Showing papers by "David G. Lowe published in 2007"

Automatic Panoramic Image Stitching using Invariant Features

Abstract: This paper concerns the problem of fully automated panoramic image stitching. Though the 1D problem (single axis of rotation) is well studied, 2D or multi-row stitching is more difficult. Previous approaches have used human input or restrictions on the image sequence in order to establish matching images. In this work, we formulate stitching as a multi-image matching problem, and use invariant local features to find matches between all of the images. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the input images. It is also insensitive to noise images that are not part of a panorama, and can recognise multiple panoramas in an unordered image dataset. In addition to providing more detail, this paper extends our previous work in the area (Brown and Lowe, 2003) by introducing gain compensation and automatic straightening steps.

Shape Descriptors for Maximally Stable Extremal Regions

Abstract: This paper introduces an affine invariant shape descriptor for maximally stable extremal regions (MSER). Affine invariant feature descriptors are normally computed by sampling the original grey-scale image in an invariant frame defined from each detected feature, but we instead use only the shape of the detected MSER itself. This has the advantage that features can be reliably matched regardless of the appearance of the surroundings of the actual region. The descriptor is computed using the scale invariant feature transform (SIFT), with the resampled MSER binary mask as input. We also show that the original MSER detector can be modified to achieve better scale invariance by detecting MSERs in a scale pyramid. We make extensive comparisons of the proposed feature against a SIFT descriptor computed on grey-scale patches, and also explore the possibility of grouping the shape descriptors into pairs to incorporate more context. While the descriptor does not perform as well on planar scenes, we demonstrate various categories of full 3D scenes where it outperforms the SIFT descriptor computed on grey-scale patches. The shape descriptor is also shown to be more robust to changes in illumination. We show that a system can achieve the best performance under a range of imaging conditions by matching both the texture and shape descriptors.

Curious George: The UBC Semantic Robot Vision System

Abstract: This report describes the robot, Curious George, that took part in, and won, the robot league of the 2007 Semantic Robot Vision Challenge (SRVC), held at the AAAI’07 conference in Vancouver, Canada. We describe the robot hardware, the algorithms used during each of the three competition phases, as well as the results obtained by the system during the competition.

The UBC semantic robot vision system

Abstract: This abstract outlines the algorithms and robot hardware used in the UBC robot competing in the Semantic Robot Vision Challenge (SRVC), held at the AAAI’07 conference in Vancouver, Canada. Successfully completing the SRVC involves smooth integration of tasks such as data acquisition, training, obstacle avoidance, visual search, and object recognition. Given that these tasks span several research disciplines, successful integration is a formidable task. The value of working on these problems jointly is that assumptions built into an isolated method will be exposed when it is integrated, thus highlighting where further research is required. In addition, this will focus research on robots that can navigate safely and identify objects in their environment. Our approach is decomposed into five primary modules, each of which relies on the success of other modules, avoiding some of the unrealistic assumptions that are sometimes made when the tasks are tackled independently. The five primary modules are: