An alignment based similarity measure for hand detection in cluttered sign language video

Locating hands in sign language video is challenging due to a number of factors. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Video can be captured under varying illumination, camera resolutions, and levels of scene clutter, e.g., high-res video captured in a studio vs. low-res video gathered by a web cam in a user’s home. Moreover, the signers’ clothing varies, e.g., skin-toned clothing vs. contrasting clothing, short-sleeved vs. long-sleeved shirts, etc. In this work, the hand detection problem is addressed in an appearance matching framework. The Histogram of Oriented Gradient (HOG) based matching score function is reformulated to allow non-rigid alignment between pairs of images to account for hand shape variation. The resulting alignment score is used within a Support Vector Machine hand/not-hand classifier for hand detection. The new matching score function yields improved performance (in ROC area and hand detection rate) over the Vocabulary Guided Pyramid Match Kernel (VGPMK) and the traditional, rigid HOG distance on American Sign Language video gestured by expert signers. The proposed match score function is computationally less expensive (for training and testing), has fewer parameters and is less sensitive to parameter settings than VGPMK. The proposed detector works well on test sequences from an inexpert signer in a non-studio setting with cluttered background.

Learning a Family of Detectors

Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes. In the first approach, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved with using a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. For applications where explicit parameterization of the within-class states is unavailable, a nonparametric formulation of the kernel can be constructed with a proper foreground distance/similarity measure. Detector training is accomplished via standard Support Vector Machine learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the image masks for foreground objects are provided in training, the detectors can also produce object segmentation. Methods for generating a representative sample set of detectors are proposed that can enable efficient detection and tracking. In addition, because individual detectors verify hypotheses of foreground state, they can also be incorporated in a tracking-by-detection frame work to recover foreground state in image sequences. To run the detectors efficiently at the online stage, an input-sensitive speedup strategy is proposed to select the most relevant detectors quickly. The proposed approach is tested on data sets of human hands, vehicles and human faces. On all data sets, the proposed approach achieves improved detection accuracy over the best competing approaches. In the second part of the thesis, we formulate a filter-and-refine scheme to speed up recognition processes. The binary outputs of the weak classifiers in a boosted detector are used to identify a small number of candidate foreground state hypotheses quickly via Hamming distance or weighted Hamming distance. The approach is evaluated in three applications: face recognition on the face recognition grand challenge version 2 data set, hand shape detection and parameter estimation on a hand data set, and vehicle detection and estimation of the view angle on a multi-pose vehicle data set. On all data sets, our approach is at least five times faster than simply evaluating all foreground state hypotheses with virtually no loss in classification accuracy.

Detecting Instances of Shape Classes That Exhibit Variable Structure

This paper proposes a method for detecting shapes of variable structure in images with clutter. The term "variable structure" means that some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. The particular variation of the shape structure that occurs in a given image is not known a priori. Existing computer vision methods, including deformable model methods, were not designed to detect shapes of variable structure; they may only be used to detect shapes that can be decomposed into a fixed, a priori known, number of parts. The proposed method can handle both variations in shape structure and variations in the appearance of individual shape parts. A new class of shape models is introduced, called Hidden State Shape Models, that can naturally represent shapes of variable structure. A detection algorithm is described that finds instances of such shapes in images with large amounts of clutter by finding globally optimal correspondences between image features and shape models. Experiments with real images demonstrate that our method can localize plant branches that consist of an a priori unknown number of leaves and can detect hands more accurately than a hand detector based on the chamfer distance.

Object Detection at the Optimal Scale with Hidden State Shape Models

Hidden State Shape Models (HSSMs) [2], a variant of Hidden Markov Models (HMMs) [9], were proposed to detect shape classes of variable structure in cluttered images. In this paper, we formulate a probabilistic framework for HSSMs which provides two major improvements in comparison to the previous method [2]. First, while the method in [2] required the scale of the object to be passed as an input, the method proposed here estimates the scale of the object automatically. This is achieved by introducing a new term for the observation probability that is based on a object-clutter feature model. Second, a segmental HMM [6, 8] is applied to model the "duration probability" of each HMM state, which is learned from the shape statistics in a training set and helps obtain meaningful registration results. Using a segmental HMM provides a principled way to model dependencies between the scales of different parts of the object. In object localization experiments on a dataset of real hand images, the proposed method significantly outperforms the method of [2], reducing the incorrect localization rate from 40% to 15%. The improvement in accuracy becomes more significant if we consider that the method proposed here is scale-independent, whereas the method of [2] takes as input the scale of the object we want to localize.

