Results 1  10
of
24
Residual reconstruction for blockbased compressed sensing of video
 in Proceedings of the Data Compression Conference
, 2011
"... A simple blockbased compressedsensing reconstruction for still images is adapted to video. Incorporating reconstruction from a residual arising from motion estimation and compensation, the proposed technique alternatively reconstructs frames of the video sequence and their corresponding motion fie ..."
Abstract

Cited by 14 (3 self)
 Add to MetaCart
(Show Context)
A simple blockbased compressedsensing reconstruction for still images is adapted to video. Incorporating reconstruction from a residual arising from motion estimation and compensation, the proposed technique alternatively reconstructs frames of the video sequence and their corresponding motion fields in an iterative fashion. Experimental results reveal that the proposed technique achieves significantly higher quality than a straightforward reconstruction that applies a stillimage reconstruction independently frame by frame; a 3D reconstruction that exploits temporal correlation between frames merely in the form of a motionagnostic 3D transform; and a similar, yet noniterative, motioncompensated residual reconstruction.
CompressedSensing Recovery of Images and Video Using Multihypothesis Predictions
 Proceedings of the 45 th Asilomar Conference on Signals, Systems, and Computers
, 2011
"... Abstract—Compressedsensing reconstruction of still images and video sequences driven by multihypothesis predictions is considered. Specifically, for still images, multiple predictions drawn for an image block are made from spatially surrounding blocks within an initial nonpredicted reconstruction. ..."
Abstract

Cited by 8 (5 self)
 Add to MetaCart
(Show Context)
Abstract—Compressedsensing reconstruction of still images and video sequences driven by multihypothesis predictions is considered. Specifically, for still images, multiple predictions drawn for an image block are made from spatially surrounding blocks within an initial nonpredicted reconstruction. For video, multihypothesis predictions of the current frame are generated from one or more previously reconstructed reference frames. In each case, the predictions are used to generate a residual in the domain of the compressedsensing random projections. This residual being typically more compressible than the original signal leads to improved reconstruction quality. To appropriately weight the hypothesis predictions, a Tikhonov regularization to an illposed leastsquares optimization is proposed. Experimental results demonstrate that the proposed reconstructions outperform alternative strategies not employing multihypothesis predictions. I.
Robust face recognition using locally adaptive sparse representation
 in Proc. IEEE Intl. Conf. Image Processing, Hong Kong
, 2011
"... This paper presents a blockbased facerecognition algorithm based on a sparse linearregression subspace model via locally adaptive dictionary constructed from past observable data (training samples). The local features of the algorithm provide an immediate benefit – the increase in robustness leve ..."
Abstract

Cited by 7 (3 self)
 Add to MetaCart
(Show Context)
This paper presents a blockbased facerecognition algorithm based on a sparse linearregression subspace model via locally adaptive dictionary constructed from past observable data (training samples). The local features of the algorithm provide an immediate benefit – the increase in robustness level to various registration errors. Our proposed approach is inspired by the way human beings often compare faces when presented with a tough decision: we analyze a series of local discriminative features (do the eyes match? how about the nose? what about the chin?...) and then make the final classification decision based on the fusion of local recognition results. In other words, our algorithm attempts to represent a block in an incoming test image as a linear combination of only a few atoms in a dictionary consisting of neighboring blocks in the same region across all training samples. The results of a series of these sparse local representations are used directly for recognition via either maximum likelihood fusion or a simple democratic majority voting scheme. Simulation results on standard face databases demonstrate the effectiveness of the proposed algorithm in the presence of multiple misregistration errors such as translation, rotation, and scaling. 1.
DICTIONARY LEARNINGBASED DISTRIBUTED COMPRESSIVE VIDEO SENSING +
"... We address an important issue of fully lowcost and lowcomplex video compression for use in resourceextremely limited sensors/devices. Conventional motion estimationbased video compression or distributed video coding (DVC) techniques all rely on the highcost mechanism, namely, sensing/sampling a ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
(Show Context)
We address an important issue of fully lowcost and lowcomplex video compression for use in resourceextremely limited sensors/devices. Conventional motion estimationbased video compression or distributed video coding (DVC) techniques all rely on the highcost mechanism, namely, sensing/sampling and compression are disjointedly performed, resulting in unnecessary consumption of resources. That is, most acquired raw video data will be discarded in the (possibly) complex compression stage. In this paper, we propose a dictionary learningbased distributed compressive video sensing (DCVS) framework to “directly” acquire compressed video data. Embedded in the compressive sensing (CS)based singlepixel camera architecture, DCVS can compressively sense each video frame in a distributed manner. At DCVS decoder, video reconstruction can be formulated as an l 1
A Tutorial on Encoding and Wireless Transmission of Compressively Sampled Videos
 IEEE Comm. Surveys and Tutorials
"... Abstract—Compressed sensing (CS) has emerged as a promising technique to jointly sense and compress sparse signals. One of the most promising applications of CS is compressive imaging. Leveraging the fact that images can be represented as approximately sparse signals in a transformed domain, images ..."
Abstract

