Video Surveillance Online Repository (ViSOR): an integrated framework

The availability of new techniques and tools for Video Surveillance and the capability of storing huge amounts of visual data acquired by hundreds of cameras every day call for a convergence between pattern recognition, computer vision and multimedia paradigms. A clear need for this convergence is shown by new research projects which attempt to exploit both ontology-based retrieval and video analysis techniques also in the field of surveillance. This paper presents the ViSOR (Video Surveillance Online Repository) framework, designed with the aim of establishing an open platform for collecting, annotating, retrieving, and sharing surveillance videos, as well as evaluating the performance of automatic surveillance systems. Annotations are based on a reference ontology which has been defined integrating hundreds of concepts, some of them coming from the LSCOM and MediaMill ontologies. A new annotation classification schema is also provided, which is aimed at identifying the spatial, temporal and domain detail level used. The ViSOR web interface allows video browsing, querying by annotated concepts or by keywords, compressed video previewing, media downloading and uploading. Finally, ViSOR includes a performance evaluation desk which can be used to compare different annotations.     

Multistage particle windows for fast and accurate object detection

The common paradigm employed for object detection is the sliding window (SW) search. This approach generates grid-distributed patches, at all possible positions and sizes, which are evaluated by a binary classifier: The tradeoff between computational burden and detection accuracy is the real critical point of sliding windows; several methods have been proposed to speed up the search such as adding complementary features. We propose a paradigm that differs from any previous approach since it casts object detection into a statistical-based search using a Monte Carlo sampling for estimating the likelihood density function with Gaussian kernels. The estimation relies on a multistage strategy where the proposal distribution is progressively refined by taking into account the feedback of the classifiers. The method can be easily plugged into a Bayesian-recursive framework to exploit the temporal coherency of the target objects in videos. Several tests on pedestrian and face detection, both on images and videos, with different types of classifiers (cascade of boosted classifiers, soft cascades, and SVM) and features (covariance matrices, Haar-like features, integral channel features, and histogram of oriented gradients) demonstrate that the proposed method provides higher detection rates and accuracy as well as a lower computational burden w.r.t. sliding window detection.     

Neighbor cache prefetching for multimedia image and video processing

Cache performance is strongly influenced by the type of locality embodied in programs. In particular, multimedia programs handling images and videos are characterized by a bidimensional spatial locality, which is not adequately exploited by standard caches. In this paper we propose novel cache prefetching techniques for image data, called neighbor prefetching, able to improve exploitation of bidimensional spatial locality. A performance comparison is provided against other assessed prefetching techniques on a multimedia workload (with MPEG-2 and MPEG-4 decoding, image processing, and visual object segmentation), including a detailed evaluation of both the miss rate and the memory access time. Results prove that neighbor prefetching achieves a significant reduction in the time due to delayed memory cycles (more than 97% on MPEG-4 with respect to 75% of the second performing technique). This reduction leads to a substantial speedup on the overall memory access time (up to 140% for MPEG-4). Performance has been measured with the PRIMA trace-driven simulator, specifically devised to support cache prefetching.     

Image analysis and rule-based reasoning for a traffic monitoringsystem

The paper presents an approach for detecting vehicles in urban traffic scenes by means of rule-based reasoning on visual data. The strength of the approach is its formal separation between the low-level image processing modules and the high-level module, which provides a general-purpose knowledge-based framework for tracking vehicles in the scene. The image-processing modules extract visual data from the scene by spatio-temporal analysis during daytime, and by morphological analysis of headlights at night. The high-level module is designed as a forward chaining production rule system, working on symbolic data, i.e., vehicles and their attributes (area, pattern, direction, and others) and exploiting a set of heuristic rules tuned to urban traffic conditions. The synergy between the artificial intelligence techniques of the high-level and the low-level image analysis techniques provides the system with flexibility and robustness     

