Article
Agronomy
Bosoon Park, Taesung Shin, Jeong-Seok Cho, Jeong-Ho Lim, Kie-Jae Park
Summary: This study investigates postharvest blueberry softening using hyperspectral microscope imaging and deep learning technology. By analyzing textural features, a method for measuring blueberry firmness based on parenchyma cell textures is proposed.
POSTHARVEST BIOLOGY AND TECHNOLOGY
(2023)
Article
Agriculture, Multidisciplinary
Gangshan Wu, Yinlong Fang, Qiyou Jiang, Ming Cui, Na Li, Yunmeng Ou, Zhihua Diao, Baohua Zhang
Summary: This study used hyperspectral imaging combined with spectral features, vegetation indices, and textural features to detect gray mold on strawberry leaves. The results showed that the models based on optimum wavelengths and significant vegetation indices performed well, with a maximum classification accuracy of 93.33%. The models with combined features outperformed the models based on single features, with an accuracy range of 93.33-96.67%. Overall, the combined feature-based method significantly improved the recognition accuracy of strawberry gray mold and accurately identified infected leaves in the early stages.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Environmental Sciences
Mohammad S. Saif, Robert Chancia, Sarah Pethybridge, Sean P. Murphy, Amirhossein Hassanzadeh, Jan van Aardt
Summary: New York state, a major producer of table beets in the United States, is focusing on precision crop management, particularly using aerial imagery to predict the weight of table beet roots. By analyzing spectral and textural features obtained from hyperspectral images collected via an unmanned aerial system, specific wavelengths with predictive ability were identified. Multivariate linear regression models at different growth stages demonstrated high accuracy and precision, with the 760-920 nm-wavelength region showing the strongest correlation with table beet root yield. Further studies are recommended to validate these findings in different geographic locations and seasons.
Article
Environmental Sciences
Mary B. Stuart, Matthew Davies, Matthew J. Hobbs, Andrew J. S. McGonigle, Jon R. Willmott
Summary: This article introduces a low-cost hyperspectral imaging technique as an alternative method for peatland health monitoring. It provides a non-invasive way to measure and record the spectral response of peatland plants. By capturing subtle spectral changes, mitigation and restoration measures can be taken before more damaging conditions occur.
Article
Instruments & Instrumentation
Qiyou Jiang, Gangshan Wu, Chongfeng Tian, Na Li, Huan Yang, Yuhao Bai, Baohua Zhang
Summary: Anthracnose and gray mold, two devastating diseases of strawberries, can cause large-scale yield losses globally. Early identification of these diseases is challenging but crucial for managing strawberry production. This study developed machine learning-aided methods based on spectral fingerprint features to achieve early detection of anthracnose and gray mold in strawberries.
INFRARED PHYSICS & TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Dong Zhao, Xuguang Zhu, Zhe Zhang, Pattathal Arun, Jialu Cao, Qing Wang, Huixin Zhou, Hao Jiang, Jianling Hu, Kun Qian
Summary: This paper proposes a novel hyperspectral video target tracking algorithm based on Pixel-wise Spectral Matching Reduction (PSMR) and Deep Spectral Cascading Texture (Deep-SCT) features. The algorithm overcomes the interference caused by illumination variation (IV) and achieves superior performance compared to state-of-the-art approaches. Experimental results demonstrate its effectiveness in handling IV.
Article
Environmental Sciences
Jianxin Jia, Changhui Jiang, Wei Li, Haohao Wu, Yuwei Chen, Peilun Hu, Hui Shao, Shaowei Wang, Fan Yang, Eetu Puttonen, Juha Hyyppa
Summary: A hyperspectral LiDAR with wide-range wavelength was developed for vegetation spectral data acquisition, parameter extraction, and classification, showing great potential in precision agriculture application.
