921 Hits in 5.1 sec

Background Subtraction Based on Low-Rank and Structured Sparse Decomposition

Xin Liu, Guoying Zhao, Jiawen Yao, Chun Qi
2015 IEEE Transactions on Image Processing  
Next, in virtue of adaptive parameters for dynamic videos, we propose a saliency measurement to dynamically estimate the support of the foreground.  ...  Low rank and sparse representation based methods, which make few specific assumptions about the background, have recently attracted wide attention in background modeling.  ...  After the decomposition, many foreground candidates will be detected and then a motion saliency map will be used to remove background motion and weigh the motion salient groups.  ... 
doi:10.1109/tip.2015.2419084 pmid:25838523 fatcat:rkeseka66bdbxfhs6cz37oqgla

Residual of Resonant SVD as Salient Feature [chapter]

Dmitry Chetverikov
2009 Lecture Notes in Computer Science  
The residual can be used to obtain saliency maps for solving challenging tasks of image and video processing.  ...  Computer vision approaches to saliency are based, among others, on uniqueness [1], local complexity [2], distinctiveness [3, 4] , spectral variation [5] , and irregularity [6] .  ...  Different salient image and video features have been proposed and successfully used in image and video retrieval, stereo vision, attention control, motion tracking, object and event detection and categorisation  ... 
doi:10.1007/978-3-642-02345-3_15 fatcat:l74vyzflgvg5bejfqoyhxwon5m

Video Saliency Detection via Spatial-Temporal Fusion and Low-Rank Coherency Diffusion

Chenglizhao Chen, Shuai Li, Yongguang Wang, Hong Qin, Aimin Hao
2017 IEEE Transactions on Image Processing  
This paper advocates a novel video saliency detection method based on the spatial-temporal saliency fusion and low-rank coherency guided saliency diffusion.  ...  First, the original long-term video sequence is equally segmented into many shortterm frame batches, and the motion clues of the individual video batch are integrated and diffused temporally to facilitate  ...  low-rank analysis based salient motion detection methods) and non-stationary videos.  ... 
doi:10.1109/tip.2017.2670143 pmid:28221994 fatcat:uugi36rpc5ey5bbbszrvxgyfby

Motion detection and tracking using space-time interest points

I. Bellamine, H. Tairi
2013 2013 ACS International Conference on Computer Systems and Applications (AICCSA)  
For a good detection of moving objects, we propose to apply the algorithm of the detection of spatiotemporal interest points on both components of the decomposition which is based on a partial differential  ...  Proposed results are obtained from very different types of videos, namely sport videos and animation movies.  ...  INTRODUCTION The motion analysis is a very active research area, which includes a number of problems: motion detection, motion estimation (optical flow), segmentation, tracking and human action recognition  ... 
doi:10.1109/aiccsa.2013.6616419 dblp:conf/aiccsa/BellamineT13 fatcat:zu7u4mghsjcu7bgu6ogjwsnqce

Spatiotemporal saliency for video classification

Konstantinos Rapantzikos, Nicolas Tsapatsoulis, Yannis Avrithis, Stefanos Kollias
2009 Signal processing. Image communication  
In this paper, we propose and elaborate on a saliency detection model that treats a video sequence as a spatiotemporal volume and generates a local saliency measure for each visual unit (voxel).  ...  This framework consists of a series of experiments that shows the effect of saliency in classification performance and let us draw conclusions on how well the detected salient regions represent the visual  ...  Fig. 6 . 6 Saliency-based classification: (a) based on foreground/background detection; and (b) based on 41 salient regions.  ... 
doi:10.1016/j.image.2009.03.002 fatcat:nj3aewdllzejramdeqwwiwv6mq

Review of Visual Saliency Detection with Comprehensive Information [article]

Runmin Cong, Jianjun Lei, Huazhu Fu, Ming-Ming Cheng, Weisi Lin, and Qingming Huang
2018 arXiv   pre-print
The goal of video saliency detection model is to locate the motion-related salient object in video sequences, which considers the motion cue and spatiotemporal constraint jointly.  ...  RGBD saliency detection, co-saliency detection, or video saliency detection.  ...  Thirdly, some commonly used visual priors in saliency detection may no longer be valid in video due to camera and object motion, such as background prior.  ... 
arXiv:1803.03391v2 fatcat:htcmhlo32jhczehvvq6nmgzwam

Human Action Recognition across Datasets by Foreground-Weighted Histogram Decomposition

Waqas Sultani, Imran Saleemi
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
We then propose a new process to obtain a measure of confidence in each pixel of the video being a foreground region, using motion, appearance, and saliency together in a 3D MRF based framework.  ...  We also propose multiple ways to exploit the foreground confidence: to improve bag-of-words vocabulary, histogram representation of a video, and a novel histogram decomposition based representation and  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA  ... 
doi:10.1109/cvpr.2014.103 dblp:conf/cvpr/SultaniS14 fatcat:cxuyyubgdrf55kspi4lb3liyzu

