☆ 4.7 Article

An improved U-Net-based in situ root system phenotype segmentation method for plants

FRONTIERS IN PLANT SCIENCE (2023)

Related references

Note: Only part of the references are listed.

Article Chemistry, Analytical

Plant Root Phenotyping Using Deep Conditional GANs and Binary Semantic Segmentation

Vaishnavi Thesma et al.

Summary: This paper proposes an approach for binary semantic segmentation of Arabidopsis thaliana root images using a conditional generative adversarial network (cGAN) to address pixel-wise class imbalance. By utilizing Pix2PixHD, a cGAN for image translation, realistic and high resolution root images and annotations are generated to expand the original dataset. The original and generated datasets are then fed into SegNet for semantic segmentation, with additional post-processing to close small gaps along the root structure. Comparative analysis demonstrates that the cGAN approach produces realistic root images, reduces class imbalance, and achieves high accuracy, low error, high Dice Score, and low inference time for real-time processing.

SENSORS (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Histogram of Oriented Gradients meet deep learning: A novel multi-task deep network for 2D surgical image semantic segmentation

Binod Bhattarai et al.

Summary: We propose a novel deep multi-task learning method for medical image segmentation. Instead of relying on ground truth annotations, we generate pseudo-labels for an auxiliary task using Histogram of Oriented Gradients (HOGs). By combining the ground truth semantic segmentation masks for the primary task and the pseudo-labels for the auxiliary task, we train deep networks to optimize the loss of both tasks jointly.

MEDICAL IMAGE ANALYSIS (2023)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network

Hu Zhang et al.

Summary: Recently, it has been shown that adding an attention module to a deep convolutional neural network can effectively improve its performance. This study proposes a lightweight and effective attention method called Pyramid Squeeze Attention (PSA) module. By replacing the 3x3 convolution with the PSA module in ResNet bottleneck blocks, a new representational block named Efficient Pyramid Squeeze Attention (EPSA) is obtained. The EPSA block can be easily integrated into a backbone network, resulting in significant improvements in model performance. This work introduces an efficient backbone architecture called EPSANet, which incorporates the ResNet-style EPSA blocks, offering stronger multi-scale representation for various computer vision tasks.

COMPUTER VISION - ACCV 2022, PT III (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Medical image segmentation using deep learning: A survey

Risheng Wang et al.

Summary: This paper is a comprehensive thematic survey on medical image segmentation using deep learning techniques. It classifies and analyzes the literature in a different way, making it more convenient for readers to understand the relevant rationale and guiding them towards improvements in medical image segmentation based on deep learning approaches.

IET IMAGE PROCESSING (2022)

Add to Collection

Article Environmental Sciences

CCTNet: Coupled CNN and Transformer Network for Crop Segmentation of Remote Sensing Images

Hong Wang et al.

Summary: This study discusses the efficient method of semantic segmentation using remote sensing images for agricultural crop classification and the challenges it faces. A novel architecture named CCTNet is proposed to address these challenges, along with two fusion modules and three effective methods aimed at improving classification accuracy and image completeness. Experimental results demonstrate that CCTNet outperforms single CNN or Transformer methods in terms of mean Intersection over Union (mIoU) scores, making it a competitive option for crop segmentation through remote sensing images.

REMOTE SENSING (2022)

Add to Collection

Article Chemistry, Analytical

Soybean Seedling Root Segmentation Using Improved U-Net Network

Xiuying Xu et al.

Summary: This paper proposes a semantic segmentation model of soybean seedling root images based on an improved U-Net network to address the problems of over-segmentation, unsmooth root edges, and root disconnection caused by background interference. The model achieves accurate root segmentation in soybean seedlings and provides a theoretical basis and technical support for the quantitative evaluation of root morphological characteristics.

SENSORS (2022)

Add to Collection

Article Agriculture, Multidisciplinary

Root hair image processing based on deep learning and prior knowledge

Wei Lu et al.

Summary: In this study, an efficient and accurate model was proposed for segmenting local detailed root (fine roots and root hairs) image using an in-ground device called microrhizotron. The model utilized a region of interest and prior knowledge in convolutional neural network, and applied transfer learning and pruning method to improve performance. The result showed successful root traits segmentation with an average F1 score over 0.9.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Agriculture, Multidisciplinary

Semantic segmentation model of cotton roots in-situ image based on attention mechanism

Jia Kang et al.