Correlación entre humedad del suelo y retrodispersión en imágenes SAR

p.163-168

Time-reversal ultrawideband breast imaging: pulse design criteria considering multiple tumors with unknown tissue properties

Pulse design is investigated for time-reversal (TR) imaging as applied to ultrawideband (UWB) breast cancer detection. Earlier it has been shown that a suitably-designed UWB pulse may help to improve imaging performance for a single-tumor breast phantom with predetermined lesion properties. The current work considers the following more general and practical situations: presence of multiple malignancies with unknown tumor size and dielectric properties. Four pulse selection criteria are proposed with each focusing on one of the following aspects: eliminating signal clutter generated by tissue inhomogeneities, canceling mutual interference among tumors, improving image resolution, and suppressing artifacts created by sidelobe of the target response. By applying the proposed criteria, the shape parameters of UWB waveforms with desirable characteristics are identified through search of all the possible pulses. Simulation example using a numerical breast phantom, comprised of two tumors and structured clutter distribution, demonstrates the effectiveness of the proposed approach. Specifically, a tradeoff between the image resolution and signal-to-clutter contrast (SCC) is observed in terms of selection of the excitation waveforms.

Can the subtropical North Atlantic permanent thermocline be observed from space?

The analysis of remotely sensed altimeter data and in situ measurements shows that ERS 2 radar can monitor the ocean permanent thermocline from space. The remotely sensed sea level anomaly data account for similar to 2/3 of the temperature variance or vertical displacement of isotherms at a depth of similar to 550 m in the Subtropical North Atlantic Ocean near 32.5 degree N. This depth corresponds closely to the region of maximum temperature gradient in the permanent thermocline where near semi-annual internal vertical displacements reach 200 to 300 m. The gradient of the altimeter sea level anomaly data correlates well with measured ocean currents to a depth of 750 m. It is shown that observations from space can account for similar to 3/4 of the variance of ocean currents measured in situ in the permanent thermocline over a 2-y period. The magnification of the permanent thermocline displacement with respect to the displacement of the sea surface was determined as - x650 and gives a measure of the ratio of barotropic to baroclinic decay scale of geostrophic current with depth. The overall results are used to interpret an eight year altimeter data tie series in the Subtropical North Atlantic at 32.5 degree N which shows a dominant wave or eddy period near 200 days, rather than semi-annual and increases in energy propagating westward in 1995 (west of 25 degree W). The effects of rapid North Atlantic Oscillation climate change on ocean circulation are discussed. The altimeter data for the Atlantic were Fourier analysed. It is shown how the annual and semi-annual components relate to the seasonal maximum cholorophyll-a SeaWiFS signal in tropical and equatorial regions due to the lifting of the thermocline caused by seasonally varying ocean currents forced by wind stress.

Chlorophyll enhancement in the central region of the Bay of Biscay as a result of internal tidal wave interaction

A multi-sensor satellite approach based on ocean colour, sunglint and Synthetic Aperture Radar imagery is used to study the impact of interacting internal tidal (IT) waves on near-surface chlorophyll-a distribution, in the central Bay of Biscay. Satellite imagery was initially used to characterize the internal solitary wave (ISW) field in the study area, where the “local generation mechanism” was found to be associated with two distinct regions of enhanced barotropic tidal forcing. IT beams formed at the French shelf-break, and generated from critical bathymetry in the vicinities of one of these regions, were found to be consistent with “locally generated” ISWs. Representative case studies illustrate the existence of two different axes of IT propagation originating from the French shelf-break, which intersect close to 46°N, − 7°E, where strong IT interaction has been previously identified. Evidence of constructive interference between large IT waves is then presented and shown to be consistent with enhanced levels of chlorophyll-a concentration detected by means of ocean colour satellite sensors. Finally, the results obtained from satellite climatological mean chlorophyll-a concentration from late summer (i.e. September, when ITs and ISWs can meet ideal propagation conditions) suggest that elevated IT activity plays a significant role in phytoplankton vertical distribution, and therefore influences the late summer ecology in the central Bay of Biscay.

Biodiversity Loss in the Ocean: How Bad Is It?

MURAWSKI AND COLLEAGUES STATE THAT OUR assessment of the impacts of global marine biodiversity loss is overly pessimistic. They imply that management interventions are likely to reverse current trends of overfishing, and that the U.S. National Marine Fisheries Service (NMFS) has already met that goal. They cite Georges Bank haddock as an example and contest that catch metrics (as used in our global analysis) are sufficient to track the status of this particular fish stock and possibly others. We agree that precise biomass data are preferable, but these are rarely available. Here, we illustrate that catches are a good proxy of the status of haddock, although there can be a short delay in detecting recovery under intense management. While NMFS’s own data show that full recovery is still uncommon (<5% of overfished stocks) (1), we strongly agree that destructive trends can be turned around and that rebuilding efforts need to be intensified to meet that goal. But we must not miss the forest for the trees: Continuing focus on single, well-assessed, economically viable species will leave most of the ocean’s declining biodiversity under the radar.

