrlfhuvk762vkeu4utku">fatcat:wgdikovrlfhuvk762vkeu4utku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190428021349/https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-1/181/2018/isprs-archives-XLII-1-181-2018.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/66/df/66df56515f5dee467b1d39f6b3c8af7f1e2a3d0e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5194/isprs-archives-xlii-1-181-2018"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Color Image Classification via Quaternion Principal Component Analysis Network [article]

Rui Zeng, Jiasong Wu, Zhuhong Shao, Yang Chen, Lotfi Senhadji, Huazhong Shu
<span title="2015-03-05">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The Principal Component Analysis Network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases.  ...  Experiments conducted on different color image datasets such as Caltech-101, UC Merced Land Use, Georgia Tech face and CURet have revealed that the proposed QPCANet achieves higher classification accuracy  ...  Note that with the increase of patch size, the accuracy of all networks decreases. The best performance for various patch sizes is highlighted in bold.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1503.01657v1">arXiv:1503.01657v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qjhjeqwdbfh4royazd6mukdlq4">fatcat:qjhjeqwdbfh4royazd6mukdlq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829231416/https://arxiv.org/ftp/arxiv/papers/1503/1503.01657.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/c2/9e/c29e8ee18d4b753b360fea58771a9621a1bc5978.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1503.01657v1" 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>

Using RGB displays to portray color realistic imagery to animal eyes

Cynthia Tedore, Sönke Johnsen
<span title="2016-06-30">2016</span> <i title="Oxford University Press (OUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/regvbsjcirddvel5cpnahcnq4q" style="color: black;">Current Zoology</a> </i> &nbsp;
i.e., a spectrometer), and data on the spectral sensitivities of the animal's photoreceptor classes.  ...  The perceptual experience of an animal looking at an RGB display of imagery designed for humans is likely to poorly represent an animal's experience of the same stimulus in the real world.  ...  Finally, the authors thank Nick Brandley, Eleanor Caves, Almut Kelber, Olle Lind, Dan Speiser, Katie Thomas, and 2 anonymous reviewers for insightful comments on the manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/cz/zow076">doi:10.1093/cz/zow076</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29491960">pmid:29491960</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5804149/">pmcid:PMC5804149</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sz4flcjpnfbjzdqr44srucahou">fatcat:sz4flcjpnfbjzdqr44srucahou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190216071316/http://pdfs.semanticscholar.org/01b3/1872f2df4731928bfdfedf5359534808eb3f.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/01/b3/01b31872f2df4731928bfdfedf5359534808eb3f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/cz/zow076"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> oup.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5804149" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

How Are LED Illumination Based Multispectral Imaging Systems Influenced by Different Factors? [chapter]

Raju Shrestha, Jon Yngve Hardeberg
<span title="">2014</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We carry out simulation experiments using monochrome and RGB camera based LEDMSI systems, under the influence of different amounts of noise and practical constraints on the number of different color LEDs  ...  The experiments confirm the influence of these factors on the performance of a LEDMSI system.  ...  Sixty two patches of the MCCDC have been used as the training data set; and one hundred and twenty-two patches remained after omitting the outer surrounding achromatic patches, multiple white patches at  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07998-1_8">doi:10.1007/978-3-319-07998-1_8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ystdh2hgunfm3dhqev7hco6zdm">fatcat:ystdh2hgunfm3dhqev7hco6zdm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501121717/https://link.springer.com/content/pdf/10.1007%2F978-3-319-07998-1_8.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/77/8f/778f89fb6b5e1909908cd10adad2261727130b87.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07998-1_8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Learning hierarchical 3D kernel descriptors for RGB-D action recognition

Yu Kong, Behnam Satarboroujeni, Yun Fu
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dsarpzh6wfgadnyijwv5l6gh2i" style="color: black;">Computer Vision and Image Understanding</a> </i> &nbsp;
on 3D patches into a powerful structure which can effectively describe the scene.  ...  Through extensive experiments we demonstrate the proposed approach achieves superior performance on four standard RGB-D sequences benchmarks.  ...  Acknowledgments This research is supported in part by the NSF CNS award 1314484, ONR award N00014-12-1-1028, ONR Young Investigator Award N00014-14-1-0484, NPS award N00244-15-1-0041, and U.S.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cviu.2015.10.001">doi:10.1016/j.cviu.2015.10.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4pwbburyfvapvorl7ku7g7oubq">fatcat:4pwbburyfvapvorl7ku7g7oubq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190415223118/https://core.ac.uk/download/pdf/81224227.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/c5/85/c5855017bee399d9568a3d00c4642e3439fc6d68.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cviu.2015.10.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Adaptive Direct RGB-D Registration and Mapping for Large Motions [chapter]

