Semantic feature-based visual attention model for pedestrian detection

Objective
Pedestrian detection under video surveillance systems has always been a hot topic in computer vision research. These systems are widely used in train stations, airports, large commercial plazas, and other public places. However, pedestrian detection remains difficult because of complex backgrounds. Given its development in recent years, the visual attention mechanism has attracted increasing attention in object detection and tracking research, and previous studies have achieved substantial progress and breakthroughs. We propose a novel pedestrian detection method based on the semantic features under the visual attention mechanism.
Method
The proposed semantic feature-based visual attention model is a spatial-temporal model that consists of two parts: the static visual attention model and the motion visual attention model. The static visual attention model in the spatial domain is constructed by combining bottom-up with top-down attention guidance. Based on the characteristics of pedestrians, the bottom-up visual attention model of Itti is improved by intensifying the orientation vectors of elementary visual features to make the visual saliency map suitable for pedestrian detection. In terms of pedestrian attributes, skin color is selected as a semantic feature for pedestrian detection. The regional and Gaussian models are adopted to construct the skin color model. Skin feature-based visual attention guidance is then proposed to complete the top-down process. The bottom-up and top-down visual attentions are linearly combined using the proper weights obtained from experiments to construct the static visual attention model in the spatial domain. The spatial-temporal visual attention model is then constructed via the motion features in the temporal domain. Based on the static visual attention model in the spatial domain, the frame difference method is combined with optical flowing to detect motion vectors. Filtering is applied to process the field of motion vectors. The saliency of motion vectors can be evaluated via motion entropy to make the selected motion feature more suitable for the spatial-temporal visual attention model.
Result
Standard datasets and practical videos are selected for the experiments. The experiments are performed on a MATLAB R2012a platform. The experimental results show that our spatial-temporal visual attention model demonstrates favorable robustness under various scenes, including indoor train station surveillance videos and outdoor scenes with swaying leaves. Our proposed model outperforms the visual attention model of Itti, the graph-based visual saliency model, the phase spectrum of quaternion Fourier transform model, and the motion channel model of Liu in terms of pedestrian detection. The proposed model achieves a 93% accuracy rate on the test video.
Conclusion
This paper proposes a novel pedestrian method based on the visual attention mechanism. A spatial-temporal visual attention model that uses low-level and semantic features is proposed to calculate the saliency map. Based on this model, the pedestrian targets can be detected through focus of attention shifts. The experimental results verify the effectiveness of the proposed attention model for detecting pedestrians.

Local Field Potentials in the Gustatory Cortex Carry Taste Information

It has been recently shownthat localfield potentials (LFPs)fromthe auditory and visual cortices carry information about sensory stimuli, but whether this is a universal property of sensory cortices remains to be determined. Moreover, little is known about the temporal dynamics of sensory information contained in LFPs following stimulus onset. Here we investigated the time course of the amount of stimulus information in LFPs and spikes from the gustatory cortex of awake rats subjected to tastants and water delivery on the tongue. We found that the phase and amplitude of multiple LFP frequencies carry information about stimuli, which have specific time courses after stimulus delivery. The information carried by LFP phase and amplitude was independent within frequency bands, since the joint information exhibited neither synergy nor redundancy. Tastant information in LFPs was also independent and had a different time course from the information carried by spikes. These findings support the hypothesis that the brain uses different frequency channels to dynamically code for multiple features of a stimulus.

Field Evaluation of a Competitive Lateral-flow Assay for Detection of Alternaria brassicae in Vegetable Brassica Crops

On-site detection of inoculum of polycyclic plant pathogens could potentially contribute to management of disease outbreaks. A 6-min, in-field competitive immunochromatographic lateral flow device (CLFD) assay was developed for detection of Alternaria brassicae (the cause of dark leaf spot in brassica crops) in air sampled above the crop canopy. Visual recording of the test result by eye provides a detection threshold of approximately 50 dark leaf spot conidia. Assessment using a portable reader improved test sensitivity. In combination with a weather-driven infection model, CLFD assays were evaluated as part of an in-field risk assessment to identify periods when brassica crops were at risk from A. brassicae infection. The weather-driven model overpredicted A. brassicae infection. An automated 7-day multivial cyclone air sampler combined with a daily in-field CLFD assay detected A. brassicae conidia air samples from above the crops. Integration of information from an in-field detection system (CLFD) with weather-driven mathematical models predicting pathogen infection have the potential for use within disease management systems.

