Adaptive Window Based 3-D Feature Selection for Multispectral Image Classification Using Firefly Algorithm

Feature extraction is the most critical step in classification of multispectral image.The classification accuracy is mainly influenced by the feature sets that are selected to classify the image.In the past,handcrafted feature sets are used which are not adaptive for different image domains.To overcome this,an evolu-tionary learning method is developed to automatically learn the spatial-spectral features for classification.A modified Firefly Algorithm(FA)which achieves maximum classification accuracy with reduced size of feature set is proposed to gain the interest of feature selection for this purpose.For extracting the most effi-cient features from the data set,we have used 3-D discrete wavelet transform which decompose the multispectral image in all three dimensions.For selecting spatial and spectral features we have studied three different approaches namely overlapping window(OW-3DFS),non-overlapping window(NW-3DFS)adaptive window cube(AW-3DFS)and Pixel based technique.Fivefold Multiclass Support Vector Machine(MSVM)is used for classification purpose.Experiments con-ducted on Madurai LISS IV multispectral image exploited that the adaptive win-dow approach is used to increase the classification accuracy.

Monitoring slope deformation using a 3-D laser image scanning system: a case study

An ILRIS-36D 3-D laser image scanning system was used to monitor the Anjialing strip mine slope on Pingshuo in Shanxi province. The basic working principles, performance indexes, features and data collection and processing methods are illus-trated. The point cloud results are analyzed in detail. The rescale range analysis method was used to analyze the deformation char-acteristics of the slope. The results show that the trend of slope displacement is stable and that the degree of landslide danger is low. This work indicates that 3-D laser image scanning can supply multi-parameter, high precision real time data over long distances. These data can be used to study the distortion of the slope quickly and accurately.

Importance of 3-D image reconstruction of spectraldomain OCT on outcome of grid laser photocoagulation for diffuse diabetic macular edema

AIM:To present the outcome of modified grid laser photocoagulation(GLP)in diffuse diabetic macular edema(DDME)in eyes without extrafoveal and/or vitreofoveal traction.METHODS:Inclusion criteria for the retrospective study were DDME eyes of patients with typeⅡdiabetes mellitus that had≥4 months of follow-up following GLP.Only one eye per patient was analyzed.Using 3-D spectral-domain optical coherence tomography(3-D SDOCT),eyes that had either extrafoveal or vitreofoveal traction,or had been previously treated by an intravitreal medication(s)were excluded.Treated DDME eyes were divided into 4 groups:A)"Classic"DDME that involved the central macula;B)edema did not involve the macular center;C)eyes associated with central epiretinal membrane(ERM);D)DDME that was associated with macular capillary dropout≥2 disc-diameter(DD).RESULTS:GLP outcome in 35 DDME eyes after 4-24(mean,13.1±6.9)months was as follows:Group A)18eyes with"classic"DDME.Following one or 2(mean,1.2)GLP treatments,best-corrected visual acuity(BCVA)improved by 1-2 Snellen lines in 44.4%(8/18)of eyes,and worsened by 1 line in 11.1%(2/18).Central macular thickness(CMT)improved by 7%-49%(mean,26.6%)in77.8%(14/18)of eyes.Causes of CMT worsening(n=4)were commonly explainable,predominantly(n=3)associated with emergence of extrafoveal traction,5-9months post-GLP.Group B)GLP(s)in DDME that did not involve the macular center(n=6)resulted in improved BCVA by 1-2 lines in 2 eyes.However,the central macula became involved in the edema process after the GLP in 3(50%)eyes,associated with an emergence of extrafoveal traction in one of these eyes 4months following the GLP.Group C)GLP failed in all 5eyes associated with central ERM.Group D)GLP was of partial benefit in 2 of 6 treated eyes with macular capillary dropout≥2DD.CONCLUSION:Eyes with DDME that involved the macular center were found to achieve favourable outcomes after GLP(s)during mid-term follow-up,unless complicated pre-GLP or post-GLP by vltreoretinal interface abnormalities,often extrafoveal traction or ERM,or by capillary dropout≥2DD.Prospective studies with larger cohorts are required.

