Development of a compressed FCN architecture for semantic segmentation using Particle Swarm Optimization

Agarwal, Mohit; Gupta, Suneet Kumar; Biswas, K. K.

doi:10.1007/s00521-023-08324-3

Cited by 14 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this goal, the semantic pixel-wise segmentation methods are proposed in our study. As a typical semantic segmentation model, the fully convolutional network (FCN) has been widely used in recent studies [ 31 , 32 ]. However, to lighten the convolution layers and the FC layers, the LW-Segnet and LW-Unet architecture, which consist of 2-stage encoder–decoder networks, are proposed in our study.…”

Section: Proposed Methodsmentioning

confidence: 99%

Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images

Zhang,

Sun,

Zhang

et al. 2023

Plant Phenomics

View full text Add to dashboard Cite

Accurate segmentation and detection of rice seedlings is essential for precision agriculture and high-yield cultivation. However, current methods suffer from high computational complexity and poor robustness to different rice varieties and densities. This article proposes 2 lightweight neural network architectures, LW-Segnet and LW-Unet, for high-precision rice seedling segmentation. The networks adopt an encoder–decoder structure with hybrid lightweight convolutions and spatial pyramid dilated convolutions, achieving accurate segmentation while reducing model parameters. Multispectral imagery acquired by unmanned aerial vehicle (UAV) was used to train and test the models covering 3 rice varieties and different planting densities. Experimental results demonstrate that the proposed LW-Segnet and LW-Unet models achieve higher F1-scores and intersection over union values for seedling detection and row segmentation across varieties, indicating improved segmentation accuracy. Furthermore, the models exhibit stable performance when handling different varieties and densities, showing strong robustness. In terms of efficiency, the networks have lower graphics processing unit memory usage, complexity, and parameters but faster inference speeds, reflecting higher computational efficiency. In particular, the fast speed of LW-Unet indicates potential for real-time applications. The study presents lightweight yet effective neural network architectures for agricultural tasks. By handling multiple rice varieties and densities with high accuracy, efficiency, and robustness, the models show promise for use in edge devices and UAVs to assist precision farming and crop management. The findings provide valuable insights into designing lightweight deep learning models to tackle complex agricultural problems.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images

Zhang,

Sun,

Zhang

et al. 2023

Plant Phenomics

View full text Add to dashboard Cite

show abstract

“…Since then, several types of CNN architectures, such as ResNet [ 18 ], ResNext [ 19 ], VGG [ 20 ], and GoogleNet [ 21 ], have been used as encoders and decoders. U-net [ 22 ] is based on FCN [ 23 ] and exhibits the advantages of good performance, low data requirement, and high speed. Various segmentation methods based on deep convolutional neural networks (CNNs), including crowd counting [ 24 , 25 ], text recognition [ 26 , 27 ], and medical image analysis [ 3 , 28 , 29 , 30 , 31 ], have been proposed and are widely used to obtain statistics on target objects [ 32 , 33 , 34 ].…”

Section: Introductionmentioning

confidence: 99%

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

Wang,

Liang,

Chang

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Accurate tooth segmentation and numbering are the cornerstones of efficient automatic dental diagnosis and treatment. In this paper, a multitask learning architecture has been proposed for accurate tooth segmentation and numbering in panoramic X-ray images. A graph convolution network was applied for the automatic annotation of the target region, a modified convolutional neural network-based detection subnetwork (DSN) was used for tooth recognition and boundary regression, and an effective region segmentation subnetwork (RSSN) was used for region segmentation. The features extracted using RSSN and DSN were fused to optimize the quality of boundary regression, which provided impressive results for multiple evaluation metrics. Specifically, the proposed framework achieved a top F1 score of 0.9849, a top Dice metric score of 0.9629, and an mAP (IOU = 0.5) score of 0.9810. This framework holds great promise for enhancing the clinical efficiency of dentists in tooth segmentation and numbering tasks.

show abstract

OCAE and OUNET: Standard automatic optimization for medical image segmentation

KETFI,

BELAHCENE,

BOURENNANE

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Development of a compressed FCN architecture for semantic segmentation using Particle Swarm Optimization

Cited by 14 publications

References 41 publications

Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images

Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

OCAE and OUNET: Standard automatic optimization for medical image segmentation

Contact Info

Product

Resources

About