Using symmetry for detecting and locating objects in a picture

Marola, G.

doi:10.1016/0734-189x(89)90168-0

Cited by 45 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some representative approaches are used some information about symmetry, color, shadow, geometrical features (e.g., corners, horizontal/vertical edges), texture, and vehicle lights [17]. …”

Section: Knowledge-based Methodsmentioning

confidence: 99%

Survey On Vision Based On-Road Vehicle Detection

Saini¹

2014

IJUNESST

View full text Add to dashboard Cite

show abstract

“…Some representative approaches are used some information about symmetry, color, shadow, geometrical features (e.g., corners, horizontal/vertical edges), texture, and vehicle lights [17]. …”

Section: Knowledge-based Methodsmentioning

confidence: 99%

Survey On Vision Based On-Road Vehicle Detection

Saini¹

2014

IJUNESST

View full text Add to dashboard Cite

show abstract

“…A measure of symmetry is defined at a position p, scale s, and orientation θ in an image. Strong symmetry at (p, s, θ) means that if we imagine a dividing line with orientation θ passing through p, the image on one side is in some way similar to a reflection of the image on the other side, at scale s. Previous object detection studies studying notions of symmetry include [16,26,13].…”

Section: Repetition and Symmetry Based Image Descriptorsmentioning

confidence: 99%

Image representations beyond histograms of gradients: The role of Gestalt descriptors

Bileschi

Wolf

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

“…In earlier work, for instance, Marola [16] used symmetry for detection and localization of objects in planar images. Symmetry has furthermore been used to control the gaze of artificial vision systems [17,18] Heidemann [19] showed that interest points detected with color symmetry are robust to noise and 3D object rotation.…”

Section: Introductionmentioning

confidence: 99%

Using Local Symmetry for Landmark Selection

Kootstra

Jong

Schomaker

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Most visual Simultaneous Localization And Mapping (SLAM) methods use interest points as landmarks in their maps of the environment. Often the interest points are detected using contrast features, for instance those of the Scale Invariant Feature Transform (SIFT). The SIFT interest points, however, have problems with stability, and noise robustness. Taking our inspiration from human vision, we therefore propose the use of local symmetry to select interest points. Our method, the MUlti-scale Symmetry Transform (MUST), was tested on a robot-generated database including ground-truth information to quantify SLAM performance. We show that interest points selected using symmetry are more robust to noise and contrast manipulations, have a slightly better repeatability, and above all, result in better overall SLAM performance.

show abstract

Using symmetry for detecting and locating objects in a picture

Cited by 45 publications

References 9 publications

Survey On Vision Based On-Road Vehicle Detection

Survey On Vision Based On-Road Vehicle Detection

Image representations beyond histograms of gradients: The role of Gestalt descriptors

Using Local Symmetry for Landmark Selection

Contact Info

Product

Resources

About