Sparse flight spotlight mode 3-D imaging of spaceborne SAR based on sparse spectrum and principal component analysis

The spaceborne synthetic aperture radar(SAR)sparse flight 3-D imaging technology through multiple observations of the cross-track direction is designed to form the cross-track equivalent aperture,and achieve the third dimensionality recognition.In this paper,combined with the actual triple star orbits,a sparse flight spaceborne SAR 3-D imaging method based on the sparse spectrum of interferometry and the principal component analysis(PCA)is presented.Firstly,interferometric processing is utilized to reach an effective sparse representation of radar images in the frequency domain.Secondly,as a method with simple principle and fast calculation,the PCA is introduced to extract the main features of the image spectrum according to its principal characteristics.Finally,the 3-D image can be obtained by inverse transformation of the reconstructed spectrum by the PCA.The simulation results of 4.84 km equivalent cross-track aperture and corresponding 1.78 m cross-track resolution verify the effective suppression of this method on high-frequency sidelobe noise introduced by sparse flight with a sparsity of 49%and random noise introduced by the receiver.Meanwhile,due to the influence of orbit distribution of the actual triple star orbits,the simulation results of the sparse flight with the 7-bit Barker code orbits are given as a comparison and reference to illuminate the significance of orbit distribution for this reconstruction results.This method has prospects for sparse flight 3-D imaging in high latitude areas for its short revisit period.

A"messenger zone hypothesis"based on the visual three-dimensional spatial distribution of motoneurons innervating deep limb muscles

Coordinated contraction of skeletal muscles relies on selective connections between the muscles and multiple classes of the spinal motoneuro ns.Howeve r,current research on the spatial location of the spinal motoneurons innervating differe nt muscles is limited.In this study,we investigated the spatial distribution and relative position of different motoneurons that control the deep muscles of the mouse hindlimbs,which were innervated by the obturator nerve,femoral nerve,inferior gluteal nerve,deep pe roneal nerve,and tibial nerve.Locations were visualized by combining a multiplex retrograde tracking technique compatible with three-dimensional imaging of solvent-cleared o rgans(3DISCO)and 3-D imaging technology based on lightsheet fluorescence microscopy(LSFM).Additionally,we propose the hypothesis that"messenger zones"exist as interlaced areas between the motoneuron pools that dominate the synergistic or antagonist muscle groups.We hypothesize that these interlaced neurons may participate in muscle coordination as messenger neurons.Analysis revealed the precise mutual positional relationships among the many motoneurons that innervate different deep muscles of the mouse.Not only do these findings update and supplement our knowledge regarding the overall spatial layout of spinal motoneurons that control mouse limb muscles,but they also provide insights into the mechanisms through which muscle activity is coordinated and the architecture of motor circuits.

MODELING OF 3-D IMAGES AND SPACE MARKOV CUBIC MESH MODELS

Three-dimensional(3-D)Markov cubic random mesh models are presented andproved in the form of two theorems in details.Its applications to the modeling and description of3-D images are described.The model presented here is a appropriate mathematical tool for thesegmentation,modeling,classification and other processing.Finally,an example is given.

An Experimental System Development for Head Posture Estimation Based on 3-D Images Measurement

Although automobile is an indispensable vehicle to modern life, it also serves as a social problem with a big traffic accident. Among the reasons of traffic accidents, careless driving accounts for the largest part. So in order to avoid the careless driving, a system which can measure the posture of a driver and warns driver to drive carefully in the case of looking aside is necessary. Although the image measurement method is used broadly, there is a problem on which measurement accuracy is influenced by environment light, makeup of the driver, etc. in the general method based on the two-dimensional image. Therefore, in this study, we propose an image measurement method to obtain the head posture of driver. First we use three-dimensional measurement method which based on the infrared pattern projection to get 3-D information of head, and then we calculate the angle for faces. In this paper, we explain the composition method of an experiment system, and the results of head posture measurement experiment.

Laser speckle contrast imaging based on uniting spatiotemporal Fourier transform

We propose a laser speckle contrast imaging method based on uniting spatiotemporal Fourier transform.First,the raw speckle images are entirely transformed to the spatiotemporal frequency domain with a three-dimensional(3D)fast Fourier transform.Second,the dynamic and static speckle components are extracted by applying 3D low-pass and high-pass filtering in the spatiotemporal frequency domain and inverse 3D Fourier transform.Third,we calculate the time-averaged modulation depth with the average of both components to map the two-dimensional blood flow distribution.The experiments demonstrate that the proposed method could effectively improve computational efficiency and imaging quality.

