Temporal Scale and Shift Invariant Automatic Event Recognition using the Mellin Transform

TL;DR

This paper introduces a method for automatic event recognition in videos that are captured at different speeds, leveraging the Mellin Transform to improve accuracy and filter unwanted events.

Contribution

The paper proposes a novel approach combining the Mellin Transform with a holographic correlator for scale and shift invariant event recognition in videos.

Findings

Enhanced recognition accuracy for videos at varying speeds

Effective filtering of unwanted events in video databases

Utilization of the Mellin Transform for scale and shift invariance

Abstract

The Spatio-temporal holographic correlator combines the traditional 2D optical image correlation techniques with inhomogeneously broadened arrays of cold atoms to achieve 3D time-space correlation to realize automatic event recognition at an ultra-high speed. Here we propose a method to realize such event recognition for videos running at different speeds. With this method, we can highly improve recognition accuracy and filter almost all the unwanted events in the video database.