Using Local Symmetry for Landmark Selection

Kootstra, Gert; Jong, Sjoerd de; Schomaker, Lambert

doi:10.1007/978-3-642-04667-4_10

Cited by 3 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the underlying physical structure of the environment may remain constant, visual effects can impact the specific places where visual techniques detect feature points. A method is proposed by [16] uses local symmetry to judge the potential future stability of a feature point. This follows their finding that feature points detected by algorithms like SIFT [17] are very susceptible to noise.…”

Section: Visual Effects On Slam Pointcloudsmentioning

confidence: 99%

Associating Landmarks from SLAM’s Visual Structure

Bradley,

Zelek

2024

Proceedings of the Conference on Robots and Vision

View full text Add to dashboard Cite

Section: Visual Effects On Slam Pointcloudsmentioning

confidence: 99%

Associating Landmarks from SLAM’s Visual Structure

Bradley,

Zelek

2024

Proceedings of the Conference on Robots and Vision

View full text Add to dashboard Cite

“…Since objects with reflection symmetry are ubiquitous, researches on reflection symmetry has become active in the field of computer vision. Apart from the various applications into high-level tasks such as face recognition [1], human perception [2] ,texture synthesis [3], 3D modeling [4] ,robotic vision [5]and sensor-based motion recognition [6],reflection symmetry as a kind of balance and harmony feature, comparing to other lower geometric features like color and line, has been extensively studied into shape analysis [7][8][9], local and global features [10][11][12][13], image segmentation [14,15],salient detection [16,17] and affective computing [18].…”

Section: Introductionmentioning

confidence: 99%

“…These considerations above motivate us to develop an informative feature with strong generalization, named salient symmetry feature in this paper, targeting for symmetry detection. The motivation of the method comes from that humans pay more attention to salient symmetry objects when interpreting a symmetry-contained scene (i.e.humans are sensitive to the symmetry) [11]. An image is a mapping of a complex real scene in two-dimension space, humans can quickly recognize the reflection symmetry structures of an image which exhibits symmetry objects, especially the image contains multiple symmetry properties [33], and it has been proved that human's eyes fixations concentrate more on the symmetry axis [16].…”

Section: Introductionmentioning

confidence: 99%

Reflection Symmetry Axes Localization Framework for Object Intelligent Perception based on Salient Symmetry Feature

Wu¹,

Qi²,

Yuan-ju³

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper presents an optimized feature-centered reflection symmetry axis detection and localization framework for object perception. The proposed framework is formed to obtain an improved reflection symmetry axis based on the salient symmetry feature. It starts with a refined Multi-scale Saliency Symmetry Model (MSSM), which is realized by applying isotropic symmetry operator on salient points in scale-space rather than all pixels. In each scale, salient points are initially extracted as local extremal from an image, and they are further refined by a multi-scale implementation for generating salient symmetry feature maps. A Symmetric Transformation Matrix is then computed using the optimal feature matching pairs, which can be explicitly used as an abstract representation of the constraint regions of symmetry objects in an image to optimize the performance of the potential symmetry axis detection. The framework has been investigated experimentally both on the classical dataset from a symmetry detection challenge and the latest dataset. It has shown that the framework can get a better or comparative result and also can be further adapted into terminated human--computer equipment for reflection symmetry object perception and tracking.

show abstract

Using symmetrical regions of interest to improve visual SLAM

Kootstra¹,

Schomaker²

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-Simultaneous Localization and Mapping (SLAM) based on visual information is a challenging problem. One of the main problems with visual SLAM is to find good quality landmarks, that can be detected despite noise and small changes in viewpoint. Many approaches use SIFT interest points as visual landmarks. The problem with the SIFT interest points detector, however, is that it results in a large number of points, of which many are not stable across observations. We propose the use of local symmetry to find regions of interest instead. Symmetry is a stimulus that occurs frequently in everyday environments where our robots operate in, making it useful for SLAM. Furthermore, symmetrical forms are inherently redundant, and can therefore be more robustly detected. By using regions instead of points-ofinterest, the landmarks are more stable. To test the performance of our model, we recorded a SLAM database with a mobile robot, and annotated the database by manually adding groundtruth positions. The results show that symmetrical regions-ofinterest are less susceptible to noise, are more stable, and above all, result in better SLAM performance.

show abstract

Using Local Symmetry for Landmark Selection

Cited by 3 publications

References 22 publications

Associating Landmarks from SLAM’s Visual Structure

Associating Landmarks from SLAM’s Visual Structure

Reflection Symmetry Axes Localization Framework for Object Intelligent Perception based on Salient Symmetry Feature

Using symmetrical regions of interest to improve visual SLAM

Contact Info

Product

Resources

About