Filters








13,430 Hits in 5.3 sec

Salient Object Detection via Recursive Sparse Representation

Yongjun Zhang, Xiang Wang, Xunwei Xie, Yansheng Li
2018 Remote Sensing  
This paper introduces an efficient unsupervised approach to salient object detection from the perspective of recursive sparse representation.  ...  Object-level saliency detection is an attractive research field which is useful for many content-based computer vision and remote-sensing tasks.  ...  Moreover, there are several proposed methods based on sparse-low rank decomposition [43] [44] [45] , which regard the salient regions as the sparse items, and methods based on sparse representation which  ... 
doi:10.3390/rs10040652 fatcat:bwvyzrlb35bbfko4j5aiv57tfe

Traffic Foreground Detection at Complex Urban Intersections Using a Novel Background Dictionary Learning Model

Qianxia Cao, Zhengwu Wang, Kejun Long, Xinqiang Chen
2021 Journal of Advanced Transportation  
Using the real-world urban traffic videos and the PV video sequences of i -LIDS, we first compare the proposed method with other detection methods based on sparse representation.  ...  In this study, a novel background subtraction algorithm based on sparse representation is proposed to detect the traffic foreground at complex intersections to obtain traffic parameters.  ...  Research Fund of Hunan Provincial Education Department (Grant no. 18B138).  ... 
doi:10.1155/2021/3515512 fatcat:ldojycxkvnfshdavca5pltlpy4

Moving Object Detection Using Sparse Approximation and Sparse Coding Migration

2020 KSII Transactions on Internet and Information Systems  
, this paper presents an object detection algorithm based on sparse approximation recursion and sparse coding migration in subspace.  ...  Combining with dictionary sparse representation, the computational model is established by the recursive formula of sparse approximation with the video sequences taken as subspace sets.  ...  Sparse representation algorithm based on dictionary learning can solve the shortcomings of traditional moving object detection algorithm.  ... 
doi:10.3837/tiis.2020.05.015 fatcat:lzyy3uzypfhszp4jd2id6geaxu

Motion Detection Algorithm for Unmanned Aerial Vehicle Nighttime Surveillance

Huaxin XIAO, Yu LIU, Wei WANG, Maojun ZHANG
2014 IEICE transactions on information and systems  
In consideration of the image noise captured by photoelectric cameras at nighttime, a robust motion detection algorithm based on sparse representation is proposed in this study.  ...  Realistic and synthetic experiments demonstrate the robustness of the proposed approach.  ...  To address this limitation, a motion detection algorithm based on the theory of sparse representation is proposed in this study. The algorithm exhibits stable and robust performance in noisy videos.  ... 
doi:10.1587/transinf.2014edl8129 fatcat:htvsrwk7xjbrdmruwhm73pwbcq

Extract foreground objects based on sparse model of spatiotemporal spectrum

Zhangjian Ji, Weiqiang Wang, Ke Lu
2013 2013 IEEE International Conference on Image Processing  
In this paper, we present a novel foreground object detection method based on the sparse model of the spectrum of spatiotemporal DCT domain, which is robust for high dynamic scenes.  ...  Then, identification of foreground pixels is formulated as the analysis of the sparse solution of an optimization problem, where foreground pixels correspond to an outlier of the sparse model.  ...  transform(LFT) [11] , and we presents a novel foreground object detection scheme based on the sparse model, as well as background update strategy.  ... 
doi:10.1109/icip.2013.6738710 dblp:conf/icip/JiWL13 fatcat:flqjkw6xwrgofmxndxofjsjese

Moving Object Detection Research Based on Background Image Set and Sparse Analysis

Huang Ke
2016 Journal of software engineering  
A moving target detection method is proposed based on the background image set and sparse representation in this stduy.  ...  from input frame by image block analysis method based on sparse representation.  ...  Image block analysis based on sparse representation: Ultra complete base is a set of base, the number of base is larger than dimension of based elements.  ... 
doi:10.3923/jse.2016.66.77 fatcat:mc4mcudyqbe3rk56jjhbliswv4

A Noisy Videos Background Subtraction Algorithm Based on Dictionary Learning

2014 KSII Transactions on Internet and Information Systems  
This paper proposes a background subtraction algorithm based on dictionary learning and sparse coding for handling low light conditions.  ...  The background subtraction is considered as the difference between sparse representations of the current frame and the background model.  ...  coding, sparse representation of the current frame and foreground detection.  ... 
doi:10.3837/tiis.2014.06.008 fatcat:2o7a4accqzgj3hxv5olhvimkv4

Saliency Detection via Dense and Sparse Reconstruction

Xiaohui Li, Huchuan Lu, Lihe Zhang, Xiang Ruan, Ming-Hsuan Yang
2013 2013 IEEE International Conference on Computer Vision  
We apply the Bayes formula to integrate saliency measures based on dense and sparse reconstruction errors.  ...  For each image region, we first compute dense and sparse reconstruction errors. Second, the reconstruction errors are propagated based on the contexts obtained from K-means clustering.  ...  Figure 7(a) shows that the sparse reconstruction error based on background templates achieves better accuracy in detecting salient objects than R-C11 [7] , while the dense one is comparable with it.  ... 
doi:10.1109/iccv.2013.370 dblp:conf/iccv/LiLZRY13 fatcat:ozcw5y34yfh2zftc3v7eojtlnq

RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection [article]

Pei Sun, Weiyue Wang, Yuning Chai, Gamaleldin Elsayed, Alex Bewley, Xiao Zhang, Cristian Sminchisescu, Dragomir Anguelov
2021 arXiv   pre-print
RSN predicts foreground points from range images and applies sparse convolutions on the selected foreground points to detect objects.  ...  As of 11/2020, RSN is ranked first in the WOD leaderboard based on the APH/LEVEL 1 metrics for LiDAR-based pedestrian and vehicle detection, while being several times faster than alternatives.  ...  of methods based on both dense range images and grids.  ... 
arXiv:2106.13365v1 fatcat:dw732pqw4fghrejrv6vgm3vj5m

A Logarithmic X-Ray Imaging Model for Baggage Inspection: Simulation and Object Detection

Domingo Mery, Aggelos K. Katsaggelos
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
This allows the use of linear strategies to superimpose images of threat objects onto X-ray images and the use of sparse representations in order to segment target objects.  ...  Some of them deal with baggage inspection, in which the aim is to detect automatically target objects.  ...  Application: Object detection In this section, we explain how to detect threat objects using a sparse representation based on the model of Section 2.  ... 
doi:10.1109/cvprw.2017.37 dblp:conf/cvpr/MeryK17 fatcat:isg4rnw2n5fzteor5v274fp2ia

Background Subtraction via Robust Dictionary Learning

Cong Zhao, Xiaogang Wang, Wai-Kuen Cham
2011 EURASIP Journal on Image and Video Processing  
We propose a learning-based background subtraction approach based on the theory of sparse representation and dictionary learning.  ...  Our method makes the following two important assumptions: (1) the background of a scene has a sparse linear representation over a learned dictionary; (2) the foreground is "sparse" in the sense that majority  ...  The key idea is based on an important observation that foreground objects not only are sparse but also have grouped pixels, that is, pixels on foreground objects are spatially correlated.  ... 
doi:10.1155/2011/972961 fatcat:47ttw4iqevhpdptsvypxt2xsfa

Learning a sparse, corner-based representation for time-varying background modelling

Qiang Zhu, S. Avidan, Kwang-Ting Cheng
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
Experiments on challenging video clips demonstrate that the proposed method achieves a higher accuracy in detecting the foreground objects than the existing methods.  ...  Experiments on challenging video clips demonstrate that the proposed method achieves a higher accuracy in detecting the foreground objects than the existing methods.  ...  In this paper, we propose a novel modelling technique, which is based on a sparse feature set of detected corners in each video frame.  ... 
doi:10.1109/iccv.2005.134 dblp:conf/iccv/ZhuAC05 fatcat:hexsdms7lzcjpl5mijxfixcbau

Dense and Sparse Reconstruction Error Based Saliency Descriptor

Huchuan Lu, Xiaohui Li, Lihe Zhang, Xiang Ruan, Ming-Hsuan Yang
2016 IEEE Transactions on Image Processing  
Index Terms-Saliency detection, dense/sparse reconstruction error, sparse representation, context-based propagation, region compactness, Bayesian integration.  ...  Experimental results show that the proposed algorithm performs favorably against 24 state-of-the-art methods in terms of precision, recall, and F-measure on three public standard salient object detection  ...  Our saliency map can well suppress the background while uniformly highlight the foreground objects. Fig. 1 . 1 Saliency maps based on dense and sparse reconstruction errors.  ... 
doi:10.1109/tip.2016.2524198 pmid:26915102 fatcat:2as3rulhana4xaf3up7b4dez2e

Real-time 3D object detection from point cloud through foreground segmentation

Bo Wang, Ming Zhu, Ying Lu, Jiarong Wang, Wen Gao, Hua Wei
2021 IEEE Access  
We propose LIDAR-based 3D object detection based on foreground segmentation using a fully sparse convolutional network (FS 2 3D).  ...  Instead of using the anchor-based method, we convert the detection problem into a foreground segmentation problem on a bird's-eye view.  ...  In this paper, we propose a novel 3D detection network, named FS 2 3D (3D object detection based on Foreground Segmentation using Fully Sparse convolutional networks) in which all convolution layers consist  ... 
doi:10.1109/access.2021.3087179 fatcat:rifcjiwyc5dk5a4otyafiqp4yu

Background Subtraction Based on Low-Rank and Structured Sparse Decomposition

Xin Liu, Guoying Zhao, Jiawen Yao, Chun Qi
2015 IEEE Transactions on Image Processing  
Based on these two observations, we first introduce a class of structured sparsity-inducing norms to model moving objects in videos.  ...  Low rank and sparse representation based methods, which make few specific assumptions about the background, have recently attracted wide attention in background modeling.  ...  Background Subtraction Based on Low-Rank and Structured Sparse Decomposition Xin Liu, Guoying Zhao, Senior Member, IEEE, Jiawen Yao, and Chun Qi, Member, IEEE Abstract-Low rank and sparse representation  ... 
doi:10.1109/tip.2015.2419084 pmid:25838523 fatcat:rkeseka66bdbxfhs6cz37oqgla
« Previous Showing results 1 — 15 out of 13,430 results