Cited by 6 (4 self)
 Add to MetaCart
(Show Context)
Abstract—Compressed sensing (CS) has emerged as a promising technique to jointly sense and compress sparse signals. One of the most promising applications of CS is compressive imaging. Leveraging the fact that images can be represented as approximately sparse signals in a transformed domain, images can be compressed and sampled simultaneously using lowcomplexity linear operations. Recently, these techniques have been extended beyond imaging to encode video. Much of the compression in traditional video encoding comes from using motion vectors to take advantage of the temporal correlation between adjacent frames. However, calculating motion vectors is a processingintensive operation that causes significant power consumption. Therefore, any technique appropriate for resource constrained video sensors must exploit temporal correlation through lowcomplexity operations. In this tutorial, we first briefly discuss challenges involved in the transmission of video over a wireless multimedia sensor network (WMSN). We then discuss the different techniques available for applying CS encoding first to images, and then to videos for errorresilient transmission in lossy channels. Existing solutions are examined, and compared in terms of applicability to wireless multimedia sensor networks (WMSNs). Finally, open issues are discussed and future research trends are outlined. Index Terms—Compressed Sensing, Multimedia communication, Wireless sensor networks, Video coding, Energyratedistortion.
Distributed Representation of Geometrically Correlated Images with Compressed Linear Measurements
, 2010
"... Abstract—This paper addresses the problem of distributed coding of images whose correlation is driven by the motion of objects or the camera positioning. It concentrates on the problem where images are encoded with compressed linear measurements. We propose a geometrybased correlation model that de ..."
Abstract

