Invalid Regions Research Articles

Efficient On-Board Compression for Arbitrary-Shaped Cloud-Covered Remote Sensing Images via Adaptive Filling and Controllable Quantization

Due to the fact that invalid cloud-covered regions in remote sensing images consume a considerable quantity of coding bit rates under the limited satellite-to-ground transmission rate, existing image compression methods suffer from low compression efficiency and poor reconstruction quality, especially in cloud-free regions which are generally regarded as regions of interest (ROIs). Therefore, we propose an efficient on-board compression method for remote sensing images with arbitrary-shaped clouds by leveraging the characteristics of cloudy images. Firstly, we introduce two novel spatial preprocessing strategies, namely, the optimized adaptive filling (OAF) strategy and the controllable quantization (CQ) strategy. Specifically, the OAF strategy fills each cloudy region using the contextual information at its inner and outer edge to completely remove the information of cloudy regions and minimize their coding consumption, which is suitable for images with only thick clouds. The CQ strategy implicitly identifies thin and thick clouds and rationally quantifies the data in cloudy regions to alleviate information loss in thin cloud-covered regions, which can achieve the balance between coding efficiency and reconstructed image quality and is more suitable for images containing thin clouds. Secondly, we develop an efficient coding method for a binary cloud mask to effectively save the bit rate of the side information. Our method provides the flexibility for users to choose the desired preprocessing strategy as needed and can be embedded into existing compression framework such as JPEG2000. Experimental results on the GF-1 dataset show that our method effectively reduces the coding consumption of invalid cloud-covered regions and significantly improve the compression efficiency as well as the quality of decoded images.

Individualised evaluation based on pathophysiology for moyamoya vasculopathy: application in surgical revascularisation

BackgroundAlthough bypass surgery is an effective treatment for moyamoya vasculopathy (MMV), the incidence of postoperative complications is still high. This study aims to introduce a novel evaluating system based on...

Journey over destination: dynamic sensor placement enhances generalization

Reconstructing complex, high-dimensional global fields from limited data points is a challenge across various scientific and industrial domains. This is particularly important for recovering spatio-temporal fields using sensor data from, for example, laboratory-based scientific experiments, weather forecasting, or drone surveys. Given the prohibitive costs of specialized sensors and the inaccessibility of certain regions of the domain, achieving full field coverage is typically not feasible. Therefore, the development of machine learning algorithms trained to reconstruct fields given a limited dataset is of critical importance. In this study, we introduce a general approach that employs moving sensors to enhance data exploitation during the training of an attention based neural network, thereby improving field reconstruction. The training of sensor locations is accomplished using an end-to-end workflow, ensuring differentiability in the interpolation of field values associated to the sensors, and is simple to implement using differentiable programming. Additionally, we have incorporated a correction mechanism to prevent sensors from entering invalid regions within the domain. We evaluated our method using two distinct datasets; the results show that our approach enhances learning, as evidenced by improved test scores.

Robust Lane Detection Method Based on Dynamic Region of Interest

Lane detection is an important component of vehicle assisted driving systems. Many lane line algorithms have been proposed, but lane line detection is still a challenging task in environments with road text or vehicle interference. To address these issues, this paper proposes a robust lane line detection method under structured roads. First, we propose a method based on the slope and length of a straight line and the distance of the line from the centre line to extract regions of interest reducing interference from other invalid regions. Afterwards, we use a new fusion method to fuse the extracted colour features with the gradient features, enhancing the lane features while greatly reducing the interference in the pixels. Next, we cut the extracted pixel feature maps in equal parts into several sub-maps and perform pixel statistics for each sub-map, replacing sub-maps with abnormal pixel values with adjacent sub-maps, which can effectively reduce noise. Finally, we use DBSCAN to cluster the pixels and fit the lane lines with least squares. The experimental results show that the method can effectively detect lane lines and has good robustness.

