Dataset: Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks

Cao Nguyen Khoa Nam, Matthias Meyer*, Lothar Thiele*, Olga Saukh*

*Corresponding author for this work

Research output: Contribution to conferencePaper

Abstract

Automatic pollen sensing is important to understand the local distribution of pollen in urban environments and to give personalized advice to the citizens suffering from seasonal pollen allergies to help milder the symptoms. We present a challenging data set of labeled sequential pollen images recorded with an off-the-shelf microscope to test and improve on a variety of tasks, such as pollen detection, classification, tracking, and novelty detection. Pollen samples were gathered using a novel cyclone-based particle collector. The data set contains 16 pollen types with around 35'000 microscopic images per type and covers pollen samples from trees and grasses gathered in Graz, Austria between February and August 2020. In addition, we share microscopic videos taken in the wild over 3 days in February and March 2020 with an automated pollen measurement system based on the same microscope technology to test and compare model performance in a natural environment. The data is available on Zenodo (https://zenodo.org/record/4120033).
Original languageEnglish
Number of pages3
Publication statusPublished - 16 Nov 2020
EventData: Acquisition to Analysis 2020: A SenSys/BuildSys 2020 Workshop - Online workshop, Virtuell, Japan
Duration: 16 Nov 202016 Nov 2020
https://workshopdata.github.io/DATA2020/

Workshop

WorkshopData: Acquisition to Analysis 2020
Abbreviated titleDATA 2020
CountryJapan
CityVirtuell
Period16/11/2016/11/20
Internet address

Keywords

  • pollen
  • microscopic images
  • detection
  • identification
  • novelty

Fingerprint Dive into the research topics of 'Dataset: Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks'. Together they form a unique fingerprint.

Cite this