SPSA Based Feature Relevance Estimation For Video Retrieval

With the availability of a huge amount of video data on various sources, efficient video retrieval tools are increasingly in demand. Video being a multi-modal data, the perceptions of ``relevance'' between the user provided query video (in case of Query-By-Example type of video search) and retrieved video clips are subjective in nature. We present an efficient video retrieval method that takes user's feedback on the relevance of retrieved videos and iteratively reformulates the input query feature vectors (QFV) for improved video retrieval. The QFV reformulation is done by a simple, but powerful feature weight optimization method based on Simultaneous Perturbation Stochastic Approximation (SPSA) technique. A video retrieval system with video indexing, searching and relevance feedback (RF) phases is built for demonstrating the performance of the proposed method. The query and database videos are indexed using the conventional video features like color, texture, etc. However, we use the comprehensive and novel methods of feature representations, and a spatio-temporal distance measure to retrieve the top M videos that are similar to the query. In feedback phase, the user activated iterative on the previously retrieved videos is used to reformulate the QFV weights (measure of importance) that reflect the user's preference, automatically. It is our observation that a few iterations of such feedback are generally sufficient for retrieving the desired video clips. The novel application of SPSA based RF for user-oriented feature weights optimization makes the proposed method to be distinct from the existing ones. The experimental results show that the proposed RF based video retrieval exhibit good performance.

Speeding up AdaBoost Classifier with Random Projection

The development of techniques for scaling up classifiers so that they can be applied to problems with large datasets of training examples is one of the objectives of data mining. Recently, AdaBoost has become popular among machine learning community thanks to its promising results across a variety of applications. However, training AdaBoost on large datasets is a major problem, especially when the dimensionality of the data is very high. This paper discusses the effect of high dimensionality on the training process of AdaBoost. Two preprocessing options to reduce dimensionality, namely the principal component analysis and random projection are briefly examined. Random projection subject to a probabilistic length preserving transformation is explored further as a computationally light preprocessing step. The experimental results obtained demonstrate the effectiveness of the proposed training process for handling high dimensional large datasets.

Image reconstruction with laterally truncated projections in helical cone-beam CT: Linear prediction based projection completion techniques

Lateral or transaxial truncation of cone-beam data can occur either due to the field of view limitation of the scanning apparatus or iregion-of-interest tomography. In this paper, we Suggest two new methods to handle lateral truncation in helical scan CT. It is seen that reconstruction with laterally truncated projection data, assuming it to be complete, gives severe artifacts which even penetrates into the field of view. A row-by-row data completion approach using linear prediction is introduced for helical scan truncated data. An extension of this technique known as windowed linear prediction approach is introduced. Efficacy of the two techniques are shown using simulation with standard phantoms. A quantitative image quality measure of the resulting reconstructed images are used to evaluate the performance of the proposed methods against an extension of a standard existing technique.

An adaptive decomposition method for video

Scalable video coding (SVC) is an emerging standard built on the success of advanced video coding standard (H.264/AVC) by the Joint video team (JVT). Motion compensated temporal filtering (MCTF) and Closed loop hierarchical B pictures (CHBP) are two important coding methods proposed during initial stages of standardization. Either of the coding methods, MCTF/CHBP performs better depending upon noise content and characteristics of the sequence. This work identifies other characteristics of the sequences for which performance of MCTF is superior to that of CHBP and presents a method to adaptively select either of MCTF and CHBP coding methods at the GOP level. This method, referred as "Adaptive Decomposition" is shown to provide better R-D performance than of that by using MCTF or CRBP only. Further this method is extended to non-scalable coders.

A model based factorization approach for dense 3D recovery from monocular video

Feature track matrix factorization based methods have been attractive solutions to the Structure-front-motion (Sfnl) problem. Group motion of the feature points is analyzed to get the 3D information. It is well known that the factorization formulations give rise to rank deficient system of equations. Even when enough constraints exist, the extracted models are sparse due the unavailability of pixel level tracks. Pixel level tracking of 3D surfaces is a difficult problem, particularly when the surface has very little texture as in a human face. Only sparsely located feature points can be tracked and tracking error arc inevitable along rotating lose texture surfaces. However, the 3D models of an object class lie in a subspace of the set of all possible 3D models. We propose a novel solution to the Structure-from-motion problem which utilizes the high-resolution 3D obtained from range scanner to compute a basis for this desired subspace. Adding subspace constraints during factorization also facilitates removal of tracking noise which causes distortions outside the subspace. We demonstrate the effectiveness of our formulation by extracting dense 3D structure of a human face and comparing it with a well known Structure-front-motion algorithm due to Brand.

Memory Bandwidth and Power Reduction Using Lossy Reference Frame Compression in Video Encoding

Large external memory bandwidth requirement leads to increased system power dissipation and cost in video coding application. Majority of the external memory traffic in video encoder is due to reference data accesses. We describe a lossy reference frame compression technique that can be used in video coding with minimal impact on quality while significantly reducing power and bandwidth requirement. The low cost transformless compression technique uses lossy reference for motion estimation to reduce memory traffic, and lossless reference for motion compensation (MC) to avoid drift. Thus, it is compatible with all existing video standards. We calculate the quantization error bound and show that by storing quantization error separately, bandwidth overhead due to MC can be reduced significantly. The technique meets key requirements specific to the video encode application. 24-39% reduction in peak bandwidth and 23-31% reduction in total average power consumption are observed for IBBP sequences.