Dynamical stability of new wormhole solutions via cold dark matter and solitonic quantum wave halos in [formula omitted] gravity

This current analysis offers novel wormhole solutions in the background of newly developed extended f(R,Lm) gravity. We use an anisotropic matter source and a particular type of energy density demonstrating cold dark matter halo and quantum wave dark matter halo to calculate two different wormhole solutions. The properties of the exotic matter within the wormhole geometry and the matter contents via energy conditions are studied in detail, both analytically and graphically, by showing valid and invalid regions. The calculated shape functions of wormhole geometry satisfy the required conditions in both cases. Further, we investigate the stability of the shell around wormhole structures by considering black hole solutions in the framework of cold dark matter halo and quantum wave dark matter by assuming matter contents located at the shell follow the phantom-like equations of state. Then, for quintessence and phantom energy type equations of state, the choice of cold dark matter halo has maximum stability at lower equilibrium shell radii and declines as the radius rises. More petite wormhole throats have an unstable configuration for the dark energy matter content, while higher wormhole throat radius has the lowest stability. For the choice of quantum wave dark matter, the shell around the wormhole structure is unstable for both quintessence and phantom energy, while dark energy shows a stable configuration for smaller values of wormhole throat.

TranSiam: Aggregating multi-modal visual features with locality for medical image segmentation

Automatic segmentation of medical images plays an important role in the diagnosis of diseases. On single-modal data, convolutional neural networks have demonstrated satisfactory performance. However, multi-modal data encompasses a greater amount of information rather than single-modal data. Multi-modal data can be effectively used to improve the segmentation accuracy of regions of interest by analyzing both spatial and temporal information. In this study, we propose a dual-path segmentation model for multi-modal medical images, named TranSiam. Taking into account that there is a significant diversity between the different modalities, TranSiam employs two parallel CNNs to extract the features which are specific to each of the modalities. In our method, two parallel CNNs extract detailed and local information in the low-level layer, and the Transformer layer extracts global information in the high-level layer. Finally, we fuse the features of different modalities via a locality-aware aggregation block (LAA block) to establish the association between different modal features. The LAA block is used to locate the region of interest and suppress the influence of invalid regions on multi-modal feature fusion. TranSiam uses LAA blocks at each layer of the encoder in order to fully fuse multi-modal information at different scales. Extensive experiments on several multi-modal datasets have shown that TranSiam achieves satisfying results.

A Mobile Sensing Framework for Bridge Modal Identification through an Inverse Problem Solution Procedure and Moving-Window Time Series Models.

With the rise and development of smart infrastructures, there has been a great demand for installing automatic monitoring systems on bridges, which are key members of transportation networks. In this regard, utilizing the data collected by the sensors mounted on the vehicles passing over the bridge can reduce the costs of the monitoring systems, compared with the traditional systems where fixed sensors are mounted on the bridge. This paper presents an innovative framework for determining the response and for identifying modal characteristics of the bridge, utilizing only the accelerometer sensors on the moving vehicle passing over it. In the proposed approach, the acceleration and displacement response of some virtual fixed nodes on the bridge is first determined using the acceleration response of the vehicle axles as the input. An inverse problem solution approach based on a linear and a novel cubic spline shape function provides the preliminary estimations of the bridge's displacement and acceleration responses, respectively. Since the inverse solution approach is only capable of determining the response signal of the nodes with high accuracy in the vicinity of the vehicle axles, a new moving-window signal prediction method based on auto-regressive with exogenous time series models (ARX) is proposed to complete the responses in the regions with large errors (invalid regions). The mode shapes and natural frequencies of the bridge are identified using a novel approach that integrates the results of singular value decomposition (SVD) on the predicted displacement responses and frequency domain decomposition (FDD) on the predicted acceleration responses. To evaluate the proposed framework, various numerical but realistic models for a single-span bridge under the effect of a moving mass are considered; the effects of different levels of ambient noise, the number of axles of the passing vehicle, and the effect of its speed on the accuracy of the method are investigated. The results show that the proposed method can identify the characteristics of the three main modes of the bridge with high accuracy.

