多光谱图像数据压缩技术的发展与现状

介绍了多光谱图像数据压缩技术的由来及目前的发展现状,重点介绍了两种目前较为成熟的编码方案,即变换编码(TC)和矢量量化编码(VQ),并就目前的各种压缩方案进行了性能比较。     

The development of a spectral-spatial classifier for earth observational data

Over the last several years a classifier for earth observational image data has been under development which is intended to achieve improved performance by utilizing spatial characteristics of the data as an adjunct to multispectral ones. This paper provides an overview of the conception, development, evaluation and documentation of this spectral-spatial classifier. The research program leading to this classifier is described, the algorithms of the current implementation called ECHO are outlined, and results on its performance are summarized. These results show it to have improved accuracy, with greater computation efficiency, and only slightly increased operator complexity.     

Determining optimal wavebands using genetic algorithm for detection of internal insect infestation in tart cherry

This paper reports the results of waveband selection for detecting internal insect infestation in tart cherries as a precursor to development of a dedicated multispectral vision system. A genetic algorithm (GA) approach was applied on hyperspectral transmittance images (580–980 nm) and reflectance spectral data (590–1,550 nm) acquired from both intact and infested tart cherries. The GA analysis indicates that the ability of using transmittance imaging approach for detecting internal insect infestation in tart cherries would be limited. According to the GA analysis on the reflectance spectra, visible wavelengths were of less importance than NIR wavelengths for the purpose of distinguishing intact cherries from infested ones. The PLSDA results indicate that models built with three or four GA selected wavelength regions gave similar classification accuracy to the model built with full wavelength region, which demonstrates the efficiency of the GA variable selection procedure. However, due to the stochastic nature of the GA, the efficiency of using these wavebands in a multispectral vision system needs to be verified in future work.     

Multispectral photodetection using low-cost sputtered NiO/Ag/ITO heterostructure: From design concept to elaboration

High-performance multispectral photodetectors (PDs) are highly attractive for the emerging optoelectronic applications. In this work, a new broadband PD based on p-NiO/Ag/n-ITO heterostructure was fabricated by RF magnetron sputtering technique at room temperature. The tri-layered structure offering multispectral detection property was first identified using theoretical calculations based on combined FDTD and Particle Swarm Optimization (PSO) techniques. The crystal structure of the elaborated sensor was analyzed using X-ray diffraction (XRD) method. The device optical properties were investigated by UV–Vis–NIR spectroscopy. The NiO/Ag/ITO heterostructured PD shows a high average absorbance of 63% over a wide spectrum range of [200 nm–1100nm]. Compared with NiO and ITO thin-films, the performances of the heterostructured device are considerably enhanced. It was found that the prepared PD with NiO/Ag/ITO heterostructure merges the benefits of multispectral photodetection with reduced optical losses and efficient transfer of photo-induced carrier. The device demonstrated a high I_ON/I_OFF ratio of 78 dB and an enhanced responsivity under UV, visible and NIR lights (171 mA/W at 365 nm, 67 mA/W at 550 nm and 93 mA/W at 850 nm). The broadband photodetection property enabled by the optimized NiO/Ag/ITO heterostructure opens a new route for the elaboration of low-cost devices that can offer multiple sensing purposes, which are highly suitable for optoelectronic applications.     

甘肃北山白峡尼山地区多源遥感岩性制图研究

甘肃北山地区地质构造复杂,岩浆活动强烈,该区工作程度较低,已有1：20万、1：5万地质图对区内岩性（如中酸性侵入岩）圈定较为笼统,且界线不够准确。以甘肃北山白峡尼山地区为研究区,利用彩色空间变换（IHS）、Brovey等方法对ETM多光谱图像与资源三号（ZY3）全色波段高分辨率图像进行空间分辨率融合,获得兼具ETM光谱分辨率与资源三号空间分辨率之长的高分辨率图像。再对原始影像进行比值、主成分分析及假彩色合成等增强处理,突出其岩性差异,将各种方法处理的影像与数字高程模型（DEM）数据结合构建三维影像,进行综合解译。对解译结果进行野外验证、样品薄片鉴定及反射光谱特征分析,据此对结果进行修正,获得了研究区遥感解译地质图。结果表明：对于西部基岩露头较好地区,利用多源遥感数据融合可更新现有地质图,为后续填图、找矿工作提供参考。     

Augmenting a deep-learning algorithm with canal inspection knowledge for reliable water leak detection from multispectral satellite images