Initial Examination of AltiKa's Individual Echoes

The AltiKa altimeter records the reflection of Ka-band radar pulses from the Earth’s surface, with the commonly used waveform product involving the summation of 96 returns to provide average echoes at 40 Hz. Occasionally there are one-second recordings of the complex individual echoes (IEs), which facilitate the evaluation of on-board processing and offer the potential for new processing strategies. Our investigation of these IEs over the ocean confirms the on-board operations, whilst noting that data quantization limits the accuracy in the thermal noise region. By constructing average waveforms from 32 IEs at a time, and applying an innovative subwaveform retracker, we demonstrate that accurate height and wave height information can be retrieved from very short sections of data. Early exploration of the complex echoes reveals structure in the phase information similar to that noted for Envisat’s IEs.

Globcurrent: Sentinel-3 synergy in action

The ESA Data User Element (DUE) funded GlobCurrent project (http://www.globcurrent.org) aims to: (i) advance the quantitative estimation of ocean surface currents from satellite sensor synergy; and (ii) demonstrate impact in user-led scientific, operational and commercial applications that, in turn, will improve and strengthen the uptake of satellite measurements. Today, a synergetic approach for quantitative analysis can build on high-resolution imaging radar and spectrometer data, infrared radiometer data and radar altimeter measurements. It will further integrate Sentinel-3 in combination with Sentinel-1 SAR data. From existing and past missions, it is often demonstrated that sharp gradients in the sea surface temperature (SST) field and the ocean surface chlorophyll-a distribution are spatially correlated with the sea surface roughness anomaly fields at small spatial scales, in the sub-mesocale (1-10 km) to the mesoscale (30-80 km). At the larger mesoscale range (>50 km), information derived from radar altimeters often depict the presence of coherent structures and eddies. The variability often appears largest in regions where the intense surface current regimes (>100 - 200 km) are found. These 2-dimensional structures manifested in the satellite observations represent evidence of the upper ocean (~100-200 m) dynamics. Whereas the quasi geostrophic assumption is valid for the upper ocean dynamics at the larger scale (>100 km), possible triggering mechanisms for the expressions at the mesoscale-to-submesoscale may include spiraling tracers of inertial motion and the interaction of the wind-driven Ekman layer with the quasi-geostrophic current field. This latter, in turn, produces bands of downwelling (convergence) and upwelling (divergence) near fronts. A regular utilization of the sensor synergy approach with the combination of Sentinel-3 and Sentinel-1 will provide a highly valuable data set for further research and development to better relate the 2-dimensional surface expressions and the upper ocean dynamics.

Generic SoC QR Array Processor for Adaptive Beamforming

A generic architecture for implementing a QR array processor in silicon is presented. This improves on previous research by considerably simplifying the derivation of timing schedules for a QR system implemented as a folded linear array, where account has to be taken of processor cell latency and timing at the detailed circuit level. The architecture and scheduling derived have been used to create a generator for the rapid design of System-on-a-Chip (SoC) cores for QR decomposition. This is demonstrated through the design of a single-chip architecture for implementing an adaptive beamformer for radar applications. Published as IEEE Trans Circuits and Systems Part II, Analog and Digital Signal Processing, April 2003 NOT Express Briefs. Parts 1 and II of Journal reorganised since then into Regular Papers and Express briefs

Multidimensional DSP Core Synthesis for FPGA

This paper, chosen as a best paper from the 2004 SAMOS Workshop on Computer Systems: describes a novel, efficient methodology for automatically creating embedded DSP computer systems. The novelty arises since now embedded electronic signal processing systems, such as radar or sonar, can be designed by anyone from the algorithm level, i.e. no low level system design experience is required, whilst still achieving low controllable implementation overheads and high real time performance. In the chosen design example, a bank of Normalised Lattice Filter (NLF) components is created which a four-fold reduction in the required processing resource with no performance decrease.

Rapid Implementation and Optimisation of DSP Systems on FPGA-Centric Hetrogeneous Platforms

This paper, chosen as a best paper from the 2005 SAMOS Workshop on Computer Systems: describes the for the first time the major Abhainn project for automated system level design of embedded signal processing systems. In particular, this describes four key novelties: novel algorithm modelling techniques for DSP systems, automated implementation realisation, algorithm transformation for system optimisation and automated inter-processor communication. This is applied to two complex systems: a radar and sonar system. In both cases technology which allows non-experts to automatically create low-overhead, high performance embedded signal processing systems is exhibited.

The fall of kinship - towards an epidemiological explanation

Kinship used to be described as what anthropologists do. Today, many might well say that it is what anthropologists do not do. One possible explanation is that the notion of kinship fell off anthropology's radar due to the criticisms raised by Needham and Schneider among others, which supposedly demonstrated that kinship is not a sound theoretical concept. Drawing inspiration from epidemiological approaches to cultural phenomena, this article aims to enrich this explanation. Kinship became an unattractive theoretical concept in the subculture of anthropology not simply because of problems with kinship theory per se, but also on account of fundamental changes in the very conception of anthropological knowledge and the impact of these changes on the personal identity of anthropologists.