- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Fruit defects
- Jujube
- Principal component analysis
- Hyperspectral imaging
- hyperspectral images
- spectral and spatial features
- classification
- SVM
- mutual information
- GLCM
- Optoelectronic Information Science and Engineering
- Mohammed V University in Rabat
- Southern Taiwan University of Science and Technology
-
[IEEE 2018 3rd International Conference on Computer Science and Engineering (UBMK) - Sarajevo, Bosnia and Herzegovina (2018.9.20-2018.9.23)] 2018 3rd International Conference on Computer Science and Engineering (UBMK) - Hyperspectral Image Classification Using Reduced Extreme Learning Machine
摘要： In the classification of hyperspectral images, kernel based approaches have been shown to be successful results. Too much training or testing data in the images increases the computation time and memory requirements in the kernel computations. Extreme learning machines that can be used with the kernel approach also need the same requirements in kernel computations. In this study, improvements were made in terms of computation time and memory using reduced kernel extreme learning machines (RKELM). The obtained results are presented comparatively through the tables of performance and time information with kernel extreme learning machine (KELM).
关键词： classification,spectral information,Hyperspectral images,reduced kernel extreme learning machine
更新于2025-09-23 15:23:52
-
A Hyperspectral Imaging Instrumentation Architecture Based on Accessible Optical Disc Technology and Frequency-Domain Analyses
摘要： Hyperspectral imaging (HSI) is an emergent instrumentation technology with great potential in many applications, due to its ability to measure important spectral features. However, the widespread adoption of HSI requires the development of accessible (i.e., inexpensive and uncomplicated) HSI instrumentation architectures. In this paper, we present, design, develop, and evaluate an accessible HSI instrumentation architecture, with snapshot operation, based on the integration of readily available components and frequency multiplexing with Fourier analyses. In the experimental work, an incident image beam is divided into spatial image channels, each with an assigned dynamic binary code via a dynamic coded aperture. This dynamic coded aperture is constructed from repurposed diffractive optical disc technologies and is patterned with strategic opaque and transparent regions. When it is rotated by a motor, dynamic binary codes are used, along with Fourier analyses, to identify the diffraction of each spatial image channel. The spatially overlapped spectra from the diffraction are directed onto a charge-coupled device sensor, and each spatial image channel is distinguished through Fourier analyses. The resulting Fourier amplitude spectra are transformed into corresponding functions of wavelength, and this transformation is based on the experimental instrumentation geometry. The performance of the HSI instrumentation architecture is evaluated using a comparison with data from a commercial spectrometer. The presented HSI instrumentation architecture can be adapted for 2-D operation. Ultimately, the presented HSI instrumentation architecture can benefit regions of the world that have limited financial resources and a need for accessible HSI technologies.
关键词： Electromagnetic devices,optical diffraction,hyperspectral sensors,multispectral imaging
更新于2025-09-23 15:23:52
-
A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei)
摘要： Hyperspectral imaging (HSI) technique with spectral range of 900e1700 nm was implemented to predict total volatile basic nitrogen (TVB-N) content in Pacific white shrimp. Successive projections algorithm (SPA) and deep-learning-based stacked auto-encoders (SAEs) algorithm were comparatively used for spectral feature extraction. Least-squares support vector machine (LS-SVM), partial least squares regression (PLSR) and multiple linear regression (MLR) were used for prediction. The results demonstrated that the SAEs-based prediction models (SAEs-LS-SVM, SAEs-MLR and SAEs-PLSR) performed better than either full wavelengths-based or SPA-based prediction models. The SAEs-LS-SVM was considered to be the best model with RP2 value of 0.921, RMSEP value of 6.22 mg N [100 g]?1, RPD value of 3.58 and computational time of 3.9 ms for predicting TVB-N in prediction set. The results of this study indicated that SAEs has a high potential in the multivariate analysis of hyperspectral images for shrimp quality inspections.
