Explainable Droplet Recognition System for Precision Sprayer Applications

Rogers, Harry ORCID: https://orcid.org/0000-0003-3227-5677 and Zebin, Tahmina ORCID: https://orcid.org/0000-0003-0437-0570 (2022) Explainable Droplet Recognition System for Precision Sprayer Applications. In: FARSCOPE CDT Conference, 2022-07-11 - 2022-07-15, Bristol.

[img]
Preview
PDF (Explainable Droplet Recognition System for Precision Sprayer Applications) - Accepted Version
Available under License Unspecified licence.

Download (716kB) | Preview

Abstract

AI-driven detection systems are playing an increasingly important role in the advancement of precision agriculture. In this paper, we have implemented a transfer learning pipeline for water droplet detection with the intent to develop quantifiable and real-time detection of post-spray areas for precision spraying applications. The object detection pipeline effectively identified multiple features for water droplet detection from the three curated datasets. We have used two pre-trained convolutional backbones as the feature extractor and achieved an overall detection mean average precision across the three curated datasets of 0.409 and 0.277 for the ResNet50, and MobileNetV3-Large backbones respectively. Additionally, for visual explanations and interpretation, we implemented EigenCAM class activation mapping techniques to highlight the regions of the input images that are important for predictions.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: explainable ai,precision spraying,computer vision,sdg 9 - industry, innovation, and infrastructure ,/dk/atira/pure/sustainabledevelopmentgoals/industry_innovation_and_infrastructure
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: LivePure Connector
Date Deposited: 03 Aug 2022 08:30
Last Modified: 07 Aug 2022 06:30
URI: https://ueaeprints.uea.ac.uk/id/eprint/87062
DOI:

Actions (login required)

View Item View Item