A design methodology for selecting and placement of sensors in multimedia surveillance systems

This paper addresses the problem of how to select the optimal number of sensors and how to determine their placement in a given monitored area for multimedia surveillance systems. We propose to solve this problem by obtaining a novel performance metric in terms of a probability measure for accomplishing the task as a function of set of sensors and their placement. This measure is then used to find the optimal set. The same measure can be used to analyze the degradation in system 's performance with respect to the failure of various sensors. We also build a surveillance system using the optimal set of sensors obtained based on the proposed design methodology. Experimental results show the effectiveness of the proposed design methodology in selecting the optimal set of sensors and their placement.

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

Integration of technologies for understanding the functional relationship between reef habitat and fish growth and production

Functional linkage between reef habitat quality and fish growth and production has remained elusive. Most current research is focused on correlative relationships between a general habitat type and presence/absence of a species, an index of species abundance, or species diversity. Such descriptive information largely ignores how reef attributes regulate reef fish abundance (density-dependent habitat selection), trophic interactions, and physiological performance (growth and condition). To determine the functional relationship between habitat quality, fish abundance, trophic interactions, and physiological performance, we are using an experimental reef system in the northeastern Gulf of Mexico where we apply advanced sensor and biochemical technologies. Our study site controls for reef attributes (size, cavity space, and reef mosaics) and focuses on the processes that regulate gag grouper (Mycteroperca microlepis) abundance, behavior and performance (growth and condition), and the availability of their pelagic prey. We combine mobile and fixed-active (fisheries) acoustics, passive acoustics, video cameras, and advanced biochemical techniques. Fisheries acoustics quantifies the abundance of pelagic prey fishes associated with the reefs and their behavior. Passive acoustics and video allow direct observation of gag and prey fish behavior and the acoustic environment, and provide a direct visual for the interpretation of fixed fisheries acoustics measurements. New application of biochemical techniques, such as Electron Transport System (ETS) assay, allow the in situ measurement of metabolic expenditure of gag and relates this back to reef attributes, gag behavior, and prey fish availability. Here, we provide an overview of our integrated technological approach for understanding and quantifying the functional relationship between reef habitat quality and one element of production – gag grouper growth on shallow coastal reefs.

Fluctuation characteristics of arc voltage and jet flow in a non-transferred dc plasma generated at reduced pressure

A torch with a set of inter-electrode inserts between the cathode and the anode/nozzle with a wide nozzle exit was designed to generate plasma jets at chamber pressures of 500–10 000 Pa. The variation of the arc voltage was examined with the change in working parameters such as gas flow rate and chamber pressure. The fluctuation in the arc voltage was recorded with an oscilloscope, and the plasma jet fluctuation near the torch exit was observed with a high-speed video camera and detected with a double-electrostatic probe. Results show that the 300 Hz wave originated from the tri-phase rectified power supply was always detected under all generating conditions. Helmholtz oscillations over 3000 Hz was detected superposed on the 300 Hz wave at gas flow rates higher than 8.8 slm with a peak to valley amplitude lower than 5% of the average voltage value. No appreciable voltage fluctuation caused by the irregular arc root movement is detected, and mechanisms for the arc voltage and jet flow fluctuations are discussed.

Assessment of fish populations and habitat on Oculina Bank, a deep-sea coral marine protected area off eastern Florida

A portion of the Oculina Bank located off eastern Florida is a marine protected area (MPA) preserved for its dense populations of the ivory tree coral (Oculina varicosa), which provides important habitat for fish. Surveys of fish assemblages and benthic habitat were conducted inside and outside the MPA in 2003 and 2005 by using remotely operated vehicle video transects and digital still imagery. Fish species composition, biodiversity, and grouper densities were used to determine whether O. varicosa forms an essential habitat compared to other structure-forming habitats and to examine the effectiveness of the MPA. Multivariate analyses indicated no differences in fish assemblages or biodiversity among hardbottom habitat types and grouper densities were highest among the most complex habitats; however the higher densities were not exclusive to coral habitat. Therefore, we conclude that O. varicosa was functionally equivalent to other hardbottom habitats. Even though fish assemblages were not different among management areas, biodiversity and grouper densities were higher inside the MPA compared to outside. The percentage of intact coral was also higher inside the MPA. These results provide initial evidence demonstrating effectiveness of the MPA for restoring reef fish and their habitat. This is the first study to compare reef fish populations on O. varicosa with other structure-forming reef habitats and also the first to examine the effectiveness of the MPA for restoring fish populations and live reef cover.