Review
Plant Sciences
Rijad Saric, Viet D. Nguyen, Timothy Burge, Oliver Berkowitz, Martin Trtilek, James Whelan, Mathew G. Lewsey, Edhem Custovic
Summary: Our ability to manipulate the genome exceeds our capacity to measure genetic changes on plant traits. Plant scientists have been using imaging approaches, specifically hyperspectral imaging, to define plant responses to environmental conditions and optimize crop management.
TRENDS IN PLANT SCIENCE
(2022)
Article
Environmental Sciences
Zeyu Xu, Cheng Su, Shirou Wang, Xiaocan Zhang
Summary: In this study, a local-global spectral feature (LGSF) extraction and optimization method is proposed for hyperspectral image (HSI) classification. The method transforms the 1D spectral vector into a 2D spectral image and automatically extracts the LGSF by using the local spectral feature extraction module (LSFEM) and the global spectral feature extraction module (GSFEM). The LGSF is further optimized using a loss function inspired by contrastive learning. The proposed method demonstrates its effectiveness in utilizing spectral information and achieving accurate HSI classification.
Article
Agriculture, Multidisciplinary
Jeanette Hariharan, Yiannis Ampatzidis, Jaafar Abdulridha, Ozgur Batuman
Summary: This study introduces a novel method using reduced datasets for extracting plant reflectance signatures. The method utilizes spectral decomposition and frequency reconstruction via Karhunen-Loeve Expansion (KLE) to generate unique biomarker signatures for plant identification and disease detection. These signatures can serve as average reflectance patterns for plant classification and biomarker identification.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Optics
Ting Yang, Zhilong Xu, Wenyi Ren, Yang Feng, Dan Wu, Rui Zhang, Yingge Xie
Summary: This paper presents a hyperspectral microscopic imaging system based on compressive sensing theory using spectral-coded illumination. A spectral modulator, consisting of a liquid crystal variable retarder and two polarizers, is used to encode the spectral transmittance of the incident light by adjusting the voltage of the liquid crystal variable retarder. The feasibility of the system is confirmed through computer simulations and laboratory experiments, offering an alternative approach for designing a low-cost and compact hyperspectral microscope.
OPTICS AND LASER TECHNOLOGY
(2023)
Article
Construction & Building Technology
Eberechi Ichi, Sattar Dorafshan
Summary: The presence of fouling contamination in railroad ballast is a growing concern that leads to deterioration, poor drainage functionality, and premature failure of railroad components. This study presents the results of characterizing laboratory ballast samples using hyperspectral imaging (HSI) sensor, showing the potential of HSI in detecting, monitoring, and quantifying moisture content (MC) and fouling content (FC) in fouled ballast. The reflectance of ballast samples with different levels of MC and FC was determined, and the presence of water was found to be prominent in the 1350 nm to 1550 nm wavelength range.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Computer Science, Artificial Intelligence
Alice Porebski, Mohamed Alimoussa, Nicolas Vandenbroucke
Summary: This study explores texture analysis methods based on color and hyperspectral imaging and compares the applications of multi spectral band (MSB) and multi color channel (MCC) representations in texture classification. Experimental results show that considering interactions between components significantly improves the classification accuracy and the proposed approaches outperform state-of-the-art hand-designed and deep learning-based texture descriptors.
PATTERN RECOGNITION LETTERS
(2022)
Article
Geochemistry & Geophysics
Weiwei Sun, Gang Yang, Jiangtao Peng, Xiangchao Meng, Ke He, Wei Li, Heng-Chao Li, Qian Du
Summary: This article introduces a method, MSFGF, for selecting proper hyperspectral bands by fusing multiscale spectral features and clusters. It aims to reflect diagnostic spectral information of ground objects at different scales and explore band selection from multiple spatial scales. Experimental results show the superiority of MSFGF in band selection over other state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Wenning Wang, Xuebin Liu, Xuanqin Mou
Summary: The article discusses how using unsupervised data augmentation and an effective spectral structure extraction method can significantly improve classification accuracy in cases of limited samples.