Recent work on computer vision analysis of crowds tends to focus on robustly tracking individuals through the crowd or on analyzing the overall pattern of flow. Our work seeks a deeper analysis of social behavior by identifying the small group structure of crowds, forming the basis for mid-level activity analysis at the granularity of human social groups. Building upon state-of-the-art algorithms for pedestrian detection and multi-object tracking, and inspired by social science models of human collective behavior, we automatically detect small groups of individuals who are traveling together. These groups are discovered using a bottom-up hierarchical clustering approach that compares sets of individuals based on a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity. We validate our results quantitatively and qualitatively on videos of real-world pedestrian scenes. Where humancoded ground truth is available, we find substantial statistical agreement between our results and the human-perceived small group structure of the crowd.

Sentencing decisions are the product of a group of courtroom actors, primarily judges and district attorneys. Although the structure of the courtroom workgroup and the interdependencies among members are assumed to be important determinants of sentencing decisions, the degree of this importance and the specific mechanisms through which workgroups affect these decisions have not been investigated. This study used data from the Pennsylvania Commission on Sentencing (PCS) for the years 1990 to 2000 to examine how three social psychological aspects of courtroom workgroups (similarity, proximity, and stability) affect sentencing decisions. Results indicated (a) that workgroups generally had very high levels of similarity in terms of race, gender, and political party but lower levels of similarity in terms of age, college education, and law school education and (b) that proximity and stability were generally high. Controlling for individual, case, and distal contextual factors, workgroup factors affected the decision to incarcerate, the decision to impose fines, and the decision to impose restitution. In particular, proximity increased the use of economic sanctions relative to incarceration and stability was associated with a decrease in the imposition of economic sanctions. Similarity had inconsistent effects.

No abstract

No abstract

No abstract