Michael F. Kelly

Bio: Michael F. Kelly is an academic researcher from McGill University. The author has contributed to research in topics: Object (computer science) & Image segmentation. The author has an hindex of 3, co-authored 4 publications receiving 50 citations.

Annular symmetry operators: a method for locating and describing objects

Abstract: We present a machine vision system in which segmentation is computed in conjunction with a structural description of objects in the scene. It is assumed that contrast edges capture all relevant object information. The principles which dictate how edge features are grouped to infer objects are based upon detecting SYMMETRICAL ENCLOSING edge configurations. These are detected using ANNULAR OPERATORS applied at multiple scales to edge data which have been extracted at multiple scales from a gray level image. The subsequent grouping of symmetry points results in a set of PARTS which make it possible to identify the LOCATION of objects within an image. These parts are used as a basis for constructing coarse graph-based DESCRIPTORS for the PERCEPTUALLY SIGNIFICANT objects found in the scene. Results are presented to illustrate the method's performance on several images. >

Recording of tagged objects in a closed environment

Abstract: The invention relates to a method of accounting for tagged objects in a closed environment The invention features the steps of visually sensing a tagged object entering the closed environment and capturing an image of the entering object, the image including at least an object identifier tag having a sequence of alphanumeric characters The method then extracts from the identifier tag an entering identifier designation which represents the sequence of alphanumeric characters on the tag and stores that sequence along with other sequences in a list of stored extracted identifiers The system then senses the tagged object when it exits the closed environment, captures an image of the exiting object and extracts a second sequence of alphanumeric characters representing the object's tag The exiting object tag is then compared to the stored extracted identifiers to determine a best match, thereby identifying the object and enabling varying operations to be performed Among the operations are the automatic identification of vehicles leaving a toll highway, the revenue verification and/or automatic charging of vehicles leaving a parking lot, the association of a second identifier, unrelated to the vehicle itself, to deter theft, for example, from an airport parking lot, and the tracking within a closed environment of varying objects in, for example, a container terminal A particularly advantageous ordered graphing comparison process provides accurate identification even in the face of degraded or occluded tags

WHERE and WHAT: object perception for autonomous robots

Abstract: It is essential that autonomous robots be able to locate and identify objects in their environment. A novel approach for visually extracting such object information from images is presented. Annular operators are used to identify existing symmetric relationships between sets of edge elements. Operators are applied at multiple scales to edge data which have been extracted at multiple scales from a gray-scale image. From the resulting symmetry points, the authors identify a set of object parts in the scene. These are used as the basis for constructing coarse graph-based object descriptors. Preliminary results are presented to illustrate the approach using natural image data.

Analysis of shape using annular symmetry operators

Abstract: A novel approach for developing symmetry-based shape representations is presented. Annular operators are used to identify symmetric relationships existing between sets of edge elements. Operators are applied at multiple scales to edge data which has been extracted at multiple scales from a grey level image. Symmetric structures make it possible to identify where objects are positioned within an image, and may be used as a basis for constructing course descriptors for the projected shape of the objects in the scene. The advantages of this method over previous ones are: (1) it can be applied directly to images with no prior segmentation of objects from ground, (2) it allows for the isolation and interpretation of image structure based upon scale, and (3) it is an entirely parallel process. Preliminary results are demonstrated for two grey-level images.

Parametrized structure from motion for 3D adaptive feedback tracking of faces

Abstract: A real-time system is described for automatically detecting, modeling and tracking faces in 3D. A closed loop approach is proposed which utilizes structure from motion to generate a 3D model of a face and then feed back the estimated structure to constrain feature tracking in the next frame. The system initializes by using skin classification, symmetry operations, 3D warping and eigenfaces to find a face. Feature trajectories are then computed by SSD or correlation-based tracking. The trajectories are simultaneously processed by an extended Kalman filter to stably recover 3D structure, camera geometry and facial pose. Adaptively weighted estimation is used in this filter by modeling the noise characteristics of the 2D image patch tracking technique. In addition, the structural estimate is constrained by using parametrized models of facial structure (eigen-heads). The Kalman filter's estimate of the 3D state and motion of the face predicts the trajectory of the features which constrains the search space for the next frame in the video sequence. The feature tracking and Kalman filtering closed loop system operates at 25 Hz.

A planar-reflective symmetry transform for 3D shapes

Abstract: Symmetry is an important cue for many applications, including object alignment, recognition, and segmentation. In this paper, we describe a planar reflective symmetry transform (PRST) that captures a continuous measure of the reflectional symmetry of a shape with respect to all possible planes. This transform combines and extends previous work that has focused on global symmetries with respect to the center of mass in 3D meshes and local symmetries with respect to points in 2D images. We provide an efficient Monte Carlo sampling algorithm for computing the transform for surfaces and show that it is stable under common transformations. We also provide an iterative refinement algorithm to find local maxima of the transform precisely. We use the transform to define two new geometric properties, center of symmetry and principal symmetry axes, and show that they are useful for aligning objects in a canonical coordinate system. Finally, we demonstrate that the symmetry transform is useful for several applications in computer graphics, including shape matching, segmentation of meshes into parts, and automatic viewpoint selection.

Automated site security, monitoring and access control system

Abstract: A video system automatically monitors and controls of the ingress and egress of vehicles to and from a secure facility and various areas within the facility. A plurality of cameras (C1-C14), such as infrared-sensitive cameras, captures images of the license plates of vehicles traveling into and within the site. The video proceesing system (16) detects and extracts a license plate number (LPN). Based on the location of the camera and the (LPN) the processor (16) store the LPN with a time-stamp in one or more databases including an “intransit” database (19), an employee database (30), a blacklist database (36), a loiterer database (38), a speeder database (40), a high security database (42), a high security parking database (44), a normal parking database (50a and 50b) and a visitor parking lot database (48).

A shock grammar for recognition

Abstract: We confront the theoretical and practical difficulties of computing a representation for two-dimensional shape, based on shocks or singularities that arise as the shape's boundary is deformed. First, we develop subpixel local detectors for finding and classifying shocks. Second, to show that shock patterns are not arbitrary but obey the rules of a grammar, and in addition satisfy specific topological and geometric constraints. Shock hypotheses that violate the grammar or are topologically or geometrically invalid are pruned to enforce global consistency. Survivors are organized into a hierarchical graph of shock groups computed in the reaction-diffusion space, where diffusion plays a role of regularization to determine the significance of each shock group. The shock groups can be functionally related to the object's parts, protrusions and bends, and the representation is suited to recognition: several examples illustrate its stability with rotations, scale changes, occlusion and movement of parts, even at very low resolutions.

Stochasticks: augmenting the billiards experience with probabilistic vision and wearable computers

Abstract: We propose a practical application of wearable computing and augmented reality which enhances the game of billiards. A vision algorithm is implemented which operates in interactive-time with the user to assist planning and aiming. Probabilistic color models and symmetry operations are used to localize the table, pockets and balls through a video camera near the user's eye. Classification of the objects of interest is performed and each possible shot is ranked in order to determine its relative usefulness. The system allows the user to proceed through a regular pool game while it automatically determines strategic shots. The resulting trajectories are rendered as graphical overlays on a head mounted live video display. The wearable video output and the computer vision system provide an integration of real and virtual environments which enhances the experience of playing and learning the game of billiards without encumbering the player.