A novel image-fusion method based on the un-mixing of mixed MS sub-pixels regarding high-resolution DSM

A major reason for the spectral distortions of fused images generated by current image-fusion methods is that the fused versions of mixed multispectral(MS)sub-pixels(MSPs)corresponding to panchromatic(PAN)pure pixels remain mixed.The MSPs can be un-mixed spectrally to pure pixels having the same land cover classes in a fine classification map during the fusion process.Since it is difficult to produce such a land cover classification map using only MS and PAN images,a Digital Surface Model(DSM)derived from airborne Light Detection And Ranging data were employed in this study to facilitate the classification.In a novel fusion method proposed in this paper,MSPs near and across boundaries between vegetation and non-vegetation are identified using MS,PAN,and normalized Digital Surface Model(nDSM).The identified MSPs then are fused to pure pixels with respect to the corresponding land cover class in the classification map.In a test on WorldView-2 images over an urban area and the corresponding nDSM,the fused image generated by the proposed method was visually and quantitatively compared with fused images obtained using common image-fusion methods.The fused images generated by the proposed method yielded minimal spectral distortions and sharpened boundaries between vegetation and non-vegetation.

Sub-pixel extraction of laser stripeand itsapplication in laser plane calibration

For calibrating the laser plane to implement 3D shape measurement, an algorithm for extracting the laser stripe with sub-pixel accuracy is proposed. The proposed algorithm mainly consists of two stages： two-side edge detection and center line extraction. First, the two-side edge of laser stripe is detected using the principal component angle-based progressive probabilistic Hough transform and its width is calculated through the distance between these two edges. Secondly, the center line of laser strip is extracted with 2D Taylor expansion at a sub-pixel level and the laser plane is calibrated with the 3D reconstructed coordinates from the extracted 2D sub-pixel ones. Experimental results demonstrate that the proposed method can not only extract the laser stripe at a high speed, nearly average 78 ms/frame, but also calibrate the coplanar laser stripes at a low error, limited to 0.3 mm. The proposed algorithm can satisfy the system requirement of two-side edge detection and center line extraction, and rapid speed, high precision, as well as strong anti-jamming.

Vibration-assisted vat photopolymerization for pixelated-aliasing-free surface fabrication

Mask image projection-based vat photopolymerization(MIP-VPP)offers advantages like low cost,high resolution,and a wide material range,making it popular in industry and education.Recently,MIP-VPP employing liquid crystal displays(LCDs)has gained traction,increasingly replacing digital micromirror devices,particularly among hobbyists and in educational settings,and is now beginning to be used in industrial environments.However,LCD-based MIP-VPPsuffers from pronounced pixelated aliasing arising from LCD’s discrete image pixels and itsdirect-contact configuration in MIP-VPP machines,leading to rough surfaces on the 3D-printed parts.Here,we propose a vibration-assisted MIP-VPP method that utilizes a microscalevibration to uniformize the light intensity distribution of the LCD-based mask image on VPP’s building platform.By maintaining the same fabrication speed,our technique generates asmoother,non-pixelated mask image,reducing the roughness on flat surfaces and boundary segments of 3D-printed parts.Through light intensity modeling and simulation,we derived an optimal vibration pattern for LCD mask images,subsequently validated by experiments.We assessed the surface texture,boundary integrity,and dimensional accuracy of componentsproduced using the vibration-assisted approach.The notably smoother surfaces and improved boundary roughness enhance the printing quality of MIP-VPP,enabling its promisingapplications in sectors like the production of 3D-printed optical devices and others.

Sub-pixel high precision dimensional measurement method for aero-engine hollow turbine blade based on industrial computed tomography image

Aero-engine hollow turbine blades are work under prolonged high temperature,requiring high dimensional accuracy.Blade profile and wall thickness are important parameters to ensure the comprehensive performance of blades,which need to be measured accurately during manufacturing process.In this study,a high accuracy industrial computed tomography(ICT)measuring method was developed based on standard cylindrical pin and ring workpieces of different sizes.Combining ICT with cubic spline interpolation,a sub-pixel accuracy was achieved in measuring the dimension of component.Compared with the traditional and whole-pixel level image measurement method,the cubic spline interpolation algorithm has the advantages of high accuracy in image edge detection and thus high accuracy of dimensional measurement.Further,the technique was employed to measure the profile and wall thickness of a typical aerospace engine turbine blade,and an accuracy higher than 0.015 mm was obtained.

