Inaccurate Localization Research Articles

Flood zoning and developing strategies to increase resilience against floods with a crisis management approach

Assessment and planning of crisis management with the approach to natural flood disasters include many factors. In this regard, one of the basic principles of crisis management is based on the resilience of urban infrastructure against floods. This study developed strategies to increase resilience by flood zoning and crisis management. The investigation of the current situation shows that despite the efforts being made, the climatic and environmental conditions of the rivers, the settlements of the infiltration basin, the constructions, and the location inaccuracy of the following structures indicate many challenges in managing the current situation in various components of crisis management. In this regard, the main direction of this article is to evaluate the urban resilience of the Khuzestan region against floods based on a crisis management approach and technique for order preference by similarity to ideal solution (TOPSIS) and Fuzzy weighting methods using geographic information system (GIS).

Arbitrary-Oriented Ship Detection Method Based on Long-Edge Decomposition Rotated Bounding Box Encoding in SAR Images

Due to the limitations of the horizontal bounding boxes for locating the oriented ship targets in synthetic aperture radar (SAR) images, the rotated bounding box (RBB) has received wider attention in recent years. First, the existing RBB encodings suffer from boundary discontinuity problems, which interfere with the convergence of the model, and then lead to some problems, such as the inaccurate location of the ship targets in the boundary state. Thus, from the perspective that the long-edge features of the ships are more representative of their orientation, the long-edge decomposition RBB encoding has been proposed in this paper, which can avoid the boundary discontinuity problem. Second, the problem of the positive and negative samples imbalance is serious for the SAR ship images because only a few ship targets exist in the vast background of these images. Since the ship targets of different sizes are subject to varying degrees of interference caused by this problem, a multiscale elliptical Gaussian sample balancing strategy has been proposed in this paper, which can mitigate the impact of this problem by labeling the loss weights of the negative samples within the target foreground area with multiscale elliptical Gaussian kernels. Finally, experiments based on the CenterNet model were implemented on the benchmark SAR image dataset SSDD (SAR ship detection dataset). The experimental results demonstrate that our proposed long-edge decomposition RBB encoding outperforms other conventional RBB encodings in the task of oriented ship detection in SAR images. In addition, our proposed multiscale elliptical Gaussian sample balancing strategy is effective and can improve the model performance.

Intelligent Wearable Wrist Pulse Detection System Based on Piezoelectric Sensor Array

The human radial artery pulse carries a rich array of biomedical information. Accurate detection of pulse signal waveform and the identification of the corresponding pulse condition are helpful in understanding the health status of the human body. In the process of pulse detection, there are some problems, such as inaccurate location of radial artery key points, poor signal noise reduction effect and low accuracy of pulse recognition. In this system, the pulse signal waveform is collected by the main control circuit and the new piezoelectric sensor array combined with the wearable wristband, creating the hardware circuit. The key points of radial artery are located by an adaptive pulse finding algorithm. The pulse signal is denoised by wavelet transform, iterative sliding window and prediction reconstruction algorithm. The slippery pulse and the normal pulse are recognized by feature extraction and classification algorithm, so as to analyze the health status of the human body. The system has accurate pulse positioning, good noise reduction effect, and the accuracy of intelligent analysis is up to 98.4%, which can meet the needs of family health care.

Robustness of imageless electrocardiographic imaging against uncertainty in atrial morphology and location

