RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images

Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces are captured at low-resolution and have a blurred appearance. Domain adaptation approaches are useful for transferring knowledge from the training (source) to the test (target) data when they have different attributes, minimizing target data labeling efforts in the process. This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images capture a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale and (iii) a combination of (i) and (ii). On the whole, the presented methods represent novel transfer learning solutions employed in the context of multi-view head pose classification. We demonstrate that the proposed solutions considerably outperform the state-of-the-art through extensive experimental validation. Finally, the DPOSE dataset compiled for benchmarking head pose classification performance with moving persons, and to aid behavioral understanding applications is presented in this work.

Skip Decision and Reference Frame Selection for Low-Complexity H.264/AVC Surveillance Video Coding

H. 264/advanced video coding surveillance video encoders use the Skip mode specified by the standard to reduce bandwidth. They also use multiple frames as reference for motion-compensated prediction. In this paper, we propose two techniques to reduce the bandwidth and computational cost of static camera surveillance video encoders without affecting detection and recognition performance. A spatial sampler is proposed to sample pixels that are segmented using a Gaussian mixture model. Modified weight updates are derived for the parameters of the mixture model to reduce floating point computations. A storage pattern of the parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. The second contribution is a low computational cost algorithm to choose the reference frames. The proposed reference frame selection algorithm reduces the cost of coding uncovered background regions. We also study the number of reference frames required to achieve good coding efficiency. Distortion over foreground pixels is measured to quantify the performance of the proposed techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence.

INTERPOL's surveillance network in curbing transnational terrorism

This paper investigates the role that INTERPOL surveillance – the Mobile INTERPOL Network Database (MIND) and the Fixed INTERPOL Network Database (FIND) – played in the War on Terror since its inception in 2005. MIND/FIND surveillance allows countries to screen people and documents systematically at border crossings against INTERPOL databases on terrorists, fugitives, and stolen and lost travel documents. Such documents have been used in the past by terrorists to transit borders. By applying methods developed in the treatment-effects literature, this paper establishes that countries adopting MIND/FIND experienced fewer transnational terrorist attacks than had they not adopted MIND/FIND. Our estimates indicate that, on average, during 2008–2011, adopting and using MIND/FIND results in 1.23 fewer transnational terrorist incidents each year per 100 million people. Thus, a country like France with a population just above 64 million people in 2008 would have 0.79 fewer transnational terrorist incidents per year owing to its use of INTERPOL surveillance. For most treatment countries, this amounts to a sizeable proportional reduction of about 60 per cent.

Oceans and human health: Sentinel habitats and sentinel species

The health of the oceans and people are inextricably linked. For many years we focused research and policy on anthropogenic impacts to oceans and coasts. Recently we have started to think about how the health of the oceans affects us. In response to the Oceans and Human Health Act of 2004, a NOAA initiative was created to explore the “One Health” of the oceans and coasts. The Center of Excellence in Oceans and Human Health at Hollings Marine Laboratory (HML) is one of three Centers dedicated to understanding the connections and forecasting changes in ocean and coastal health and human health. The Center at HML is developing new tools and approaches, including sentinel habitats and sentinel species, to evaluate linkages between ecological process and human health and wellbeing. The results provide environmental and public health managers, policy-makers and communities forecasts and assessments to improve ecosystem-based management that protects health and mitigates risks for the oceans, coasts and people.(PDF contains 4 pages)

Biological surveillance of chalk-streams

An article reviewing the methods of biological surveillance of chalk-streams developed and commonly used at that time, with a focus on their application to the River Frome catchment in Dorset. In evaluating the surveillance methods, the author looks at sampling methods (including cores and kick-sampling), the level of identification of macroinvertebrates, and temporal and spatial variations. Responses of indices to organic pollution are also discussed. A number of accompanying figures are also included.

Joint Anglo-Soviet biological surveillance exercise on River Dnieper

As one part of an on-going programme concerned with environmental protection as provided for under the terms of a UK/USSR Joint Environmental Protection Agreement signed in London, 21 May 1974, a seminar — ”The elaboration of the scientific basis for monitoring the quality of surface water by hydrobiological indices” was held at Valdai in Russia 12—14 July, 1976. As a continuation of this theme it was agreed that delegations of hydrobiologists from each side should carry out reciprocal visits to carry out comparative field tests on selected systems of biological surveillance in use in the respective countries. In May 1978 a team of British hydrobiologists visited the USSR, under the auspices of the Department of Environment, to carry out joint exercises on the River Dnieper and some tributaries. This paper reports the results of selected methods used by the British side when applied to the conditions found in the River Dnieper.