Surface Defect Detection of Hot Rolled Steel Based on Attention Mechanism and Dilated Convolution for Industrial Robots

In the manufacturing process of industrial robots, the defect detection of raw materials includes two types of tasks, which makes the defect detection guarantee its accuracy. It also makes the defect detection task challenging in practical work. In analyzing the disadvantages of the existing defect detection task methods, such as low precision and low generalization ability, a detection method on the basis of attention mechanism and dilated convolution module is proposed. In order to effectively extract features, a two-stage detection framework is chosen by applying Resnet50 as the pre-training network of our model. With this foundation, the attention mechanism and dilated convolution are utilized. With the attention mechanism, the network can focus on the features of effective regions and suppress the invalid regions during detection. With dilated convolution, the receptive field of the model can be increased without increasing the calculation amount of the model. As a result, it can achieve a larger receptive field, which will obtain more dense data and improve the detection effect of small target defects. Finally, great experiments are conducted on the NEU-DET dataset. Compared with the baseline network, the proposed method in this paper achieves 81.79% mAP, which are better results.

Multi-point attention-based semi-supervised learning for diabetic retinopathy classification

In recent years, the severity classification of some well-known diseases has gradually become a focus of researchers, especially diabetic retinopathy (DR) recognition caused by diabetes. Existing diagnostic methods usually require many annotated fundus images for training. However, in practical situations, the high time and economic cost of annotating images make it unaffordable for many researchers. In this paper, we design a semi-supervised learning framework to explore the associations between unlabeled data, with the help of a small number of labeled samples, for accurate fundus image classification of DR. Through the analysis of semi-supervised tasks, it can be observed that: (1) an attention mechanism that fits the data can improve the network’s potential to extract critical features; (2) unlabeled data is as potentially valuable as labeled ones, and the association between these unknown samples can further improve the model’s performance. Therefore, we propose a Multi-point Attention-based Semi-supervised Learning (MASL) framework that efficiently utilizes the massive unlabeled data for accurate DR classification. Specifically, we propose a multi-point attention mechanism that enables the model to extract subtle features from multiple perspectives of fundus images and discard invalid regions. In addition, we design a new self-supervision mechanism to force the model to perform mandatory similarity mining on unknown samples, maximizing the potential of squeezing unlabeled data based on the confidence of the selected unannotated samples. Sufficient experimental results demonstrate that our MASL method significantly outperforms other methods on two public datasets.

An Efficient YOLO Algorithm with an Attention Mechanism for Vision-Based Defect Inspection Deployed on FPGA.

Industry 4.0 features intelligent manufacturing. Among them, the vision-based defect inspection algorithm is remarkable for quality control in parts manufacturing. With the help of AI and machine learning, auto-adaptive instead of manual operation is achievable in this field, and much progress has been made in recent years. In this study, considering the demand of inspection features in industrialization, we made further improvement in smart defect inspection. An efficient algorithm using Field Programmable Gate Array (FPGA)-accelerated You Only Look Once (YOLO) v3 based on an attention mechanism is proposed. First, because of the relatively fixed camera angle and defect features, an attention mechanism based on the concept of directing the focus of defect inspection is proposed. The attention mechanism consists of three improvements: (a) image preprocessing, which is to tailor images for selectively concentrating on the defect relevant things. Image preprocessing mainly includes cutting, zooming and splicing, named CZS operations. (b) Tailoring the YOLOv3 backbone network, which is to ignore invalid inspection regions in deep neural networks and optimize the network structure. (c) Data augmentation. First, two improvements can be made to efficiently reduce deep learning operations and accelerate the inspection speed, but the preprocessed images are similar and the lack of diversity will reduce network accuracy. So, (c) is added to mitigate the lack of considerable amounts of training data. Second, the algorithm is deployed on a PYNQ-Z2 FPGA board to meet the industrialization production requirements for accuracy, efficiency and extensibility. FPGA can provide a low-latency, low-cost, high-power-efficiency and flexible architecture that enables deep learning acceleration for industrial scenarios. A Xilinx Deep Neural Network Development Kit (DNNDK) converted the improved YOLOv3 to Programmable Logic (PL), which can be deployed on FPGA. The conversion process mainly consists of pruning, quantization and compilation. Experimental results showed that the algorithm had high efficiency, inspection accuracy reached 99.2%, processing speed reached 1.54 Frames per Second (FPS), and power consumption was only 10 W.