IntroductionElectrocardiographic Imaging is a non-invasive technique that requires cardiac Imaging for the reconstruction of cardiac electrical activity. In this study, we explored imageless ECGI by quantifying the errors of using heart meshes with either an inaccurate location inside the thorax or an inaccurate geometry. MethodsMultiple‑lead body surface recordings of 25 atrial fibrillation (AF) patients were recorded. Cardiac atrial meshes were obtained by segmentation of medical images obtained for each patient. ECGI was computed with each patient's segmented atrial mesh and compared with the ECGI obtained under errors in the atrial mesh used for ECGI estimation. We modeled both the uncertainty in the location of the atria inside the thorax by artificially translating the atria inside the thorax and the geometry of the atrial mesh by using an atrial mesh in a reference database. ECGI signals obtained with the actual meshes and the translated or estimated meshes were compared in terms of their correlation coefficients, relative difference measurement star, and errors in the dominant frequency (DF) estimation in epicardial nodes. ResultsCC between ECGI signals obtained after translating the actual atrial meshes from the original position by 1 cm was above 0.97. CC between ECGIs obtained with patient specific atrial geometry and estimated atrial geometries was 0.93 ± 0.11. Mean errors in DF estimation using an estimated atrial mesh were 7.6 ± 5.9%. ConclusionImageless ECGI can provide a robust estimation of cardiac electrophysiological parameters such as activation rates even during complex arrhythmias. Furthermore, it can allow more widespread use of ECGI in clinical practice.

A Novel Detection Method for Pavement Crack with Encoder-Decoder Architecture

As a current popular method, intelligent detection of cracks is of great significance to road safety, so deep learning has gradually attracted attention in the field of crack image detection. The nonlinear structure, low contrast and discontinuity of cracks bring great challenges to existing crack detection methods based on deep learning. Therefore, an end-to-end deep convolutional neural network (AttentionCrack) is proposed for automatic crack detection to overcome the inaccuracy of boundary location between crack and non-crack pixels. The AttentionCrack network is built on U-Net based encoder-decoder architecture, and an attention mechanism is incorporated into the multi-scale convolutional feature to enhance the recognition of crack region. Additionally, a dilated convolution module is introduced in the encoder-decoder architecture to reduce the loss of crack detail due to the pooling operation in the encoder network. Furthermore, since up-sampling will lead to the loss of crack boundary information in the decoder network, a depthwise separable residual module is proposed to capture the boundary information of pavement crack. The AttentionCrack net on public pavement crack image datasets named CrackSegNet and Crack500 is trained and tested, the results demonstrate that the AttentionCrack achieves <i>F1</i> score over 0.70 on the CrackSegNet and 0.71 on the Crack500 in average and outperforms the current state-of-the-art methods.

ViTALnet: Anomaly on Industrial Textured Surfaces With Hybrid Transformer

The coexistence of subtle and long-range anomalies in real-world industrial applications brings significant challenges for anomaly localization. Existing methods typically train deep models by utilizing the multi-level patches or layers-fusion approaches for learning the global-local distribution. However, these methods do not consider learning local and global features simultaneously, which suffer from inaccurate localization results. To this end, a hybrid transformer model (ViTALnet) is proposed here, which is established based on fine-grained feature reconstruction. Our ViTALnet first adopts the vision transformer to extract local discriminatory features as feature representation, which leverages the global semantic capturing capability. Then, an anomaly estimation module is proposed by integrating global attention and a pyramidal architecture to enhance contextual information for fine-grain anomaly localization. The experiments were extensively conducted on industrial anomaly localization datasets MVTec AD-Texture, NanoTWICE, and general textured datasets KolektorSDD2, MT Defect, and Dot-patterned Fabric, where our proposed ViTALnet outperformed major state-of-the-art methods.

Crown-CAM: Interpretable Visual Explanations for Tree Crown Detection in Aerial Images

Visual explanation of “black-box” models allows researchers in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">explainable artificial intelligence</i> (XAI) to interpret the model’s decisions in a human-understandable manner. In this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">interpretable class activation mapping for tree crown detection</i> (Crown-CAM) that overcomes inaccurate localization & computational complexity of previous methods while generating reliable visual explanations for the challenging and dynamic problem of tree crown detection in aerial images. It consists of an unsupervised selection of activation maps, computation of local score maps, and non-contextual background suppression to efficiently provide fine-grain localization of tree crowns in scenarios with dense forest trees or scenes without tree crowns. Additionally, two <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Intersection over Union</i> (IoU)-based metrics are introduced to effectively quantify both the accuracy and inaccuracy of generated explanations with respect to regions with or even without tree crowns in the image. Empirical evaluations demonstrate that the proposed Crown-CAM outperforms the Score-CAM, Augmented Score-CAM, and Eigen-CAM methods by an average IoU margin of 8.7, 5.3, and 21.7 (and 3.3, 9.8, and 16.5) respectively in improving the accuracy (and decreasing inaccuracy) of visual explanations on the challenging NEON tree crown dataset.

