연구동향 분석

Deep image feature extraction for change detection and stereo vision

Nguyen, Phuoc Tien 2020년

논문상세정보
인용/피인용
' Deep image feature extraction for change detection and stereo vision' 의 주제별 논문영향력
논문영향력 선정 방법
논문영향력 요약
주제
  • Feature extraction
  • change detection
  • deep neural network
  • stereo vision
동일주제 총논문수 논문피인용 총횟수 주제별 논문영향력의 평균
236 0

0.0%

' Deep image feature extraction for change detection and stereo vision' 의 참고문헌

  • ¡±Wallflower : Principles and practice of background maintenance.¡±
    pp . 255- 261 [1999]
  • ¡±Spatio-temporalContext forCodebook-based dynamic background subtraction
    vol . 64 , no . 8 , pp . 739-747 [2010]
  • ¡±Robust online matrix factorization for dynamic background subtraction
    [2017]
  • ¡±Robust and efficient foreground analysis inComplex surveillance videos
    vol . 23 , no . 5 , pp . 967-983 [2012]
  • ¡±Object Tracking Using Background Subtraction and Motion Estimation in MPEG Videos
    [2006]
  • ¡±Neural network approach to background modeling for video object segmentation
    vol . 18 , no . 6 , pp . 1614-1627 [2007]
  • ¡±Multiple human object tracking using background subtraction and shadow removal techniques
    pp . 79-84 . [2010]
  • ¡±Matchnet : Unifying feature and metric learning for patch-based matching
    pp . 3279-3286 . [2015]
  • ¡±Learning fine-grained image similarity with deep ranking
    pp . 1386-1393 . [2014]
  • ¡±Incremental tensor subspace learning and its applications toforeground segmentation and tracking ,
    vol . 91 , no . 3 , pp . 303-327 [2011]
  • ¡±Improving foreground segmentations with probabilistic superpixel markov random fields ,
    pp . 27- 31 [2012]
  • ¡±Discriminative video pattern search for efficient action detection
    vol . 33 , no . 9 , pp . 1728-1743 [2011]
  • ¡±Controlling background subtraction algorithms for robust object detection
    [2009]
  • ¡±A bayesian approach forCamouflaged moving object detection
    vol . PP , no . 99 , pp . 1-1 [2016]
  • ¡±A New Framework for Background Subtraction Using MultipleCues¡±
    pp . 493-506
  • ¡°Very deepConvolutional networks for largescale image recognition
    [2015]
  • ¡°ORB : An efficient alternative to SIFT or SURF ,
    [2011]
  • ¡°Multi-scaleContext aggregation by dilatedConvolutions
    [2016]
  • ¡°Applications of a direct algorithm for the rectification of uncalibrated images
    vol . 160 , no . 1 , pp . 53 ? 71 [2004]
  • stereo and flow estimation
    [2014]
  • [89] V. Nair, G. E. Hinton, Rectified linear units improve restricted boltzmann machines, in: Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML¡¯10, 2010, pp. 807?814.
  • [88] S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, in: ICML, 2015.
  • [87] H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in:CVPR, 2017.
    [2017]
  • [82] S. Gidaris, N. Komodakis, ¡°Detect, replace, refine: Deep structured prediction for pixel wise labeling¡±, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 7187?7196.
  • [80] F. Tombari, S. Mattoccia, L. D. Stefano, E. Addimanda, ¡°Classification and evaluation of cost aggregation methods for stereo correspondence¡±, IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1?8.
  • [78] A. Geiger, M. Roser, R. Urtasun, Efficient large-scale stereo matching, in: R. Kimmel, R. Klette, A. Sugimoto (Eds.),Computer Vision ? ACCV 2010, Springer Berlin Heidelberg, Berlin, Heidelberg, 2011, pp. 25?38.
    pp . 25 ? 38 [2010]
  • [77] H. Hirschmuller, D. Scharstein, Evaluation of cost functions for stereo matching, in: 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp. 1?8.
  • [74] A. Sobral, ¡±BGSLibrary: An opencv c++ background subtraction library,¡± in IX Workshop de Viso Computacional (WVC2013), Rio de Janeiro, Brazil, 2013.
  • [73] P. L. St-Charles and G. A. Bilodeau, ¡±Improving background subtraction using local binary similarity patterns,¡± in IEEE Winter Conference on Applications of Computer Vision, 2014, pp. 509-515.
  • [70] M. Sokolova and G. Lapalme, ¡±A systematic analysis of performance measures for classification tasks,¡± Information Processing and Management, vol. 45, no. 4, pp. 427-437, 2009.
