Machine learning-based detection of freezing events using infrared thermography

Shammi, Sayma; Sohel, Ferdous; Diepeveen, Dean; Zander, Sebastian; Jones, M. G. K.; Bekuma, Amanuel; Biddulph, Ben

doi:10.1016/j.compag.2022.107013

Cited by 10 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Freezing of wood tissues can lead to frost cracking and freezing damage, and even threaten the survival of trees ( Pearce, 2001 ; Guy, 2003 ). The damage to wood cell membranes is attributed to ice formation and cellular dehydration resulting from chilling and freezing ( Shammi et al., 2022 ; Tian et al., 2022 ). Deep supercooling or extracellular freezing is the mechanism whereby wood tissues and organs adapt to subfreezing temperatures to resist freezing damage ( Gusta and Wisniewski, 2013 ; Wisniewski et al., 2014a ).…”

Section: Introductionmentioning

confidence: 99%

Experimental investigation of freeze injury temperatures in trees and their contributing factors based on electrical impedance spectroscopy

Song,

Gao,

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

In trees, injuries resulting from subfreezing temperatures can cause damage to the cellular biofilm system, metabolic functions, and fibrous reticulum, and even cell death. Investigating the occurrence of freezing damage and its contributing factors could help understand the mechanisms underlying freezing injury and prevent the subsequent damage in trees. To achieve this, a laboratory experiment was conducted using cut wood samples from Korean pine (Pinus koraiensis Siebold & Zucc) and Simon poplar (Populus simonii Carr.), and the effects of environmental freezing factors, including freezing temperatures, freezing duration, and cooling rate, on the temperature at which freezing injuries occur were examined using the electrical impedance spectroscopy (EIS) method. The semi-lethal temperature (LT50), as an indicator of freezing injury in wood tissue, was theoretically deduced based on the measured extracellular resistance (re) using EIS. The contributory factors to changes in LT50 were determined and their relationship was established. The results revealed that all freezing factors exhibited significant effects on electrical impedance characteristics (re, ri, and τ), significantly influencing the LT50 of the wood. Random forest (RF) and support vector machine (SVM) models were used to assess the contribution of the freezing factors and moisture content (MC). Among the factors examined, freezing duration had the greatest impact on LT50, followed by the MC, whereas the contribution of the cooling rate was minimal. The model accuracies were 0.89 and 0.86 for Korean pine and Simon poplar, respectively. The findings of our study illustrate that the occurrence of freezing injury in trees is primarily influenced by the duration of freezing at specific subzero temperatures. Slow cooling combined with prolonged freezing at low subzero temperatures leads to earlier and more severe freezing damage.

show abstract

Section: Introductionmentioning

confidence: 99%

Experimental investigation of freeze injury temperatures in trees and their contributing factors based on electrical impedance spectroscopy

Song,

Gao,

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Deep learning-based high performing object detection and classification models include R-CNN [6], fast R-CNN [7], YOLO family [8], faster R-CNN [9], SSD (single-shot multi-box detector) [10], and R-FCN (region-based fully convolutional network) [11]. Due to its significant impact and outstanding classification performance, the use of deep learning in the agricultural field, especially in agricultural image processing areas increased tremendously over the years, e.g., weed detection [12], frost detection [13], pest detection [14], agriculture robot [15], and crop disease [16][17][18][19]. However, there is a problem concerning the availability of large datasets with reliable ground truth, which is needed to build a good predictive model with high predictive performance [20,21].…”

Section: Introductionmentioning

confidence: 99%

Deep Network with Score Level Fusion and Inference-Based Transfer Learning to Recognize Leaf Blight and Fruit Rot Diseases of Eggplant

Haque

Sohel

2022

Agriculture

Self Cite

View full text Add to dashboard Cite

Eggplant is a popular vegetable crop. Eggplant yields can be affected by various diseases. Automatic detection and recognition of diseases is an important step toward improving crop yields. In this paper, we used a two-stream deep fusion architecture, employing CNN-SVM and CNN-Softmax pipelines, along with an inference model to infer the disease classes. A dataset of 2284 images was sourced from primary (using a consumer RGB camera) and secondary sources (the internet). The dataset contained images of nine eggplant diseases. Experimental results show that the proposed method achieved better accuracy and lower false-positive results compared to other deep learning methods (such as VGG16, Inception V3, VGG 19, MobileNet, NasNetMobile, and ResNet50).

show abstract

Detecting emerging frost crystals on leaf surfaces using microscopic imaging

Song

2023

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Machine learning-based detection of freezing events using infrared thermography

Cited by 10 publications

References 39 publications

Experimental investigation of freeze injury temperatures in trees and their contributing factors based on electrical impedance spectroscopy

Experimental investigation of freeze injury temperatures in trees and their contributing factors based on electrical impedance spectroscopy

Deep Network with Score Level Fusion and Inference-Based Transfer Learning to Recognize Leaf Blight and Fruit Rot Diseases of Eggplant

Detecting emerging frost crystals on leaf surfaces using microscopic imaging

Contact Info

Product

Resources

About