Optimising sampling designs for habitat fragmentation studies

Abstract Habitat fragmentation has become one of the largest areas of research in conservation biology. Empirical studies into habitat fragmentation impacts typically measure ecological responses to metrics describing fragmentation processes, for example ‘distance to the nearest forest edge’, ‘forest fragment area’ and ‘landscape habitat amount’. However, these studies often fail to sample across representative ranges of fragmentation metrics characterising the study region. They therefore lack the data to account for correlation among multiple fragmentation metrics and for spatial autocorrelation among sample sites, which reduces the strength of derived predictive models. Here, we draw on approaches used in the mining and soil science industry to develop standardised and repeatable protocols for designing optimised sampling schemes of biodiversity in fragmented landscapes that meet three criteria: the distance between sample sites is maximised to reduce spatial autocorrelation, the full range of values of the metrics of interest are sampled and the confounding effects of correlated metrics are minimised. We show that our computational methods can optimise the placement of sample sites in fragmented landscapes to minimise, and in some cases to entirely avoid, over‐ or under‐sampling of fragmentation metrics. Our method is flexible enough to cater for any continuous (e.g. maps of percentage tree cover) or categorical (e.g. habitat and land use types) fragmentation metric, and to simultaneously handle combinations of multiple fragmentation metrics and habitat types. We implement our methods as open‐source code which includes options to mask invalid or inaccessible regions, update designs to adapt to unforeseen constraints in the field and suggest optimal numbers of sample sites for given design criteria. Using a case study landscape, we demonstrate how the approach improves on manually generated sampling designs. We also show that the methods are flexible enough to be applied to landscape studies beyond the field of habitat fragmentation. We introduce our package as a novel research tool that is able to streamline the experimental design process for biodiversity sampling and monitoring at landscape scales, leading to improved data quality and representativeness.

Hierarchical Scheme for Vehicle Make and Model Recognition

A vehicle make and model recognition (VMMR) system is a common requirement in the field of intelligent transportation systems (ITS). However, it is a challenging task because of the subtle differences between vehicle categories. In this paper, we propose a hierarchical scheme for VMMR. Specifically, the scheme consists of (1) a feature extraction framework called weighted mask hierarchical bilinear pooling (WMHBP) based on hierarchical bilinear pooling (HBP) which weakens the influence of invalid background regions by generating a weighted mask while extracting features from discriminative regions to form a more robust feature descriptor; (2) a hierarchical loss function that can learn the appearance differences between vehicle brands, and enhance vehicle recognition accuracy; (3) collection of vehicle images from the Internet and classification of images with hierarchical labels to augment data for solving the problem of insufficient data and low picture resolution and improving the model’s generalization ability and robustness. We evaluate the proposed framework for accuracy and real-time performance and the experiment results indicate a recognition accuracy of 95.1% and an FPS (frames per second) of 107 for the framework for the Stanford Cars public dataset, which demonstrates the superiority of the method and its availability for ITS.

Interactive information module for person re-identification

In person re-identification (Re-ID) task, multi-branch networks acquire better performance by combining global features and local features. Obviously, local branch can obtain detailed information of person pictures but may work on invalid regions when person pictures have imprecise bounding boxes. On the contrary, global branch can be aware of the position of person but hard to acquire detailed information of person pictures. Meanwhile, lots of multi-branch networks ignore mutual information among different branches. Therefore, it is necessary to enhance interaction of global branch and local branch. For this purpose, we propose Interactive Information Module (IIM). IIM includes two components named Global-map Attention Module (GAM) and Labeled-class Mutual Learning (LML), respectively. GAM leverages heatmaps generated by global branch to guide calculation of local attention and obtains a composite global feature by combining local features. GAM relys more on the performance of global branch which decides the quality of heatmaps. To improve performance of global branch, we propose LML to promote convergent rate of global branch. Extensive experiments implemented on Market-1501, DukeMTMC-ReID, and CUHK03-NP datasets confirm that our method achieves state-of-the-art results.

