Dense Sampling Method Research Articles

The phylogeny of ceutorhynchine weevils (Ceutorhynchinae, Curculionidae): Mitogenome data improve the resolution of tribal relationships

AbstractCeutorhynchinae Gistel are a diverse weevil subfamily of almost worldwide distribution and considerable economic importance. Nevertheless, the classification of Ceutorhynchinae and their phylogenetic relationships are not yet fully resolved. Here, we sequenced the mitogenomes of 54 ceutorhynchine species. Phylogenetic analyses by maximum likelihood and Bayesian inference were performed on a dataset of 13 protein‐coding and two ribosomal genes. All analyses recovered three well supported clades A–C. A principal component analysis shows that codon usage differs considerably between these clades, indicating a compositional asymmetry in ceutorhynchine mitogenomes. This increased the challenge of resolving the early relationships among the three clades. The resolution of the later diversification was more robust, and the resulting topologies were largely compatible with each other and with the current taxonomic classification. Exceptions are the genera Micrelus Thomson, which is transferred from the tribe Ceutorhynchini to Egriini Pajni and Kohli (new position) and Amalus Schoenherr, which is transferred to Phytobiini Gistel (new position). Amalini Wagner 1936 is a junior synonym of Phytobiini Gistel 1848 (syn. n.). Coeliodini Lacordaire (new status), a tribe previously regarded as junior synonym of Ceutorhynchini, is re‐established. Our analyses also clarified the difficult assignments of taxa to the tribes Scleropterini Schultze and Phytobiini. All taxa with the ability to jump as adult beetles belong to clade B, which comprises the tribes Cnemogonini Colonnelli, Hypurini Schultze, Mecysmoderini Wagner and Phytobiini. With dense taxon sampling and appropriate analytical methods, mitogenome data provide a phylogeny well suited to improve the traditional classification of this neglected and species‐rich taxon.

Fast inverse lithography approach based on a model-driven graph convolutional network.

Inverse lithography technique (ILT) is a leading-edge method to improve the image fidelity of an advanced optical lithography system by performing pixel-wise optimization on the transmission function of photomask. However, traditional ILTs are computationally intensive, which limits their application in high volume manufacturing of integrated circuits. This paper proposes a model-driven graph convolutional network (MGCN) framework combined with the dense concentric circular sampling (DCCS) method to effectively improve computational efficiency and imaging fidelity of current ILTs. Firstly, the DCCS template is used to extract the geometric features from the layout pattern of integrated circuits, which are then input into a GCN-based encoder to predict the optimized mask pattern of the ILT. Then, a model-driven decoder based on the lithography imaging process is developed to retrieve the print image of the predicted ILT mask. By means of the cooperation between the encoder and decoder, an unsupervised training strategy is proposed to avoid the time-consuming labelling process of the training samples. With the help of the parallel computing under GPU framework, the well-trained encoder can make a fast prediction of ILT mask with high-fidelity image results. The results demonstrate the state-of-the-art performance of the proposed MGCN approach compared to some other comparative ILT methods.

Bidirectional Long Short-Term Memory with Temporal Dense Sampling for human action recognition

Long Short-Term Memory networks are making significant inroads into improving time series applications, including human action recognition. In a human action video, the spatial and temporal streams carry distinctive yet prominent information, hence many researchers turn to spatio-temporal models for human action recognition. A spatio-temporal model integrates the temporal network (e.g. Long Short-Term Memory) and spatial network (e.g. Convolutional Neural Networks). There are few challenges in the existing human action recognition: (1) the uni-directional modeling of Long Short-Term Memory making it unable to preserve the information from the future, (2) the sparse sampling strategy tends to lose prominent information when performing dimension reduction on the input of Long Short-Term Memory, and (3) the fusion strategy for consolidating the temporal network and spatial network. In view of this, we propose a Bidirectional Long Short-Term Memory with Temporal Dense Sampling and Fusion Network method to address the above-mentioned challenges. The Temporal Dense Sampling partitions the human action video into segments and then performs maxpooling operation along the temporal axis in each segment. A multi-stream bidirectional Long Short-Term Memory network is adopted to encode the long-term spatial and temporal dependencies in both forward and backward directions. Instead of assigning fixed weights to the spatial network and temporal network, we propose a fusion network where a fully-connected layer is trained to adaptively assign the weights for the networks. The empirical results demonstrate that the proposed Bidirectional Long Short-Term Memory with Temporal Dense Sampling and Fusion Network method outshines the state-of-the-art methods with an accuracy of 94.78% on UCF101 dataset and 70.72% on HMDB51 dataset.

