Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses

Environmental control based on growth stage is critical for enhancing the yield and quality of industrially cultivated <i>Pleurotus pulmonarius</i>. Challenges such as scene complexity and overlapping mushroom clusters can impact the accuracy of growth stage detection and target segmenta...

Full description

Saved in:
Bibliographic Details
Main Authors: Can Wang, Xinhui Wu, Zhaoquan Wang, Han Shao, Dapeng Ye, Xiangzeng Kong
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/10/1033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850254667614781440
author Can Wang
Xinhui Wu
Zhaoquan Wang
Han Shao
Dapeng Ye
Xiangzeng Kong
author_facet Can Wang
Xinhui Wu
Zhaoquan Wang
Han Shao
Dapeng Ye
Xiangzeng Kong
author_sort Can Wang
collection DOAJ
description Environmental control based on growth stage is critical for enhancing the yield and quality of industrially cultivated <i>Pleurotus pulmonarius</i>. Challenges such as scene complexity and overlapping mushroom clusters can impact the accuracy of growth stage detection and target segmentation. This study introduces a lightweight method called the real-time detection model for the growth stages of <i>P. pulmonarius</i> (GSP-RTMDet). A spatial pyramid pooling fast network with simple parameter-free attention (SPPF-SAM) was proposed, which enhances the backbone’s capability to extract key feature information. Additionally, it features an interactive attention mechanism between spatial and channel dimensions to build a cross-stage partial spatial group-wise enhance network (CSP-SGE), improving the feature fusion capability of the neck. The class-aware adaptive feature enhancement (CARAFE) upsampling module is utilized to enhance instance segmentation performance. This study innovatively fusions the improved methods, enhancing the feature representation and the accuracy of masks. By lightweight model design, it achieves real-time growth stage detection of <i>P. pulmonarius</i> and accurate instance segmentation, forming the foundation of an environmental control strategy. Model evaluations reveal that GSP-RTMDet-S achieves an optimal balance between accuracy and speed, with a bounding box mean average precision (bbox mAP) and a segmentation mAP (segm mAP) of 96.40% and 93.70% on the test set, marking improvements of 2.20% and 1.70% over the baseline. Moreover, it boosts inference speed to 39.58 images per second. This method enhances detection and segmentation outcomes in real-world environments of <i>P. pulmonarius</i> houses, offering a more accurate and efficient growth stage perception solution for environmental control.
format Article
id doaj-art-de1af4bceffd48a9ba82a9859b466d37
institution OA Journals
issn 2077-0472
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-de1af4bceffd48a9ba82a9859b466d372025-08-20T01:57:04ZengMDPI AGAgriculture2077-04722025-05-011510103310.3390/agriculture15101033Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom HousesCan Wang0Xinhui Wu1Zhaoquan Wang2Han Shao3Dapeng Ye4Xiangzeng Kong5College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaSchool of Future Technology, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaEnvironmental control based on growth stage is critical for enhancing the yield and quality of industrially cultivated <i>Pleurotus pulmonarius</i>. Challenges such as scene complexity and overlapping mushroom clusters can impact the accuracy of growth stage detection and target segmentation. This study introduces a lightweight method called the real-time detection model for the growth stages of <i>P. pulmonarius</i> (GSP-RTMDet). A spatial pyramid pooling fast network with simple parameter-free attention (SPPF-SAM) was proposed, which enhances the backbone’s capability to extract key feature information. Additionally, it features an interactive attention mechanism between spatial and channel dimensions to build a cross-stage partial spatial group-wise enhance network (CSP-SGE), improving the feature fusion capability of the neck. The class-aware adaptive feature enhancement (CARAFE) upsampling module is utilized to enhance instance segmentation performance. This study innovatively fusions the improved methods, enhancing the feature representation and the accuracy of masks. By lightweight model design, it achieves real-time growth stage detection of <i>P. pulmonarius</i> and accurate instance segmentation, forming the foundation of an environmental control strategy. Model evaluations reveal that GSP-RTMDet-S achieves an optimal balance between accuracy and speed, with a bounding box mean average precision (bbox mAP) and a segmentation mAP (segm mAP) of 96.40% and 93.70% on the test set, marking improvements of 2.20% and 1.70% over the baseline. Moreover, it boosts inference speed to 39.58 images per second. This method enhances detection and segmentation outcomes in real-world environments of <i>P. pulmonarius</i> houses, offering a more accurate and efficient growth stage perception solution for environmental control.https://www.mdpi.com/2077-0472/15/10/1033environmental parameter controlgrowth stage detectioncomputer visioninstance segmentationlightweight
spellingShingle Can Wang
Xinhui Wu
Zhaoquan Wang
Han Shao
Dapeng Ye
Xiangzeng Kong
Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
Agriculture
environmental parameter control
growth stage detection
computer vision
instance segmentation
lightweight
title Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
title_full Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
title_fullStr Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
title_full_unstemmed Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
title_short Real-Time Detection and Instance Segmentation Models for the Growth Stages of <i>Pleurotus pulmonarius</i> for Environmental Control in Mushroom Houses
title_sort real time detection and instance segmentation models for the growth stages of i pleurotus pulmonarius i for environmental control in mushroom houses
topic environmental parameter control
growth stage detection
computer vision
instance segmentation
lightweight
url https://www.mdpi.com/2077-0472/15/10/1033
work_keys_str_mv AT canwang realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses
AT xinhuiwu realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses
AT zhaoquanwang realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses
AT hanshao realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses
AT dapengye realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses
AT xiangzengkong realtimedetectionandinstancesegmentationmodelsforthegrowthstagesofipleurotuspulmonariusiforenvironmentalcontrolinmushroomhouses