A comparison of n-ary simple code and n-ary gray code phase unwrapping in high-speed fringe projection profilometry

Binary defocusing technique has been widely used in fringe projection profilometry for high-speed measurement. This technique projects designed binary patterns with a defocused projector to generate fringes for wrapped phase calculation, and n-ary simple codes (nSC) or n-ary gray codes (nGC) for phase unwrapping. The unwrapped phase reflecting the object surface profile is calculated by a phase-shifting algorithm with nSC/nGC phase unwrapping. However, it remains unclear which phase unwrapping method, nSC or nGC, is more appropriate for high-accuracy and high-speed measurement. This paper comprehensively compares nSC and nGC with the consideration of various factors, including the strategies for error removal, the base n, the step heights and invalid regions on the measured objects, defocusing level and noise level of the system. From simulations and experiments, we conclude that, (i) in general, nSC with a proposed identification and binary classification (IBC) method has a similar result as nGC; (ii) when accuracy is critical, binary simple code (nSC with n = 2) and binary gray code (nGC with n = 2) methods are recommended; (iii) when speed is critical, quaternary simple code (nSC with n = 4) method with continuity/geometry constraints is recommended.

An Invalid Cloud Region Masking Method for Remote Sensing Image Compression

An invalid cloud region masking method based on local edge context is proposed for the compression of remote sensing images. Through analyzing the characteristics of various compression algorithms and taking the local edge information of the cloud region into account, the decompression quality is improved. First, according to the cloud mask information, labeling the connected cloud region, second, performing region growth on the labeled mask image, then differing the two mask images to obtain the local edge context, and finally different invalid cloud regions are filled with the average of the respective local edge context pixels. Using the image testing set generated from QuickBird and OrbView images, our method’s impact on six common remote sensing image compression algorithms is analyzed experimentally. The experimental results show that our masking method can improve the decompressed image quality when the compression ratio is certain. When the image quality is fixed, it can further reduce the compressed bitrate. For onboard application, our masking method can increase the onboard imaging time of the satellites, and eventually improve the onboard specifications of remote sensing satellites.

Deep Residual Network With Adaptive Learning Framework for Fingerprint Liveness Detection

Today, fingerprint recognition technology has aroused wide attention in the society, especially in the application of identity authentication with a smartphone as a carrier. However, the disadvantage of these devices is that the identification sensors are vulnerable to spoofing attacks from artificial replicas made from clay, gelatin, silicon, etc. To resolve it, a feasible anti-deception countermeasure, called fingerprint liveness detection (FLD), has been proposed. Different from most shallow feature methods, the deep convolutional neural network (DCNN)-based FLD methods have been widely explored with the properties of fast operation, few parameters, and end-to-end feature self-learning. Meanwhile, DCNN faces a pair of contradictory problems, on the one hand, the training accuracy will keep rising with the increasement of multilayer perceptron (MLP), finally tends to a stable value. Continue to increase the number of MLP, results will decline. Much research, on the other hand, shows that the number of MLP is the foundation for realizing a high performance detection. Hereby, we apply deep residual network (DRN) to FLD for the first time to solve the contradiction mentioned in this paper. Next, to eliminate the interference of invalid regions of given images, a region-of-interest (ROI) extraction algorithm is put forward. Afterward, to avoid the parameters learned plunging into local optimization, adaptive learning-based DRNs (ALDRNs), which automatically adjust the learning rate if those monitoring parameters (verification accuracy) are stable, are explored. Finally, we propose a novel texture enhancement based on the local gradient pattern (LGP) method to improve the generalization of a model classifier as well. Experimental results on three benchmark data sets: LivDet 2011, 2013, and 2015, show that our results outperform the state-of-the-art FLD methods.