Renato Martins, Eduardo Fernandez-Moral, Patrick Rives
<span title="">2017</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
First, we propose an activation function based on the conditioning of the RGB and ICP point-to-plane error terms.  ...  Finally, our method is validated in different RGB-D spherical datasets, including both indoor and outdoor real sequences and using the KITTI VO/SLAM benchmark dataset.  ...  The authors thank Josh Picard and Paolo Salaris for the discussions/proof reading of the manuscript, and the reviewers for their thoughtful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-54190-7_12">doi:10.1007/978-3-319-54190-7_12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gv33quoevzhptix4tivlfmir7q">fatcat:gv33quoevzhptix4tivlfmir7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220005428/http://pdfs.semanticscholar.org/218a/45f6f07dcad4fbc952b33ccbad542f7f956a.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/21/8a/218a45f6f07dcad4fbc952b33ccbad542f7f956a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-54190-7_12"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

StablePose: Learning 6D Object Poses from Geometrically Stable Patches [article]

Yifei Shi, Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu
<span title="2021-03-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from observed 3D point clouds  ...  We train a deep neural network to regress 6D object pose based on geometrically stable patch groups via learning both intra-patch geometric features and inter-patch contextual features.  ...  Acknowledgements We thank the anonymous reviewers for their valuable comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09334v2">arXiv:2102.09334v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qq7rf6hxirc77ebyytekskz5iu">fatcat:qq7rf6hxirc77ebyytekskz5iu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210331070223/https://arxiv.org/pdf/2102.09334v2.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/1c/51/1c5185175409593a77a37556f6ccccae2de36f6a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09334v2" 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>

21/2 D Scene Reconstruction of Indoor Scenes from Single RGB-D Images [chapter]

Natalia Neverova, Damien Muselet, Alain Trémeau
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The main novelty of our proposal is that it allows estimating geometry of a whole environment from a single Kinect RGB-D image and does not rely on complex optimization methods.  ...  Using the Manhattan world assumption we propose a new method for global 2 1 /2D geometry estimation of indoor environments from single low quality RGB-D images.  ...  One of the most illustrative examples in outdoor environments is the concept of autonomously driving cars.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-36700-7_22">doi:10.1007/978-3-642-36700-7_22</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kl4zq5u3wbe5tg33kg4k4cm6ia">fatcat:kl4zq5u3wbe5tg33kg4k4cm6ia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200709090724/https://liris.cnrs.fr/Documents/Liris-5954.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/b1/dd/b1dd159ddae9fbae70e7c25d76fd0b3b73569fa0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-36700-7_22"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Fast depth edge detection and edge based RGB-D SLAM

Laurie Bose, Arthur Richards
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nytnrt3gtzbixld5r6a4talbky" style="color: black;">2016 IEEE International Conference on Robotics and Automation (ICRA)</a> </i> &nbsp;
Full terms of use are available: Abstract-This paper presents a method of occluding depth edge-detection targeted towards RGB-D video streams and explores the use of these and other edge features in RGB-D  ...  Pixels belonging to both the depth and colour edges of an RGB-D image can be back projected using the depth component to form 3D point clouds of edge points.  ...  It is important to note that we reject all RGB edge pixels located in close proximity to occluding depth edges in the corresponding depth image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icra.2016.7487265">doi:10.1109/icra.2016.7487265</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icra/BoseR16.html">dblp:conf/icra/BoseR16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/boqlwissk5a4nbilhojry5zqxu">fatcat:boqlwissk5a4nbilhojry5zqxu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719204903/https://research-information.bristol.ac.uk/ws/files/96325084/Bose_L_Fast_Depth_Edge_Detection_and_Edge_Based_RGB_D_SLAM.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/d7/f7/d7f7dba8e2a6d488de85df79b403b1d625a4d06d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icra.2016.7487265"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning Effective RGB-D Representations for Scene Recognition

Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen
<span title="">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
Our approach obtains state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.  ...  Focusing on this scenario, we introduce the ISIA RGB-D video dataset to evaluate RGB-D scene recognition with videos.  ...  Note that, as in the case of images, the depth CNN is pretrained with patches while the RGB CNN is pretrained using a Places-CNN.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2872629">doi:10.1109/tip.2018.2872629</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30281448">pmid:30281448</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lnhv5g46s5dpngmstriivjncgy">fatcat:lnhv5g46s5dpngmstriivjncgy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824105951/https://arxiv.org/pdf/1809.06269v1.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/ac/d6/acd6ff8d8a81eb838f7f6025d0ce5053671e27ca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2872629"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Study on the Use of a Binary Local Descriptor and Color Extensions of Local Descriptors for Video Concept Detection [chapter]

Foteini Markatopoulou, Nikiforos Pittaras, Olga Papadopoulou, Vasileios Mezaris, Ioannis Patras
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
in the task of video concept detection. 2) Based on a previously proposed paradigm for introducing color extensions of SIFT, we define in the same way color extensions for two other non-binary or binary  ...  We evaluate the proposed techniques on the dataset of the 2013 Semantic Indexing Task of TRECVID.  ...  Acknowledgements This work was supported by the European Commission under contracts FP7-287911 LinkedTV and FP7-600826 ForgetIT.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-14445-0_25">doi:10.1007/978-3-319-14445-0_25</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ehor6wooj5h3tn6ekiedsarkda">fatcat:ehor6wooj5h3tn6ekiedsarkda</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830030800/http://www.iti.gr/~bmezaris/publications/mmm15_preprint.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/f0/65/f065eead8b606c535c6e6215f654a1e977a82ab6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-14445-0_25"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 8,872 results