Novel gray coded pattern for unwrapping phase in fringe projection based 3D profiling

A method to reliably extract object profiles even with height discontinuities (that leads to 2n pi phase jumps) is proposed. This method uses Fourier transform profilometry to extract wrapped phase, and an additional image formed by illuminating the object of interest by a novel gray coded pattern for phase unwrapping. Simulation results suggest that the proposed approach not only retains the advantages of the original method, but also contributes significantly in the enhancement of its performance. Fundamental advantage of this method stems from the fact that both extraction of wrapped phase and unwrapping the same were done by gray scale images. Hence, unlike the methods that use colors, proposed method doesn't demand a color CCD camera and is ideal for profiling objects with multiple colors.

Video coding mode decision as a classification problem

In this paper, we show that it is possible to reduce the complexity of Intra MB coding in H.264/AVC based on a novel chance constrained classifier. Using the pairs of simple mean-variances values, our technique is able to reduce the complexity of Intra MB coding process with a negligible loss in PSNR. We present an alternate approach to address the classification problem which is equivalent to machine learning. Implementation results show that the proposed method reduces encoding time to about 20% of the reference implementation with average loss of 0.05 dB in PSNR.

A Unified Approach to Encoding and Classification Using Bimodal Projection-Based Features

In general the objective of accurately encoding the input data and the objective of extracting good features to facilitate classification are not consistent with each other. As a result, good encoding methods may not be effective mechanisms for classification. In this paper, an earlier proposed unsupervised feature extraction mechanism for pattern classification has been extended to obtain an invertible map. The method of bimodal projection-based features was inspired by the general class of methods called projection pursuit. The principle of projection pursuit concentrates on projections that discriminate between clusters and not faithful representations. The basic feature map obtained by the method of bimodal projections has been extended to overcome this. The extended feature map is an embedding of the input space in the feature space. As a result, the inverse map exists and hence the representation of the input space in the feature space is exact. This map can be naturally expressed as a feedforward neural network.

A Fast Linear Separability Test by Projection of Positive Points on Subspaces

A geometric and non parametric procedure for testing if two finite set of points are linearly separable is proposed. The Linear Separability Test is equivalent to a test that determines if a strictly positive point h > 0 exists in the range of a matrix A (related to the points in the two finite sets). The algorithm proposed in the paper iteratively checks if a strictly positive point exists in a subspace by projecting a strictly positive vector with equal co-ordinates (p), on the subspace. At the end of each iteration, the subspace is reduced to a lower dimensional subspace. The test is completed within r ≤ min(n, d + 1) steps, for both linearly separable and non separable problems (r is the rank of A, n is the number of points and d is the dimension of the space containing the points). The worst case time complexity of the algorithm is O(nr3) and space complexity of the algorithm is O(nd). A small review of some of the prominent algorithms and their time complexities is included. The worst case computational complexity of our algorithm is lower than the worst case computational complexity of Simplex, Perceptron, Support Vector Machine and Convex Hull Algorithms, if d

Estimation of missing data using windowed linear prediction in laterally truncated projection & in cone beam CT

In this paper, we address the reconstruction problem from laterally truncated helical cone-beam projections. The reconstruction problem from lateral truncation, though similar to that of interior radon problem, is slightly different from it as well as the local (lambda) tomography and pseudo-local tomography in the sense that we aim to reconstruct the entire object being scanned from a region-of-interest (ROI) scan data. The method proposed in this paper is a projection data completion approach followed by the use of any standard accurate FBP type reconstruction algorithm. In particular, we explore a windowed linear prediction (WLP) approach for data completion and compare the quality of reconstruction with the linear prediction (LP) technique proposed earlier.

Analog/RF Built-in-Self-Test Subsystem for a Mobile Broadcast Video Receiver in 65-nm CMOS

A built-in-self-test (BIST) subsystem embedded in a 65-nm mobile broadcast video receiver is described. The subsystem is designed to perform analog and RF measurements at multiple internal nodes of the receiver. It uses a distributed network of CMOS sensors and a low bandwidth, 12-bit A/D converter to perform the measurements with a serial bus interface enabling a digital transfer of measured data to automatic test equipment (ATE). A perturbation/correlation based BIST method is described, which makes pass/fail determination on parts, resulting in significant test time and cost reduction.

3D Image Reconstruction From Truncated Helical Cone Beam Projection Data - A Linear Prediction Approach

With the introduction of 2D flat-panel X-ray detectors, 3D image reconstruction using helical cone-beam tomography is fast replacing the conventional 2D reconstruction techniques. In 3D image reconstruction, the source orbit or scanning geometry should satisfy the data sufficiency or completeness condition for exact reconstruction. The helical scan geometry satisfies this condition and hence can give exact reconstruction. The theoretically exact helical cone-beam reconstruction algorithm proposed by Katsevich is a breakthrough and has attracted interest in the 3D reconstruction using helical cone-beam Computed Tomography.In many practical situations, the available projection data is incomplete. One such case is where the detector plane does not completely cover the full extent of the object being imaged in lateral direction resulting in truncated projections. This result in artifacts that mask small features near to the periphery of the ROI when reconstructed using the convolution back projection (CBP) method assuming that the projection data is complete. A number of techniques exist which deal with completion of missing data followed by the CBP reconstruction. In 2D, linear prediction (LP)extrapolation has been shown to be efficient for data completion, involving minimal assumptions on the nature of the data, producing smooth extensions of the missing projection data.In this paper, we propose to extend the LP approach for extrapolating helical cone beam truncated data. The projection on the multi row flat panel detectors has missing columns towards either ends in the lateral direction in truncated data situation. The available data from each detector row is modeled using a linear predictor. The available data is extrapolated and this completed projection data is backprojected using the Katsevich algorithm. Simulation results show the efficacy of the proposed method.