Summary: The growth and distribution of root system in soil plays a crucial role in plant growth and crop production. This study focused on the segmentation of cotton mature root system using a semantic segmentation model with attention mechanism, which showed higher accuracy and efficiency compared to other models. The proposed model accurately distinguishes cotton roots from complex soil background, providing important theoretical value and practical application reference for deep learning in plant root segmentation.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

Add to Collection

Review Geochemistry & Geophysics

Recent Advances in Tree Root Mapping and Assessment Using Non-destructive Testing Methods: A Focus on Ground Penetrating Radar

Amir M. Alani et al.

SURVEYS IN GEOPHYSICS (2020)

Add to Collection

Article Plant Sciences

Shared Genetic Control of Root System Architecture between Zea mays and Sorghum bicolor

Zihao Zheng et al.

PLANT PHYSIOLOGY (2020)

Add to Collection

Article Biochemical Research Methods

Segmentation of roots in soil with U-Net

Abraham George Smith et al.

PLANT METHODS (2020)

Add to Collection

Article Biochemical Research Methods

High-throughput three-dimensional visualization of root system architecture of rice using X-ray computed tomography

Shota Teramoto et al.

PLANT METHODS (2020)

Add to Collection

Article Agriculture, Multidisciplinary

Overcoming small minirhizotron datasets using transfer learning

Weihuang Xu et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2020)

Add to Collection

Article Multidisciplinary Sciences

Root angle modifications by the DRO1 homolog improve rice yields in saline paddy fields

Yuka Kitomi et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Add to Collection

Article Plant Sciences

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+Method

Chen Shen et al.

FRONTIERS IN PLANT SCIENCE (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Detection of Apple Lesions in Orchards Based on Deep Learning Methods of CycleGAN and YOLOV3-Dense

Yunong Tian et al.

JOURNAL OF SENSORS (2019)

Add to Collection

Article Agriculture, Multidisciplinary

SegRoot: A high throughput segmentation method for root image analysis

Tao Wang et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2019)

Add to Collection

Article Agronomy

A multispectral camera system for automated minirhizotron image analysis

Simon Fiil Svane et al.

PLANT AND SOIL (2019)

Add to Collection

Article Biochemistry & Molecular Biology

VERNALIZATION1 Modulates Root System Architecture in Wheat and Barley

Kai P. Voss-Fels et al.

MOLECULAR PLANT (2018)

Add to Collection

Article Plant Sciences

Quantitative 3D Analysis of Plant Roots Growing in Soil Using Magnetic Resonance Imaging

Dagmar van Dusschoten et al.

PLANT PHYSIOLOGY (2016)

Add to Collection

Article Plant Sciences

X-Ray Computed Tomography Reveals the Response of Root System Architecture to Soil Texture

Eric D. Rogers et al.

PLANT PHYSIOLOGY (2016)

Add to Collection

Article Plant Sciences

Quantitative trait locus mapping of deep rooting by linkage and association analysis in rice

Qiaojun Lou et al.

JOURNAL OF EXPERIMENTAL BOTANY (2015)

Add to Collection

Article Biochemical Research Methods

Direct comparison of MRI and X-ray CT technologies for 3D imaging of root systems in soil: potential and challenges for root trait quantification

Ralf Metzner et al.

PLANT METHODS (2015)

Add to Collection

Article Biochemical Research Methods

High-throughput phenotyping of seminal root traits in wheat

Cecile A. I. Richard et al.

PLANT METHODS (2015)

Add to Collection

Article Plant Sciences

Soil coring at multiple field environments can directly quantify variation in deep root traits to select wheat genotypes for breeding

A. P. Wasson et al.

JOURNAL OF EXPERIMENTAL BOTANY (2014)

Add to Collection

Article Agronomy

Mapping QTLs for seedling root traits in a doubled haploid wheat population under different water regimes

Xiulin Liu et al.

EUPHYTICA (2013)

Add to Collection

Article Agriculture, Multidisciplinary

Adventitious root mass distribution in progeny of four perennial ryegrass (Lolium perenne L.) groups selected for root shape

J. R. Crush et al.

NEW ZEALAND JOURNAL OF AGRICULTURAL RESEARCH (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.