Learning Adaptive Spatial-Temporal Context-Aware Correlation Filters for UAV Tracking

Tracking in the unmanned aerial vehicle (UAV) scenarios is one of the main components of target-tracking tasks. Different from the target-tracking task in the general scenarios, the target-tracking task in the UAV scenarios is very challenging because of factors such as small scale and aerial view. Although the discriminative correlation filter (DCF)-based tracker has achieved good results in tracking tasks in general scenarios, the boundary effect caused by the dense sampling method will reduce the tracking accuracy, especially in UAV-tracking scenarios. In this work, we propose learning an adaptive spatial-temporal context-aware (ASTCA) model in the DCF-based tracking framework to improve the tracking accuracy and reduce the influence of boundary effect, thereby enabling our tracker to more appropriately handle UAV-tracking tasks. Specifically, our ASTCA model can learn a spatial-temporal context weight, which can precisely distinguish the target and background in the UAV-tracking scenarios. Besides, considering the small target scale and the aerial view in UAV-tracking scenarios, our ASTCA model incorporates spatial context information within the DCF-based tracker, which could effectively alleviate background interference. Extensive experiments demonstrate that our ASTCA method performs favorably against state-of-the-art tracking methods on some standard UAV datasets.

Dense Sampling of Time Series for Forecasting

A time series contain a large amount of information suitable for forecasting. Classical statistical and recent deep learning models have been widely used in a variety of forecasting applications. During the training data preparation stage, most models collect samples by sliding a fixed-sized window over the time axis of the input time series. We refer to this conventional method as “sparse sampling” because it cannot extract sufficient samples because it ignores another important axis representing the window size. In this study, a dense sampling method is proposed that extends the sampling space from one to two dimensions. The new space consists of time and window axes. Dense sampling provides several desirable effects, such as a larger training dataset, an intra-model ensemble, model-agnosticism, and an easier setting of the optimal window. The experiments were conducted using four real datasets: Bitcoin price, influenza-like illness, household electric power consumption, and wind speed. The mean absolute percentage error was measured extensively in terms of varying window sizes, horizons, and lengths of time series. The resulting data showed that dense sampling significantly and consistently outperformed sparse sampling. The source codes and datasets are available at https://github.com/isoh24/Dense-sampling-time-series.

Optimized Classification of Suspended Particles in Seawater by Dense Sampling of Polarized Light Pulses.

Suspended particles affect the state and vitality of the marine ecosystem. In situ probing and accurately classifying the suspended particles in seawater have an important impact on ecological research and environmental monitoring. Individual measurement of the optical polarization parameters scattered by the suspended particles has been proven to be a powerful tool to classify the particulate compositions in seawater. In previous works, the temporal polarized light pulses are sampled and averaged to evaluate the polarization parameters. In this paper, a method based on dense sampling of polarized light pulses is proposed and the experimental setup is built. The experimental results show that the dense sampling method optimizes the classification and increases the average accuracy by at least 16% than the average method. We demonstrate the feasibility of dense sampling method by classifying the multiple types of particles in mixed suspensions and show its excellent generalization ability by multi-classification of the particles. Additional analysis indicates that the dense sampling method basically takes advantage of the high-quality polarization parameters to optimize the classification performance. The above results suggest that the proposed dense sampling method has the potential to probe the suspended particles in seawater in red-tide early warning, as well as sediment and microplastics monitoring.