Earring Lesion Of The Parotid Tail

Masses in the Parotid tail can be source of consternation to radiologist and clinicians and therefore need attention. Inaccurate localization may lead to significant iatrogenic complications. Anatomically localization lesions of Parotid tails is of relevance as it often creates radiological confusion, as was in this case also. Imaging features of Parotid tail involvement need to be reviewed for, proper understanding and discussed with radiologist for complication free management. A Clinico-radiological correlation reviewing 111 such cases was found which described pleomorphic adenoma(15) , Warthins tumor (14) , infective pathologies, Sjogren disease and also malignant lesions in 27 cases. The notable radiological findings in the cases where enhancement, multiplicity of lesions, on CT and diffusion weighted (varied) signal intensity of MR changes. Relationship of parotid tail/ lesions with surrounding structures like facial nerve or its branches , sternocleidomastoid muscle and posterior belly of digastric muscle, proximity close to the level II LN and posterior part of submandibular salivary gland all need to clearly examined and analyzed. Such a lesion has been referred to as Earring lesions in literature. Earring lesion is best appreciated and less confusing in coronal images and equally challenging in palpation. Though rare, localizing anatomical features of parotid tail lesions are reviewed in this paper along with a case report of parotid tail tumor.

TextDC: Exploring Multidimensional Text Detection via a New Benchmark and Solution

Text detection has been significantly boosted by the development of deep neural networks but most existing methods focus on a single kind of text instance (i.e., overlaid text, layered text, scene text). In this paper, we expand the text detection task from a single dimension to multiple dimensions, thus providing multi-type text descriptions for the scene and content analysis of videos. Specifically, we establish a new task to detect and classify text instances simultaneously, termed TextDC. As far as we know, existing benchmarks cannot meet the requirements of the proposed task. To this end, we collect a large-scale text detection and classification dataset, named Text3C, which is annotated using multilingual labels, location information, and text categories. Together with the collected dataset, we introduce a multi-stage and strict evaluation metric, which penalizes detection approaches for missing text instances, false positive detection, inaccurate location boxes, and error text categories, developing a new benchmark for the proposed TextDC task. In addition, we extend several state-of-the-art detectors by modifying the prediction head to solve the new task. Then, a generalized text detection and classification framework is designed and formulated. Extensive experiments using the updated methods are conducted on the established benchmark to verify the solvability of the proposed task, the challenges of the dataset, and the effectiveness of the solution.

Detection of Water Changes in Plant Stems In Situ by the Primary Echo of Ultrasound RF with an Improved AIC Algorithm

The detection of water changes in plant stems by non-destructive online methods has become a hot spot in studying the physiological activity of plant water. In this paper, the ultrasonic radio-frequency echo (RFID) technique was used to detect water changes in stems. An algorithm (improved hybrid differential Akaike's Information Criterion (AIC)) was proposed to automatically compute the position of the primary ultrasonic echo of stems, which is the key parameter of water changes in stems. This method overcame the inaccurate location of the primary echo, which was caused by the anisotropic ultrasound propagation and heterogeneous stems. First of all, the improved algorithm was analyzed and its accuracy was verified by a set of simulated signals. Then, a set of cutting samples from stems were taken for ultrasonic detection in the process of water absorption. The correlation between the moisture content of stems and ultrasonic velocities was computed with the algorithm. It was found that the average correlation coefficient of the two parameters reached about 0.98. Finally, living sunflowers with different soil moistures were subjected to ultrasonic detection from 9:00 to 18:00 in situ. The results showed that the soil moisture and the primary ultrasonic echo position had a positive correlation, especially from 12:00 to 18:00; the average coefficient was 0.92. Meanwhile, our results showed that the ultrasonic detection of sunflower stems with different soil moistures was significantly distinct. Therefore, the improved AIC algorithm provided a method to effectively compute the primary echo position of limbs to help detect water changes in stems in situ.

