N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions

Murphy-Chutorian, E.; Trivedi, Mohan M.

doi:10.5244/c.20.76

Cited by 18 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An extremal region is said to be maximally stable if the relative area change, as a result of modifying the threshold, is a local minimum. The MSER algorithm has been extended to volumetric [31] and color images [32] as well as been subject to efficiency enhancements [33,34,35] and a multiresolution version [36].…”

Section: Related Workmentioning

confidence: 99%

Context-aware features and robust image representations

Martins

Carvalho

Gatta

2014

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation.

show abstract

Section: Related Workmentioning

confidence: 99%

Context-aware features and robust image representations

Martins

Carvalho

Gatta

2014

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

show abstract

“…More details on MSER can be found in Section 5.2. The method was extended in [56,161] with tree like representation of watershed evolution in the image.…”

Section: Segmentation-based Methodsmentioning

confidence: 99%

Local Invariant Feature Detectors: A Survey

Tuytelaars

Mikolajczyk

2007

FNT in Computer Graphics and Vision

1,126

573

View full text Add to dashboard Cite

In this survey, we give an overview of invariant interest point detectors, how they evolved over time, how they work, and what their respective strengths and weaknesses are. We begin with defining the properties of the ideal local feature detector. This is followed by an overview of the literature over the past four decades organized in different categories of feature extraction methods. We then provide a more detailed analysis of a selection of methods which had a particularly significant impact on the research field. We conclude with a summary and promising future research directions.

show abstract

“…In this space, every pixel has a luminance component L and two chrominance components a and b. We create a system that is sensitive to color but invariant to intensity changes using only the luminance components, as also done in [4]. Gaussian models have been successfully applied to automatic detection of mobile targets using color information [14,9].…”

Section: Color-based Sign Detectionmentioning

confidence: 99%

“…In general, these methods are sensitive to total or partial occlusion and target rotation. Color-based methods detect signs in a scene using the pixel intensity in RGB [3], CIELab [4] or other color spaces [13]. A few typical problems in the detection of road signs using color information are that vandalism, long exposure to the sun, or camera sensitivity produce a change in the apparent color of the sign.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Color-Based Road Sign Detection and Tracking

Lopez

Fuentes

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper describes a general framework for the detection and tracking of traffic and road signs from image sequences using only color information. The approach consists of two independent parts. In the first we use a set of Gaussian distributions that model each color for detecting road and traffic signs. In the second part we track the targets detected in the first step over time. Our approach is tested using image sequences with high clutter that contain targets with the presence of rotation and partial occlusion. Experimental results show that the proposed system detects on average 97% of the targets in the scene in near real-time with an average of 2 false detections per sequence.

show abstract

N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions

Cited by 18 publications

References 18 publications

Context-aware features and robust image representations

Context-aware features and robust image representations

Local Invariant Feature Detectors: A Survey

Color-Based Road Sign Detection and Tracking

Contact Info

Product

Resources

About