Global motion compensated visual attention-based video watermarking

Matthew Oakes, Deepayan Bhowmik, Charith Abhayaratne
2016 Journal of Electronic Imaging (JEI)  
This paper proposes a unique video watermarking algorithm that offers a fine balance between imperceptibility and robustness using motion compensated wavelet-based visual attention model (VAM).  ...  The proposed VAM outperforms the state-of-the-art video visual attention methods in joint saliency detection and low computational complexity performance.  ...  Acknowledgments We acknowledge the support of the UK Engineering and Physical Research Council (EPSRC), through a Dorothy Hodgkin Postgraduate Award and a Doctoral Training Award at the University of Sheffield  ... 
doi:10.1117/1.jei.25.6.061624 fatcat:q7gic5pm5rerjls4elofkwuu5q

Improved Deer Hunting Optimization Algorithm for Video- based Salient Object Detection

Puttaswamy M R
2020 Multimedia Research  
Subsequently, the outcomes attained from the contourlet mapping and saliency mapping are combined by exploiting the random coefficients in order to attain the last consequence which is used to recognize  ...  Moreover, the developed Improved-DHO is used to select the optimal coefficients in order to detect salient objects.  ...  In the saliency detection community, it is classified into video and image salient object detection using the input of saliency models.  ... 
doi:10.46253/ fatcat:h2ugjm6glfaoxaya4s5dkx5n5a


2014 Journal of Computer Science  
For a good detection of moving objects, we propose to apply the algorithm of the detection of spatiotemporal interest points on both components of the decomposition which is based on a Partial Differential  ...  Proposed results are obtained from very different types of videos, namely sport videos and animation movies.  ...  In recent years, several models based on total variation, which are inspired by the ROF model, were created (Aujol, 2004; Gilles, 2006) .  ... 
doi:10.3844/jcssp.2014.828.839 fatcat:nfcggomui5dylchjwgxyuw63ny

Detecting Spatiotemporal Structure Boundaries: Beyond Motion Discontinuities [chapter]

Konstantinos G. Derpanis, Richard P. Wildes
2010 Lecture Notes in Computer Science  
The detection of motion boundaries has been and remains a longstanding challenge in computer vision.  ...  Toward this end, a novel representation and method for detecting these boundaries in raw image sequence data are presented.  ...  This research was supported in part by NSERC and Precarn. F. Estrada provided software for computing precision/recall curves and helpful discussion.  ... 
doi:10.1007/978-3-642-12304-7_29 fatcat:xanctvu2dnhcdbbuodqmrltbfy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 5596-5611 A Signal Adaptive Prediction Filter for Video Coding Using Directional Total Variation: Mathematical Framework and Parameter Selection.  ...  Mustafa, A., +, TIP 2020 1711-1724 Improved Saliency Detection in RGB-D Images Using Two-Phase Depth Estimation and Selective Deep Fusion.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Weakly Supervised Salient Object Detection with Spatiotemporal Cascade Neural Networks

Yi Tang, Wenbin Zou, Zhi Jin, Yuhuan Chen, Yang Hua, Xia Li
2018 IEEE transactions on circuits and systems for video technology (Print)  
This paper proposes a novel weakly supervised approach to salient object detection in a video, which can learn a robust saliency prediction model by using very limited manually labeled data and a large  ...  and temporal cues to lead the optimal video saliency prediction.  ...  The authors would like to thank the anonymous reviewers and the Associate Editor for their insightful comments and suggestions, which are greatly helpful for improving the quality of this paper.  ... 
doi:10.1109/tcsvt.2018.2859773 fatcat:l2m646l5m5a6bo4f2dgevffwlm

Anomaly detection in crowded scenes

Vijay Mahadevan, Weixin Li, Viral Bhalodia, Nuno Vasconcelos
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Temporal anomalies are equated to events of low-probability, while spatial anomalies are handled using discriminant saliency.  ...  and the abilities to detect 2) temporal, and 3) spatial abnormalities.  ...  Mahadevan and Vasconcelos [20] proposed the use of DTs with discriminant saliency in the context of background subtraction [20] .  ... 
doi:10.1109/cvpr.2010.5539872 dblp:conf/cvpr/MahadevanLBV10 fatcat:gm55i2kv4rbehpvujfqajhrxoi

Moving Object Detection under a Moving Camera via Background Orientation Reconstruction

Wenlong Zhang, Xiaoliang Sun, Qifeng Yu
2020 Sensors  
It can highlight the motion saliency of the moving objects and improve the consistency within the object and background region simultaneously.  ...  Then, the motion saliency map is calculated by the difference between the original and the reconstructed orientation field.  ...  Usually, the moving object is detected based on the motion difference with the background, where the motion of the background and object are estimated by calculating the optical flow between adjacent frames  ... 
doi:10.3390/s20113103 pmid:32486336 pmcid:PMC7309005 fatcat:5firji57ojahvnoxvlg2k6g7dy
« Previous Showing results 1 — 15 out of 921 results