MobileDenseNet: A new approach to object detection on mobile devices

Object detection problem-solving has witnessed vast developments in the past few years. There is a need for lighter models in cases where hardware limitations exist, together with a demand for models to be designed to run on mobile devices. This paper assesses methods used for algorithms which are created to address these issues. The main goal of this article is to improve accuracy in state-of-the-art algorithms while maintaining speed and real-time efficiency. Small objects and inaccurate localization are the main issues in one-stage object detection. To resolve these issues, in this paper, a new network entitled “MobileDenseNet” was created, which is suitable for embedded systems. We also developed a light neck, called “FCPNLite” for mobile devices, which facilitates the detection of small objects. Our research suggests that necks in embedded systems have been sporadically mentioned by the existing studies. The novelty of our network lies in the use of concatenation features. A small yet significant change to the head of the network improved accuracy without increasing speed or limiting parameters. Overall, the accuracy of our method on the challenging CoCo and Pascal VOC datasets were 24.8 and 76.8 percentage, respectively. This has been by far the highest rate recorded by other state-of-the-art systems. Our network has the capability to increase accuracy while maintaining real-time efficiency in mobile devices. We calculated the operating speed on Pixel 3 (Snapdragon 845) at 22.8 fps. The source code of this research is available on https://github.com/hajizadeh/MobileDenseNet.

Multi-Defect Detection in Additively Manufactured Lattice Structures Using 3D Electrical Resistance Tomography

Cellular lattice structures possess high strength-to-weight ratios suitable for advanced lightweight engineering applications. However, their quality and mechanical performance can degrade because of defects introduced during manufacturing or in-service. Their complexity and small length scale features make defects difficult to detect using conventional nondestructive evaluation methods. Here we propose a current injection-based method, electrical resistance tomography (ERT), that can be used to detect damaged struts in conductive cellular lattice structures with their intrinsic electromechanical properties. The reconstructed conductivity distributions from ERT can reveal the severity and location of damaged struts without having to probe each strut. However, the low central sensitivity of ERT may result in image artifacts and inaccurate localization of damaged struts. To address this issue, this study introduces an absolute, high throughput, conductivity reconstruction algorithm for 3D ERT. The algorithm incorporates a strut-based normalized sensitivity map to compensate for lower interior sensitivity and suppresses reconstruction artifacts. Numerical simulations and experiments on fabricated representative cellular lattice structures were performed to verify the ability of ERT to quantitatively identify single and multiple damaged struts. The improved performance of this method compared with classical ERT was observed, based on greatly decreased imaging and reconstructed value errors.

Broaden Horizons: The Advancement of Interstitial Cystitis/Bladder Pain Syndrome.

