Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing

A disease detection network based on a sparse parallel attention mechanism is proposed and experimentally validated in the passion fruit (<i>Passiflora edulis</i> [Sims]) disease detection task. <i>Passiflora edulis</i>, as a tropical and subtropical fruit tree, is loved worl...

Full description

Saved in:
Bibliographic Details
Main Authors: Yajie He, Ningyi Zhang, Xinjin Ge, Siqi Li, Linfeng Yang, Minghao Kong, Yiping Guo, Chunli Lv
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/7/733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188298504372224
author Yajie He
Ningyi Zhang
Xinjin Ge
Siqi Li
Linfeng Yang
Minghao Kong
Yiping Guo
Chunli Lv
author_facet Yajie He
Ningyi Zhang
Xinjin Ge
Siqi Li
Linfeng Yang
Minghao Kong
Yiping Guo
Chunli Lv
author_sort Yajie He
collection DOAJ
description A disease detection network based on a sparse parallel attention mechanism is proposed and experimentally validated in the passion fruit (<i>Passiflora edulis</i> [Sims]) disease detection task. <i>Passiflora edulis</i>, as a tropical and subtropical fruit tree, is loved worldwide for its unique flavor and rich nutritional value. The experimental results demonstrate that the proposed model performs excellently across various metrics, achieving a precision of 0.93, a recall of 0.88, an accuracy of 0.91, an mAP@50 (average precision at the IoU threshold of 0.50) of 0.90, an mAP@50–95 (average precision at IoU thresholds from 0.50 to 0.95) of 0.60, and an F1-score of 0.90, significantly outperforming traditional object detection models such as Faster R-CNN, SSD, and YOLO. The experiments show that the sparse parallel attention mechanism offers significant advantages in disease detection with multi-scale and complex backgrounds. This study proposes a lightweight deep learning model incorporating a sparse parallel attention mechanism (SPAM) for passion fruit disease detection. Built upon a Convolutional Neural Network (CNN) backbone, the model integrates a dynamically selective attention mechanism to enhance detection performance in cases with complex backgrounds and multi-scale objects. Experimental results demonstrate that the model has superior precision, recall, and mean average precision (mAP) compared with state-of-the-art detection models while maintaining computational efficiency.
format Article
id doaj-art-e5ee2dc868324270a89ce86cb631e0f7
institution OA Journals
issn 2077-0472
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-e5ee2dc868324270a89ce86cb631e0f72025-08-20T02:15:54ZengMDPI AGAgriculture2077-04722025-03-0115773310.3390/agriculture15070733Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical SensingYajie He0Ningyi Zhang1Xinjin Ge2Siqi Li3Linfeng Yang4Minghao Kong5Yiping Guo6Chunli Lv7China Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaA disease detection network based on a sparse parallel attention mechanism is proposed and experimentally validated in the passion fruit (<i>Passiflora edulis</i> [Sims]) disease detection task. <i>Passiflora edulis</i>, as a tropical and subtropical fruit tree, is loved worldwide for its unique flavor and rich nutritional value. The experimental results demonstrate that the proposed model performs excellently across various metrics, achieving a precision of 0.93, a recall of 0.88, an accuracy of 0.91, an mAP@50 (average precision at the IoU threshold of 0.50) of 0.90, an mAP@50–95 (average precision at IoU thresholds from 0.50 to 0.95) of 0.60, and an F1-score of 0.90, significantly outperforming traditional object detection models such as Faster R-CNN, SSD, and YOLO. The experiments show that the sparse parallel attention mechanism offers significant advantages in disease detection with multi-scale and complex backgrounds. This study proposes a lightweight deep learning model incorporating a sparse parallel attention mechanism (SPAM) for passion fruit disease detection. Built upon a Convolutional Neural Network (CNN) backbone, the model integrates a dynamically selective attention mechanism to enhance detection performance in cases with complex backgrounds and multi-scale objects. Experimental results demonstrate that the model has superior precision, recall, and mean average precision (mAP) compared with state-of-the-art detection models while maintaining computational efficiency.https://www.mdpi.com/2077-0472/15/7/733passion fruit disease detectionmulti-scale detectionsmart agricultureimage processingdeep learning
spellingShingle Yajie He
Ningyi Zhang
Xinjin Ge
Siqi Li
Linfeng Yang
Minghao Kong
Yiping Guo
Chunli Lv
Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
Agriculture
passion fruit disease detection
multi-scale detection
smart agriculture
image processing
deep learning
title Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
title_full Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
title_fullStr Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
title_full_unstemmed Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
title_short Passion Fruit Disease Detection Using Sparse Parallel Attention Mechanism and Optical Sensing
title_sort passion fruit disease detection using sparse parallel attention mechanism and optical sensing
topic passion fruit disease detection
multi-scale detection
smart agriculture
image processing
deep learning
url https://www.mdpi.com/2077-0472/15/7/733
work_keys_str_mv AT yajiehe passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT ningyizhang passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT xinjinge passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT siqili passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT linfengyang passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT minghaokong passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT yipingguo passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing
AT chunlilv passionfruitdiseasedetectionusingsparseparallelattentionmechanismandopticalsensing