Search

Pedestrians, in videos taken from fixed cameras, tend to appear and disappear at precise locations such as doors, gateways or edges of the scene: we refer to locations where pedestrians appear as sources (potential origins) and the locations where they disappear as sinks (potential destinations). The detection of these points and the characterization of the flows connecting them represent a typical preliminary step in most pedestrian studies and it can be supported by computer vision approaches. In this paper we propose an algorithm in which a scene is overlaid by a grid of particles initializing a dynamical system defined by optical flow, a high level global motion information. Time integration of the dynamical system produces short particle trajectories (tracklets), representing dense but short motion patterns in segments of the scene; tracklets are then extended into longer tracks that are grouped using an unsupervised clustering algorithm, where the similarity is measured by the Longest Common Subsequence. The analysis of these clusters supports the identification of sources and sinks related to a single video segment. Local segment information is finally combined to achieve a global set of traces identifying sources and sinks, and characterizing the flow of pedestrians connecting them. The paper presents the defined technique and it discusses its application in a real-world scenario.

Studies related to crowds of pedestrians, both those of theoretical nature and application oriented ones, have generally focused on either the analysis or the synthesis of the phenomena related to the interplay between individual pedestrians, each characterised by goals, preferences and potentially relevant relationships with others, and the environment in which they are situated. The cases in which these activities have been systematically integrated for a mutual benefit are still very few compared to the corpus of crowd related literature. This paper presents a case study of an integrated approach to the definition of an innovative model for pedestrian and crowd simulation (on the side of synthesis) that was actually motivated and supported by the analyses of empirical data acquired from both experimental settings and observations in real world scenarios. In particular, we will introduce a model for the adaptive behaviour of pedestrians that are also members of groups, that strive to maintain their cohesion even in difficult (e.g. high density) situations. The paper will show how the synthesis phase also provided inputs to the analysis of empirical data, in a virtuous circle., Comment: Preprint submitted to Pattern Recognition Letters March 20, 2013

Urbanisation is growingly generating crowding situations which generate potential issues for planning and public safety. This paper proposes new techniques of crowd analysis and precisely crowd flow segmentation and crowd counting framework for estimating the number of people in each flow segment. We use two foreground masks, one generated by Horn-Schunck optical flow, used by crowd flow segmentation, and another by Gaussian background subtraction, used by crowd counting framework. For crowd flow segmentation, we adopt K-means clustering algorithm which segments the crowd in different flows. After clustering, some small blobs can appear which are removed by blob absorption method. After blob absorption, crowd flow is segmented into different dominant flows. Finally, we estimate the number of people in each flow segment by using blob analysis and blob size optimization methods. Our experimental results demonstrate the effectiveness of the proposed method comparing to other stateof- the-art approaches and our proposed crowd counting framework estimates the number of people with about 90% accuracy.