Integration of spatial attractions between and within pixels for sub-pixel mapping

As a promising technique to enhance the spatial reso- lution of remote sensing imagery, sub-pixel mapping is processed based on the spatial dependence theory with the assumption that the land cover is spatially dependent both within pixels and be- tween them. The spatial attraction is used as a tool to describe the dependence. First, the spatial attractions between pixels, sub- pixel/pixel spatial attraction model （SPSAM）, are described by the modified SPSAM （MSPSAM） that estimates the attractions accord- ing to the distribution of sub-pixels within neighboring pixels. Then a mixed spatial attraction model （MSAM） for sub-pixel mapping is proposed that integrates the spatial attractions both within pix- els and between them. According to the expression of the MSAM maximumising the spatial attraction, the genetic algorithm is em- ployed to search the optimum solution and generate the sub-pixel mapping results. Experiments show that compared with SPSAM, MSPSAM and pixel swapping algorithm modified by initialization from SPSAM （MPS）, MSAM can provide higher accuracy and more rational sub-pixel mapping results.

Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage:A Case Study from Beijing Municipality,China

The sub-pixel impervious surface percentage(SPIS) is the fraction of impervious surface area in one pixel,and it is an important indicator of urbanization.Using remote sensing data,the spatial distribution of SPIS values over large areas can be extracted,and these data are significant for studies of urban climate,environment and hydrology.To develop a stabilized,multi-temporal SPIS estimation method suitable for typical temperate semi-arid climate zones with distinct seasons,an optimal model for estimating SPIS values within Beijing Municipality was built that is based on the classification and regression tree(CART) algorithm.First,models with different input variables for SPIS estimation were built by integrating multi-source remote sensing data with other auxiliary data.The optimal model was selected through the analysis and comparison of the assessed accuracy of these models.Subsequently,multi-temporal SPIS mapping was carried out based on the optimal model.The results are as follows:1) multi-seasonal images and nighttime light(NTL) data are the optimal input variables for SPIS estimation within Beijing Municipality,where the intra-annual variability in vegetation is distinct.The different spectral characteristics in the cultivated land caused by the different farming characteristics and vegetation phenology can be detected by the multi-seasonal images effectively.NLT data can effectively reduce the misestimation caused by the spectral similarity between bare land and impervious surfaces.After testing,the SPIS modeling correlation coefficient(r) is approximately 0.86,the average error(AE) is approximately 12.8%,and the relative error(RE) is approximately 0.39.2) The SPIS results have been divided into areas with high-density impervious cover(70%–100%),medium-density impervious cover(40%–70%),low-density impervious cover(10%–40%) and natural cover(0%–10%).The SPIS model performed better in estimating values for high-density urban areas than other categories.3) Multi-temporal SPIS mapping(1991–2016) was conducted based on the optimized SPIS results for 2005.After testing,AE ranges from 12.7% to 15.2%,RE ranges from 0.39 to 0.46,and r ranges from 0.81 to 0.86.It is demonstrated that the proposed approach for estimating sub-pixel level impervious surface by integrating the CART algorithm and multi-source remote sensing data is feasible and suitable for multi-temporal SPIS mapping of areas with distinct intra-annual variability in vegetation.

Sub-pixel mapping method based on BP neural network

A new sub-pixel mapping method based on BP neural network is proposed in order to determine the spatial distribution of class components in each mixed pixel.The network was used to train a model that describes the relationship between spatial distribution of target components in mixed pixel and its neighboring information.Then the sub-pixel scaled target could be predicted by the trained model.In order to improve the performance of BP network,BP learning algorithm with momentum was employed.The experiments were conducted both on synthetic images and on hyperspectral imagery(HSI).The results prove that this method is capable of estimating land covers fairly accurately and has a great superiority over some other sub-pixel mapping methods in terms of computational complexity.

Fast Approaches for Sub-pixel Precision Variable Block Size Motion Estimation

The new features of H. 264 video coding standard make the motion estimation module much more time consuming than before. Especially, the motion search is required for each of the 4 modes for inter prediction. In order to reduce the computational complexity, we analyze the statistics of results of motion estimation, such as the continuity of best modes of blocks in successive frames and the chance to give up a sub-partition mode （smaller than 16 × 16） after integer-pixel motion estimation, from which we suggest to make mode prediction based on the motion information of the previous frame and skip sub-pixel motion estimation in subpartition mode selectively. According to the experimental result, the proposed algorithm can save 75 % of the computational time with a slight degradation （0.03 dB） on PSNR compared with the pseudocode of fast search motion estimation in JM12.2.

Fast Sub-Pixel Motion Estimation Algorithm For H.264

A novel fast sub-pixel search algorithm is proposed to accelerate sub-pixel search. Based on the features of predicted motion vector (PMV) and texture direction observed, the proposed method effectively filters out impossible points and thus decreases 11 searched points in average during the sub-pixel search stage. A threshold is also adopted to early terminate the sub-pixel search. Simulation results show that the proposed method can achieve up to 4.8 times faster than full sub-pixel motion search scheme (FSPS) with less than 0.025 dB PSNR losses and 2.2% bit-length increases.