A visual system for distributed mosaics using an auvs fleet

The use of teams of Autonomous Underwater Vehicles for visual inspection tasks is a promising robotic field. The images captured by different robots can be also to aid in the localization/navigation of the fleet. In a previous work, a distributed localization system was presented based on the use of Augmented States Kalman Filter through the visual maps obtained by the fleet. In this context, this paper details a system for on-line construction of visual maps and its use to aid the localization and navigation of the robots. Different aspects related to the capture, treatment and construction of mosaics by fleets of robots are presented. The developed system can be executed on-line on different robotic platforms. The paper is concluded with a series of tests and analyses aiming at to system validation.

The 2001 BFA Graduating Class Department of Visual Arts

One of the highlights of Grenfells annual Convocation is the exhibition of the works of the graduating class in visual arts. The exhibition gives us a priviledged glimpse into the accomplishments of our students as these have emerged directly out of their studies. By their nature, most other disciplines do not afford such a view. In a sense, then, the exhibition of works by our visual arts students represents by analogy what can be achieved in four years of intensive university study under the guidance of dedicated professionals, no matter what the field of endeavour. These particular students began with a natural ability to see and to imagine.During tha past four years, they have been challenged to build on that base talent and to develop and educate their visual imaginations. Significant creative development is never easy but the results can be inspiring. The works represent the accomplishments of all our students and provide a fresh energeticaesthetic framework within which to contemplate them.

Epistemología del pensamiento visual contemporáneo desde el imaginario transdisciplinario

El pensamiento visual contemporáneo trae consigo un campo nuevo deconocimiento. Los llamados estudios visuales implican nuevos problemas, que se caracterizan, a su vez, por niveles de complejidad inéditos y requerimientos transdisciplinarios de abordaje. Este estudio propone un análisis epistemológico a partir del problema de la construcción de la realidad, en su relación con el imaginario y el régimen escópico. En este sentido, se insiste en la apertura al estudio de la visualidad –sobre todo– desde una perspectiva compleja y transdisciplinaria.

‘Ladd traps’ as a visual trap for male and female Queensland fruit fly, Bactrocera tryoni (Diptera: Tephritidae)

Bactrocera tryoni (Froggatt) is Australia's major horticultural insect pest, yet monitoring females remains logistically difficult. We trialled the ‘Ladd trap’ as a potential female surveillance or monitoring tool. This trap design is used to trap and monitor fruit flies in countries other (e.g. USA) than Australia. The Ladd trap consists of a flat yellow panel (a traditional ‘sticky trap’), with a three dimensional red sphere (= a fruit mimic) attached in the middle. We confirmed, in field-cage trials, that the combination of yellow panel and red sphere was more attractive to B. tryoni than the two components in isolation. In a second set of field-cage trials, we showed that it was the red-yellow contrast, rather than the three dimensional effect, which was responsible for the trap's effectiveness, with B. tryoni equally attracted to a Ladd trap as to a two-dimensional yellow panel with a circular red centre. The sex ratio of catches was approximately even in the field-cage trials. In field trials, we tested the traditional red-sphere Ladd trap against traps for which the sphere was painted blue, black or yellow. The colour of sphere did not significantly influence trap efficiency in these trials, despite the fact the yellow-panel/yellow-sphere presented no colour contrast to the flies. In 6 weeks of field trials, over 1500 flies were caught, almost exactly two-thirds of them being females. Overall, flies were more likely to be caught on the yellow panel than the sphere; but, for the commercial Ladd trap, proportionally more females were caught on the red sphere versus the yellow panel than would be predicted based on relative surface area of each component, a result also seen the field-cage trial. We determined that no modification of the trap was more effective than the commercially available Ladd trap and so consider that product suitable for more extensive field testing as a B. tryoni research and monitoring tool.