Multispectral Interlaced Sparse Sampling Photoacoustic Tomography.

Multispectral photoacoustic tomography (PAT) is capable of resolving tissue chromophore distribution based on spectral un-mixing. It works by identifying the absorption spectrum variations from a sequence of photoacoustic images acquired at multiple illumination wavelengths. Due to multispectral acquisition, this inevitably creates a large dataset. To cut down the data volume, sparse sampling methods that reduce the number of detectors have been developed. However, image reconstruction of sparse sampling PAT is challenging because of insufficient angular coverage. During spectral un-mixing, these inaccurate reconstructions will further amplify imaging artefacts and contaminate the results. To solve this problem, we present the interlaced sparse sampling (ISS) PAT, a method that involved: 1) a novel scanning-based image acquisition scheme in which the sparse detector array rotates while switching illumination wavelength, such that a dense angular coverage could be achieved by using only a few detectors; and 2) a corresponding image reconstruction algorithm that makes use of an anatomical prior image created from the ISS strategy to guide PAT image computation. Reconstructed from the signals acquired at different wavelengths (angles), this self-generated prior image fuses multispectral and angular information, and thus has rich anatomical features and minimum artefacts. A specialized iterative imaging model that effectively incorporates this anatomical prior image into the reconstruction process is also developed. Simulation, phantom, and in vivo animal experiments showed that even under 1/6 or 1/8 sparse sampling rate, our method achieved comparable image reconstruction and spectral un-mixing results to those obtained by conventional dense sampling method.

Transformative Urban Changes of Beijing in the Decade of the 2000s

The rapid economic growth, the exodus from rural to urban areas, and the associated extreme urban development that occurred in China in the decade of the 2000s have severely impacted the environment in Beijing, its vicinity, and beyond. This article presents an innovative approach for assessing mega-urban changes and their impact on the environment based on the use of decadal QuikSCAT (QSCAT) satellite data, acquired globally by the SeaWinds scatterometer over that period. The Dense Sampling Method (DSM) is applied to QSCAT data to obtain reliable annual infrastructure-based urban observations at a posting of ~1 km. The DSM-QSCAT data, along with different DSM-based change indices, were used to delineate the extent of the Beijing infrastructure-based urban area in each year between 2000 and 2009, and assess its development over time, enabling a physical quantification of its urbanization which reflects the implementation of various development policies during the same time period. Eventually, as a proxy for the impact of Beijing urbanization on the environment, the decadal trend of its infrastructure-based urbanization is compared with that of the corresponding tropospheric nitrogen dioxide (NO2) column densities as observed from the Global Ozone Monitoring Experiment (GOME) instrument aboard the second European Remote Sensing satellite (ERS-2) between 2000 and 2002, and from the SCanning Imaging Absorption SpectroMeter for Atmospheric CHartographY aboard of the ESA’s ENVIronmental SATellite (SCIAMACHY /ENVISAT) between 2003 and 2009. Results reveal a threefold increase of the yearly tropospheric NO2 column density within the Beijing infrastructure-based urban area extent in 2009, which had quadrupled since 2000.