  • [68] A. W. Antoine Vacavant, Thierry Chateau and L. Lequivre, ¡±A benchmark dataset for foreground/background extraction,¡± In ACCV 2012, Workshop: Background Models Challenge, pp. 291-300, 2012.
  • [66] O. Barnich and M. V. Droogenbroeck, ¡±Vibe: A universal background subtraction algorithm for video sequences,¡± IEEE Transactions on Image Processing, vol. 20, no. 6, pp. 1709-1724, 2011.
  • [65] F. Schroff, D. Kalenichenko, and J. Philbin, ¡±Facenet: A unified descriptor for face recognition and clustering,: in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815-823.
  • [62] P. F. Felzenszwalb and D. R. Huttenlocher, ¡±Efficient belief propagation for early vision,¡± in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., vol. 1, 2004, pp. I261-I-268 Vol.1.
  • [60] J. Migdal and W. E. L. Grimson, ¡±Background subtraction using markov thresholds,¡± in Application of Computer Vision, 2005. WACV/MOTIONS 05 Volume 1. Seventh IEEE Workshops on, vol. 2, 2005, pp. 58-65.
  • [58] G. Gemignani and A. Rozza, ¡±A robust approach for the background subtraction based on multi-layered self-organizing maps,¡± IEEE Transactions on Image Processing, vol. 25, no. 11, pp. 5239-5251, 2016.
  • [56] L. Maddalena and A. Petrosino, ¡±A self-organizing approach to background subtraction for visual surveillance applications,¡± IEEE Transactions on Image Processing, vol. 17, no. 7, pp. 1168-1177, 2008.
  • [51] T. S. F. Haines and T. Xiang, ¡±Background subtraction with dirichlet process mixture models,¡± IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 4, pp. 670-683, 2014.
  • [49] Z. Zivkovic, ¡±Improved adaptive gaussian mixture model for background subtraction,¡± in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., vol. 2, 2004, pp. 28-31 Vol.2.
  • [48] P. KaewTraKulPong and R. Bowden, ¡±An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection,¡± Springer 2002, pp. 135-144.
  • [47] C. Stauffer and W. E. L. Grimson, ¡±Adaptive background mixture models for real-time tracking,¡± in Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), vol. 2, 1999, p. 252 Vol. 2.
  • [45] M. Heikkila and M. Pietikainen, ¡±A texture-based method for modeling the background and detecting moving objects,¡± IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 657-662, 2006.
  • [3] B. Herbert and E. Andreas and T. Tinne and V. G. Luc, "Speeded-Up Robust Features (SURF)", Computer Vision and Image Understanding, vol. 110, no.3, pp. 346-359, 2008.
  • [39] Y. Wanga, Z. Luoab, and Pierre-Marc Jodoin, ¡±Interactive deep learning method for segmenting moving objects,¡± Pattern Recognition Letters, pp. 66-75, 2016.
  • [32] D. Navneet and T. Bill, "Histograms of Oriented Gradients for Human Detection,2005 IEEEComputer SocietyConference onComputer Vision and Pattern Recognition, pp. 886-893, 2005.
    pp . 886-893 [2005]
  • [2] D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
  • [28] R. Zabih, J. Woodfill, Non-parametric local transforms for computing visual correspondence, in: Proceedings of the Third European Conference on Computer Vision (Vol. II), ECCV ¡¯94, 1994, pp. 151?158.
  • [25] A. Seki, M. Pollefeys, Sgm-nets: Semi-global matching with neural networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6640?6649.
  • [1] C. Harris and M. Stephens, "A combined corner and edge detector,¡± in In Proc. of Fourth Alvey Vision Conference, 1988, pp. 147-151.
  • V. Vanhoucke and A. Rabinovich , Going deeper with convolutions
    [2015]
  • Traditional and recent approaches in background modeling for foreground detection : An overview
    vol . 1112 , pp . 31- 66 [2014]
  • Subsense : A universal change detection method with local adaptive sensitivity
    vol . 24 , no . 1 , pp . 359-373 [2015]
  • Stereo matching by training a convolutional neural network to compare image patches
    17 [2016]
  • Stereo Processing by Semiglobal Matching and Mutual Information
    30 ( 2 ) ( [2008]
  • Static and moving object detection using flux tensor with split Gaussian models
    pp . 420- 424 [2014]
  • Stacked hourglass networks for human pose estimation , in : Computer Vision ? ECCV 2016
    pp . 483 ? 499 [2016]
  • Spatial pyramid pooling in deepConvolutional networks for visual recognition , in :Computer Vision ? ECCV 2014
