Point Context: An Effective Shape Descriptor for RST-invariant Trajectory Recognition

TL;DR

This paper introduces a novel RST-invariant shape descriptor called point context for trajectory recognition, combined with kernel discriminant analysis for compact feature representation, leading to improved recognition accuracy.

Contribution

It proposes a new RST-invariant shape descriptor for trajectories and a kernel-based method for compact feature extraction, enhancing recognition performance.

Findings

Outperforms state-of-the-art methods in recognition accuracy

Provides a complete shape descriptor with flexible complexity

Achieves effective low-dimensional trajectory representation

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.