Learning temporal-spatial consistency correlation filter for visual tracking

Discriminant correlation filter-based tracking approaches, which adopt a circular shift operator on the tracking target object (the only accurate positive sample) to obtain training data and rely on the potential sample periodic extension hypothesis that enables model training and detection, can be efficiently accomplished through FFT. However, real background information is not modeled during the total learning process. The background-aware correlation filter (BACF) tracking algorithm uses a binary matrix to acquire real positive and negative samples using a dense sampling method to model the targets appearance. However, the BACF algorithm does not consider temporal and spatial consistency information, and when a target undergoes an abrupt change, the learned correlation filter will drift to the background. To solve this problem, in this paper, we introduce temporal and spatial consistency constraints into the baseline BACF framework and propose a learning temporal-spatial consistency correlation filter (TSCF) tracking algorithm. This enables the correlation filter to learn to adapt to the appearance of mutation between successive frames. The temporal consistency constraint smooths the multi-channel correlation filter in the time series, and the spatial consistency constraint smooths the multi-channel correlation filter in spatial distribution, thus making the energy distribution more uniform of the correlation filter learned. In this paper, the TSCF model has closed solutions and the conjugate gradient descent method is used to approximate the optimal solution of a system of closed solutions. The optimization process can then be transformed into the Fourier domain using cyclic matrix properties to quickly obtain a solution, which effectively reduces the cost of calculating large matrices. In this paper, our TSCF algorithm increases distance precision by 5.5$%$ and raises the AUC by 4.3$%$ compared to the baseline BACF algorithm on the TB100 public database. The distance precision achieves 0.879 and the AUC reaches 0.663 on the TB100 database making use of only hand-crafted features. The TSCF algorithm proposed in this paper can be applied to challenging conditions such as short time occlusion, out-of-plane rotation, in-plane rotation, and so on, thus demonstrating its robustness and effectiveness.

Vision-Based Flying Targets Detection via Spatiotemporal Context Fusion

Deriving from the imperative necessities for developing Sense and Avoid (SAA) capability of Unmanned Aerial Vehicle (UAV), a newly designed flying targets detection algorithm is presented in this paper for enhancing the UAV environment perception ability. Since spatiotemporal context is crucial for insuring the effectiveness of flying targets detection, the algorithm is constructed on the basis of spatiotemporal context fusion. The algorithm proposed in this paper contains three parts, namely the spatial context extraction, temporal context extraction and spatiotemporal context fusion. 1) In order to extract spatial context, dense sampling method is firstly applied to obtain dense image grids, then spatial context is generated via pre-learned conditional random field (CRF) model using a layered structure: dense image patches, bottom feature descriptors, sparse codes, and predicted CRF labels. 2) In order to extract temporal context, the forward and back motion history image (FBMHI) is firstly computed for detecting motion cues, and the adaptive foreground and background isolation is further adopted for acquiring the temporal probability map. 3) The presence probability map of flying targets is finally obtained by spatiotemporal context fusion, and flying targets is therefore picked out by analyzing fused presence probability map. A set of videos containing different drone models are selected for evaluation, and the comparisons against other algorithms demonstrate superiority of the proposed algorithm.

Adaptive repair and digitization for hybrid manufacturing

Abstract Repair of aerospace components represents a significant opportunity for hybrid manufacturing systems to reduce high scrap rate through automation of the inspection, additive and subtractive processes. In this study, a series of on-machine profile digitization strategies were investigated to determine the effects on accuracy of non-rigid registration of blade component geometry and downstream quality measures pertaining to parent material blendlines. The profile digitization strategies investigated include dense sampling methods and curvature-based segmentation approaches. A model was developed to predict the accuracy of the digitization approaches and a series of machining tests were also conducted to show the predictive capability of the model. From these results, it is seen that curvature-based segmentation methods provide an accurate and rapid digitization solution for blend-type repairs.

The method of distinguishing sedimentary environment of sandstone reservoirs by XRF

Although XRF elemental analysis is one of the major methods of depositional environment research in shale, it has not formed a unified standard in sandstone. With XRF portable analysis technology developing recently, the advantages of its portability, economy, high efficiency and the protection of the original sample make it more widely used. This study area has only few wells in the northern part of Xihu Sag with the problem of unclear sedimentary facies and sedimentary environment definition. In this case, the work attempts to determine the ancient depositional environment and typical sedimentary microfacies by using XRF core dense sampling method. According to the test accuracy of the hand-held X fluorescence spectrometer, the environmental discrimination elements of Sr, Mn, Ti, Mg, Ca and Fe were selected. The data of the cementing development layer were excluded by the casting and scanning electron microscopy. This paper normalized the relevant elements by GR curve, and the content of related elements in the fine sediment of one unit is obtained, which eliminates possible misjudgement caused by the content of fine sediment in determination of sedimentary environment in the sandstone reservoir. Then this study uses the standardized elemental and elemental ratio of the study area to determine the ancient depositional environment. Finally, according to the relationship between sedimentary microfacies and elements in the study area, two types of reference plate are selected to determine the sedimentary microfacies, providing the basis for fine grading of sedimentary microfacies.