    pp . 346 ? 361 [2014]
  • Segnet : A deepConvolutional encoder-decoder architecture for image segmentation2481 ? 2495
    39 ( 12 ) ( [2017]
  • SIFT MeetsCNN : A Decade Survey of Instance Retrieval ,
    [2016]
  • Real-time foreground-background segmentation usingCodebook model
    vol . 11 , no . 3 , pp . 172-185 , [2005]
  • On building an accurate stereo matching system on graphics hardware
    pp . 467 ? 474 [2011]
  • Object Scene Flow for Autonomous Vehicles
    [2015]
  • Learning to Compare Image Patches via Convolutional Neural Networks
    [2015]
  • Learning deconvolution network for semantic segmentation
    [2015]
  • Learning Spatio-Temporal Representations for Action Recognition : A Genetic Programming Approach
    vol . 46 , no . 1 , pp.158-170 [2016]
  • Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
    pp . 1183-1192 [2016]
  • L2-Net : Deep Learning of Discriminative Patch Descriptor in Euclidean Space
    [2017]
  • Improved stereo matching with constant highway networks and reflective loss
  • ImagenetClassification with deepConvolutional neural networks
    [2012]
  • Fully Convolutional Networks for Semantic Segmentation
    vol . 39 , no . 4 , pp . 640-651 [2017]
  • Features from Accelerated Segment Test ( FAST )
    [2011]
  • Feature learning for image classification via multi objective genetic programmming
    vol . 25 , no . 7 , pp.1359-1371 [2014]
  • Fast r-cnn , in : Proceedings of the 2015 IEEE International Conference on Computer Vision ( ICCV ) , ICCV ¡¯15
    pp . 1440 ? 1448 . doi:10.1109/ICCV.2015.169 [2015]
  • Fast Background Subtraction Based on a Multilayer Codebook Model for Moving Object Detection
    vol . 23 , no . 10 , pp . 1809-1821 [2013]
  • End-to-end training of hybridCnn-crf models for stereo , 2017 IEEEConference onComputer Vision and Pattern Recognition (CVPR ) 1456 ? 1465
  • End-to-end training of hybrid cnn-crf models for stereo , 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ) ( 2017 ) 1456 ? 1465
  • End-to-end learning of geometry and context for deep stereo regression
    pp . 66 ? 75 , [2017]
  • Encoder-decoder with atrous separable convolution for semantic image segmentation , in : Computer Vision ? ECCV 2018
    pp . 833 ? 851 [2018]
  • Efficient deep learning for stereo matching
    [2016]
  • Efficient Non parametric Kernel Density Estimation for Real-time Computer Vision
    [2002]
  • Dynamic background modeling and subtraction using spatio-temporal local binary patterns ,
    pp . 1556- 1559 . [2008]
  • Discriminative Learning of Deep Convolutional Feature Point Descriptors
    [2015]
  • Delving deep into rectifiers : Surpassing human-level performance on imagenet classification
    vol . abs/1502.01852 , [2015]
  • Deep residual learning for image recognition
    pp . 770 ? 778 .
  • Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
    vol . 39 , pp.1089-1102 [2017]
  • Cross-Based Local Stereo Matching Using Orthogonal Integral Images ,
    19 ( 7 ) ( [2009]
  • Computing visual correspondence with occlusions using graph cuts
    Vol . 2 , 2001 , pp . 508 ? 515 vol.2 [2001]
  • Cbmv : A coalesced bidirectional matching volume for disparity estimation
    [2018]
  • CDnet 2014 : An expanded change detection benchmark dataset
    pp . 393-400 . [2014]
  • Brief : Binary robust independent elementary features , in : K. Daniilidis , P. Maragos , N. Paragios ( Eds . ) , Computer Vision ? ECCV 2010
    pp . 778 ? 792 [2010]
  • Boosting Binary Keypoint Descriptors
    [2013]
  • Background segmentation with feedback : The pixel-based adaptive segmenter
    pp . 38- 43 . [2012]
  • A. H. K. S. Wah , and W.-Y . Yau , ¡±Robust human detection within a highly dynamic aquatic environment in real time
    vol . 15 , no . 6 , pp . 1583-1600 [2006]
  • A taxonomy and evaluation of dense two-frame stereo correspondence algorithms ,
    47 ( 1-3 ) ( [2002]
  • A large dataset to train convolutional networks for disparity , optical flow , and scene flow estimation
    [2016]
  • A deep visual correspondence embedding model for stereo matching costs
    [2014]
  • A Method for Stochastic Optimization ''