A survey of deep-water coral and sponge habitats along the west coast of the US using a remotely operated vehicle: NOAA Fisheries Survey Vessel (FSV)'Bell M. Shimada', November 1-5, 2010

Remotely operated vehicle (ROV) surveys were conducted from NOAA’s state-of-the-art Fisheries Survey Vessel (FSV) Bell M. Shimada during a six-day transit November 1-5, 2010 between San Diego, CA and Seattle, WA. The objective of this survey was to locate and characterize deep-sea coral and sponge ecosystems at several recommended sites in support of NOAA’s Coral Reef Conservation Program. Deep-sea corals and sponges were photographed and collected whenever possible using the Southwest Fisheries Science Center’s (SWFSC) Phantom ROV ‘Sebastes’ (Fig. 1). The surveyed sites were recommended by National Marine Sanctuary (NMS) scientists at Monterey Bay NMS, Gulf of the Farallones NMS, and Olympic Coast NMS (Fig. 2). The specific sites were: Sur Canyon, The Football, Coquille Bank, and Olympic Coast NMS. During each dive, the ROV collected digital still images, video, navigation, and along-track conductivity-temperature-depth (CTD), and optode data. Video and high-resolution photographs were used to quantify abundance of corals, sponges, and associated fishes and invertebrates to the lowest practicable taxonomic level, and also to classify the seabed by substrate type. A reference laser system was used to quantify area searched and estimate the density of benthic fauna.

The socio-economic and cultural structures of the fisherfolk communities

Fishing communities that have exploited the resource for generations constitute the main stakeholder groups in the fisheries of Lake Victoria. Several studies have examined Uganda's Lake Victoria fishing communities and characterised key stakeholders at community level over the last decade (SEDAWOG 1999a and b; Geheb 1997; FeSEP 1997; Kitakule 1991). The communities are made up of scattered settlements at the shores and on islands. The categories of people living in these communities include fishers who consist primarily of large numbers of male youths who provide labour to boat and gear owners. There are resident and non-resident fish traders who after securing their supplies at the beaches, depart for their market destinations. In addition, there are fish processors, mostly operating traditional and improved smoking kilns. Many other people, dealing in provisions and supplies also stay at the beaches, their activities depending on the level of fish catch. The fishing communities of Lake Victoria, Uganda, include auxiliary livelihood activities such as boat building, net repairing and transportation; bait supply and beachside kiosks, video halls and retail shop business. Other economic activities are brick making, charcoal burning/wood trade, farming and livestock keeping.

Video segmentation with superpixels

Due to its importance, video segmentation has regained interest recently. However, there is no common agreement about the necessary ingredients for best performance. This work contributes a thorough analysis of various within- and between-frame affinities suitable for video segmentation. Our results show that a frame-based superpixel segmentation combined with a few motion and appearance-based affinities are sufficient to obtain good video segmentation performance. A second contribution of the paper is the extension of [1] to include motion-cues, which makes the algorithm globally aware of motion, thus improving its performance for video sequences. Finally, we contribute an extension of an established image segmentation benchmark [1] to videos, allowing coarse-to-fine video segmentations and multiple human annotations. Our results are tested on BMDS [2], and compared to existing methods. © 2013 Springer-Verlag.

Synchronization of user-generated videos through trajectory correspondence and a refinement procedure

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied through the time-stamp information embedded in the video streams. User-generated videos shot using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. Our first contribution is a synchronization technique which tries to establish correspondence between feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. We evaluate performance using a number of real video recordings and show that our method is able to synchronize to within 1 sec, which is significantly better than previous approaches. Our second contribution is a robust and unsupervised view-invariant activity recognition descriptor that exploits recurrence plot theory on spatial tiles. The descriptor is individually shown to better characterize the activities from different views under occlusions than state-of-the-art approaches. We combine this descriptor with our proposed synchronization method and show that it can further refine the synchronization index. © 2013 ACM.

Extra- and intra-cellular ice formation of red seabream (Pagrus major) embryos at different cooling rates

The ice crystal formation is assumed as the most lethal factor for the failure of fish embryo cryopreservation and intracellular ice formation (IIF) plays a central role in cell injury during cooling. The objectives were to observe the morphological changes of red seabream (Pagrus major) embryo during the cooling-thawing process, and to examine the effect of cryoprotectant and cooling rate on the temperatures of oil globule ice formation (T-OIF), extra-cellular ice formation (T-EIF) and intracellular ice formation (T-IIF) using cryomicroscope. After thawing, the morphological changes of embryos were observed and recorded by the video attachment and monitor under the microscope. During the cooling process, three representative phenomena were observed: oil globule gradually turned bright firstly, then the whole field of view flashed and the embryo blackened. Cooling rate affect the temperature of both extra- and intra-cellular ice formations. T-EIF and T-IIF at high cooling rate were much lower than that at low cooling rate. And the value of T-EIF - T-IIF increased from 0.45 to 11.11 degrees C with the increase of cooling rate from 3 to 130 degrees C/min. Taken together, our results suggested that high cooling rate with proper cryoprotectant would be a good option for red seabream embryo cryopreservation. (C) 2009 Elsevier Inc. All rights reserved.

