Search

This chapter presents a multi-perspective vision-based analysis of the activities of vehicles and persons for the enhancement of situational awareness in surveillance. Multiple perspectives provide a useful invariant feature of the object in the image, i.e., the footage area on the ground. Moving objects are detected in the image domain, and the tracking results of the objects are represented in the projection domain using planar homography. Spatio-temporal relationships between human and vehicle tracks are categorized as safe or unsafe situation depending on the site context such as walkway and driveway locations. Semantic-level information of the situation is achieved with the anticipation of possible directions of near-future tracks using piecewise velocity history. Crowd density is estimated from the footage on the homography plane. Experimental data show promising results. Our framework can be applied to broad range of situational awareness for emergency response, disaster prevention, human interactions in structured environments, and crowd movement analysis in a wide field of view. [ABSTRACT FROM AUTHOR]

This paper presents a multi-perspective vision-based analysis of people and vehicle activities for the enhancement of situational awareness. Multiple perspectives provide a useful invariant feature of object in image, i.e., the footage area on the ground. Moving objects are detected in image domain, and tracking results of the objects are represented in projection domain using planar homography. Spatio-temporal relationships between human and vehicle tracks are categorized to safe or unsafe situation depending on site context such as walkway and driveway locations. Semantic-level information of the situation is achieved with the anticipation of possible directions of near-future tracks using piecewise velocity history. Crowd density is estimated from the footage in homography plane. Experimental data show promising results. Our framework can be applied to broad range of situational awareness for emergency response, disaster prevention, human interactions in structured environments, and crowd movement analysis in wide-view areas. [ABSTRACT FROM AUTHOR]

Subspace analysis has been widely used for head pose estimation. However, such techniques are usually sensitive to data alignment and background noise. In this paper a two-stage approach is proposed to address this issue by combining the subspace analysis together with the topography method. The first stage is based on the subspace analysis of Gabor wavelets responses. Different subspace techniques were compared for better exploring the underlying data structure. Nearest prototype matching using Euclidean distance was used to get the pose estimate. The single pose estimated was relaxed to a subset of poses around it to incorporate certain tolerance to data alignment and background noise. In the second stage, the uncertainty is eliminated by analyzing finer geometrical structure details captured by bunch graphs. This coarse-to-fine framework was evaluated with a large data set. We examined 86 poses, with the pan angle spanning from -90o to 90o and the tilt angle spanning from -60o to 45o. The experimental results indicate that the integrated approach has a remarkably better performance than using subspace analysis alone. [ABSTRACT FROM AUTHOR]

This paper presents an integrated approach for robustly loca ting facial landmark for drivers. In the first step a cascade of probability learners is used to detect the face edge primitives from fine to coarse, so that faces with variant head poses can be located. The edge density descriptors and skin-tone color features are combined together as the basic features to examine the probability of an edge being a face primitive. A cascade of the probability learner is used. In each scale, only edges with sufficient large probabilities are kept and passed on to the next scale. The final output of the cascade gives the edge primitives that belong to faces, which determine the face location. In the second step, a facial landmark detection procedure is applied on the segmented face pixels. Facial landmark candidates are first detected by learning the posteriors in multiple resolutions. Then geometric constraint and the local appearance, modeled by SIFT descriptor, are used to find the set of facial landmarks with largest matching score. Experiments over high-resolution images (FERET database) as well as the real-world drivers' data are used to evaluate the performance. A fairly good results can be obtained, which validates the proposed approach. [ABSTRACT FROM AUTHOR]