A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models

This study aims to achieve efficient and accurate detection of lotus seedpod maturity in complex environments. To address the challenges associated with existing object detection algorithms, which often involve numerous model parameters and high computational loads that hinder deployment on resource...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Tang, Min Jin, Gaohong Yu, Rui Feng, Bingliang Ye
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10925342/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393324011552768
author Tao Tang
Min Jin
Gaohong Yu
Rui Feng
Bingliang Ye
author_facet Tao Tang
Min Jin
Gaohong Yu
Rui Feng
Bingliang Ye
author_sort Tao Tang
collection DOAJ
description This study aims to achieve efficient and accurate detection of lotus seedpod maturity in complex environments. To address the challenges associated with existing object detection algorithms, which often involve numerous model parameters and high computational loads that hinder deployment on resource-limited mobile terminals, we propose an efficient lotus seedpod maturity detection method based on a compressed model. First, data augmentation techniques were employed to enhance the diversity of lotus seedpod image samples. Next, a model was established under the CSPDarknet53 framework, incorporating a fast spatial pyramid pooling module to detect the maturity of lotus seedpods. To simplify the model and improve detection speed, a channel pruning algorithm was utilized for model compression. Finally, the compressed model was fine-tuned to restore accuracy. Experimental results demonstrate that the compressed model reduced the number of parameters, model size, and inference time by 72.96%, 70.96%, and 26.92%, respectively, achieving a mean Average Precision (mAP) of 99.2%, representing only a 0.20% decrease compared to the original model. Compared to Faster R-CNN, SSD, YOLOv5, YOLOv7-tiny, YOLOv10 and YOLOv11 models, the proposed model significantly reduces parameter count, computational load, and model size while maintaining a high mAP, thus demonstrating feasibility for rapid and accurate detection of lotus seedpod maturity. Additionally, a prototype testing platform for lotus seedpod maturity detection was established, and the compressed model was deployed on an NVIDIA® Jetson Xavier NX mobile terminal. The testing results indicated that the compressed model size was 3.95 MB, with a detection speed of 416.67 frames per second, meeting real-time detection requirements and confirming its applicability for low-computational-capacity mobile terminals. This research provides valuable technical support for the subsequent development of lotus seedpod harvesting robots.
format Article
id doaj-art-4e070a6270fe47dda6fa7ffbfa3aa660
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4e070a6270fe47dda6fa7ffbfa3aa6602025-08-20T03:40:26ZengIEEEIEEE Access2169-35362025-01-0113470994711010.1109/ACCESS.2025.355107010925342A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed ModelsTao Tang0Min Jin1Gaohong Yu2Rui Feng3Bingliang Ye4https://orcid.org/0009-0007-2679-1460Faculty of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, ChinaFaculty of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, ChinaFaculty of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, ChinaFaculty of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, ChinaFaculty of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, ChinaThis study aims to achieve efficient and accurate detection of lotus seedpod maturity in complex environments. To address the challenges associated with existing object detection algorithms, which often involve numerous model parameters and high computational loads that hinder deployment on resource-limited mobile terminals, we propose an efficient lotus seedpod maturity detection method based on a compressed model. First, data augmentation techniques were employed to enhance the diversity of lotus seedpod image samples. Next, a model was established under the CSPDarknet53 framework, incorporating a fast spatial pyramid pooling module to detect the maturity of lotus seedpods. To simplify the model and improve detection speed, a channel pruning algorithm was utilized for model compression. Finally, the compressed model was fine-tuned to restore accuracy. Experimental results demonstrate that the compressed model reduced the number of parameters, model size, and inference time by 72.96%, 70.96%, and 26.92%, respectively, achieving a mean Average Precision (mAP) of 99.2%, representing only a 0.20% decrease compared to the original model. Compared to Faster R-CNN, SSD, YOLOv5, YOLOv7-tiny, YOLOv10 and YOLOv11 models, the proposed model significantly reduces parameter count, computational load, and model size while maintaining a high mAP, thus demonstrating feasibility for rapid and accurate detection of lotus seedpod maturity. Additionally, a prototype testing platform for lotus seedpod maturity detection was established, and the compressed model was deployed on an NVIDIA® Jetson Xavier NX mobile terminal. The testing results indicated that the compressed model size was 3.95 MB, with a detection speed of 416.67 frames per second, meeting real-time detection requirements and confirming its applicability for low-computational-capacity mobile terminals. This research provides valuable technical support for the subsequent development of lotus seedpod harvesting robots.https://ieeexplore.ieee.org/document/10925342/Lotus seedpod maturity detectionmodel compressiondeep learningmobile deploymentreal-time detection
spellingShingle Tao Tang
Min Jin
Gaohong Yu
Rui Feng
Bingliang Ye
A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
IEEE Access
Lotus seedpod maturity detection
model compression
deep learning
mobile deployment
real-time detection
title A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
title_full A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
title_fullStr A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
title_full_unstemmed A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
title_short A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models
title_sort novel approach for efficient detection of lotus seedpod maturity using compressed models
topic Lotus seedpod maturity detection
model compression
deep learning
mobile deployment
real-time detection
url https://ieeexplore.ieee.org/document/10925342/
work_keys_str_mv AT taotang anovelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT minjin anovelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT gaohongyu anovelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT ruifeng anovelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT bingliangye anovelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT taotang novelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT minjin novelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT gaohongyu novelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT ruifeng novelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels
AT bingliangye novelapproachforefficientdetectionoflotusseedpodmaturityusingcompressedmodels