Sub-pixel edge detection method for miniature parts in microscopic field of view

In order to improve the edge detection precision of miniature parts in microscopic field of viewa sub-pixel edge detectionalgorithm combining non-orthogonal quadratic B-spline wavelet transform algorithm and Zernike moment algorithm is proposed.Non-orthogonal quadratic B-spline wavelet transform algorithm is adopted to get the pixel edge of miniature parts?andthe moment invariant of Zernike moment algorithm is used for refining the pixel edge to get sub-pixel edges.A real-time detectionsystem based on the proposed algorithm for miniature parts is established.The general system structure and operational principle are given,the real-time image acquisition and detection are completed,the results of edge detection are analyzed and the detection precision is evaluated.The results show that parts size can be0.01-10mm and the detection precision reaches0.01%-0.1%.Therefore,the edge of the miniature parts can be accurately identified and the detection precision can be improved to sub-pixel level,which meets the requirements of miniature parts precision detection.

4K-DMDNet:diffraction model-driven network for 4K computer-generated holography

Deep learning offers a novel opportunity to achieve both high-quality and high-speed computer-generated holography(CGH).Current data-driven deep learning algorithms face the challenge that the labeled training datasets limit the training performance and generalization.The model-driven deep learning introduces the diffraction model into the neural network.It eliminates the need for the labeled training dataset and has been extensively applied to hologram generation.However,the existing model-driven deep learning algorithms face the problem of insufficient constraints.In this study,we propose a model-driven neural network capable of high-fidelity 4K computer-generated hologram generation,called 4K Diffraction Model-driven Network(4K-DMDNet).The constraint of the reconstructed images in the frequency domain is strengthened.And a network structure that combines the residual method and sub-pixel convolution method is built,which effectively enhances the fitting ability of the network for inverse problems.The generalization of the 4K-DMDNet is demonstrated with binary,grayscale and 3D images.High-quality full-color optical reconstructions of the 4K holograms have been achieved at the wavelengths of 450 nm,520 nm,and 638 nm.

基于改进SSD算法的交通标识检测方法研究

针对目前SSD算法对小目标检测精确度低,泛化能力弱,且存在误检、漏检等问题,提出一种基于SSD网络的交通标识检测方法。为增加对目标的检测精度,使用ResNet-50网络作为SSD算法的骨干网络,在额外添加层中加入BN层,提高训练速度;使用sub-pixel来代替上采样,提高识别目标分辨率,并加入MFPN模型融合低层与高层特征信息,避免出现漏检问题。实验结果表明与现有的SSD算法相比,改进的SSD算法在公开数据集CCTSDB和GTSDB数据集上mAP值分别提高4.2%和3.1%,FPS保持在87.2 f/s,检测精度显著提升。满足对交通标识实时检测的要求,在无人驾驶领域具有广泛的应用前景。

A Real-Time System for Monitoring Distant Dynamic Displacement of Structures

Based on digital image processing technique, a real-time system is developed to monitor and detect the dynamic displacement of engineering structures. By processing pictures with a self-programmed software, the real-time coordinate of an object in a certain coordinate system can be obtained, and further dynamic displacement data and curve of the object can also be achieved. That is, automatic gathering and real-time processing of data can be carried out by this system simultaneously. For this system, first, an untouched monitoring technique is adopted, which can monitor or detect objects several to hundreds of meters apart; second, it has flexible installation condition and good monitoring precision of sub-millimeter degree; third, it is fit for dynamic, quasi-dynamic and static monitoring of large engineering structures. Through several tests and applications in large bridges, good reliability and dominance of the system is proved.

Visual positioning of rectangular lead components based on Harris corners and Zernike moments

With the increasing necessities for reliable printed circuit board(PCB) product, there has been a considerable demand for high speed and high precision vision positioning system. To locate a rectangular lead component with high accuracy and reliability, a new visual positioning method was introduced. Considering the limitations of Ghosal sub-pixel edge detection algorithm, an improved algorithm was proposed, in which Harris corner features were used to coarsely detect the edge points and Zernike moments were adopted to accurately detect the edge points. Besides, two formulas were developed to determine the edge intersections whose sub-pixel coordinates were calculated with bilinear interpolation and conjugate gradient method. The last experimental results show that the proposed method can detect the deflection and offset, and the detection errors are less than 0.04° and 0.02 pixels.

TWO-STAGE OCCLUDED OBJECT RECOGNITION METHOD FOR MICROASSEMBLY

A two-stage object recognition algorithm with the presence of occlusion is presented for microassembly. Coarse localization determines whether template is in image or not and approximately where it is, and fine localization gives its accurate position. In coarse localization, local feature, which is invariant to translation, rotation and occlusion, is used to form signatures. By comparing signature of template with that of image, approximate transformation parameter from template to image is obtained, which is used as initial parameter value for fine localization. An objective function, which is a function of transformation parameter, is constructed in fine localization and minimized to realize sub-pixel localization accuracy. The occluded pixels are not taken into account in objective function, so the localization accuracy will not be influenced by the occlusion.