Up and out: A multifaceted approach to characterizing urbanization in Greater Saigon, 2000–2009

In this case study of Greater Saigon, two types of satellite data are used to estimate the rate of change in urban spatial expansion, both horizontally and volumetrically (horizontal and vertical components), and integrates them with socioeconomic data to examine the correlates and potential causes of both kinds of change. We employ new data products – the Global Human Settlement Layer (GHSL) derived largely from Landsat and a Dense Sampling Method (DSM) product based on QuikSCAT – in combination with data from the 1999 and 2009 censuses of Vietnam. Unlike past studies, we examine horizontal and volumetric changes in urban form and pay particular attention to the role of migration in locations experiencing those different types of change. We find these two types of urban change occur at different rates and in different localities, with the highest rates of horizontal change occurring to the north of administrative Saigon. In contrast, we find the highest rates of volumetric change in the areas north of the central districts but mostly within administrative Saigon. In-migration is strongly associated with horizontal change, whereas increases in population density appears to drive volumetric change, controlling for other factors. Positive volumetric change is associated with necessary amenities of modern urban living, often in high-rise buildings found in dense population centers like Saigon: the increasing presence in households of computers, air conditioners, piped water, and gas fuel. Use of these new integrated data hold promise to shed new light on both the built-environment and social dimensions of urbanization in low- and middle-income settings.

Plant species classification using flower images—A comparative study of local feature representations

Steady improvements of image description methods induced a growing interest in image-based plant species classification, a task vital to the study of biodiversity and ecological sensitivity. Various techniques have been proposed for general object classification over the past years and several of them have already been studied for plant species classification. However, results of these studies are selective in the evaluated steps of a classification pipeline, in the utilized datasets for evaluation, and in the compared baseline methods. No study is available that evaluates the main competing methods for building an image representation on the same datasets allowing for generalized findings regarding flower-based plant species classification. The aim of this paper is to comparatively evaluate methods, method combinations, and their parameters towards classification accuracy. The investigated methods span from detection, extraction, fusion, pooling, to encoding of local features for quantifying shape and color information of flower images. We selected the flower image datasets Oxford Flower 17 and Oxford Flower 102 as well as our own Jena Flower 30 dataset for our experiments. Findings show large differences among the various studied techniques and that their wisely chosen orchestration allows for high accuracies in species classification. We further found that true local feature detectors in combination with advanced encoding methods yield higher classification results at lower computational costs compared to commonly used dense sampling and spatial pooling methods. Color was found to be an indispensable feature for high classification results, especially while preserving spatial correspondence to gray-level features. In result, our study provides a comprehensive overview of competing techniques and the implications of their main parameters for flower-based plant species classification.

Action recognition by saliency-based dense sampling

Action recognition, aiming to automatically classify actions from a series of observations, has attracted more attention in the computer vision community. The state-of-the-art action recognition methods utilize dense sampled trajectories to build feature representations. However, their performances are limited due to action region clutters and camera motions in real world applications. No matter how the scenario changes in different backgrounds, the salient cues of actions are highly dependent on their appearances and motions. Based on this discovery, in this paper we propose a novel saliency-based dense sampling strategy named improved dense trajectories (iDT) on salient region-based contrast boundary (iDT-RCB). Without any external human detector, a robust mask is generated to overcome the limitations of global contrast based saliency in action sequences. Warped optical flow is exploited to adjust the interest points sampling to remove subtle motions. We show that an appropriate pruning of feature points can achieve a good balance between saliency and density of the sampled points. Experiments conducted on three benchmark datasets have demonstrated the effectiveness of the proposed method. More specifically, the fusion of deep-learned features and our hand-crafted features can even improve the recognition performance over baseline dense sampling methods. In particular, the fusion scheme achieves the state-of-the-art accuracy at 73.8% and 94.8% on Hollywood2 and UCF50, respectively.