Interstitial cystitis/bladder pain syndrome (IC/BPS) is a debilitating disease that induces mental stress, lower urinary symptoms, and pelvic pain, therefore resulting in a decline in quality of life. The present diagnoses and treatments still lead to unsatisfactory outcomes, and novel diagnostic and therapeutic modalities are needed. Although our understanding of the etiology and pathophysiology of IC/BPS is growing, the altered permeability of the impaired urothelium, the sensitized nerves on the bladder wall, and the chronic or intermittent sensory pain with inaccurate location, as well as pathologic angiogenesis, fibrosis, and Hunner lesions, all act as barriers to better diagnoses and treatments. This study aimed to summarize the comprehensive information on IC/BPS research, thereby promoting the progress of IC/BPS in the aspects of diagnosis, treatment, and prognosis. According to diverse international guidelines, the etiology of IC/BPS is associated with multiple factors, while the presence of Hunner lesions could largely distinguish the pathology, diagnosis, and treatment of non-Hunner lesions in IC/BPS patients. On the basis of the diagnosis of exclusion, the diverse present diagnostic and therapeutic procedures are undergoing a transition from a single approach to multimodal strategies targeting different potential phenotypes recommended by different guidelines. Investigations into the mechanisms involved in urinary symptoms, pain sensation, and bladder fibrosis indicate the pathophysiology of IC/BPS for further potential strategies, both in diagnosis and treatment. An overview of IC/BPS in terms of epidemiology, etiology, pathology, diagnosis, treatment, and fundamental research is provided with the latest evidence. On the basis of shared decision-making, a multimodal strategy of diagnosis and treatment targeting potential phenotypes for individual patients with IC/BPS would be of great benefit for the entire process of management. The complexity and emerging evidence on IC/BPS elicit more relevant studies and research and could optimize the management of IC/BPS patients.

A boundary-preserving conditional convolution network for instance segmentation

Single-stage instance segmentation approaches have been attracting increasing attention in research communities because of faster speed, more straightforward design, and competitive accuracy than two-stage methods. However, the currently available methods only generate pixel-level classification , which ignores the information of shapes and object boundaries and thus results in wild and fuzzy mask predictions and inaccurate localization . To address these issues, we propose BCondInst, an effective boundary-preserving conditional convolution network aiming at adopting object boundary information to improve the accuracy of mask localization. Specifically, BCondInst replaces the original mask branch with a boundary-mask branch containing two sub-networks designed to jointly learn object boundaries and masks. Different from the existing segmentation approaches, in which the parameters of filters in the boundary head remain unchanged for all instances, the filters in the mask’s head and boundary’s head in BCondInst are created according to specific instances. Furthermore, we design a post-processing mechanism that adopts the predicted boundaries to further improve the quality of predicted masks in the testing phase. Consequently, masks predicted by BCondInst generally preserve more details and more accurate boundaries. Extensive experimental results on Microsoft COCO 2017 benchmark indicate that the performance of the proposed BCondInst exceeds the current popular one-stage instance segmentation approaches by a large margin.

Target Detection Network for Underwater Image Based on Adaptive Anchor Frame and Re-parameterization

For low target detection rate and inaccurate localization of most target detection networks in special underwater environments, we propose an underwater target detection algorithm with adaptive anchor frames. The adaptive anchor frame selection strategy differs from the traditional methods of manually designing anchor frames and obtaining anchor frames using the K-means clustering algorithm. Our method is based on the K-means clustering algorithm and consists of a grouping strategy and a dynamic K-value strategy. It can also automatically calculate the appropriate numbers of anchor boxes and layers of network output based on the characteristics of label data. And performance of the network is guaranteed while avoiding the computation caused by redundant structures. The simple but powerful RepVGG classification network is used as the backbone network. Therefore, the feature extraction capability of the network is enhanced and the detection performance of the network on fuzzy targets is improved. The experimental results show that the algorithm in this paper achieves better detection results in the underwater target detection task compared to other algorithms.

Improving Map Matching of Floating Car Data with Artificial Intelligence Techniques

Map matching is a crucial data processing task for transferring measurements from the dynamic sensor location to the relevant road segment. It is especially important when estimating road network speed by using probe vehicles (floating car data) as speed measurement sensors. Most common approaches rely on finding the closet road segment, but road network geometry (e.g., dense areas, two-way streets, and superposition of road segments due to different heights) and inaccuracy in the GNSS location (up to decades of meters in urban areas) can wrongly allocate up to 30% of the measurements. More advanced methods rely on taking the topology of the network into account, significantly improving the accuracy at a higher computational cost, especially when the accuracy of the GNSS location is low. In order to both improve the accuracy of the “closet road segment” methods and reduce the processing time of the topology-based methods, the data can be pre-processed using AI techniques to reduce noise created by the inaccuracy of the GNSS location and improve the overall accuracy of the map-matching task. This paper applies AI to correct GNSS locations and improve the map-matching results, achieving a matching accuracy of 76%. The proposed methodology is demonstrated to the floating car data generated by a fleet of 1200 taxi vehicles in Thessaloniki used to estimate road network speed in real time for information services and for supporting traffic management in the city.