Identify Plant Drought Stress by 3D-Based Image

Plants respond to drought stress with different physical manners, such as morphology and color of leaves. Thus, plants can be considered as a sort of living-sensors for monitoring dynamic of soil water content or the stored water in plant body. Because of difficulty to identify the early wilting symptom of plants from the results in 2D （two-dimension） space, this paper presented a preliminary study with 3D （three-dimension）-based image, in which a laser scanner was used for achieving the morphological information of zucchini （Cucurbita pepo） leaves. Moreover, a leaf wilting index （DLWIF） was defined by fractal dimension. The experiment consisted of phase-1 for observing the temporal variation of DLWIF and phase-2 for the validation of this index. During the experiment, air temperature, luminous intensity, and volumetric soil water contents （VSWC） were simultaneously recorded over time. The results of both phases fitted the bisector （line： 1：1） with R2=0.903 and REMS=0.155. More significantly, the influence of VSWC with three levels （0.22, 0.30, and 0.36 cm3 cm-3） on the response of plant samples to drought stress was observed from separated traces of DLWIF. In brief, two conclusions have been made： （i） the laser scanner is an effective tool for the non-contact detection of morphological wilting of plants, and （ii） defined DLWIF can be a promising indicator for a category of plants like zucchini.

SAR tomography imaging via higher-order spectrum analysis

To deal with the non-Caussian noise in standard 2-D SAR images, the deramped signal in imaging plane, and the possible symmetric distribution of complex noise, the fourth-order cumulant of complex process is introduced into SAR tomography. With the estimated AR parameters of ARMA model of noise through Yule-Walker equation, the signal series of height is pre-filtered. Then, through ESPRIT, the spectrum is obtained and the aperture in height direction is synthesized. Finally, the SAR tomography imaging of scene is achieved. The results of processing on signal with non-Gaussian noise demonstrate the robustness of the proposed method. The tomography imaging of the scenes shows that the higher-order spectrum analysis is feasible in the application.

Imaging plaque inflammation in asymptomatic cocaine addicted individuals with simultaneous positron emission tomography/magnetic resonance imaging

BACKGROUND Chronic cocaine use is associated with stroke, coronary artery disease and myocardial infarction, resulting in severe impairments or sudden mortality. In the absence of clear cardiovascular symptoms, individuals with cocaine use disorder (iCUD) seeking addiction treatment receive mostly psychotherapy and psychiatric pharmacotherapy, with no attention to vascular disease (i.e., atherosclerosis). Little is known about the pre-clinical signs of cardiovascular risk in iCUD and early signs of vascular disease are undetected in this underserved population. AIM To assess inflammation, plaque burden and plaque composition in iCUD aiming to detect markers of atherosclerosis and vascular disease. METHODS The bilateral carotid arteries were imaged with positron emission tomography/magnetic resonance imaging (PET/MRI) in iCUD asymptomatic for cardiovascular disease, healthy controls, and individuals with cardiovascular risk. PET with 18F-fluorodeoxyglucose (18F-FDG) evaluated vascular inflammation and 3-D dark-blood MRI assessed plaque burden including wall area and thickness. Drug use and severity of addiction were assessed with standardized instruments. RESULTS The majority of iCUD and controls had carotid FDG-PET signal greater than 1.6 but lower than 3, indicating the presence of mild to moderate inflammation. However, the MRI measure of wall structure was thicker in iCUD as compared to the controls and cardiovascular risk group, indicating greater carotid plaque burden. iCUD had larger wall area as compared to the healthy controls but not as compared to the cardiovascular risk group, indicating structural wall similarities between the non-control study groups. In iCUD, wall area correlated with greater cocaine withdrawal and craving. CONCLUSION These preliminary results show markers of carotid artery disease burden in cardiovascular disease-asymptomatic iCUD. Broader trials are warranted to develop protocols for early detection of cardiovascular risk and preventive intervention in iCUD.

Comparison of Laboratory Measurements for IR Imaging System Performance

Sensitivity and human performance are two important parameters for IR imaging system. Noise equivalent temperature difference (NETD) and minimum resolvable temperature difference (MRTD) can describe sensitivity and human performance of IR imaging system. So a lot of engineers apply themselves to studying the methods to measure NETD and MRTD for IR imaging system. The classical laboratory measurement methodologies for NETD and MRTD are introduced. And, two new approaches to three-dimensional (3-D) noise and MRTD/MRC are also portrayed, which can overcome some of the disadvantages existed in classical testing of NETD and MRTD. With the help of the new laboratory measurements, the disadvantages of the classical methods to measure NETD and MRTD can be solved.