Sistema de informação: uma proposição para o Hospital Universitário da Universidade Federal de Juiz de Fora-MG

Esse trabalho aborda a elaboração de requisitos dos usuários como parte da adequação do sistema de informação-SISTEMA DE INFORMAÇÃO DE GESTÃO ACADÊMICA-Administrativo- SIGA-Adm, proposto para o Hospital Universitário da Universidade Federal de Juiz de Fora. SIGA-Adm está em utilização, desde 2007, na Universidade Federal de Juiz de Fora. No entanto, para a efetiva aplicabilidade no âmbito do Hospital Universitário, torna-se necessário uma investigação acerca dos processos de trabalho, dentro do HU e uma ação de melhoria desses processos, a fim de evitar a incorporação de um sistema de informação que não corresponda a realidade apresentada. A elaboração dos requisitos dos usuários para a adequação visa a ser um instrumento de intermediação para discussão acerca da elaboração do SIGA-Adm para o HU/UFJF. Os requisitos apresentados originaram-se no processo de gerenciamento de materiais, como resultado da utilização da Metodologia de Análise e Melhoria de Processos-MAMP, aplicada na cadeia de suprimentos do Hospital Universitário, no período de 2004 a 2005. O acompanhamento do gerenciamento de materiais é uma estratégia utilizada pela Rede Sentinela para o desenvolvimento de ações de pós-comercialização de produtos para a saúde tais como: investigação de uso, registro de produtos, retirada de produto do mercado e etc... O Hospital Universitário da UFJF é integrante da Rede Brasileira de Hospitais Sentinela, implementada pela Agência Nacional de Vigilância Sanitária, desde 2001. As ações Pós-Comercialização de Produtos para a Saúde, em Tecnovigilância, são compartilhadas pela ANVISA e pelos integrantes da Rede Sentinela, através de informações relativas a queixas técnicas e/ou eventos adversos que possam causar algum dano à população. A pesquisa indica a possibilidade do SIGA-Adm armazenar informações sobre os produtos que permitam o rastreamento em condições normais e/ou anormais de uso pela instituição, contribuindo para o exercício em Tecnovigilância. Além disso, espera-se que construção do SIGA-Adm/HU-UFJF permita integrar os sistemas existentes no HU.

Integrated assessment of environmental pollution using diverse sentinel organisms within Basque marine environments

294 p.

Gulf of Mexico tidal creeks serve as sentinel habitats for assessing the impact of coastal development on ecosystem health

