Slicing aided large scale tomato fruit detection and counting in 360-degree video data from a greenhouse

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F22%3A63556519" target="_blank" >RIV/70883521:28140/22:63556519 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0263224122011733?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0263224122011733?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.measurement.2022.111977" target="_blank" >10.1016/j.measurement.2022.111977</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Slicing aided large scale tomato fruit detection and counting in 360-degree video data from a greenhouse

Popis výsledku v původním jazyce

This paper proposes an automated tomato fruit detection and counting process without a need for any human intervention. First of all, wide images of whole tomato plant rows were extracted from a 360-degree video taken in a greenhouse. These images were utilized to create a new object detection dataset. The original tomato detection methodology uses a deep CNN model with slicing-aided inference. The process encompasses two stages: first, the images are cut into patches for object detection, and consequently, the predictions are stitched back together. The paper also presents an extensive study of post-processing parameters needed to stitch object detections correctly, especially on the patch&apos;s borders. Final results reach 83.09% F1 score value on a test set, proving the suitability of the proposed methodology for robotic farming.

Název v anglickém jazyce

Slicing aided large scale tomato fruit detection and counting in 360-degree video data from a greenhouse

Popis výsledku anglicky

This paper proposes an automated tomato fruit detection and counting process without a need for any human intervention. First of all, wide images of whole tomato plant rows were extracted from a 360-degree video taken in a greenhouse. These images were utilized to create a new object detection dataset. The original tomato detection methodology uses a deep CNN model with slicing-aided inference. The process encompasses two stages: first, the images are cut into patches for object detection, and consequently, the predictions are stitched back together. The paper also presents an extensive study of post-processing parameters needed to stitch object detections correctly, especially on the patch&apos;s borders. Final results reach 83.09% F1 score value on a test set, proving the suitability of the proposed methodology for robotic farming.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/FW01010381" target="_blank" >FW01010381: Inteligentní robotická ochrana zdraví ekosystému hydroponického skleníku</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Measurement

ISSN

0263-2241

e-ISSN

1873-412X

Svazek periodika

204

Číslo periodika v rámci svazku

Neuveden

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

11

Strana od-do

1-11

Kód UT WoS článku

000876254100002

EID výsledku v databázi Scopus

2-s2.0-85140136384