Robust background model for pixel based people counting using a single uncalibrated camera

Several pixel-based people counting methods have been developed over the years. Among these the product of scale-weighted pixel sums and a linear correlation coefficient is a popular people counting approach. However most approaches have paid little attention to resolving the true background and instead take all foreground pixels into account. With large crowds moving at varying speeds and with the presence of other moving objects such as vehicles this approach is prone to problems. In this paper we present a method which concentrates on determining the true-foreground, i.e. human-image pixels only. To do this we have proposed, implemented and comparatively evaluated a human detection layer to make people counting more robust in the presence of noise and lack of empty background sequences. We show the effect of combining human detection with a pixel-map based algorithm to i) count only human-classified pixels and ii) prevent foreground pixels belonging to humans from being absorbed into the background model. We evaluate the performance of this approach on the PETS 2009 dataset using various configurations of the proposed methods. Our evaluation demonstrates that the basic benchmark method we implemented can achieve an accuracy of up to 87% on sequence ¿S1.L1 13-57 View 001¿ and our proposed approach can achieve up to 82% on sequence ¿S1.L3 14-33 View 001¿ where the crowd stops and the benchmark accuracy falls to 64%.

Performance evaluation of crowd image analysis using the PETS2009 dataset

This paper presents the PETS2009 outdoor crowd image analysis surveillance dataset and the performance evaluation of people counting, detection and tracking results using the dataset submitted to five IEEE Performance Evaluation of Tracking and Surveillance (PETS) workshops. The evaluation was carried out using well established metrics developed in the Video Analysis and Content Extraction (VACE) programme and the CLassification of Events, Activities, and Relationships (CLEAR) consortium. The comparative evaluation highlights the detection and tracking performance of the authors’ systems in areas such as precision, accuracy and robustness and provides a brief analysis of the metrics themselves to provide further insights into the performance of the authors’ systems.

Autosomal recessive ataxias: 20 types, and counting

More than 140 years after the first description of Friedreich ataxia, autosomal recessive ataxias have become one of the more complex fields in Neurogenetics. Currently this group of diseases contains more than 20 clinical entities and an even larger number of associated genes. Some disorders are very rare, restricted to isolated populations, and others are found worldwide. An expressive number of recessive ataxias are treatable, and responsibility for an accurate diagnosis is high. The purpose of this review is to update the practitioner on clinical and pathophysiological aspects of these disorders and to present an algorithm to guide the diagnosis.

Crowd scene during Ky visit to Brisbane

Crowd scene during visit of former South Vietnamese vice president Nguyen Cao Ky to Brisbane, Australia in January 1967.

Event-related potentials in the emotional colour naming stroop task and the emotional counting stroop task

This study compared emotional Stroop interference in the emotional colour naming Stroop and the emotional counting Stroop by measuring reaction times and event-related potentials to positive, negative and neutral words. Twenty participants had ERPs recorded at 61 sites while performing both types of emotional Stroop tasks as well as congruent and incongruent conflict conditions. All participants rated stimulus emotionality retrospectively. A robust reaction time Stroop effect was observed in response latency for the traditional ‘‘conflict’’ conditions (congruent vs. incongruent) for the counting Stroop though not the colour naming Stroop task. There was also no evidence of emotional interference for either of the tasks; however, there was trend for positive interference in the colour naming Stroop. The P5 was identified as the event-related potential associated with emotional processing. For the P5 component, significant emotionality effects were evident in the emotional colour naming Stroop for latency (542 ms). There was a significant interaction between valence and hemisphere. The latency of the P5 in the right hemisphere was later for the positive words than negative and neutral. Comparable effects of valence were evident for the emotional counting Stroop for amplitude but not latency.

Improved method for counting virus and virus like particles

An improved method for counting virus and virus like particles by electron microscopy (EM) was developed. The procedure involves the determination of the absolute concentration of pure or semi-pure particles once deposited evenly on EM grids using either centrifugation or antibody capture techniques. The counting of particles was done with a Microfiche unit which enlarged approximately 50 x the image of particles on a developed negative film which had been taken at a relatively low magnification (2500 x) by EM. Initially, latex particles of a known concentration were counted using this approach, to prove the accuracy of the technique. The latex particles were deposited evenly on an EM grid using centrifugation (Modified Beckmen EM-90 Airfuge technique). Subsequently, recombinant Bluetongue virus (BTV) core-like particles (CLPs) captured by a Monoclonal antibody using a hovel sample loading method were counted by the Microfiche unit method and by a direct EM method. Comparison of the simplified counting method developed with a conventional method, showed good agreement. The method is simple, accurate, rapid, and reproducible when used with either pure particles or with particles from crude cell culture extracts.

