A Keygraph Classification Framework for Real-Time Object Detection

TL;DR

This paper introduces a graph-based keypoint classification method for real-time object detection that leverages structural information to improve robustness and computational efficiency.

Contribution

The paper presents a novel graph classification framework for keypoints, enhancing robustness and efficiency over traditional appearance-based methods.

Findings

Effective real-time object detection in video sequences

Graph-based approach outperforms traditional keypoint classification methods

Method is adaptable to larger graph structures

Abstract

In this paper, we propose a new approach for keypoint-based object detection. Traditional keypoint-based methods consist in classifying individual points and using pose estimation to discard misclassifications. Since a single point carries no relational features, such methods inherently restrict the usage of structural information to the pose estimation phase. Therefore, the classifier considers purely appearance-based feature vectors, thus requiring computationally expensive feature extraction or complex probabilistic modelling to achieve satisfactory robustness. In contrast, our approach consists in classifying graphs of keypoints, which incorporates structural information during the classification phase and allows the extraction of simpler feature vectors that are naturally robust. In the present work, 3-vertices graphs have been considered, though the methodology is general and larger order graphs may be adopted. Successful experimental results obtained for real-time object detection in video sequences are reported.