Robust Detection of Objects under Periodic Motion with Gaussian Process Filtering

TL;DR

This paper introduces a data-driven Gaussian Process filtering method to enhance object detection in videos where objects exhibit periodic motion, significantly reducing errors and improving detection accuracy.

Contribution

It formalizes the problem of periodic object detection and proposes a novel Gaussian Process-based filtering approach to improve detection performance in such scenarios.

Findings

Filtering with Gaussian Processes significantly improves detection accuracy.

The approach effectively reduces false positives in periodic motion scenarios.

Simulation results demonstrate large performance gains.

Abstract

Object Detection (OD) is an important task in Computer Vision with many practical applications. For some use cases, OD must be done on videos, where the object of interest has a periodic motion. In this paper, we formalize the problem of periodic OD, which consists in improving the performance of an OD model in the specific case where the object of interest is repeating similar spatio-temporal trajectories with respect to the video frames. The proposed approach is based on training a Gaussian Process to model the periodic motion, and use it to filter out the erroneous predictions of the OD model. By simulating various OD models and periodic trajectories, we demonstrate that this filtering approach, which is entirely data-driven, improves the detection performance by a large margin.