Fragment-based real-time object tracking: a sparse representation approach

Real-time object tracking is a critical task in many computer vision applications. Achieving rapid and robust tracking while handling changes in object pose and size, varying illumination and partial occlusion, is a challenging task given the limited amount of computational resources. In this paper we propose a real-time object tracker in l(1) framework addressing these issues. In the proposed approach, dictionaries containing templates of overlapping object fragments are created. The candidate fragments are sparsely represented in the dictionary fragment space by solving the l(1) regularized least squares problem. The non zero coefficients indicate the relative motion between the target and candidate fragments along with a fidelity measure. The final object motion is obtained by fusing the reliable motion information. The dictionary is updated based on the object likelihood map. The proposed tracking algorithm is tested on various challenging videos and found to outperform earlier approach.

FeatureMatch: A General ANNF Estimation Technique and its Applications

In this paper, we propose FeatureMatch, a generalised approximate nearest-neighbour field (ANNF) computation framework, between a source and target image. The proposed algorithm can estimate ANNF maps between any image pairs, not necessarily related. This generalisation is achieved through appropriate spatial-range transforms. To compute ANNF maps, global colour adaptation is applied as a range transform on the source image. Image patches from the pair of images are approximated using low-dimensional features, which are used along with KD-tree to estimate the ANNF map. This ANNF map is further improved based on image coherency and spatial transforms. The proposed generalisation, enables us to handle a wider range of vision applications, which have not been tackled using the ANNF framework. We illustrate two such applications namely: 1) optic disk detection and 2) super resolution. The first application deals with medical imaging, where we locate optic disks in retinal images using a healthy optic disk image as common target image. The second application deals with super resolution of synthetic images using a common source image as dictionary. We make use of ANNF mappings in both these applications and show experimentally that our proposed approaches are faster and accurate, compared with the state-of-the-art techniques.

Energy Efficient GPS Acquisition with Sparse-GPS

Following rising demands in positioning with GPS, low-cost receivers are becoming widely available; but their energy demands are still too high. For energy efficient GPS sensing in delay-tolerant applications, the possibility of offloading a few milliseconds of raw signal samples and leveraging the greater processing power of the cloud for obtaining a position fix is being actively investigated. In an attempt to reduce the energy cost of this data offloading operation, we propose Sparse-GPS(1): a new computing framework for GPS acquisition via sparse approximation. Within the framework, GPS signals can be efficiently compressed by random ensembles. The sparse acquisition information, pertaining to the visible satellites that are embedded within these limited measurements, can subsequently be recovered by our proposed representation dictionary. By extensive empirical evaluations, we demonstrate the acquisition quality and energy gains of Sparse-GPS. We show that it is twice as energy efficient than offloading uncompressed data, and has 5-10 times lower energy costs than standalone GPS; with a median positioning accuracy of 40 m.

Robust tracking with interest points: A sparse representation approach

Visual tracking is an important task in various computer vision applications including visual surveillance, human computer interaction, event detection, video indexing and retrieval. Recent state of the art sparse representation (SR) based trackers show better robustness than many of the other existing trackers. One of the issues with these SR trackers is low execution speed. The particle filter framework is one of the major aspects responsible for slow execution, and is common to most of the existing SR trackers. In this paper,(1) we propose a robust interest point based tracker in l(1) minimization framework that runs at real-time with performance comparable to the state of the art trackers. In the proposed tracker, the target dictionary is obtained from the patches around target interest points. Next, the interest points from the candidate window of the current frame are obtained. The correspondence between target and candidate points is obtained via solving the proposed l(1) minimization problem. In order to prune the noisy matches, a robust matching criterion is proposed, where only the reliable candidate points that mutually match with target and candidate dictionary elements are considered for tracking. The object is localized by measuring the displacement of these interest points. The reliable candidate patches are used for updating the target dictionary. The performance and accuracy of the proposed tracker is benchmarked with several complex video sequences. The tracker is found to be considerably fast as compared to the reported state of the art trackers. The proposed tracker is further evaluated for various local patch sizes, number of interest points and regularization parameters. The performance of the tracker for various challenges including illumination change, occlusion, and background clutter has been quantified with a benchmark dataset containing 50 videos. (C) 2014 Elsevier B.V. All rights reserved.