Dietary treatment for regurgitation--recommendations from a working party

Previous studies established that retrovirally infected young mice produced large amounts of autoantibodies to certain T-cell receptor (TCR) peptides whose administration diminished retrovirus-induced immune abnormalities. C57BL/6 young (4 weeks) and old (16 months) female mice were injected with these same synthetic human TCR V beta 8.1 or 5.2 peptides. Administration of these autoantigenic peptides to old mice prevent immunosenescence, such as age-related reduction in splenocyte proliferation and interleukin-2 (IL-2) secretion. TCR V beta peptide injection into young mice had no effect on T- or B-cell mitogenesis and IL-4 production while modifying tumour necrosis factor-alpha (TNF-alpha), IL-6, and interferon-gamma (IFN-gamma) secreted by mitogen-stimulated spleen cells. TCR V beta injection also retarded the excessive production of IL-4, IL-6 and TNF-alpha induced by ageing. These data suggest that immune dysfunction and abnormal cytokine production, induced by the ageing process, were largely prevented by injection of selected TCR V beta CDR1 peptides.     

Probabilistic posture classification for Human-behavior analysis

Computer vision and ubiquitous multimedia access nowadays make feasible the development of a mostly automated system for human-behavior analysis. In this context, our proposal is to analyze human behaviors by classifying the posture of the monitored person and, consequently, detecting corresponding events and alarm situations, like a fall. To this aim, our approach can be divided in two phases: for each frame, the projection histograms (Haritaoglu et al., 1998) of each person are computed and compared with the probabilistic projection maps stored for each posture during the training phase; then, the obtained posture is further validated exploiting the information extracted by a tracking module in order to take into account the reliability of the classification of the first phase. Moreover, the tracking algorithm is used to handle occlusions, making the system particularly robust even in indoors environments. Extensive experimental results demonstrate a promising average accuracy of more than 95% in correctly classifying human postures, even in the case of challenging conditions.     

Bayesian-competitive consistent labeling for people surveillance

This paper presents a novel and robust approach to consistent labeling for people surveillance in multi-camera systems. A general framework scalable to any number of cameras with overlapped views is devised. An off-line training process automatically computes ground-plane homography and recovers epipolar geometry. When a new object is detected in any one camera, hypotheses for potential matching objects in the other cameras are established. Each of the hypotheses is evaluated using a prior and likelihood value. The prior accounts for the positions of the potential matching objects, while the likelihood is computed by warping the vertical axis of the new object on the field of view of the other cameras and measuring the amount of match. In the likelihood, two contributions (forward and backward) are considered so as to correctly handle the case of groups of people merged into single objects. Eventually, a maximum-a-posteriori approach estimates the best label assignment for the new object. Comparisons with other methods based on homography and extensive outdoor experiments demonstrate that the proposed approach is accurate and robust in coping with segmentation errors and in disambiguating groups.     

Gastric emptying delay and gastric electrical derangement in IDDM

BACKGROUND: Attention has long been drawn to the potentially harmful effects of coffee on health, however recent epidemiological studies have suggested unexpected, possibly beneficial effects of coffee against the occurrence of alcoholic liver cirrhosis and upon serum liver enzyme levels. METHODS: We examined the potential inverse association between coffee drinking and serum concentrations of gamma-glutamyltransferase (GGT) and aminotransferases, with special reference to interaction with alcohol consumption, in a cross-sectional study involving 12687 health examinees (7398 men and 5289 women) aged 40-69 years from over 1000 workplaces in Nagano prefecture in central Japan. Those who had a history of liver disease and/or serum aminotransferases exceeding the normal range were excluded. Possible confounding effects of alcohol consumption, body mass index, cigarette smoking, and green tea consumption were controlled through multivariate analyses. RESULTS: Increased coffee consumption was strongly and independently associated with decreased GGT activity among males (P trend < 0.0001); the inverse association between coffee and serum GGT was more evident among heavier alcohol consumers (P < 0.0001), and was absent among non-alcohol drinkers. Among females, however, coffee was only weakly related to lower GGT level. Similar inverse associations with coffee and interactions between coffee and alcohol intake were observed for serum aspartate aminotransferase and alanine aminotransferase. Intake of green tea, another popular source of caffeine in Japan, did not materially influence the liver enzyme levels. CONCLUSIONS: Our results suggest that coffee may inhibit the induction of GGT in the liver by alcohol consumption, and may possibly protect against liver cell damage due to alcohol.