Multi-view object detection in dual-energy X-ray images

Automatic inspection of X-ray scans at security checkpoints can improve the public security. X-ray images are different from photographic images. They are transparent. They contain much less texture. They may be highly cluttered. Objects may undergo in- and out-of-plane rotations. On the other hand, scale and illumination change is less of an issue. More importantly, X-ray imaging provides extra information which are usually not available in regular images: dual-energy imaging, which provides material information about the objects; and multi-view imaging, which provides multiple images of objects from different viewing angles. Such peculiarities of X-ray images should be leveraged for high-performance object recognition systems to be deployed on X-ray scanners. To this end, we first present an extensive evaluation of standard local features for object detection on a large X-ray image dataset in a structured learning framework. Then, we propose two dense sampling methods as keypoint detector for textureless objects and extend the SPIN color descriptor to utilize the material information. Finally, we propose a multi-view branch-and-bound search algorithm for multi-view object detection. Through extensive experiments on three object categories, we show that object detection performance on X-ray images improves substantially with the help of extended features and multiple views.

Groundwater vulnerability maps derived from a time-dependent method using satellite scatterometer data

Introducing the time variable in groundwater vulnerability assessment is an innovative approach to study the evolution of contamination by non-point sources and to forecast future trends. This requires a determination of the relationship between temporal changes in groundwater contamination and in land use. Such effort will enable breakthrough advances in mapping hazardous areas, and in assessing the efficacy of land-use planning for groundwater protection. Through a Bayesian spatial statistical approach, time-dependent vulnerability maps are derived by using hydrogeological variables together with three different time-dependent datasets: population density, high-resolution urban survey, and satellite QuikSCAT (QSCAT) data processed with the innovative dense sampling method (DSM). This approach is demonstrated extensively over the Po Plain in Lombardy region (northern Italy). Calibrated and validated maps show physically consistent relations between the hydrogeological variables and nitrate trends. The results indicate that changes of urban nitrate sources are strongly related to groundwater deterioration. Among the different datasets, QSCAT-DSM is proven to be the most efficient dataset to represent urban nitrate sources of contamination, with major advantages: a worldwide coverage, a continuous decadal data collection, and an adequate resolution without spatial gaps. This study presents a successful approach that, for the first time, allows the inclusion of the time dimension in groundwater vulnerability assessment by using innovative satellite remote sensing data for quantitative statistical analyses of groundwater quality changes.

The challenges of forecasting resilience.

Developing prospective models of resilience using the translational and transdiagnostic framework proposed in the target article is a challenging endeavor and will require large-scale data sets with dense intraindividual temporal sampling and innovative analytic methods.

Use of scatterometer data in groundwater vulnerability assessment

Lombardy in Italy has been selected as a case study to evaluate the capability of the QuikSCAT - Dense Sampling Method (QSCAT-DSM) data in delineating urban extent, estimating rate of urban changes, and assessing aquifer vulnerability, in particular to investigate the relationship between land-use changes and groundwater contamination.QSCAT-DSM data represent an innovative approach to delineate urban and interurban areas with satellite scatterometer data. Radar backscatter acquired by the SeaWinds scatterometer aboard the QSCAT satellite together with the DSM are used to identify and map surface features at a posting scale of about 1 km².Through the spatial statistical methods Weight of Evidence (WofE), both urban changes given by QSCAT-DSM data and population changes in the decade of the 2000’s have been correlated to nitrate concentration trend in groundwater in the same time period.Both analyses based on urban change and on population change lead to the same result: urban nitrate sources in Lombardy increase the level of nitrate concentration in groundwater, indicating a degradation of the water quality. Moreover, QSCAT-DSM data proved to be a reliable tool for evaluating urban changes continuously without a temporal or spatial gap, and to be a strategic variable allowing the assessment of groundwater vulnerability consistently throughout the decadal time scale.

A dense sampling method for calibrating non-see-through head mounted displays

A dense sampling method for calibrating non-see-through head mounted displays