Search

This paper describes a method for the detection of tracking of elongated structures that is robust under changes of scale and orientation. This method is based on extending the concept of scale invariant natural interest points to include elongated ridge structures. An operator is proposed that directly detects ridge points and provides an estimation of their elongation and orientation. A tracking process is used to follow elongated features over time and to robustly observe changes in scale and orientation. Changes in scale are used to directly estimate time to contact. Experimental results demonstrate that the method works well in cluttered scenes that are typical of urban environments. [ABSTRACT FROM AUTHOR]

In this paper, we propose a real-time method to detect obstacles using theoretical models of the ground plane, first in a 3D point cloud given by a stereo camera, and then in an optical flow field given by one of the stereo pair's camera. The idea of our method is to combine two partial occupancy grids from both sensor modalities with an occupancy grid framework. The two methods do not have the same range, precision and resolution. For example, the stereo method is precise for close objects but cannot see further than 7 m (with our lenses), while the optical flow method can see considerably further but has lower accuracy. Experiments that have been carried on the CyCab mobile robot and on a tractor demonstrate that we can combine the advantages of both algorithms to build local occupancy grids from incomplete data (optical flow from a monocular camera cannot give depth information without time integration). [ABSTRACT FROM AUTHOR]

Time-to-collision can be directly measured from a spatio-temporal image sequence obtained from an uncalibrated camera. This it would appear to offer a simple, elegant measurement for use in obstacle avoidance. However, previous techniques for computing time to collision from an optical flow have proven impractical for real applications. This paper present a new approach for computing time to collision (TTC) based on the idea of measuring the rate of change of the "intrinsic scale". Intrinsic scale is a geometric invariant that is valid at most points in an image, and can be rapidly determined using a multi-resolution pyramid. In this paper we develop the approach and demonstrate its feasibility by comparing the results with range measurements obtained from a laser ranging device on a moving vehicle. Experimental results show that this is a simple method to obtain reliable TTC with a low computational cost. [ABSTRACT FROM AUTHOR]

This paper addresses the detection of activities of individuals in a smart home environment. Our system is based on a robust video tracker that creates and tracks targets using a wide-angle camera. The system uses target position, size and orientation as input for interpretation. Interpretation produces activity labels such as "walking", "standing", "sitting", "interacting with table", or "sleeping" for each target. Bayesian Classifier and Support Vector Machines (SVMs) are compared for learning and recognizing previously defined individual activities. These methods are evaluated on recorded data sets. A novel Hybrid Classifier is then proposed. This classifier combines generative Bayesian methods and discriminative SVMs. Bayesian methods are used to detect previously unseen activities, while the SVMs are shown to provide high discriminative power for recognizing examples of learned activity classes. The evaluation results of the Hybrid classifier for the recorded data sets show that the combination of generative and discriminative classification methods outperforms the individual methods when identifying unseen activities. [ABSTRACT FROM AUTHOR]

This paper addresses the extraction of small group configurations and activities in an intelligent meeting environment. The proposed approach takes a continuous stream of observations coming from different sensors in the environment as input. The goal is to separate distinct distributions of these observations corresponding to distinct group configurations and activities. In this paper, we explore an unsupervised method based on the calculation of the Jeffrey divergence between histograms over observations. The obtained distinct distributions of observations can be interpreted as distinct segments of group configuration and activity. To evaluate this approach, we recorded a seminar and a cocktail party meeting. The observations of the seminar were generated by a speech activity detector, while the observations of the cocktail party meeting were generated by both the speech activity detector and a visual tracking system. We measured the correspondence between detected segments and labelled group configurations and activities. The obtained results are promising, in particular as our method is completely unsupervised. [ABSTRACT FROM AUTHOR]

Human activity is extremely complex. Current technology allows us to handcraft real-time perception systems for a specific perceptual task. However, such an approach is inadequate for building systems that accommodate the variety that is typical of human environments. In this paper we define a framework for context aware observation of human activity. A context in this framework is defined as a network of situations. A situation network is interpreted as a specification for a federation of processes to observe humans and their actions. We present a process-based software architecture for building systems for observing activity. We discuss methods for building systems using this framework. The framework and methods are illustrated with examples from observation of human activity in an "Augmented Meeting Environment". [ABSTRACT FROM AUTHOR]

New display technologies will enable designers to use every surface as a support for interaction with information technology. In this article, we describe techniques and tools for enabling efficient man-machine interaction in computer augmented multi-surface environments. We focus on explicit interaction, in which the user decides when and where to interact with the system. We present three interaction techniques using simple actuators: fingers, a laser pointer, and a rectangular piece of cardboard. We describe a graphical control interface constructed from an automatically generated and maintained environment model. We implement both the automatic model acquisition and the interaction techniques using a Steerable Camera-Projector (SCP) system. [ABSTRACT FROM AUTHOR]

In this article we learn significant local appearance features for visual classes. Generic feature detectors are obtained by unsupervised learning using clustering. The resulting clusters, referred to as "classtons", identify the significant class characteristics from a small set of sample images. The classton channels mark these characteristics reliably using a probabilistic cluster representation. The classtons demonstrate good generalisation with respect to viewpoint changes and previously unseen objects. In all experiments, the classton channels of similar images have the same spatial relations. Learning of these relations allows to generate a classification model that combines the generalisation ability from the classtons and the discriminative power from the spatial relations. [ABSTRACT FROM AUTHOR]

The characteristic (or intrinsic) scale of a local image pattern is the scale parameter at which the Laplacian provides a local maximum. Nearly every position in an image will exhibit a small number of such characteristic scales. Computing a vector of Gaussian derivatives (a Gaussian jet) at a characteristic scale provides a scale invariant feature vector for tracking, matching, indexing and recognition. However, the computational cost of directly searching the scale axis for the characteristic scale at each image position can be prohibitively expensive. We describe a fast method for computing a vector of Gaussian derivatives that are normalised to the characteristic scale at each pixel. This method is based on a scale equivariant half-octave binomial pyramid. The characteristic scale for each pixel is determined by an interpolated maximum in the Difference of Gaussian as a function of scale. We show that interpolation between pixels across scales can be used to provide an accurate estimate of the intrinsic scale at each image point. We present an experimental evaluation that compares the scale invariance of this method to direct computation using FIR filters, and to an implementation using recursive filters. With this method we obtain a scale normalised Gaussian Jet at video rate for a 1/4 size PAL image on a standard 1.5 Ghz Pentium workstation. [ABSTRACT FROM AUTHOR]