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.

Multimodal attention system for an interactive robot

[EN]Social robots are receiving much interest in the robotics community. The most important goal for such robots lies in their interaction capabilities. An attention system is crucial, both as a filter to center the robot’s perceptual resources and as a mean of letting the observer know that the robot has intentionality. In this paper a simple but flexible and functional attentional model is described. The model, which has been implemented in an interactive robot currently under development, fuses both visual and auditive information extracted from the robot’s environment, and can incorporate knowledge-based influences on attention.

Paradigms that guide the models of attention to the health in Brazil: an analytic essay

SILVA, Flávio César Bezerra da ; COSTA, Francisca Marta de Lima; ANDRADE, Hamilton Leandro Pinto de; FREIRE, Lúcia de Fátima; MACIEL, Patrícia Suerda de Oliveira; ENDERS, Bertha Cruz ; MENEZES, Rejane Maria Paiva de. Paradigms that guide the models of attention to the health in Brazil: an analytic essay. Revista de Enfermagem UFPE On Line., Recife, v.3,n.4, p.460-65. out/dez. 2009. Disponível em < http://www.ufpe.br/revistaenfermagem/index.php/revista/search/results >.

Funções Executivas (Frontal Assessment Battery), Capacidade Visuo Construtiva e Memória (Rey Complex Figure) numa Amostra de Idosos sob Resposta Social

Introdução: As funções executivas (FE) têm sido sistematicamente associadas ao funcionamento dos lobos frontais e sabemos que o declínio cognitivo se associa a piores resultados em provas que avaliam estas funções. Para além de pretendermos analisar se um teste que avalia as FE (Frontal Assessment Battery/FAB) discrimina idosos com/sem declínio cognitivo, avaliado através do Montreal Cognitive Assessment (MoCA) e se existem associações entre os resultados obtidos com a Figura Complexa de Rey-Osterreith/FCR-O (qualidade da cópia, memória de 3 e de 20 minutos) e a presença/ausência de declínio cognitivo, queremos sobretudo analisar se a qualidade e exactidão da cópia (capacidade visuo construtiva) e a memória de 3 minutos na FCR-O se associam ao resultado obtido com a FAB, dado que as duas provas estão supostamente associadas às FE e ao funcionamento dos lobos frontais avaliados com o FAB, por oposição à memória de 20 minutos (supostamente associada à área temporal, não avaliada pela FAB). Não deixámos de considerar, ainda, a associação entre as variáveis sociodemográficas e os resultados na FAB, na FCR-O e no MoCA. Metodologia: A amostra total incluiu 556 idosos (média de idades, M = 80,2; Desvio-padrão, DP = 5,23; variação = 60-100) sob resposta social em diferentes instituições do Concelho de Coimbra que aceitou responder voluntariamente (ou cujos familiares/cuidadores concederam consentimento) a uma bateria de testes (incluindo questões sociodemográficas, a FCR-O, o MoCA e a FAB). Estas variáveis foram estratificadas de acordo com a idade e escolaridade dos idosos e dicotomizadas. Para testar os nossos objetivos recorremos a diferentes sub amostras compostas pelos sujeitos que tinham resultados nas provas cujas associações queríamos testar. Resultados: De acordo com o MoCA, 59,7% dos idosos apresentavam declínio cognitivo, com 73,9% a apresentar défice executivo ligeiro, de acordo com a FAB. Quanto à FCR-O, 24,0% dos idosos apresentavam défice práxico ligeiro a moderado, 73,9% défice mnésico visual a curto prazo leve (3 minutos) e 60.9% défice mnésico visual a longo prazo leve a moderado (20 minutos). Não se verificaram associações estatisticamente significativas entre o género, estado civil e tipo de resposta social e as três variáveis centrais do estudo (MoCA, FAB e FCR-O). Quer a FAB, quer a FCR-O (as três provas: qualidade e exatidão da cópia, memória de 3 e 20 minutos) revelaram associações com a ausência/presença de declínio cognitivo. Considerando as variáveis estratificadas pela idade e escolaridade dos idosos e dicotomizadas, um teste do qui quadrado para a independência mostrou que a prova qualidade da FCR-O não estava associada ao resultado na FAB (com/sem défice executivo), ao contrário da prova memória de 3 minutos da FCR-O, que se mostrou associada a este resultado. A prova memória de 20 minutos da FCR-O voltou a não estar associada à ausência/presença de défice executivo (usando o mesmo teste). Analisando as diferentes provas da FCR-O e a FAB, sem estratificação, correlações de Spearman confirmaram as associações encontradas, mas também entre a prova qualidade da cópia da FCR-O e a FAB. Conclusão/Discussão: Os resultados seguem a literatura quanto à associação entre a prova da FCR-O memória a curto prazo/3 minutos e as funções executivas (associadas aos lobos frontais e testadas através da FAB), por oposição com a memória a longo prazo que aparece, na literatura, como mais associada/ou envolvendo à/a área temporal e que, de facto, não se mostrou associada ao resultado na FAB. Os resultados não são tão claros/consensuais no que toca à prova qualidade da cópia da FCR-O.