Plug-and-Play Based Optimization Algorithm for New Crime Density Estimation

Different from a general density estimation, the crime density estimation usually has one important factor: the geographical constraint. In this paper, a new crime density estimation model is formulated, in which the regions where crime is impossible to happen, such as mountains and lakes, are excluded. To further optimize the estimation method, a learning-based algorithm, named Plug-and-Play, is implanted into the augmented Lagrangian scheme, which involves an off-the-shelf filtering operator. Different selections of the filtering operator make the algorithm correspond to several classical estimation models. Therefore, the proposed Plug-and-Play optimization based estimation algorithm can be regarded as the extended version and general form of several classical methods. In the experiment part, synthetic examples with different invalid regions and samples of various distributions are first tested. Then under complex geographic constraints, we apply the proposed method with a real crime dataset to recover the density estimation. The state-of-the-art results show the feasibility of the proposed model.

A sensor node scheduling algorithm for heterogeneous wireless sensor networks

To improve the regional coverage rate and network lifetime of heterogeneous wireless sensor networks, a sensor node scheduling algorithm for heterogeneous wireless sensor networks is proposed. In sensor node scheduling algorithm, heterogeneous perception radius of sensor node is considered. Incomplete coverage constraint and arc coverage interval are analyzed. Regional coverage increment optimization model, arc coverage increment optimization model, and residual energy optimization model are proposed. Multi-objective scheduling model is established using weight factors and integrated function. Furthermore, the heuristic method is proposed to solve the multi-objective optimization model, and scheduling scheme of heterogeneous sensor nodes is obtained. When the network is in operation for a period of time, some sensor nodes are invalid and relevant regions are uncovered. The repair method is proposed to wake up sleep sensor nodes and repair the coverage blind area. The simulation results show that if keeping the same regional coverage rate, sensor node scheduling algorithm improves network lifetime, increases number of living sensor nodes, and keeps average node energy consumption at a low level. Under certain conditions, sensor node scheduling algorithm outperforms DGREEDY, two-tiered scheduling, and minimum connected cover.

Edge-Preserving Stereo Matching Using Minimum Spanning Tree

Despite that the accuracy and efficiency of stereo matching technology have significantly improved in the past decades, the issue of edge-blurring remains a challenge to most of the existing approaches. In this paper, we propose a minimum spanning tree (MST) based stereo matching method by using the image edge and segmentation optimization to preserve the image boundary. We first exploit a fast disparity range estimation method by combining the Surf and Akaze feature points to improve the computational efficiency. Second, we utilize the image edges and brightness information to generate a self-adaptive weight function, which is able to significantly improve the accuracy of MST aggregating in the regions of complex texture and boundaries with similar color distribution. Third, we employ the image segmentation to extract the invalid regions of the estimated disparity map, and propose a post-processing scheme to refine the disparity result. Finally, we run our method on several Middlebury and KITTI datasets. The comparison results between our method and other state-of-the-art approaches demonstrate that the proposed method has high accuracy for disparity computation and is especially robust to the edge-blurring.

RETRACTED ARTICLE: A method for spectral image registration based on feature maximum submatrix

In order to solve the geometric offset caused by replacing the filter during imaging of multichannel spectral image data, a multichannel spectral image registration method based on SURF feature merged with maximum submatrix is proposed. Firstly, the feature of multichannel spectral image is extracted by SURF. Then, a perspective transformation is performed to obtain a preliminary registration image. For the problem of invalid areas with zero pixel values appearing at the boundary of the image after registration, the largest submatrix is used to detect the maximum inscribed rectangle of the image to remove the invalid boundary region, and maximize the reserved effective region information. Experimented was processed with multichannel imaging data of murals. Experimental results agree with the theoretic analysis and verified that the proposed registration method is better adapted to image scale and brightness changing. At the same time, it can avoid the influence of invalid regions generated by other registration methods on subsequent spectral reconstruction and color restoration which has better performance.