Local Field Potentials in the Gustatory Cortex Carry Taste Information

It has been recently shownthat localfield potentials (LFPs)fromthe auditory and visual cortices carry information about sensory stimuli, but whether this is a universal property of sensory cortices remains to be determined. Moreover, little is known about the temporal dynamics of sensory information contained in LFPs following stimulus onset. Here we investigated the time course of the amount of stimulus information in LFPs and spikes from the gustatory cortex of awake rats subjected to tastants and water delivery on the tongue. We found that the phase and amplitude of multiple LFP frequencies carry information about stimuli, which have specific time courses after stimulus delivery. The information carried by LFP phase and amplitude was independent within frequency bands, since the joint information exhibited neither synergy nor redundancy. Tastant information in LFPs was also independent and had a different time course from the information carried by spikes. These findings support the hypothesis that the brain uses different frequency channels to dynamically code for multiple features of a stimulus.

Análise da silvicultura na bacia hidrográfica do rio Jaguarão (Brasil-Uruguai) : diagnóstico para a gestão geoambiental em bacia transfronteiriça

Dissertação (mestrado)—Universidade de Brasília, Instituto de Ciências Humanas, Departamento de Geografia, 2015.

Comparison of two field methods for estimating body fat in different Spanish Dance disciplines

The purpose of the present study was to investigate percentage body fat (%BF) differences in three Spanish dance disciplines and to compare skinfold and bioelectrical impedance predictions of body fat percentage in the same sample. Seventy-six female dancers, divided into three groups, Classical (n=23), Spanish (n=29) and Flamenco (n=24), were measured using skinfold measurements at four sites: triceps, subscapular, biceps and iliac crest, and whole body multi-frequency bioelectrical impedance (BIA). The skin-fold measures were used to predict body fat percentage via Durnin and Womersley's and Segal, Sun and Yannakoulia equations by BIA. Differences in percent fat mass between groups (Classical, Spanish and Flamenco) were tested by using repeated measures analysis (ANOVA). Also, Pearson's product-moment correlations were performed on the body fat percentage values obtained using both methods. In addition, Bland-Altman plots were used to assess agreement, between anthropometric and BIA methods. Repeated measures analysis of variance did not found differences in %BF between modalities (p<0.05). Fat percentage correlations ranged from r= 0.57 to r=0.97 (all, p<0.001). Bland-Altman analysis revealed differences between BIA Yannakoulia as a reference method with BIA Segal (-0.35 ± 2.32%, 95%CI: -0.89to 0.18, p=0.38), with BIA Sun (-0.73 ± 2.3%, 95%CI: -1.27 to -0.20, p=0.014) and Durnin-Womersley (-2.65 ± 2,48%, 95%CI: -3.22 to -2.07, p<0.0001). It was concluded that body fat percentage estimates by BIA compared with skinfold method were systematically different in young adult female ballet dancers, having a tendency to produce underestimations as %BF increased with Segal and Durnin-Womersley equations compared to Yannakoulia, concluding that these methods are not interchangeable.

O museu virtual Google Art Project : um estudo de caso em contexto de ensino-aprendizagem da educação visual

A educação na arte e pela arte confere a todos os seus intervenientes a estimulação da sua criatividade e da sua consciência cultural, proporcionando meios para se exprimirem e participarem ativamente no mundo que nos rodeia. A integração das tecnologias de informação e comunicação no processo de ensino-aprendizagem veio alargar o papel que a arte pode desempenhar neste processo, promovendo novas formas de aprender, de ensinar e de pensar. Assim, a utilização de ambientes virtuais em contexto educativo tem revelado um enorme potencial, sobretudo ao nível da comunicação e da interação entre alunos e obras de arte. Neste sentido, considerou-se importante desenvolver um estudo de caso em contexto de sala de aula da Educação Visual, promovendo uma aprendizagem baseada na articulação entre a observação, interpretação e análise da obra de arte e o museu virtual. Assim o principal objetivo deste estudo foi avaliar as potencialidades do Google Art Project, enquanto objeto de aprendizagem, na promoção da aprendizagem na área da literacia em artes. Para além disso, procurámos ainda avaliar se a utilização de ferramentas multimédia como o referido Google Art Project e o Quadro Interativo, constituem fatores de motivação na aprendizagem da disciplina de Educação Visual. Do ponto de vista metodológico desenvolvemos uma estratégia baseada na investigação-ação. Procurámos, por um lado, descobrir e compreender o significado de uma realidade vivida por um grupo de alunos e, por outro lado, refletir sobre a prática educativa com o intuito de a melhorar e transformar. Este estudo envolveu cinco turmas do sexto ano do ensino público. Para a recolha de dados utilizámos técnicas baseadas na conversação e na observação, no questionário e nas notas de campo. Os resultados deste estudo revelam que as ferramentas tecnológicas utilizadas podem efetivamente contribuir para a promoção da aprendizagem dos alunos na área da Educação Visual, mais concretamente ao nível do domínio da literacia artística, da representação e da interpretação visual.