Os deícticos no discurso narrativo: demonstrativos e advérbios de lugar em Far from the madding crowd

O artigo está disponível em texto integral no link da versão do editor

People counting system using existing surveillance video camera

The Casa da Música Foundation, responsible for the management of Casa da Música do Porto building, has the need to obtain statistical data related to the number of building’s visitors. This information is a valuable tool for the elaboration of periodical reports concerning the success of this cultural institution. For this reason it was necessary to develop a system capable of returning the number of visitors for a requested period of time. This represents a complex task due to the building’s unique architectural design, characterized by very large doors and halls, and the sudden large number of people that pass through them in moments preceding and proceeding the different activities occurring in the building. To achieve the technical solution for this challenge, several image processing methods, for people detection with still cameras, were first studied. The next step was the development of a real time algorithm, using OpenCV libraries and computer vision concepts,to count individuals with the desired accuracy. This algorithm includes the scientific and technical knowledge acquired in the study of the previous methods. The themes developed in this thesis comprise the fields of background maintenance, shadow and highlight detection, and blob detection and tracking. A graphical interface was also built, to help on the development, test and tunning of the proposed system, as a complement to the work. Furthermore, tests to the system were also performed, to certify the proposed techniques against a set of limited circumstances. The results obtained revealed that the algorithm was successfully applied to count the number of people in complex environments with reliable accuracy.

Neuronal counting and parasympathetic dysfunction in the hearts of chronically Trypanosoma cruzi - infected rats

Ten male Wistar rats, chronically infected with Colombian, São Felipe (12SF) and Y strains of Trypanosoma cruzi and ten non-infected control animals were submitted to the bradycardia responsiveness test, an assessment of heart parasympathetic function, after phenylephrine injection. Six chagasic animals showed heart parasympathetic dysfuntion characterized by reduction in the index of bradycardia baroreflex responsiveness, as compared with the control group. Microscopic examination of the atrial heart ganglia of chagasic rats showed ganglionitis, but no statiscally significant reduction in the number of neurons.

Methodological limitations of counting total leukocytes and thrombocytes in reptiles (Amazon turtle, Podocnemis expansa): an analysis and discussion

The aim of this paper is to compare three different methods for counting white blood cells [WBC] (Natt and Herrick method, estimation with 1,000 and 2,000 erythrocytes) and three methods for counting total thrombocytes [TT] (Wojtaszek method, estimation with 1,000 and 2,000 erythrocytes) in a South American freshwater turtle species, Podocnemis expansa, Schweigger 1812 (Reptilia, Pelomedusidae). Direct WBC counts using the Natt and Herrick method showed limitations, which are discussed here. The WBC and TT counts using 1,000 erythrocytes from blood smears are not recommended for Amazon turtles nor other reptilian species, since wide variation in counts can be observed. Estimation methods for determining WBC and TT based on 2,000 erythrocytes of blood smears were most acceptable because they allow a differentiation between leukocytes and thrombocytes and also had a smaller variation. The methods investigated here for the Amazon turtle, which have been widely used in other reptile species, provided evidence that the most acceptable method is not that of using diluted stains and a hemocytometer.

Preschool education in Brazil: does public supply crowd out private enrollment?

Expanding access to preschool education is a particularly important policy issue in developing countries, where enrollment rates are generally much lower, and where private institutions constitute a much larger share of the formal preschool sector, than in developed countries. This paper examines if an expansion in the supply of public preschool crowds-out private enrollment using rich data for municipalities in Brazil from 2000 to 2006, where federal transfers to local governments change discontinuously with given population thresholds. Results from a regression-discontinuity design reveal that larger federal transfers lead to a significant expansion of local public preschool services, but show no evidence of crowding-out of private enrollment, nor of negative impacts on the quality of private providers. This finding is consistent with a theory in which households differ in willingness-to-pay for preschool services, and private suppliers optimally adjust prices in response to an expansion of lower-quality, free-of-charge public supply. In the context of the model, the absence of crowding-out effects of more public preschool providers can be rationalized by the existence of relatively large differences in willingness-to-pay for preschool services across different demand segments. Our theoretical and empirical findings therefore suggest that in developing country settings characterized by relatively high income inequality, an expansion in public preschool supply will likely significantly increase enrollment among the poorest segments of society, and need not have adverse effects on the quantity or quality of local private supply.