Learning object segmentation from video data

This memo describes the initial results of a project to create a self-supervised algorithm for learning object segmentation from video data. Developmental psychology and computational experience have demonstrated that the motion segmentation of objects is a simpler, more primitive process than the detection of object boundaries by static image cues. Therefore, motion information provides a plausible supervision signal for learning the static boundary detection task and for evaluating performance on a test set. A video camera and previously developed background subtraction algorithms can automatically produce a large database of motion-segmented images for minimal cost. The purpose of this work is to use the information in such a database to learn how to detect the object boundaries in novel images using static information, such as color, texture, and shape. This work was funded in part by the Office of Naval Research contract #N00014-00-1-0298, in part by the Singapore-MIT Alliance agreement of 11/6/98, and in part by a National Science Foundation Graduate Student Fellowship.

Benefits and Effects of Interactive Gaming Exercise as Compared to Traditional Exercise Techniques: An Investigation of the Relationship Between Physical Activity Levels and Mode of Activity in College Students

Gemstone Team F.I.T.N.E.S.S. (Fun Interactive Techniques for New Exercise and Sport Styles)

Development of a decision aid to inform patients' and families' renal replacement therapy selection decisions.

BACKGROUND: Few educational resources have been developed to inform patients' renal replacement therapy (RRT) selection decisions. Patients progressing toward end stage renal disease (ESRD) must decide among multiple treatment options with varying characteristics. Complex information about treatments must be adequately conveyed to patients with different educational backgrounds and informational needs. Decisions about treatment options also require family input, as families often participate in patients' treatment and support patients' decisions. We describe the development, design, and preliminary evaluation of an informational, evidence-based, and patient-and family-centered decision aid for patients with ESRD and varying levels of health literacy, health numeracy, and cognitive function. METHODS: We designed a decision aid comprising a complementary video and informational handbook. We based our development process on data previously obtained from qualitative focus groups and systematic literature reviews. We simultaneously developed the video and handbook in "stages." For the video, stages included (1) directed interviews with culturally appropriate patients and families and preliminary script development, (2) video production, and (3) screening the video with patients and their families. For the handbook, stages comprised (1) preliminary content design, (2) a mixed-methods pilot study among diverse patients to assess comprehension of handbook material, and (3) screening the handbook with patients and their families. RESULTS: The video and handbook both addressed potential benefits and trade-offs of treatment selections. The 50-minute video consisted of demographically diverse patients and their families describing their positive and negative experiences with selecting a treatment option. The video also incorporated health professionals' testimonials regarding various considerations that might influence patients' and families' treatment selections. The handbook was comprised of written words, pictures of patients and health care providers, and diagrams describing the findings and quality of scientific studies comparing treatments. The handbook text was written at a 4th to 6th grade reading level. Pilot study results demonstrated that a majority of patients could understand information presented in the handbook. Patient and families screening the nearly completed video and handbook reviewed the materials favorably. CONCLUSIONS: This rigorously designed decision aid may help patients and families make informed decisions about their treatment options for RRT that are well aligned with their values.

Computer vision tools for low-cost and noninvasive measurement of autism-related behaviors in infants.

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral signs can be observed late in the first year of life. Many of these studies involve extensive frame-by-frame video observation and analysis of a child's natural behavior. Although nonintrusive, these methods are extremely time-intensive and require a high level of observer training; thus, they are burdensome for clinical and large population research purposes. This work is a first milestone in a long-term project on non-invasive early observation of children in order to aid in risk detection and research of neurodevelopmental disorders. We focus on providing low-cost computer vision tools to measure and identify ASD behavioral signs based on components of the Autism Observation Scale for Infants (AOSI). In particular, we develop algorithms to measure responses to general ASD risk assessment tasks and activities outlined by the AOSI which assess visual attention by tracking facial features. We show results, including comparisons with expert and nonexpert clinicians, which demonstrate that the proposed computer vision tools can capture critical behavioral observations and potentially augment the clinician's behavioral observations obtained from real in-clinic assessments.

An information system to exploit the use of metadata within film and television production

The article focuses on an information system to exploit the use of metadata within film and television production. It is noted that the television and film industries are used to working on big projects. This involves the use of actual film, video tape, and P.E.R.T charts for project planning. Scripts are in most instances revised. It is essential to attach information on these in order to manage, track and retrieve them. The use of metadata eases the operations involved in these industries.