Point context: an effective shape descriptor for RST-invariant trajectory recognition

DOI10.1007/S10851-016-0648-6zbMATH Open1386.68183arXiv1501.05432OpenAlexW3103902601MaRDI QIDQ333618FDOQ333618

Authors: Xingyu Wu, Xia Mao, Yuli Xue, Alberto Rovetta, Li-Jiang Chen 

Publication date: 31 October 2016

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Abstract: Motion trajectory recognition is important for characterizing the moving property of an object. The speed and accuracy of trajectory recognition rely on a compact and discriminative feature representation, and the situations of varying rotation, scaling and translation has to be specially considered. In this paper we propose a novel feature extraction method for trajectories. Firstly a trajectory is represented by a proposed point context, which is a rotation-scale-translation (RST) invariant shape descriptor with a flexible tradeoff between computational complexity and discrimination, yet we prove that it is a complete shape descriptor. Secondly, the shape context is nonlinearly mapped to a subspace by kernel nonparametric discriminant analysis (KNDA) to get a compact feature representation, and thus a trajectory is projected to a single point in a low-dimensional feature space. Experimental results show that, the proposed trajectory feature shows encouraging improvement than state-of-art methods.

Full work available at URL: https://arxiv.org/abs/1501.05432

Recommendations

• Integral invariants for space motion trajectory matching and recognition
• Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition
• Mixed signature: an invariant descriptor for 3D motion trajectory perception and recognition
• Invariant multiscale triangle feature for shape recognition
• Motion trajectory reproduction from generalized signature description

zbMATH Keywords

nonlinear dimensionality reductionshape descriptormotion trajectoryRST-invariant

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Cites Work

• Title not available (Why is that?)
• Pattern classification.
• Compressed Sensing With Cross Validation
• Mixed signature: an invariant descriptor for 3D motion trajectory perception and recognition
• The generalized uniqueness wavelet descriptor for planar closed curves
• The Construction of Bounded Irregular Pyramids with a Union-Find Decimation Process
• Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition

Cited In (1)

• Motion trajectory reproduction from generalized signature description

This page was built for publication: Point context: an effective shape descriptor for RST-invariant trajectory recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q333618)