Gérard G. Medioni

Object modelling by registration of multiple range images

We study the problem of creating a complete model of a physical object. Although this may be possible using intensity images, we here use images which directly provide access to three dimensional information. The first problem that we need to solve is to find the transformation between the different views. Previous approaches either assume this transformation to be known (which is extremely difficult for a complete model), or compute it with feature matching (which is not accurate enough for integration). In this paper, we propose a new approach which works on range data directly and registers successive views with enough overlapping area to get an accurate transformation between views. This is performed by minimizing a functional which does not require point-to-point matches. We give the details of the registration method and modelling procedure and illustrate them on real range images of complex objects.

Object modeling by registration of multiple range images

The problem of creating a complete model of a physical object is studied. Although this may be possible using intensity images, the authors use range images which directly provide access to three-dimensional information. The first problem that needs to be solved is to find the transformation between the different views. Previous approaches have either assumed this transformation to be known (which is extremely difficult for a complete model) or computed it with feature matching (which is not accurate enough for integration. The authors propose an approach that works on range data directly and registers successive views with enough overlapping area to get an accurate transformation between views. This is performed by minimizing a functional that does not require point-to-point matches. Details are given of the registration method and modeling procedure, and they are illustrated on range images of complex objects.<<ETX>>

Structural indexing: efficient 3-D object recognition

The authors present an approach for the recognition of multiple 3-D object models from three 3-D scene data. The approach uses two different types of primitives for matching: small surface patches, where differential properties can be reliably computed, and lines corresponding to depth or orientation discontinuities. These are represented by splashes and 3-D curves, respectively. It is shown how both of these primitives can be encoded by a set of super segments, consisting of connected linear segments. These super segments are entered into a table and provide the essential mechanism for fast retrieval and matching. The issues of robustness and stability of the features are addressed in detail. The acquisition of the 3-D models is performed automatically by computing splashes in highly structured areas of the objects and by using boundary and surface edges for the generation of 3-D curves. The authors present results with the current system (3-D object recognition based on super segments) and discuss further extensions. >

Event detection and analysis from video streams

We present a system which takes as input a video stream obtained from an airborne moving platform and produces an analysis of the behavior of the moving objects in the scene. To achieve this functionality, our system relies on two modular blocks. The first one detects and tracks moving regions in the sequence. It uses a set of features at multiple scales to stabilize the image sequence, that is, to compensate for the motion of the observer, then extracts regions with residual motion and uses an attribute graph representation to infer their trajectories. The second module takes as input these trajectories, together with user-provided information in the form of geospatial context and goal context to instantiate likely scenarios. We present details of the system, together with results on a number of real video sequences and also provide a quantitative analysis of the results.

Detection of Intensity Changes with Subpixel Accuracy Using Laplacian-Gaussian Masks

We present a system that takes a gray level image as input, locates edges with subpixel accuracy, and links them into lines. Edges are detected by finding zero-crossings in the convolution of the image with Laplacian-of-Gaussian (LoG) masks. The implementation differs markedly from M.I.T.s as we decompose our masks exactly into a sum of two separable filters instead of the usual approximation by a difference of two Gaussians (DOG). Subpixel accuracy is obtained through the use of the facet model [1]. We also note that the zero-crossings obtained from the full resolution image using a space constant ¿ for the Gaussian, and those obtained from the 1/n resolution image with 1/n pixel accuracy and a space constant of ¿/n for the Gaussian, are very similar, but the processing times are very different. Finally, these edges are grouped into lines using the technique described in [2].

