Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EEPPR: Event-based Estimation of Periodic Phenomena Rate using Correlation in 3D

Jakub Kolář, Radim Špetlík, Jiří Matas

TL;DR

The paper tackles non-contactly estimating the rate of diverse periodic phenomena from event camera data. It introduces EEPPR, which quantises events into a 3D spatio-temporal tensor, automatically selects per-region templates, and uses 3D correlation to detect period peaks, with the final rate derived as the median across regions from the time deltas between peaks. On a 12-sequence dataset spanning flicker, vibration, rotation, and translation, EEPPR achieves a mean relative error of $0.1\%$, setting a new state-of-the-art and outperforming multiple baselines and published methods. This work demonstrates robust, marker-free frequency estimation across challenging conditions, including non-frontal viewpoints and high-frequency regimes up to $2$ kHz, with public dataset and code supporting reproducibility and application in industry and research.

Abstract

We present a novel method for measuring the rate of periodic phenomena (e.g., rotation, flicker, and vibration), by an event camera, a device asynchronously reporting brightness changes at independently operating pixels with high temporal resolution. The approach assumes that for a periodic phenomenon, a highly similar set of events is generated within a spatio-temporal window at a time difference corresponding to its period. The sets of similar events are detected by a correlation in the spatio-temporal event stream space. The proposed method, EEPPR, is evaluated on a dataset of 12 sequences of periodic phenomena, i.e. flashing light and vibration, and periodic motion, e.g., rotation, ranging from 3.2 Hz to 2 kHz (equivalent to 192 - 120 000 RPM). EEPPR significantly outperforms published methods on this dataset, achieving a mean relative error of 0.1%, setting new state-of-the-art. The dataset and codes are publicly available on GitHub.

EEPPR: Event-based Estimation of Periodic Phenomena Rate using Correlation in 3D

TL;DR

The paper tackles non-contactly estimating the rate of diverse periodic phenomena from event camera data. It introduces EEPPR, which quantises events into a 3D spatio-temporal tensor, automatically selects per-region templates, and uses 3D correlation to detect period peaks, with the final rate derived as the median across regions from the time deltas between peaks. On a 12-sequence dataset spanning flicker, vibration, rotation, and translation, EEPPR achieves a mean relative error of , setting a new state-of-the-art and outperforming multiple baselines and published methods. This work demonstrates robust, marker-free frequency estimation across challenging conditions, including non-frontal viewpoints and high-frequency regimes up to kHz, with public dataset and code supporting reproducibility and application in industry and research.

Abstract

We present a novel method for measuring the rate of periodic phenomena (e.g., rotation, flicker, and vibration), by an event camera, a device asynchronously reporting brightness changes at independently operating pixels with high temporal resolution. The approach assumes that for a periodic phenomenon, a highly similar set of events is generated within a spatio-temporal window at a time difference corresponding to its period. The sets of similar events are detected by a correlation in the spatio-temporal event stream space. The proposed method, EEPPR, is evaluated on a dataset of 12 sequences of periodic phenomena, i.e. flashing light and vibration, and periodic motion, e.g., rotation, ranging from 3.2 Hz to 2 kHz (equivalent to 192 - 120 000 RPM). EEPPR significantly outperforms published methods on this dataset, achieving a mean relative error of 0.1%, setting new state-of-the-art. The dataset and codes are publicly available on GitHub.
Paper Structure (28 sections, 2 figures, 3 tables)

This paper contains 28 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Baselines
  4. A Simple baseline
  5. An FFT baseline
  6. EEPPR -- The proposed method
  7. Experiments
  8. Dataset
  9. Measuring rotation speed
  10. Felt disc with a high-contrast line
  11. Fronto-parallel velcro disc
  12. Velcro disc with a non-frontal camera behind a glass sheet
  13. High-contrast dot
  14. Hand fidget spinner
  15. Whirling Pholcus phalangioides
  16. ...and 13 more sections

Figures (2)

  • Figure 1: (a) EEPPR: (i) data captured from an event camera is aggregated into a 3D array, (ii) the array is split into same-sized areas, and in each area a template depth is automatically selected, (iii) a correlation of the template with the event stream is computed in 3D, (iv) a frequency is calculated from the median of time deltas measured between correlation peaks for each window, (v) the output frequency is computed as a median of measurements from all windows. (b) Normalised correlation responses of a selected 3D template with $1000$ ms of spatio-temporal event stream. Periodic peaks are highly distinctive, highly regular and indicate a periodic phenomenon. (c) Ground-truth rates of experiments in order of appearance in this work.
  • Figure 2: Velcro disc with a non-frontal camera behind a glass sheet (see Sec. \ref{['sec:velcro_side']}): (a) physical setup; (b) events from a 250-millisecond window visualised in spatio-temporal space; (c) a close-up photo of the target; (d) aggregated events captured by the event camera ($1280\times720$px) within a time window of length equal to the period of the observed phenomenon. Positive events are represented by white colour, negative events are bright blue.