关键词： Stacked auto-encoders,Pacific white shrimp,Total volatile basic nitrogen,Nondestructive prediction,Hyperspectral imaging
更新于2025-09-23 15:23:52
-
Detection of peanut leaf spots disease using canopy hyperspectral reflectance
摘要： Leaf spot is one of the most destructive diseases, which has a significant impact on the peanut production. Detecting leaf spot via spectral measurement and analysis is a possible alternative to traditional methods in detecting the spatial distribution of this disease. In this study, we identified sensitive bands and derived hyperspectral vegetation index specific to leaf spot detection. Hyperspectral canopy reflectance spectra of peanut cultivars susceptibilities to leaf spot were measured at two experimental sites in 2017. The normalized difference spectral index (NDSI) was derived based on their correlation with disease index (DI) in the leaf spectrum between 325 nm and 1075 nm. The results showed that canopy spectral reflectance decreased significantly in the near-infrared regions (NIR) as DI increased (r < -0.90). The spectral index for detecting leaf spot in peanut were LSI: (NDSI (R938, R761)) with R2 values of up to 0.68 for the regression model. The high fit between the observed and estimated values indicates that the DI detecting model based on the index could be used in peanut leaf spot detection in the absence of other stresses causing unhealthy symptoms. The results of this study show that it will provide a reliable, effective and accurate method for detecting leaf spot diseases in peanut through the analysis of hyperspectral data in the future.
关键词： Vegetation index,Disease index,Arachis hypogaea L.,Canopy hyperspectral reflectance
更新于2025-09-23 15:23:52
-
Ground based hyperspectral imaging for extensive mango yield estimation
摘要： Fruit yield estimation in orchard blocks is an important objective in the context of precision agriculture, as it makes it easier for the farmer to plan ahead and efficiently use resources. Nevertheless, its implementation is labour-intensive and involves the manual counting of the fruit present in the trees. While colour (RGB) has been widely shown to be successful and arguably sufficient for yield estimation in orchards, hyperspectral imaging (HSI) shows promise for more nuanced tasks such as disease detection, cultivar classification and fruit maturity estimation. Therefore, it is important to ask how appropriate is HSI for the task of yield estimation, with a view to performing all of these tasks with just one sensor. This paper presents a novel mango yield estimation pipeline using ground based line-scan HSI acquired from an unmanned ground vehicle. Hyperspectral images were collected on a commercial mango orchard block in December 2017 and pre-processed for illumination compensation. After tree delimitation and mango pixel identification, an optimisation process was carried out to obtain the best models for fruit counting, using mango counts obtained by manually counting the fruit on-tree, and using state-of-the-art RGB techniques for yield estimation. Models were validated and tested on hundreds of trees, and subsequently mapped. In testing, determination coefficients reached values of up to 0.75 against field counts (predicting 18 trees) and 0.83 against RGB mango counts (predicting 216 trees). These results suggest that line-scan HSI can be used to accurately estimate yield in orchards, especially in scenarios in which this technology is already chosen for the determination of other traits.
关键词： Field robotics,Computer vision,Lidar,Hyperspectral,Fruit counting
更新于2025-09-23 15:23:52
-
[ACM Press the 2017 International Conference - Singapore, Singapore (2017.12.27-2017.12.29)] Proceedings of the 2017 International Conference on Information Technology - ICIT 2017 - The Detection of Nitrite Content in Bacon based on Hyperspectral Technique
摘要： As a common food additive, nitrite has been widely used in meet products such as bacon. However, when the content of nitrite in food is overproof, consumer’s health will be seriously endangered. To solve this problem, this paper takes bacon as the sample to research the feasibility of hyperspectral technique in nitrite fast detecting. The partial least- squares (PLS) is utilized to associate the nitrite content data obtained via hyperspectral technique with the data obtained via GB method, and then the nitrite content calculating model is built. After comparing several models that adopt different spectrum pre-processing methods, the research team find that the first-order derivative plus vector normalization model is the best, whose RMSECV is 0.251 and r2 is 0.972. The result proves that hyperspectral can be effectively used in nitrite content prediction.
关键词： Chinese bacon,PLS,Hyperspectral,Nitrite
更新于2025-09-23 15:23:52
-
Low-rank and sparse matrix decomposition with background position estimation for hyperspectral anomaly detection
摘要： Hyperspectral anomaly detection (AD) has attracted much attention over the last 20 years. It distinguishes pixels with significant spectral differences from the background without any prior knowledge. The low-rank and sparse matrix decomposition (LRaSMD)-based detector has been applied to AD, where the anomaly value is measured by Euclidean distance based on the sparse component. However, the background interference in sparse component seriously increases the false alarm rate and influences the detection of real anomalies. In this paper, a novel AD method based on LRaSMD and background position estimation is proposed, which aims to suppress background interference in the sparse component for a better separation between background and anomalies. Firstly, the original sparse matrix is obtained using the traditional LRaSMD method. Secondly, the abundance maps are constructed by the sequential maximum angel convex cone (SMACC) endmember extraction model. Thirdly, considering that the anomalies occupy only a few pixels with a low probability, the coordinate positions of background pixels are estimated through these abundance maps. Finally, the spectra corresponding to these positions in the original sparse matrix are replaced with zero vectors, and the final anomaly value is calculated based on the improved sparse matrix. The proposed method achieves an outstanding performance by considering both the spectral and spatial characteristics of anomalies. Experimental results on synthetic and real-world hyperspectral datasets demonstrate the superiority of the proposed method compared with several state-of-the-art AD detectors.
关键词： Anomaly detection,Background estimation,Low-rank and sparse matrix decomposition,Hyperspectral imagery,Endmember extraction
更新于2025-09-23 15:23:52
-
A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection
摘要： In recent years, some adaptive subspace models perform well for hyperspectral anomaly detection (AD). In this paper, a stacked autoencoders-based adaptive subspace model (SAEASM) is proposed. First, three windows, namely, inner, outer and dictionary window, centered at the test point are used to obtain the local background pixel points and dictionary in the hyperspectral image (HSI). Second, the deep features of differences between the test point and the local dictionary pixels are first acquired by the use of SAE architectures. Then, the deep features of differences between the local background pixels and the local dictionary pixels are also acquired by the use of SAE architectures. Finally, the detection result is obtained by the stacked autoencoders-based adaptive subspace model that is based on the 2-norm of the above two deep features. The experimental results carried out on real and synthetic HSI demonstrate that the proposed SAEASM generally performs better than the comparison algorithms.
关键词： Hyperspectral image,Stacked autoencoders,Adaptive subspace,Anomaly detection
更新于2025-09-23 15:23:52
-
Reweighted Local Collaborative Sparse Regression for Hyperspectral Unmixing
摘要： Sparse unmixing is based on the assumption that each mixed pixel in the hyperspectral image can be expressed in the form of linear combinations of known pure signatures in the spectral library. Collaborative sparse regression improves the unmixing results by solving a joint sparse regression problem, where the sparsity is simultaneously imposed to all pixels in the data set. However, hyperspectral images exhibit rich spatial correlation that can be exploited to better estimate endmember abundances. The work, based on the iterative reweighted algorithm and local collaborative sparse unmixing, utilized a reweighted local collaborative sparse unmixing (RLCSU). The simultaneous utilization of iterative reweighted minimization and local collaborative sparse unmixing (including spectral information and spatial information in the formulation, respectively) significantly improved the sparse unmixing performance. The optimization problem was simply solved by the variable splitting and augmented Lagrangian algorithm. Our experimental results were obtained by using both simulated and real hyperspectral data sets. The proposed RLCSU algorithm obtain better signal-to-reconstruction error (SRE, measured in dB) results than LCSU and CLSUnSAL algorithms in all considered signal-to-noise ratio (SNR) levels, especially in the case of low noise values. The RLCSU algorithm obtains a better SRE(dB) result (30.01) than LCSU (20.08) and CLSUnSAL (17.28) algorithms for the simulated data 1 with SNR=50dB. It demonstrated that the proposed method is an effective and accurate spectral unmixing algorithm.
关键词： Hyperspectral unmixing,spectral unmixing,reweighted local collaborative,spatial information,sparse regression
更新于2025-09-23 15:23:52
-
Near-Infrared Hyperspectral Imaging Rapidly Detects the Decay of Postharvest Strawberry Based on Water-Soluble Sugar Analysis
摘要： This paper presents a novel strategy to detect the fungal decay in strawberry using reflectance near-infrared hyperspectral imaging (NIR-HSI, 1000–2500 nm). The variation of fructose, glucose, sucrose, and total water-soluble sugar (TWSS) content was analyzed using HPLC with a reference method during fungal infection in strawberry. The feasibility of quantifying sugar constituents relevant to the different stages of decay in strawberry was evaluated using NIR-HSI with key wavelengths selected via successive projection algorithm. The results showed that the predicted performance of TWSS content was acceptable within 2 and 2.603 for RPD, respectively. Five to seven key wavelengths were obtained based on sugar constituents, and excellent performance for classification accuracy among the three stages of decay was 89.4 to 95.4% for calibration and 87.0 to 94.4% for prediction, respectively. This rapid approach provides a new strategy for the selection of key wavelengths to detect the decay and sugar constituents in strawberries.
关键词： Strawberry,Key wavelength,Decay,Sugar content,Hyperspectral imaging
更新于2025-09-23 15:23:52