Áreas grises: territorio de investigación artística = Gray areas: artistic research field

El presente estudio refleja los argumentos teóricos y propuestas en el campo de la investigación artística, que resultaron de la autoreflexión en torno a la tesis Art Realities y el proyecto artístico visual The Cloudwalkers, que el autor realizó para la obtención del grado MFA in New Media en la Danube Universität (Austria), en colaboración con el Transart Institute (E.U.A.). Es un análisis autocrítico de caso que abarca tanto la parte escrita como práctica del proyecto de titulación, del que se deriva un estudio teórico que expone posibles instrumentos y estrategias de investigación para las artes visuales.

Les tableaux homonymiques, principe d’unité du Cornet à dés de Max Jacob

Ce mémoire s’intéresse à la structure du recueil de poésie en prose Le Cornet à dés (1917) de Max Jacob. À la lecture de l’ensemble, on remarque qu’il est sans cesse question de choses ou d’évènements auxquels renvoient les diverses significations du mot tableau : œuvres picturales, descriptions imagées, cadres de fenêtre ou de porte, vieillards (vieux tableaux), tableaux vivants, subdivisions de pièces de théâtre ou encore tableaux d’école. Subdivisé en trois chapitres, ce travail s’attachera dans un premier temps au fait que tous ces homonymes sont traités, dans les poèmes, comme des peintures. Entre fixité et mouvement, les descriptions et les narrations rapprochent la littérature de l’art pictural, ce qui contribue à l’esthétique du doute caractéristique de l’œuvre de Max Jacob. Le deuxième chapitre s’intéresse aux procédés de reprise et à la manière dont ils permettent de faire des liens entre les poèmes. À partir des théories du mouvement et de la répétition, nous verrons comment les divers motifs forment, à la manière des dés, différentes combinaisons d’une pièce à l’autre. Inspiré par les peintres cubistes qui présentent simultanément tous les angles d’un même objet, l’auteur fait le tour du mot tableau. Dans le dernier chapitre, il ressort que la juxtaposition des poèmes donne accès à un surcroît de signification : certains éléments arbitraires comme des titres obscurs prennent soudainement sens. Une réflexion sur la lecture vient compléter ce travail puisque les nombreuses répétitions sont traitées dans la mémoire. Ce travail s’inscrit dans le champ des études sur le recueil et s’appuie principalement sur l’analyse de poèmes.

Les tableaux homonymiques, principe d’unité du Cornet à dés de Max Jacob

Ce mémoire s’intéresse à la structure du recueil de poésie en prose Le Cornet à dés (1917) de Max Jacob. À la lecture de l’ensemble, on remarque qu’il est sans cesse question de choses ou d’évènements auxquels renvoient les diverses significations du mot tableau : œuvres picturales, descriptions imagées, cadres de fenêtre ou de porte, vieillards (vieux tableaux), tableaux vivants, subdivisions de pièces de théâtre ou encore tableaux d’école. Subdivisé en trois chapitres, ce travail s’attachera dans un premier temps au fait que tous ces homonymes sont traités, dans les poèmes, comme des peintures. Entre fixité et mouvement, les descriptions et les narrations rapprochent la littérature de l’art pictural, ce qui contribue à l’esthétique du doute caractéristique de l’œuvre de Max Jacob. Le deuxième chapitre s’intéresse aux procédés de reprise et à la manière dont ils permettent de faire des liens entre les poèmes. À partir des théories du mouvement et de la répétition, nous verrons comment les divers motifs forment, à la manière des dés, différentes combinaisons d’une pièce à l’autre. Inspiré par les peintres cubistes qui présentent simultanément tous les angles d’un même objet, l’auteur fait le tour du mot tableau. Dans le dernier chapitre, il ressort que la juxtaposition des poèmes donne accès à un surcroît de signification : certains éléments arbitraires comme des titres obscurs prennent soudainement sens. Une réflexion sur la lecture vient compléter ce travail puisque les nombreuses répétitions sont traitées dans la mémoire. Ce travail s’inscrit dans le champ des études sur le recueil et s’appuie principalement sur l’analyse de poèmes.

