This paper describes a novel technique for synthesizing a dynamic scene from two images without the use of a 3D model. A scene containing rigid or non-rigid objects, in which each object can move in any orientation or direction, is considered. It is shown that such a scene can be converted into several equivalent static scenes, where each scene only includes one rigid object. Our method can generate a series of continuous and realistic intermediate views from only two reference images without 3D knowledge. The procedure consists of three main steps: segmentation, morphing and postwarping. The key frames are first segmented into several layers. Each layer can be realistically morphed after determining its fundamental matrix. Based on the decomposition of 3D rotation matrix, an optimized and unique postwarping path is automatically determined by the least distortion method and boundary connection constraint. Finally, four experiments, which include morphing of a rotating rigid object in presence of occlusion and morphing of non-rigid objects (human), are demonstrated.

In this paper, we present a method which combines imagebased visual hull and human body part segmentation for overcoming the inability of the visual hull method to reconstruct concave regions. The virtual silhouette image corresponding to the given viewing direction is first produced with image-based visual hull. Human body part localization technique is used to segment the input images and the rendered virtual silhouette image into convex body parts. The body parts in the virtual view are generated separately from the corresponding body parts in the input views and then assembled together. The previously rendered silhouette image is used to locate the corresponding body parts in input views and avoid the unconnected or squeezed regions in the assembled final view. Experiments show that this method can improve the reconstruction of concave regions for human postures and texture mapping. 1.

The capability to follow a person in a domestic environment is an important prerequisite for a robot companion. In this paper, a tracking algorithm is presented that makes it possible to follow a person using a small robot. This algorithm can track a person while moving around, regardless of the sometimes erratic movements of the legged robot. Robust performance is obtained by fusion of two algorithms, one based on salient features and one on color histograms. Reinitializing object histograms enables the system to track a person even when the illumination in the environment changes. By being able to re-initialize the system on run time using background subtraction, the system gains an extra level of robustness. Categories and Subject Descriptors I.2.9 [Artificial Intelligence]: Robotics — Commercial robots and applications; K.4.2 [Computers and Society]:

In this paper we describe a surveillance system that is not only able to detect blobs and track them but also determines if a blob is a person. The given blob is segmented into sub-regions. A person model is fit to these regions such that a likelihood measure is maximized. The likelihood measure depends on the number of identified body parts, their length, location, and aspect ratio. The method is translation, rotation, and scaling invariant and computationally efficient. The results obtained for test video sequences are very encouraging. 1.

this paper: 1) a correlation-based method, 2) a variant of the linear subspace method suggested in [150], 3) an eigenface method [173], and 4) a Fisherface method which uses subspace projection prior to LDA projection to avoid the possible singularity in Sw as in [166]. The results of the experiments showed that the Fisherface method performed significantly better than the other three methods. However, no claim was made about the relative performance of these algorithms on larger databases

In this paper we present a computer vision algorithm for building a human body model skeleton in an automatic way. The algorithm is based on analyzing the human shape. We decompose the body into its main parts by computing the curvature of a B-Spline parameterization of the human contour. This algorithm has been applied in a context where the user is standing in front of a camera stereo pair. The process is completed after the user performs a predefined initial posture for identifying her principal joints, and building the human model. Using this model, we solve the initialization problem of a vision-based markerless motion capture system of the human body.

We propose a novel evidence accumulation framework that accurately estimates the positions of humans in a 3D environment. The framework consists of a network of distributed agents having different functionalities. The modular structure of the network allows scalability to large surveillance areas and robust operation. The framework does not assume reliable measurements in single cameras (referred to as ’sensing agents ’ in our framework) or reliable communication between different agents. There is a position uncertainty associated with single camera measurements and it is reduced through an uncertainty reducing transform that performs evidence accumulation using multiple camera measurements. Our framework has the advantage that single camera measurements do not need to be temporally synchronized to perform evidence accumulation. The system has been tested for detecting single and multiple humans in the environment. We conducted experiments to evaluate the localization accuracy of the position estimates obtained from the system by comparing them with the ground truth. Also, two different configurations of the agents were tested to compare their detection performance. Index Terms — camera networks, distributed processing, evidence accumulation, uncertainty reduction. I.

Abstract — Human-robot interaction (HRI) encompasses numerous disciplines from psychology to mechanical engineering. Each field contributes to a robot’s ability to better understand and respond to humans actions, and behaviors. A common thread is the need to detect a person and their location within an environment. In this paper we tackle the issue of identifying which objects in a scene are people. We also discuss current work on human detection, and strategies for improved performance. I.

Summary. This article presents a shape extraction and results of a preliminary validation stage for a pedestrian detection system based on the use of active contours. The complete system is based on the use of both far infrared and visible cameras to detect areas that potentially contain pedestrians; in order to validate and filter such result a refinement of the human shape by means of active contours is performed followed by a neural network based filtering. 1