Context tracker: Exploring supporters and distracters in unconstrained environments

Visual tracking in unconstrained environments is very challenging due to the existence of several sources of varieties such as changes in appearance, varying lighting conditions, cluttered background, and frame-cuts. A major factor causing tracking failure is the emergence of regions having similar appearance as the target. It is even more challenging when the target leaves the field of view (FoV) leading the tracker to follow another similar object, and not reacquire the right target when it reappears. This paper presents a method to address this problem by exploiting the context on-the-fly in two terms: Distracters and Supporters. Both of them are automatically explored using a sequential randomized forest, an online template-based appearance model, and local features. Distracters are regions which have similar appearance as the target and consistently co-occur with high confidence score. The tracker must keep tracking these distracters to avoid drifting. Supporters, on the other hand, are local key-points around the target with consistent co-occurrence and motion correlation in a short time span. They play an important role in verifying the genuine target. Extensive experiments on challenging real-world video sequences show the tracking improvement when using this context information. Comparisons with several state-of-the-art approaches are also provided.

Inferring global perceptual contours from local features

We address the problem of contour inference from partial data, as obtained from state-of-the-art edge detectors.We argue that in order to obtain more pereeptually salient contours, it is necessary to impose generic constraints such as continuity and co-curvilinearity.The implementation is in the form of a convolution with a mask which encodes both the orientation and the strength of the possible continuations. We first show how the mask, called the “Extension field” is derived, then how the contributions from different sites are collected to produce a saliency map.We show that the scheme can handle a variety of input data, from dot patterns to oriented edgels in a unified manner, and demonstrate results on a variety of input stimuli.We also present a similar approach to the problem of inferring contours formed by end points. In both cases, the scheme is non-linear, non iterative, and unified in the sense that all types of input tokens are handled in the same manner.

Recognizing 3-D objects using surface descriptions

The authors provide a complete method for describing and recognizing 3-D objects, using surface information. Their system takes as input dense range date and automatically produces a symbolic description of the objects in the scene in terms of their visible surface patches. This segmented representation may be viewed as a graph whose nodes capture information about the individual surface patches and whose links represent the relationships between them, such as occlusion and connectivity. On the basis of these relations, a graph for a given scene is decomposed into subgraphs corresponding to different objects. A model is represented by a set of such descriptions from multiple viewing angles, typically four to six. Models can therefore be acquired and represented automatically. Matching between the objects in a scene and the models is performed by three modules: the screener, in which the most likely candidate views for each object are found; the graph matcher, which compares the potential matching graphs and computes the 3-D transformation between them; and the analyzer, which takes a critical look at the results and proposes to split and merge object graphs. >

3-D surface description from binocular stereo

A stereo vision system that attempts to achieve robustness with respect to scene characteristics, from textured outdoor scenes to environments composed of highly regular man-made objects is presented. It integrates area-based and feature-based primitives. The area-based processing provides a dense disparity map, and the feature-based processing provides an accurate location of discontinuities. An area-based cross correlation, an ordering constraint, and a weak surface smoothness assumption are used to produce an initial disparity map. This disparity map is only a blurred version of the true one because of the smoothing introduced by the cross correlation. The problem can be reduced by introducing edge information. The disparity map is smoothed and the unsupported points removed. This method gives an active role to edgels parallel to the epipolar lines, whereas they are discarded in most feature-based systems. Very good results have been obtained on complex scenes in different domains. >A stereo vision system that attempts to achieve robustness with respect to scene characteristics, from textured outdoor scenes to environments composed of highly regular man-made objects is present...

Continuous tracking within and across camera streams

This paper presents a new approach for continuous tracking of moving objects observed by multiple, heterogeneous cameras. Our approach simultaneously processes video streams from stationary and pan-tilt-zoom cameras. The detection of moving objects from moving camera streams is performed by defining an adaptive background model that takes into account the camera motion approximated by an affine transformation. We address the tracking problem by separately modeling motion and appearance of the moving objects using two probabilistic models. For the appearance model, multiple color distribution components are proposed for ensuring a more detailed description of the object being tracked. The motion model is obtained using a Kalman filter (KF) process, which predicts the position of the moving object. The tracking is performed by the maximization of a joint probability model. The novelty of our approach consists in modeling the multiple trajectories observed by the moving and stationary cameras in the same KF framework. It allows deriving a more accurate motion measurement for objects simultaneously viewed by the two cameras and an automatic handling of occlusions, errors in the detection and camera handoff. We demonstrate the performances of the system on several video surveillance sequences.