Robust image corner detection based on scale evolution difference of planar curves

Zhang, Xiaohong; Wang, Hongxing; Hong, Mingjian; Xu, Lan; Yang, Dan; Lovell, Brian C.

doi:10.1016/j.patrec.2008.11.002

Cited by 55 publications

(54 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A similar distance function was used in [11]. The maxima of F d are simply passed as the candidate points.…”

Section: A Distance Functionmentioning

confidence: 99%

“…We evaluated seven detectors namely CSS [10], ARCSS [3], He & Yung [8], MSCP [12], Zhang et al [11], CPDA [5] and the proposed improved CPDA detector. All the detectors, except the CPDA detector, were set at the default parameter settings indicated by their authors.…”

Section: Performance Studymentioning

confidence: 99%

“…CSS [10] 0.0084 ARCSS [3] 0.0156 He & Yung [8] 0.0090 MSCP [12] 0.0056 Zhang [11] 0.0146 CPDA [3] 0 intervals, excluding sh x = sh y = 0. Therefore, the database had a total of 450 rotated, 375 uniform scaled, 2925 non-uniform scaled, 3750 rotated and scaled transformed images.…”

Section: Detectorsmentioning

confidence: 99%

“…On the other hand, multi-scale detectors using a small set of smoothing-scales [3], [10]- [12] are computationally less expensive and more popular. They detect corners using one [10], two [11] or three [3], [12] smoothing-scales and may track the detected corners to a common small smoothing-scale to combine the detected corners and to improve their localization.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique

Awrangjeb

Fraser

et al. 2009

2009 Digital Image Computing: Techniques and Applications

View full text Add to dashboard Cite

Abstract-The previously proposed contour-based multi-scale corner detector based on the chord-to-point distance accumulation (CPDA) technique has proved its superior robustness over many other single-and multi-scale detectors. However, the original CPDA detector is computationally expensive since it calculates the CPDA discrete curvature on each point of the curve. The proposed improvement obtains a set of probable candidate points before the CPDA curvature estimation. The CPDA curvature is estimated on these chosen candidate points only. Consequently, the improved CPDA detector becomes faster, while retaining a similar robustness to the original CPDA detector.

show abstract

“…A similar distance function was used in [11]. The maxima of F d are simply passed as the candidate points.…”

Section: A Distance Functionmentioning

confidence: 99%

Section: Performance Studymentioning

confidence: 99%

Section: Detectorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique

Awrangjeb

Fraser

et al. 2009

2009 Digital Image Computing: Techniques and Applications

View full text Add to dashboard Cite

show abstract

“…It combines a partitioning of ultrametric contour maps (UCM; generated via [3,4]) with normal descriptors, dense local features and a random-forest regressor. UCM region boundaries are partitioned at keypoints detected as local maxima of the Difference of Gaussian (DoG) function D(u, σ ) detailed by Zhang et al [10]. We generate fin candidates as contour strokes by sampling the region contour between every permutation of keypoint pairs.…”

mentioning

confidence: 99%

Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery

Hughes

Burghardt

2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

Introduction. Recognising individuals repeatedly over time is a basic requirement for field-based ecology and related life sciences [5,6]. In this paper we propose a visual identification approach for great white shark fins as outlined in Figure 1, one that is applicable to unconstrained fin imagery and fully automates the pipeline from feature extraction to matching of identities. We pose the associated vision task as a fine-grained, multiinstance classification problem for flexible, smooth and partly occluded object parts. To the best of our knowledge, the proposed system is the first fully automated contour-based animal biometrics system. Contour Stroke Object Model. A key technical contribution of the paper is a contour stroke model trained for fin detection. It combines a partitioning of ultrametric contour maps (UCM; generated via [3,4]) with normal descriptors, dense local features and a random-forest regressor. UCM region boundaries are partitioned at keypoints detected as local maxima of the Difference of Gaussian (DoG) function D(u, σ ) detailed by Zhang et al. [10]. We generate fin candidates as contour strokes by sampling the region contour between every permutation of keypoint pairs. Each stroke is then described by a 160 dimensional feature vector consisting of two components: the first is a bag of opponentSIFT [9] visual words, the second describes boundary shape using a histogram of boundary normals. A random forest regressor is finally trained to predict the fin-like quality of contour stroke candidates. Figure 2 illustrates fins detected by this strategy. In common with the segmentation stage of Arandjelovic and Zisserman's 'Bag of Boundaries' pipeline [2], our contour stroke model separates objects in natural images and against cluttered backgrounds, but differs in that it exploits species characteristic shape encoded in the open contours, to specifically and explicitly detect fin parts.Biometric Encoding: [1, 2] perform smooth object recognition using semi-local boundary normal and HoG+occupancy representations, respectively. These allow efficient and robust matching, but their encoding of inter-class variance will always be sub-maximal. Meanwhile, the semiautomated fin recognition system DARWIN [8] uses a global 2D Cartesian representation. This encoding maximises inter-class variance, but is sensitive to partial occlusions and detection errors. By contrast we utilise semi-local and global shape descriptions in a vector-based combinatorial encoding strategy, one that enables efficient and accurate individual recognition while being robust to noisy, partially occluded input.As with generating contour strokes, we combinatorially sample fin boundaries between pairs of keypoints detected using D(u, σ ), reparameterised for fine-grained feature detection. We then scale-normalise the resulting contour subsections and encode their shape over various spectral scales. Denoting the set of descriptors for a query object at scale j as D

show abstract

Corner Detection via Two-Layer Threshold Method

Yang

Han

2012

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Robust image corner detection based on scale evolution difference of planar curves

Cited by 55 publications

References 20 publications

A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique

A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique

Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery

Corner Detection via Two-Layer Threshold Method

Contact Info

Product

Resources

About