Cited by 5 (4 self)
 Add to MetaCart
(Show Context)
Abstract—This paper addresses the problem of distributed coding of images whose correlation is driven by the motion of objects or the camera positioning. It concentrates on the problem where images are encoded with compressed linear measurements. We propose a geometrybased correlation model that describes the common information in pairs of images. We assume that the constitutive components of natural images can be captured by visual features that undergo local transformations (e.g., translation) in different images. We first identify prominent visual features by computing a sparse approximation of a reference image with a dictionary of geometric basis functions. We then pose a regularized optimization problem in order to estimate the corresponding features in correlated images that are given by quantized linear measurements. The correlation model is thus given by the relative geometric transformations between corresponding features. We then propose an efficient joint decoding algorithm that reconstructs the compressed images such that they are consistent with both the quantized measurements and the correlation model. Experimental results show that the proposed algorithm effectively estimates the correlation between images in multiview data sets. In addition, the proposed algorithm provides effective decoding performance that advantageously compares to independent coding solutions and stateoftheart distributed coding schemes based on disparity learning. Index Terms—Correlation estimation, geometric transformations, quantization, random projections, sparse approximations. I.
Compressive Video Streaming: Design and RateEnergyDistortion Analysis
 IEEE Trans. on Multimedia, In Press
, 2013
"... Abstract—Realtime encoding and errorresilient wireless transmission of multimedia content using traditional encoding techniques requires relatively high processing and transmission power, while pervasive surveillance and monitoring systems often referred to as wireless multimedia sensor networks ( ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Realtime encoding and errorresilient wireless transmission of multimedia content using traditional encoding techniques requires relatively high processing and transmission power, while pervasive surveillance and monitoring systems often referred to as wireless multimedia sensor networks (WMSNs) [1] are generally composed of lowpower, lowcomplexity devices. To bridge this gap, this article introduces and analyzes a compressive video sensing (CVS) encoder designed to reduce the required energy and computational complexity at the source node. The proposed encoder leverages the properties of compressed sensing (CS) to overcome many of the limitations of traditional encoding techniques, specifically lack of resilience to channel errors, and high computational complexity. Recognizing the inadequacy of traditional ratedistortion analysis to account for the constraints introduced by resourcelimited devices, we introduce the notion of rateenergydistortion, based on which we develop an analytical/empirical model that predicts the received video quality when the overall energy available for both encoding and transmission of each frame of a video is fixed and limited and the transmissions are affected by channel errors. The model allows comparing the received video quality, computation time, and energy consumption per frame of different wireless streaming systems, and can be used to determine the optimal allocation of encoded video rate and channel encoding rate for a given available energy budget. Based on the proposed model, we show that the CVS video encoder outperforms (in an energy constrained system) two common encoders suitable for a wireless multimedia sensor network environment; H.264/AVC intra and motion JPEG (MJPEG). Extensive results show that CVS is able to deliver video at good quality (an SSIM value of 0.8) through lossy wireless networks with lower energy consumption per frame than competing encoders. Index Terms—Compressed sensing, video surveillance, video encoding, multimedia sensor networks. I.
Image Reconstruction from Compressed Linear Measurements with Side Information
 Conference Papers C.1
, 2011
"... This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We consider the particular problem where one image is selected as the reference image and it is used as a side information for decoding the compressed correlate ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We consider the particular problem where one image is selected as the reference image and it is used as a side information for decoding the compressed correlated images. These compressed images are given under the form of random measurements that are further quantized and entropy coded. The joint decoder estimates the correlation model based on the geometric transformation of features captured by a structured dictionary. We observe that the high frequency components are not efficiently captured in the estimated image when the correlation information is used alone for image prediction. Hence, we propose a reconstruction strategy that uses the information in the measurements to recover the missing visual information in the predicted image. The reconstruction is based on an optimization algorithm that enforces the reconstructed image to be consistent with the quantized measurements. We further add additional constraints to ensure that the reconstructed image is close to the image predicted from the correlation estimation. The nonlinearities introduced due to quantization are considered on both correlation and reconstruction algorithms in order to improve the performance. Experimental results demonstrate the benefit of the reconstruction algorithm as it brings improved coding performance especially at high rate and outperforms independent coding solutions based on JPEG 2000. 1.
JOINT RECONSTRUCTION OF CORRELATED IMAGES FROM COMPRESSED LINEAR MEASUREMENTS
"... This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We first propose a geometry based model in order to describe the correlation between visual information in a pair of images, which is mostly driven by the trans ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
(Show Context)
This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We first propose a geometry based model in order to describe the correlation between visual information in a pair of images, which is mostly driven by the translational motion of objects or vision sensors. We consider the particular problem where one image is selected as the reference image and it is used as the side information for decoding the compressed correlated images. These compressed images are built on random measurements that are further quantized and entropy coded. The joint decoder first captures the most prominent visual features in the reference image using geometric basis functions. Since images are correlated, these features are likely to be present in the compressed images too, possibly with some small transformation. Hence, the reconstruction of the compressed image is based on a regularized optimization problem that estimates these features in the compressed images. The regularization term further enforces the consistency between the reconstructed images and the quantized measurements. Experimental results show that the proposed scheme is able to efficiently estimate the correlation between images. It further leads to good reconstruction performance. The proposed scheme is finally shown to outperform DSC schemes based on unsupervised disparity or motion learning as well as independent coding solution based on JPEG2000 from a ratedistortion perspective. 1.
Reconstruction of Hyperspectral Imagery From Random Projections Using Multihypothesis Prediction
"... Abstract—Reconstruction of hyperspectral imagery from spectral random projections is considered. Specifically, multiple predictions drawn for a pixel vector of interest are made from spatially neighboring pixel vectors within an initial nonpredicted reconstruction. A twophase hypothesisgenerat ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
Abstract—Reconstruction of hyperspectral imagery from spectral random projections is considered. Specifically, multiple predictions drawn for a pixel vector of interest are made from spatially neighboring pixel vectors within an initial nonpredicted reconstruction. A twophase hypothesisgeneration procedure based on partitioning and merging of spectral bands according to the correlation coefficients between bands is proposed to finetune the hypotheses. The resulting prediction is used to generate a residual in the projection domain. This residual being typically more compressible than the original pixel vector leads to improved reconstruction quality. To appropriately weight the hypothesis predictions, a distanceweighted Tikhonov regularization to an illposed leastsquares optimization is proposed. Experimental results demonstrate that the proposed reconstruction significantly outperforms alternative strategies not employing multihypothesis prediction. Index Terms—Compressed sensing, hyperspectral data, multihypothesis prediction, principal component analysis, Tikhonov regularization. I.