Flowering Intensity Estimation Using Computer Vision

Flowering intensity is an important parameter to predict and control fruit yield. However, its estimation is often based on subjective evaluations of fruit growers. This study explores the application of the YOLO framework for flowering intensity estimation. YOLO is a popular computer vision solutio...

Full description

Saved in:
Bibliographic Details
Main Authors: Sergejs Kodors, Imants Zarembo, Ilmars Apeinans, Edgars Rubauskis, Lienite Litavniece
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:AgriEngineering
Subjects:
Online Access:https://www.mdpi.com/2624-7402/7/4/117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183181207076864
author Sergejs Kodors
Imants Zarembo
Ilmars Apeinans
Edgars Rubauskis
Lienite Litavniece
author_facet Sergejs Kodors
Imants Zarembo
Ilmars Apeinans
Edgars Rubauskis
Lienite Litavniece
author_sort Sergejs Kodors
collection DOAJ
description Flowering intensity is an important parameter to predict and control fruit yield. However, its estimation is often based on subjective evaluations of fruit growers. This study explores the application of the YOLO framework for flowering intensity estimation. YOLO is a popular computer vision solution for object-detecting tasks. It was applied to detect flowers in different studies. Still, it requires manual annotation of photographs of flowering trees, which is a complex and time-consuming process. It is hard to distinguish individual flowers in photos due to their overlapping and indistinct outlines, false positive flowers in the background, and the density of flowers in panicles. Our experiment shows that the small dataset of images (320 × 320 px) is sufficient to achieve an accuracy of 0.995 and 0.994 mAP@50 for YOLOv9m and YOLOv11m using aggregated mosaic augmentation. The AI-based method was compared with the manual method (flowering intensity estimation, 0–9 scale). The comparison was completed using data analysis and the MobileNetV2 classifier as an evaluation model. The analysis shows that the AI-based method is more effective than the manual method.
format Article
id doaj-art-9b1088e9fcf04e9baf5b8ef0c899a232
institution OA Journals
issn 2624-7402
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series AgriEngineering
spelling doaj-art-9b1088e9fcf04e9baf5b8ef0c899a2322025-08-20T02:17:25ZengMDPI AGAgriEngineering2624-74022025-04-017411710.3390/agriengineering7040117Flowering Intensity Estimation Using Computer VisionSergejs Kodors0Imants Zarembo1Ilmars Apeinans2Edgars Rubauskis3Lienite Litavniece4Engineering Center, Rezekne Academy of Riga Technical University, LV-4601 Rezekne, LatviaEngineering Center, Rezekne Academy of Riga Technical University, LV-4601 Rezekne, LatviaEngineering Center, Rezekne Academy of Riga Technical University, LV-4601 Rezekne, LatviaInstitute of Horticulture (LatHort), LV-3701 Dobele, LatviaCentre for Economics and Governance, Rezekne Academy of Riga Technical University, LV-4601 Rezekne, LatviaFlowering intensity is an important parameter to predict and control fruit yield. However, its estimation is often based on subjective evaluations of fruit growers. This study explores the application of the YOLO framework for flowering intensity estimation. YOLO is a popular computer vision solution for object-detecting tasks. It was applied to detect flowers in different studies. Still, it requires manual annotation of photographs of flowering trees, which is a complex and time-consuming process. It is hard to distinguish individual flowers in photos due to their overlapping and indistinct outlines, false positive flowers in the background, and the density of flowers in panicles. Our experiment shows that the small dataset of images (320 × 320 px) is sufficient to achieve an accuracy of 0.995 and 0.994 mAP@50 for YOLOv9m and YOLOv11m using aggregated mosaic augmentation. The AI-based method was compared with the manual method (flowering intensity estimation, 0–9 scale). The comparison was completed using data analysis and the MobileNetV2 classifier as an evaluation model. The analysis shows that the AI-based method is more effective than the manual method.https://www.mdpi.com/2624-7402/7/4/117artificial intelligencecomputer visionflowering intensityhorticultureprecision agriculture
spellingShingle Sergejs Kodors
Imants Zarembo
Ilmars Apeinans
Edgars Rubauskis
Lienite Litavniece
Flowering Intensity Estimation Using Computer Vision
AgriEngineering
artificial intelligence
computer vision
flowering intensity
horticulture
precision agriculture
title Flowering Intensity Estimation Using Computer Vision
title_full Flowering Intensity Estimation Using Computer Vision
title_fullStr Flowering Intensity Estimation Using Computer Vision
title_full_unstemmed Flowering Intensity Estimation Using Computer Vision
title_short Flowering Intensity Estimation Using Computer Vision
title_sort flowering intensity estimation using computer vision
topic artificial intelligence
computer vision
flowering intensity
horticulture
precision agriculture
url https://www.mdpi.com/2624-7402/7/4/117
work_keys_str_mv AT sergejskodors floweringintensityestimationusingcomputervision
AT imantszarembo floweringintensityestimationusingcomputervision
AT ilmarsapeinans floweringintensityestimationusingcomputervision
AT edgarsrubauskis floweringintensityestimationusingcomputervision
AT lienitelitavniece floweringintensityestimationusingcomputervision