Impact de la cécité sur le système nociceptif

La vision joue un rôle très important dans la prévention du danger. La douleur a aussi pour fonction de prévenir les lésions corporelles. Nous avons donc testé l’hypothèse qu’une hypersensibilité à la douleur découlerait de la cécité en guise de compensation sensorielle. En effet, une littérature exhaustive indique qu’une plasticité intermodale s’opère chez les non-voyants, ce qui module à la hausse la sensibilité de leurs sens résiduels. De plus, plusieurs études montrent que la douleur peut être modulée par la vision et par une privation visuelle temporaire. Dans une première étude, nous avons mesuré les seuils de détection thermique et les seuils de douleur chez des aveugles de naissance et des voyants à l’aide d’une thermode qui permet de chauffer ou de refroidir la peau. Les participants ont aussi eu à quantifier la douleur perçue en réponse à des stimuli laser CO2 et à répondre à des questionnaires mesurant leur attitude face à des situations douloureuses de la vie quotidienne. Les résultats obtenus montrent que les aveugles congénitaux ont des seuils de douleur plus bas et des rapports de douleur plus élevés que leurs congénères voyants. De plus, les résultats psychométriques indiquent que les non-voyants sont plus attentifs à la douleur. Dans une deuxième étude, nous avons mesuré l’impact de l'expérience visuelle sur la perception de la douleur en répliquant la première étude dans un échantillon d’aveugles tardifs. Les résultats montrent que ces derniers sont en tous points similaires aux voyants quant à leur sensibilité à la douleur. Dans une troisième étude, nous avons testé les capacités de discrimination de température des aveugles congénitaux, car la détection de changements rapides de température est cruciale pour éviter les brûlures. Il s’est avéré que les aveugles de naissance ont une discrimination de température plus fine et qu’ils sont plus sensibles à la sommation spatiale de la chaleur. Dans une quatrième étude, nous avons examiné la contribution des fibres A∂ et C au traitement nociceptif des non-voyants, car ces récepteurs signalent la première et la deuxième douleur, respectivement. Nous avons observé que les aveugles congénitaux détectent plus facilement et répondent plus rapidement aux sensations générées par l’activation des fibres C. Dans une cinquième et dernière étude, nous avons sondé les changements potentiels qu’entrainerait la perte de vision dans la modulation descendante des intrants nociceptifs en mesurant les effets de l’appréhension d’un stimulus nocif sur la perception de la douleur. Les résultats montrent que, contrairement aux voyants, les aveugles congénitaux voient leur douleur exacerbée par l’incertitude face au danger, suggérant ainsi que la modulation centrale de la douleur est facilitée chez ces derniers. En gros, ces travaux indiquent que l’absence d’expérience visuelle, plutôt que la cécité, entraine une hausse de la sensibilité nociceptive, ce qui apporte une autre dimension au modèle d’intégration multi-sensorielle de la vision et de la douleur.