Simulation of Central Subpixel Location Method in Remote Sensing Multi-View Image

Subpixel localization in image center is one of the key technologies of vision measurement. In order to meet the requirements of accurate calibration and measurement in multi-field, the existing sub-pixel positioning methods are complex, the positioning accuracy is greatly affected by the effect of initial edge extraction, and the positioning accuracy is low. Because remote sensing multi-view images are usually not stationary random signals, in order to better express the non-stationary characteristics of images, random analysis is combined to segment sub-pixel objects in the center of remote sensing images. The accuracy of mark positioning will affect the accuracy of the whole measurement. The control point signs with different characteristics correspond to different recognition methods, so the selection of control point marks should be based on different requirements. It is used to describe the target view from different viewpoints and use the geometric features to retrieve the model library. The matching process uses global and local, statistical and structural target recognition features hierarchically, and is divided into two steps of retrieval and exact matching. The experiment was carried out to verify the effectiveness of the method.

Employment of predictive search algorithm in digital image correlation

A predictive search algorithm to estimate the size and direction of displacement vectors was presented.The algorithm decreased the time of calculating the displacement of each pixel.In addition,the updating reference image scheme was used to update the reference image and to decrease the computation time when the displacement was larger than a certain number.In this way,the search range and computational complexity were cut down,and less EMS memory was occupied.The capability of proposed search algorithm was then verified by the results of both computer simulation and experiments.The results showed that the algorithm could improve the efficiency of correlation method and satisfy the accuracy requirement for practical displacement measuring.

HIGH PRECISION CCD CALIBRATION AND ITS APPLICATIONS

With the help of CCD images,the realization of high precision po-sitioning and measurement has become the basic standard for machine vision andreal time photogrammetry systems.However,deformation and other sorts ofdegradation occurring during transmission are major limiting factors of the preci-sion attainable with most current CCD cameras and frame grabbers.So a preciseradiometric and geometric transmission of images from CCD sensor to memory is afundamental aspect of CCD camera calibration.The geometric calibration system,which uses some image processing algorithms of the CCD camera based on the re-searched and developed system is discussed.The reliability and validity are alsodiscussed.The experimental results for the calibration of the CCD array will betaken as an important quality index for CCD evaluation.

Sub-pixel change detection for urban land-cover analysis via multi-temporal remote sensing images

Conventional change detection approaches are mainly based on per-pixel processing,which ignore the sub-pixel spectral variation resulted from spectral mixture.Especially for medium-resolution remote sensing images used in urban landcover change monitoring,land use/cover components within a single pixel are usually complicated and heterogeneous due to the limitation of the spatial resolution.Thus,traditional hard detection methods based on pure pixel assumption may lead to a high level of omission and commission errors inevitably,degrading the overall accuracy of change detection.In order to address this issue and find a possible way to exploit the spectral variation in a sub-pixel level,a novel change detection scheme is designed based on the spectral mixture analysis and decision-level fusion.Nonlinear spectral mixture model is selected for spectral unmixing,and change detection is implemented in a sub-pixel level by investigating the inner-pixel subtle changes and combining multiple composition evidences.The proposed method is tested on multi-temporal Landsat Thematic Mapper and China–Brazil Earth Resources Satellite remote sensing images for the land-cover change detection over urban areas.The effectiveness of the proposed approach is confirmed in terms of several accuracy indices in contrast with two pixel-based change detection methods(i.e.change vector analysis and principal component analysis-based method).In particular,the proposed sub-pixel change detection approach not only provides the binary change information,but also obtains the characterization about change direction and intensity,which greatly extends the semantic meaning of the detected change targets.

Multi-resolution integration of land cover for sub-pixel estimation of urban impervious surface and forest cover

A methodology is presented for estimating percent coverage of impervious surface(IS)and forest cover(FC)within Landsat thematic mapper(TM)pixels of urban areas.High-resolution multi-spectral images from Quickbird(QB)play a key role in the sub-pixel mapping process by providing information on the spatial distributions of ISs and FCs at 2.4 m ground sampling intervals.Thematic classifications,also derived from the Landsat imagery,have then been employed to define relationships between 30 m Landsat-derived greenness values and percent IS and FC.By also utilizing land cover/land use classification derived from Landsat and defining unique relationships for urban sub-classes(i.e.residential,commercial/industrial,open land),confusion between impervious and fallow agricultural lands has been overcome.Test results are presented for Ottawa-Gatineau,an urban area that encompasses many aspects typical of the North American urban landscape.Multiple QB scenes have been acquired for this urban centre,thereby allowing us to undertake an in-depth study of the error budgets associated with the fractional inference process.