Showing papers by "David G. Lowe published in 2003"

Recognising Panoramas

Abstract: The problem considered in this paper is the fully asutomaticconstruction of panoramas.Fundamentally, thisproblem requires recognition, as we need to know whichparts of the panorama join up.Previous approaches haveused human input or restrictions on the image sequencefor the matching step.In this work we use object recognitiontechniques based on invariant local features to selectmatchings images, and a probabilistic model for verification.Because of this our method is insensitive to the ordering, orientation, scale and illumination of the images.It is also insensitive to 'noise' images which are not partof the panorama at all, that is, it recognises panoramas.This suggests a useful application for photographers: thesystem takes as input the images on an entire flash card orfilm, recognises images that form part of a panorama, andstitches them with no user input whatsoever.

Automatic rectification of long image sequences

Abstract: This paper addresses the problem of automatically computing homographies between successive frames in image sequences and compensating for the panning, tilting and zooming of the cameras. A homography is a projective mapping between two image planes and describes the transformation created by a fixed camera as it pans, tilts, rotates, and zooms around its optical centre. Our algorithm achieves improved robustness for large motions by combining elements of two previous approaches: it first computes the local displacements of image features using the KanadeLucas-Tomasi (KLT) tracker and determines local matches. The majority of these features are selected by RANSAC and give the initial estimate of the homography. Our modelbased correction system then compensates for remaining projection errors in the image to rink mapping. The system is demonstrated on a digitized sequence of an NHL hockey game, and it is capable of analyzing long sequences of consecutive frames from broadcast video by mapping them into the rink coordinates.

Automatic acquisition of motion trajectories : tracking hockey players

Abstract: Computer systems that have the capability of analyzing complex and dynamic scenes play an essential role in video annotation. Scenes can be complex in such a way that there are many cluttered objects with different colors, shapes and sizes, and can be dynamic with multiple interacting moving objects and a constantly changing background. In reality, there are many scenes that are complex, dynamic, and challenging enough for computers to describe. These scenes include games of sports, air traffic, car traffic, street intersections, and cloud transformations. Our research is about the challenge of inventing a descriptive computer system that analyzes scenes of hockey games where multiple moving players interact with each other on a constantly moving background due to camera motions. Ultimately, such a computer system should be able to acquire reliable data by extracting the players’ motion as their trajectories, querying them by analyzing the descriptive information of data, and predict the motions of some hockey players based on the result of the query. Among these three major aspects of the system, we primarily focus on visual information of the scenes, that is, how to automatically acquire motion trajectories of hockey players from video. More accurately, we automatically analyze the hockey scenes by estimating parameters (i.e., pan, tilt, and zoom) of the broadcast cameras, tracking hockey players in those scenes, and constructing a visual description of the data by displaying trajectories of those players. Many technical problems in vision such as fast and unpredictable players' motions and rapid camera motions make our challenge worth tackling. To the best of our knowledge, there have not been any automatic video annotation systems for hockey developed in the past. Although there are many obstacles to overcome, our efforts and accomplishments would hopefully establish the infrastructure of the automatic hockey annotation system and become a milestone for research in automatic video annotation in this domain.

3D localization and tracking in unknown environments

Abstract: This paper describes a vision-based system for 3D localization and tracking of a mobile robot in an unmodified environment. The system includes a mountable head with three on-board stereo CCD cameras that can be installed on the robot. There the main emphasis is on the ability to estimate the geometric information of the robot independently from any prior scene knowledge, landmark or extra sensory device. Distinctive scene features are identified using a novel algorithm and their 3D locations are estimated with a stereo algorithm. Using multi-stage feature tracking and motion estimation in a symbolic manner, precise motion vectors are obtained. The 3D positions of the scene features are updated by a Kalman filtering process. Experimental results show that robust tracking and localization can be achieved using our vision system.