Structure and motion from line segments in multiple images

Taylor, C. James; Kriegman, David

doi:10.1109/34.473228

Cited by 222 publications

(105 citation statements)

References 23 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…Faugeras et al [12] solved for camera motion and scene structure from three perspective images using an EKF to minimize an objective function based on the epipolar constraint. Related is Taylor and Kriegman's work [13] which proposed minimizing a cost function measuring the least squares distance between observed edge segments and the projection of reconstructed lines, and Bartoli and Sturm [14] discuss optimal line parametrisations for the the minimisation procedure. SfM using lines with uncalibrated cameras has also been demonstrated, leading to the exposition of Shashua [15] on projective tri-focal constraints.…”

Section: Related Workmentioning

confidence: 99%

Improving the Agility of Keyframe-Based SLAM

Klein

Murray

2008

Lecture Notes in Computer Science

266

227

View full text Add to dashboard Cite

Abstract. The ability to localise a camera moving in a previously unknown environment is desirable for a wide range of applications. In computer vision this problem is studied as monocular SLAM. Recent years have seen improvements to the usability and scalability of monocular SLAM systems to the point that they may soon find uses outside of laboratory conditions. However, the robustness of these systems to rapid camera motions (we refer to this quality as agility) still lags behind that of tracking systems which use known object models. In this paper we attempt to remedy this. We present two approaches to improving the agility of a keyframe-based SLAM system: Firstly, we add edge features to the map and exploit their resilience to motion blur to improve tracking under fast motion. Secondly, we implement a very simple inter-frame rotation estimator to aid tracking when the camera is rapidly panning -and demonstrate that this method also enables a trivially simple yet effective relocalisation method. Results show that a SLAM system combining points, edge features and motion initialisation allows highly agile tracking at a moderate increase in processing time.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving the Agility of Keyframe-Based SLAM

Klein

Murray

2008

Lecture Notes in Computer Science

266

227

View full text Add to dashboard Cite

show abstract

“…Marr conceived an outline of a solution for this problem [13] by combining low-, mid-, and high-level cues. Despite promising work in this direction [4,21,5,15], no complete solution has been established so far. Recently, the problem of combining low-,mid-, and highlevel information for this task has become more tractable due to progress in machine learning and statistics.…”

Section: Introductionmentioning

confidence: 99%

Detecting Object Boundaries Using Low-, Mid-, and High-level Information

Zheng¹,

Tu²,

Yuille³

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…It should be noted that the semantically relevant feature is not the in nite supporting line of the segment but the nite length segment. Despite this, only a few works ( 2,3]) have proposed models that include the nite length of the line segments in structure and motion computing. The consideration of the segment nite length has renewed interest in the usage of straight features in structure and motion problems.…”

Section: Introductionmentioning

confidence: 99%

Structure and motion from straight line segments

Montiel

Tardós

Montano

2000

Pattern Recognition

View full text Add to dashboard Cite

A method to determine both the camera location and scene structure from image straight segment correspondences is presented. The proposed method considers the nite segment length in order to use stronger constraints than do those that use the in nite line that supports the image segment. The constraints between image segments involve a weak pairing between image segment midpoints. This allows deviations of the midpoint only in the segment direction. Experimental results are presented of structure and motion computations from the image straight line segment-matching using two real images.

show abstract

Structure and motion from line segments in multiple images

Cited by 222 publications

References 23 publications

Improving the Agility of Keyframe-Based SLAM

Improving the Agility of Keyframe-Based SLAM

Detecting Object Boundaries Using Low-, Mid-, and High-level Information

Structure and motion from straight line segments

Contact Info

Product

Resources

About