Maintenance planning of groundwater delivery infrastructure, such as canals, requires labor-intensive field inspection for properly allocating maintenance resources to sections of water infrastructure based on their deterioration conditions. Defective canal sections have cracks where the water delivery performance degrades. In practice, canals can be tens or even hundreds of miles long. Manual canal inspections could take weeks, while could hardly achieve comprehensive water leakage assessment. Another difficulty is that most cracks are developing under the water. Without drying up the canals, inspectors could not observe underwater conditions. They would have to assess visible parts of water facilities and environments (e.g., humidity changes and vegetation growths nearby) for prioritizing canal sections in terms of leaking risks. Even experienced inspectors need much time to complete a reliable canal condition assessment.This paper presents a deep-learning approach augmented by canal inspection knowledge to achieve automated and reliable water leak detection of canal sections from Landsat 8 satellite images. Such integration utilizes the domain knowledge of experienced inspectors in augmenting the deep-learning methods for more reliable image pattern classification that supports rapid canal condition assessment. Compared with machine learning algorithms trained by raw satellite images manually labeled as leaking, domain-knowledge-augmented deep learning algorithms use satellite image augmented by pixel-level land surface temperature (LST), fractional vegetation coverage (FVC) and Temperature Vegetation Dryness Index (TVDI) as training samples. Specifically, LST, FVC, and TVDI for each pixel are physical parameters derived from Landsat 8 satellite images by remote sensing methods. The “leaking” or “no-leaking” labels of the training samples are from the concrete surface inspection records collected during annual dry-ups of the canal from 2016 to 2019. Testing results on data sets collected for canals flowing through both urban and rural areas show that the proposed approach can achieve recall at 86%, precision at 86%, and accuracy at 85%. The precision, recall, and accuracy of the proposed approach are similar to a conventional deep learning algorithm that uses raw images for training while being more computationally efficient. The reason is that the new approach only processes three channels rather than the 11 channels in raw images. The authors also tested how different combinations of environmental features influence the performance of the algorithm. The results showed that two feature combinations: (LST, FVC) and (LST, FVC, TVDI) achieve the most robust performance in diverse geospatial environments.     

PoNet: A universal physical optimization-based spectral super-resolution network for arbitrary multispectral images

Spectral super-resolution is a very important technique to obtain hyperspectral images from only multispectral images, which can effectively solve the high acquisition cost and low spatial resolution of hyperspectral images. However, in practice, multispectral channels or images captured by the same sensor are often with different spatial resolutions, which brings a severe challenge to spectral super-resolution. This paper proposed a universal spectral super-resolution network based on physical optimization unfolding for arbitrary multispectral images, including single-resolution and cross-scale multispectral images. Furthermore, two new strategies are proposed to make full use of the spectral information, namely, cross-dimensional channel attention and cross-depth feature fusion. Experimental results on five data sets show superiority and stability of PoNet addressing any spectral super-resolution situations.     

Challenges and solutions of optical-based nondestructive quality inspection for robotic fruit and vegetable grading systems: A technical review

BackgroundOptical techniques, including computer vision, spectral imaging, near-infrared technology and other emerging imaging and spectroscopy techniques, have been rapidly developing and widely applied in fruit and vegetable grading systems for nondestructive quality inspecting and grading over the past decades. However, automatic detection of quality and grading is still difficult due to some still existing challenges, which are the key of blocking their commercialization in robotic fruit and vegetable grading systems. The challenges include the following aspects: the influence of physical and biological variability, whole surface detection, discrimination between defects and stems/calyxes, unobvious defect detection, robustness of the features and algorithms, as well as rapid optical detection system development. These challenges can reduce the fruit or vegetable quality inspection accuracy, thus greatly reducing automatic level of the quality inspecting and grading machines.Scope and approachAs agricultural engineers with about eight years of technical experience in fruit grading systems, we believe the ultimate goal of each scientific research should seek its task in serving the engineering. So, we have made many attempts to solve the challenges and increase the automation of the grading machines.Key findings and conclusionsThe review gives a detailed summary about the challenges and solutions of optical-based nondestructive quality inspection for fruit or vegetable grading systems from the perspective of engineering. Particular attention has been paid to the techniques that can improve the automation degree of the grading robot in this review. The advantages and disadvantages of the solutions are compared and discussed. Additionally, the remaining engineering challenges and future trends are also discussed.     

Predicting beef tenderness using color and multispectral image texture features

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner-Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender.     

基于主分量和独立成分分析的多光谱目标检测

不同材料的物体具有不同的光谱特性, 基于这一原理, 可以利用多光谱图像数据对不同的目标进行检测。对于具有相似或相同外形特征( 颜色和形状) 的物体, 利用全色图像一般达不到检测与识别的目的; 利用传统的多光谱目标检测方法, 则因计算量较大, 识别精度低等, 达不到满意的效果。提出了一种基于主分量与独立成分分析相结合的多光谱目标检测的新方法。通过对多光谱图像数据进行主分量分析, 可以降低多光谱的维数, 去掉冗余成份, 保留其主要信息; 对降维后的数据再进行独立成分分析, 提取各种目标的光谱特性, 实现目标的检测与识别。将这两种方法有机的结合起来, 发挥各自的优点, 实现对多光谱图像目标快速的检测与识别。以真假树叶( 真树叶和塑料树叶) 为例, 验证了该方法的有效性和正确性。