A TENSOR ANALYSIS METHOD FOR ESTIMATING 3-D MOTION PARAMETERS

By using the center projection image sequence to estimate 3-D motion parameters,one needs to know the corresponding relationship between the feature of motion object in spaceand the projection coordinate on image plane.In order to avoid using the relationship of featurecorrespondence,the tensor analysis method in the affine transformation system is presented,andthe simulation data of experimental results are given.

3D particle tracking velocimetry for the determination of temporally resolved particle trajectories within laser powder bed fusion of metals

Within this work,we present a system for the measurement of the three-dimensional(3D)trajectories of spatters and entrained particles during laser powder bed fusion(L-PBF)of metals.It is comprised of two ultrahigh-speed cameras and a reconstruction task specific processing reconstruction algorithm.The system enables an automated determination of 3D measures from the trajectories of a large number of tracked particles.Ambiguity evolving from an underdetermined geometrical situation induced by a two-camera setup is resolved within the tracking using a priori knowledge of L-PBF of metals.All processing steps were optimized to run on a graphics processing unit to allow the processing of large amounts of data within an appropriate time frame.The overall approach was validated by a comparison of the measurement results to synthetic images with a known 3D ground truth.

Linear Phase FIR Filter on Measuring 3-D Surface

ＬｉｎｅａｒＰｈａｓｅＦＩＲＦｉｌｔｅｒｏｎＭｅａｓｕｒｉｎｇ３－ＤＳｕｒｆａｃｅ①ＷＡＮＧＹｕｎｓｈａｎ，ＹＡＮＧＦｕｊｕｎ，ＬＩＷｅｉ（ＳｈａｎｄｏｎｇＵｎｉｖｅｒｓｉｔｙｏｆＴｅｃｈｎｏｌｏｇｙ，Ｊｉｎａｎ２５００６１，ＣＨＮ）Ａｂｓｔｒａｃｔ...

ACQUIREMENT AND COMPUTER PROCESSING OF 3-D SURFACE SHAPE DATA

The laser scanning and CCD image-transmitting measurement method and principle on acquiring 3-D curved surface shape data are discussed. Computer processing technique of 3-D curved surface shape(be called“ 3 - D surface shape”for short) data is analysed. This technique in- cludes these concrete methods and principles such as data smoothing, fitting, reconstructing ,elimi- nating and so on. The example and result about computer processing of 3- D surface shape data are given .

三维激光3D打印技术在数字化重现中的应用

为了提高3D模型多媒体数字化重现的逼真性以及多媒体数字信息的三维表达能力,提出一种基于三维激光3D打印的多媒体数字化重现技术。首先采用三维激光3D打印技术进行多媒体数字信息的图像采样,进行多媒体数字模型的三维激光成像的边缘轮廓特征提取,利用激光3D打印的三维离散点数据重构出多媒体图像的视觉模型。然后采用Taubin平滑算子进行三维激光3D图像的平滑处理,在三维非线性空间中修正数字化3D激光打印图像的局部细节,使得输出的数字化三维激光图像更好地贴合真实的3D模型。最后进行实际3D数字化重现的仿真实验,结果表明,采用该方法进行3D打印数字化重现,输出三维激光图像的信噪比较高,归一化误差较低,数字化重现的视觉效果较好。

Laser Scanning的基本原理及其应用前景

首先介绍了激光测距仪的发展历程,针对应用领域的不同,分别对3维激光成像仪和机载/星载激光测高仪的测量原理进行了阐述,并分别介绍了两种激光测距仪的工作流程以及数据处理流程,最后对两种激光测距仪的应用范围进行了阐述,并把两种激光测距技术和普通摄影测量进行了比较,指出了激光测距技术相对于普通摄影测量的优点,即高精度性、穿透性、实时性。

一种高分辨率3维图像的自适应降噪算法

为了获得高保真3维图像,采用了一种针对高分辨率3维图像的自适应均值降噪算法。首先使用一种由激光器、高分辨率3维相机、直线电机和计算机等设备组成的线激光高精度3维测量实验系统对自然纹理皮革进行测量。然后针对系统测量所得的高分辨率3维自然纹理图像(每英寸点数大于1000),进行了理论分析和实验验证,取得了降噪后的高保真3维图像数据,并与传统的均值滤波、小波变换滤波的降噪效果进行对比。结果表明,该算法能自动选取最优的降噪窗口,有效地去除3维图像的噪声信息,并保留高分辨率图像丰富的边缘、细节信息,最终得到高保真的高分辨率3维自然纹理图像。该实验结果对于高分辨率图像的降噪问题是十分有帮助的。