Sparse coding based VLAD for efficient image retrieval

Representing images and videos in the form of compact codes has emerged as an important research interest in the vision community, in the context of web scale image/video search. Recently proposed Vector of Locally Aggregated Descriptors (VLAD), has been shown to outperform the existing retrieval techniques, while giving a desired compact representation. VLAD aggregates the local features of an image in the feature space. In this paper, we propose to represent the local features extracted from an image, as sparse codes over an over-complete dictionary, which is obtained by K-SVD based dictionary training algorithm. The proposed VLAD aggregates the residuals in the space of these sparse codes, to obtain a compact representation for the image. Experiments are performed over the `Holidays' database using SIFT features. The performance of the proposed method is compared with the original VLAD. The 4% increment in the mean average precision (mAP) indicates the better retrieval performance of the proposed sparse coding based VLAD.

Synthetic image super resolution using FeatureMatch

In this paper, we propose a super resolution (SR) method for synthetic images using FeatureMatch. Existing state-of-the-art super resolution methods are learning based methods, where a pair of low-resolution and high-resolution dictionary pair are trained, and this trained pair is used to replace patches in low-resolution image with appropriate matching patches from the high-resolution dictionary. In this paper, we show that by using Approximate Nearest Neighbour Fields (ANNF), and a common source image, we can by-pass the learning phase, and use a single image for dictionary. Thus, reducing the dictionary from a collection obtained from hundreds of training images, to a single image. We show that by modifying the latest developments in ANNF computation, to suit super resolution, we can perform much faster and more accurate SR than existing techniques. To establish this claim we will compare our algorithm against various state-of-the-art algorithms, and show that we are able to achieve better and faster reconstruction without any training phase.

Translation Induction on Indian Language Corpora Using Translingual Themes from Other Languages

Identifying translations from comparable corpora is a well-known problem with several applications, e.g. dictionary creation in resource-scarce languages. Scarcity of high quality corpora, especially in Indian languages, makes this problem hard, e.g. state-of-the-art techniques achieve a mean reciprocal rank (MRR) of 0.66 for English-Italian, and a mere 0.187 for Telugu-Kannada. There exist comparable corpora in many Indian languages with other ``auxiliary'' languages. We observe that translations have many topically related words in common in the auxiliary language. To model this, we define the notion of a translingual theme, a set of topically related words from auxiliary language corpora, and present a probabilistic framework for translation induction. Extensive experiments on 35 comparable corpora using English and French as auxiliary languages show that this approach can yield dramatic improvements in performance (e.g. MRR improves by 124% to 0.419 for Telugu-Kannada). A user study on WikiTSu, a system for cross-lingual Wikipedia title suggestion that uses our approach, shows a 20% improvement in the quality of titles suggested.

Sparse Representation based Anomaly Detection using HOMV in H.264 Compressed Videos

In this paper, we have proposed an anomaly detection algorithm based on Histogram of Oriented Motion Vectors (HOMV) 1] in sparse representation framework. Usual behavior is learned at each location by sparsely representing the HOMVs over learnt normal feature bases obtained using an online dictionary learning algorithm. In the end, anomaly is detected based on the likelihood of the occurrence of sparse coefficients at that location. The proposed approach is found to be robust compared to existing methods as demonstrated in the experiments on UCSD Ped1 and UCSD Ped2 datasets.

Comparison of Matching Pursuit Algorithm with Other Signal Processing Techniques for Computation of the Time-Frequency Power Spectrum of Brain Signals

Signals recorded from the brain often show rhythmic patterns at different frequencies, which are tightly coupled to the external stimuli as well as the internal state of the subject. In addition, these signals have very transient structures related to spiking or sudden onset of a stimulus, which have durations not exceeding tens of milliseconds. Further, brain signals are highly nonstationary because both behavioral state and external stimuli can change on a short time scale. It is therefore essential to study brain signals using techniques that can represent both rhythmic and transient components of the signal, something not always possible using standard signal processing techniques such as short time fourier transform, multitaper method, wavelet transform, or Hilbert transform. In this review, we describe a multiscale decomposition technique based on an over-complete dictionary called matching pursuit (MP), and show that it is able to capture both a sharp stimulus-onset transient and a sustained gamma rhythm in local field potential recorded from the primary visual cortex. We compare the performance of MP with other techniques and discuss its advantages and limitations. Data and codes for generating all time-frequency power spectra are provided.