Omega-3 Fatty Acids are Related to Abnormal Emotion Processing in Adolescent Boys with Attention Deficit Hyperactivity Disorder

Background In addition to the core symptoms, attention deficit hyperactivity disorder (ADHD) is associated with poor emotion regulation. There is some evidence that children and young adults with ADHD have lower omega-3 levels and that supplementation with omega-3 can improve both ADHD and affective symptoms. We therefore investigated differences between ADHD and non-ADHD children in omega-3/6 fatty acid plasma levels and the relationship between those indices and emotion-elicited event-related potentials (ERPs). Methods Children/adolescents with (n=31) and without ADHD (n=32) were compared in their plasma omega-3/6 indices and corresponding ERPs during an emotion processing task. Results Children with ADHD had lower mean omega-3/6 and ERP abnormalities in emotion processing, independent of emotional valence relative to control children. ERP abnormalities were significantly associated with lower omega-3 levels in the ADHD group. Conclusions The findings reveal for the first time that lower omega-3 fatty acids are associated with impaired emotion processing in ADHD children.

Omega-3 Fatty Acids are Inversely Related to Callous and Unemotional Traits in Adolescent Boys with Attention Deficit Hyperactivity Disorder

A number of research studies have reported abnormal plasma fatty acid profiles in children with ADHD along with some benefit of n−3 to symptoms of ADHD. However, it is currently unclear whether (lower) long chain-polyunsaturated fatty acids (LC-PUFAs) are related to ADHD pathology or to associated behaviours. The aim of this study was to test whether (1) ADHD children have abnormal plasma LC-PUFA levels and (2) ADHD symptoms and associated behaviours are correlated with LC-PUFA levels. Seventy-two, male children with (n=29) and without a clinical diagnosis of ADHD (n=43) were compared in their plasma levels of LC-PUFA. Plasma DHA was higher in the control group prior to statistical correction. Callous–unemotional (CU) traits were found to be significantly negatively related to both eicosapentaenoic acid (EPA), and total omega-3 in the ADHD group. The findings unveil for the first time that CU and anti-social traits in ADHD are associated with lower omega-3 levels.

Fatores psicológicos preditores do grau de funcionalidade em idosos

A velhice pode estar associada ao sofrimento, aumento da dependência física, declínio funcional, isolamento social, depressão e improdutividade. No envelhecimento observam-se lentificação no processamento cognitivo, redução da atenção, dificuldades na retenção das informações aprendidas (memória de trabalho) e diminuição na velocidade de pensamento e habilidades visuoespaciais. Por outro lado, as que se mantêm inalteradas são: inteligência verbal, atenção básica, habilidade de cálculo e a maioria das habilidades de linguagem (Moraes, Moraes & Lima, 2010). O objetivo deste estudo é comparar funções executivas com grau de funcionalidade para averiguar em que medida estas variáveis predizem funcionalidade. Trinta idosos de três valências diferentes constituíram a amostra deste estudo. Os instrumentos de avaliação administrados foram os seguintes: Escala de Barthel, MontrealCognitiveAssessment (MoCA), Trail Making Test (TMT), Teste de Aprendizagem Audio-Verbal de Rey (RAVLT), Figura Complexa de Rey, Teste Stroop de Cores e Palavras (TSCP), DigitSpan, Escala Geriátrica de Depressão. Dos resultados obtidos destacam-se a existência de relações estatisticamente significativas entre a saúde mental e a funcionalidade. Quanto melhor é a saúde mental, maior é o grau de funcionalidade e os participantes do “Domicílio” possuem melhor saúde mental, atenção, planeamento e construção visuo-espacial do que os do “Centro de Dia”, e estes melhor do que os do “Lar”. A Organização Mundial de Saúde (OMS) destaca a capacidade funcional e a independência como fatores preponderantes para o diagnóstico de saúde física e mental na população idosa. Alguns autores indicam que a avaliação cognitiva deve ser sempre acompanhada de uma avaliação funcional e vice-versa.

Classification multi-échelle d'images à très haute résolution spatiale basée sur une nouvelle approche texturale