A study was conducted, in association with the Alabama and Mississippi National Estuarine Research Reserves (NERRs) in the Gulf of Mexico (GoM) as well as the Georgia, South Carolina, and North Carolina NERRs in the Southeast (SE), to evaluate the impacts of coastal development on tidal creek sentinel habitats, including potential impacts to human health and well-being. Uplands associated with Southeast and Gulf of Mexico tidal creeks, and the salt marshes they drain, are popular locations for building homes, resorts, and recreational facilities because of the high quality of life and mild climate associated with these environments. Tidal creeks form part of the estuarine ecosystem characterized by high biological productivity, great ecological value, complex environmental gradients, and numerous interconnected processes. This research combined a watershed-level study integrating ecological, public health and human dimension attributes with watershed-level land cover data. The approach used for this research was based upon a comparative watershed and ecosystem approach that sampled tidal creek networks draining developed watersheds (e.g., suburban, urban, and industrial) as well as undeveloped sites (Holland et al. 2004, Sanger et al. 2008). The primary objective of this work was to define the relationships between coastal development with its concomitant land cover changes, and non-point source pollution loading and the ecological and human health and wellbeing status of tidal creek ecosystems. Nineteen tidal creek systems, located along the Southeastern United States coast from southern North Carolina to southern Georgia, and five Gulf of Mexico systems from Alabama and Mississippi were sampled during summer (June-August) 2005, 2006 (SE) and 2008 (GoM). Within each system, creeks were divided into two primary segments based upon tidal zoning: intertidal (i.e., shallow, narrow headwater sections) and subtidal (i.e., deeper and wider sections), and watersheds were delineated for each segment. In total, we report findings on 29 intertidal and 24 subtidal creeks. Indicators sampled throughout each creek included water quality (e.g., dissolved oxygen, salinity, nutrients, chlorophyll-a levels), sediment quality (e.g., characteristics, contaminant levels including emerging contaminants), pathogen and viral indicators (e.g., fecal coliform, enterococci, F+ coliphages, F- coliphages), and abundance and tissue contamination of biological resources (e.g., macrobenthic and nektonic communities, shellfish tissue contaminants). Tidal creeks have been identified as a sentinel habitat to assess the impacts of coastal development on estuarine areas in the southeastern US. A conceptual model for tidal creeks in the southeastern US identifies that human alterations (stressors) of upland in a watershed such as increased impervious cover will lead to changes in the physical and chemical environment such as microbial and nutrient pollution (exposures), of a receiving water body which then lead to changes in the living resources (responses). The overall objective of this study is to evaluate the applicability of the current tidal creek classification framework and conceptual model linking tidal creek ecological condition to potential impacts of development and urban growth on ecosystem value and function in the Gulf of Mexico US in collaboration with Gulf of Mexico NERR sites. The conceptual model was validated for the Gulf of Mexico US tidal creeks. The tidal creek classification system developed for the southeastern US could be applied to the Gulf of Mexico tidal creeks; however, some differences were found that warrant further examination. In particular, pollutants appeared to translate further downstream in the Gulf of Mexico US compared to the southeastern US. These differences are likely the result of the morphological and oceanographic differences between the two regions. Tidal creeks appear to serve as sentinel habitats to provide an early warning of the ensuing harm to the larger ecosystem in both the Southeastern and Gulf of Mexico US tidal creeks.

A surveillance strategy for invasive species of concern in deepwater habitats of the Northwestern Hawaiian Islands

This report describes a surveillance strategy to detect deepwater invasive species in the Northwestern Hawaiian Islands. A need for this strategy was identified in the Papahānaumokuākea Marine National Monument Management Plan and the Monument’s Draft Natural Resources Science Plan. This strategy focuses on detecting two species of concern, the octocoral Carijoa riisei and the red alga Hypnea musciformis. Most research on invasive species in the Hawaiian archipelago has focused on shallow water habitats within the limits of conventional SCUBA (0-30 m). Deeper habitats such as mesophotic reefs are much more difficult to access and consequently little is known about the distribution of deepwater invasive species or their impacts. Recent deepwater (>30 m) sightings of H. musciformis and C. riisei, in and near NWHI, respectively, have prompted a call for further research and surveillance of invasive species in deepwater habitats. This report compiles the most up to date information about these two species of concern in deepwater habitats. A literature search and conversations with subject matter experts was used to identify their current distribution, preferred habitat types, optimal detection methods and ways to efficiently sample the vast extent of NWHI. The proposed sampling strategy prioritizes survey effort where C. riisei and H. musciformis are most likely to be found. At coarse spatial scales (tens to hundreds of kilometers), opportunistic observations and distance from the Main Hawaiian Islands, a principal propagule source, are used to identify high-risk islands and banks. At fine spatial scales (meters to tens of kilometers) a habitat suitability model was developed to identify high-risk habitats. The habitat suitability model focused on habitat preferences of C. riisei, since the species is well studied and adequate data exists to map habitats. There was insufficient information to identify suitable habitat for H. muscifomis. Habitat preferences for the algae are poorly understood and there is a lack of data at relevant spatial scales to map those preferences which are known. The principal habitats identified by the habitat suitability model were ledges and the edges of rugose coral reefs, where the shade loving octocoral would likely be found. Habitat suitability maps were developed for seven atolls and banks to aid in survey site selection. The protocol relied on technical divers to conduct visual surveys of benthic habitats. It was developed to increase the efficiency of surveys, maximize the probability of detection, identify important information relevant to future surveys and standardize results. The strategy, model and protocol were tested during a field mission in 2009 at several atolls and islands in NWHI. The field mission did not detect any invasive species among deepwater habitats and much was learned to improve future surveys. Data gaps and improvements are discussed.