Apprendre avec la technologie : l'impact sur l'enseignement et l'apprentissage de l’utilisation de la technologie numérique (SMARTBOARD) dans les classes

This research was devoted to gaining information on teachers? use of technology, specifically SMARTBOARD technology, for teaching and promoting learning in the classroom. Research has suggested that use of technology can enhance learning and classroom practices. This has resulted in administrators encouraging the use of SMARTBOARDS, installing them in classrooms and providing training and support for teachers to use this technology. Adoption of new technology, however, is not simple. It is even more challenging because making the best use of new technologies requires more than training; it requires a paradigm shift in teachers? pedagogical approach. Thus, while it may be reasonable to believe that all we need to do is show teachers the benefits of using the SMARTBOARD; research tells us that changing paradigms is difficult for a variety of reasons. This research had two main objectives. First, to discover what factors might positively or negatively affect teachers? decisions to take up this technology. Second, to investigate how the SMARTBOARD is used by teachers who have embraced it and how this impacts participation in classrooms. The project was divided into two parts; the first was a survey research (Part 1), and the second was an ethnographic study (Part 2). A thirty-nine item questionnaire was designed to obtain information on teachers? use of technology and the SMARTBOARD. The questionnaire was distributed to fifty teachers at two EMSB schools: James Lyng Adult Centre (JLAC) and the High School of Montreal (HSM). Part 2 was an ethnographic qualitative study of two classes (Class A, Class B) at JLAC. Class A was taught by a male teacher, an early-adopter of technology and a high-level user of the SMARTBOARD; Class B was taught by a female teacher who was more traditional and a low-level user. These teachers were selected because they had similar years of experience and general competence in their subject matter but differed in their use of the technology. The enrollment in Class A and Class B were twenty-three and twenty-four adult students, respectively. Each class was observed for 90 minutes on three consecutive days in April 2010. Data collection consisted of videotapes of the entire period, and observational field notes with a graphical recording of participatory actions. Information from the graphical recording was converted to sociograms, a graphic representation of social links among individuals involved in joint action. The sociogram data was tabulated as quantified data. The survey results suggest that although most teachers are interested in and use some form of technology in their teaching, there is a tendency for factors of gender and years of experience to influence the use of and opinions on using technology. A Chi Square analysis of the data revealed (a) a significant difference (2 = 6.031, p < .049) for gender in that male teachers are more likely to be interested in the latest pedagogic innovation compared to female teachers; and, (b) a significant difference for years of experience (2 = 10.945, p < .004), showing that teachers with ?6 years experience were more likely to use the SMARTBOARD, compared to those with more experience (>6 years). All other items from the survey data produced no statistical difference. General trends show that (a) male teachers are more willing to say yes to using the SMARTBOARD compared to female teachers, and (b) teachers with less teaching experience were more likely to have positive opinions about using the SMARTBOARD compared to teachers with more experience. The ethnographic study results showed differences in students? response patterns in the two classrooms. Even though both teachers are experienced and competent, Teacher A elicited more participation from his students than Teacher B. This was so partly because he used the SMARTBOARD to present visual materials that the students could easily respond to. By comparison, Teacher B used traditional media or methods to present most of her course material. While these methods also used visual materials, students were not able to easily relate to these smaller, static images and did not readily engage with the material. This research demonstrates a generally positive attitude by teachers towards use of the SMARTBOARD and a generally positive role of this technology in enhancing students? learning and engagement in the classroom. However, there are many issues related to the SMARTBOARD use that still need to be examined. A particular point is whether teachers feel adequately trained to integrate SMARTBOARD technology into their curricula. And, whether the gender difference revealed is related to other factors like a need for more support, other responsibilities, or a general sense of anxiety when it comes to technology. Greater opportunity for training and ongoing support may be one way to increase teacher use of the SMARTBOARD; particularly for teachers with more experience (>6 years) and possibly also for female teachers.