Résumé : Face à l’accroissement de la résolution spatiale des capteurs optiques satellitaires, de nouvelles stratégies doivent être développées pour classifier les images de télédétection. En effet, l’abondance de détails dans ces images diminue fortement l’efficacité des classifications spectrales; de nombreuses méthodes de classification texturale, notamment les approches statistiques, ne sont plus adaptées. À l’inverse, les approches structurelles offrent une ouverture intéressante : ces approches orientées objet consistent à étudier la structure de l’image pour en interpréter le sens. Un algorithme de ce type est proposé dans la première partie de cette thèse. Reposant sur la détection et l’analyse de points-clés (KPC : KeyPoint-based Classification), il offre une solution efficace au problème de la classification d’images à très haute résolution spatiale. Les classifications effectuées sur les données montrent en particulier sa capacité à différencier des textures visuellement similaires. Par ailleurs, il a été montré dans la littérature que la fusion évidentielle, reposant sur la théorie de Dempster-Shafer, est tout à fait adaptée aux images de télédétection en raison de son aptitude à intégrer des concepts tels que l’ambiguïté et l’incertitude. Peu d’études ont en revanche été menées sur l’application de cette théorie à des données texturales complexes telles que celles issues de classifications structurelles. La seconde partie de cette thèse vise à combler ce manque, en s’intéressant à la fusion de classifications KPC multi-échelle par la théorie de Dempster-Shafer. Les tests menés montrent que cette approche multi-échelle permet d’améliorer la classification finale dans le cas où l’image initiale est de faible qualité. De plus, l’étude effectuée met en évidence le potentiel d’amélioration apporté par l’estimation de la fiabilité des classifications intermédiaires, et fournit des pistes pour mener ces estimations.

Event-related potential effects of object repetition depend on attention and part-whole configuration

The effects of spatial attention and part-whole configuration on recognition of repeated objects were investigated with behavioral and event-related potential (ERP) measures. Short-term repetition effects were measured for probe objects as a function of whether a preceding prime object was shown as an intact image or coarsely scrambled (split into two halves) and whether or not it had been attended during the prime display. In line with previous behavioral experiments, priming effects were observed from both intact and split primes for attended objects, but only from intact (repeated same-view) objects when they were unattended. These behavioral results were reflected in ERP waveforms at occipital-temporal locations as more negative-going deflections for repeated items in the time window between 220 and 300 ms after probe onset (N250r). Attended intact images showed generally more enhanced repetition effects than split ones. Unattended images showed repetition effects only when presented in an intact configuration, and this finding was limited to the right-hemisphere electrodes. Repetition effects in earlier (before 200 ms) time-windows were limited to attended conditions at occipito-temporal sites (N1), a component linked to the encoding of object structure, while repetition effects at central locations during the same time window (P150) were found only from objects repeated in the same intact configuration—both previously attended and unattended probe objects. The data indicate that view-generalization is mediated by a combination of analytic (part-based) representations and automatic view-dependent representations.

The Effect of Dietary Tartrazine on Brain Dopamine and the Behavioral Symptoms of Attention Deficit Hyperactivity Disorder

Attention Deficit Hyperactivity Disorder is a neurodevelopmental disorder correlated with a decrease in brain dopamine and an increase in behavioral symptoms of hyperactivity and impulsivity. This experiment explored how tartrazine (Yellow #5) impacts these symptoms. After tartrazine administration to Spontaneously Hypertensive Rats (SHR), dopamine concentrations in regions of brain tissue were measured using Enzyme-Linked Immunosorbent Assay analysis. Behavioral testing with a T-maze and open field test measured impulsivity and hyperactivity, respectively. Results indicate that dietary tartrazine increases hyperactive behaviors in the SHR. However, results do not indicate a relationship between dietary tartrazine and brain dopamine. No conclusions regarding the relationship between dietary tartrazine and impulsivity were drawn.

Childhood Attention Problems and the Development of Comorbid Symptoms at the Transition to High School: The Mediating Role of Parent and Peer Relationships

Children with Attention-Deficit/Hyperactivity Disorder (ADHD) are at increased risk for the development of depression and delinquent behavior. Children and adolescents with ADHD also experience difficulty creating/maintaining high quality friendships and parent-child relationships, and these difficulties may contribute to the development of co-morbid internalizing and externalizing symptoms in adolescence. However, there is limited research examining whether high quality friendships and parent-child relationships mediate the relation between ADHD and the emergence of these co-morbid symptoms at the transition to high school. This study examines the mediating role of relationship quality in the association between ADHD and depressive symptoms/delinquent behaviors at this developmentally significant transition point. Results revealed significant indirect effects of grade 6 attention problems on grade 9 depressive symptoms through friendship quality and quality of the mother-child relationship in grade 8. Interventions targeting parent and peer relationships may be valuable for youth with ADHD to promote successful transitions to high school.