Mobile Anchor and Kalman Filter Boosted Bounding Box for Localization in Wireless Sensor Networks

Event detection is usually the primary purpose of wireless sensor networks (WSNs). Therefore, it is crucial to determine where and when an event occurs in order to map the event to its spatio-temporal domain. In WSN localization, a few anchor nodes are those aware of their locations via the Global Positioning System (GPS), which is energy-consuming. Non-anchor nodes self-localize by gathering information from anchor nodes to estimate their positions using a localization technique. Traditional algorithms use at least three static anchors for the localization process. Recently, researchers opted to replace multiple static anchors by a single mobile anchor during the localization process. This paper proposes a Kalman filter based on bounding box localization algorithm (KF-BBLA) in WSNs with mobile anchor node. We present a new mobile anchor localization strategy to minimize energy, hardware costs, and computation complexity, while improving accuracy and cost-effectiveness. Network connectivity measurement and the bounding box localization method are used in order to identify the bounded possible localization zone. The Kalman filter is then used to minimize the uncertainty produced by the connectivity process. We aim also to minimize the localization inaccuracies generated by the bounding box algorithm. Simulation results show that our proposed approach significantly reduces the localization error compared to other localization algorithms chosen from the recent literature by up to 20%. We use the cumulative distribution function (CDF) as an indicator to assess the accuracy of our proposed algorithm.

Predicting to Improve: Integrity Measures for Assessing Visual Localization Performance

Visual Place Recognition (VPR) is a key component of many robot localization and mapping system processing pipelines, providing loop closure and coarse topological localization priors for pose refinement stages. When deploying these systems in the real-world, system self-characterization of when it is performing well or poorly can be more important than absolute performance. In this research, we demonstrate a new supervised learning approach to predicting localization integrity on a frame-by-frame basis along a route, using artefacts from the localization technique itself. Our method involves a lightweight post-processing step that is VPR technique-agnostic; it can be calibrated for any given place recognition technique, such that inaccurate localization points along a route can be identified and discarded. Unlike the normal parameter sweeping evaluation of a VPR system, which directly trades precision for recall, when deployed on a baseline VPR system our approach improves the precision without significantly reducing recall, resulting in improved average localization performance. Over twelve combinations of varied datasets and VPR techniques, we demonstrate our approach is able to predict localization errors with an average precision of 74%, resulting in an improvement in mean localization accuracy.

Efficient Video Grounding With Which-Where Reading Comprehension

Video grounding aims at localizing the temporal moment related to the given language description, which is very helpful to many cross-modal content understanding applications like visual question answering and sentence-video search. Existing approaches usually directly regress the temporal boundaries of an event described by a query sentence in the video sequence. This direct regression manner often encounters a large decision space due to diverse target events and variable video durations, leading to inaccurate localization as well as inefficient grounding. This paper presents an efficient framework termed from which to where to facilitate video grounding. The core idea is imitating the reading comprehension process to gradually narrow the decision space, in what we decompose the direct regression into two steps. The “which” step first roughly selects a candidate area by evaluating which video segment in the predefined set is closest to the ground truth. To this end, we formulate this step into a multi-choice reading comprehension problem and propose a criterion to select the best-matched segment. In this way, the excessive decision space is effectively reduced. The “where” step aims to precisely regress the temporal boundary of the selected video segment from the shrunk decision space. We thus introduce a triple-span representation for each candidate video segment to use the regional context for better boundary regression. The “which” and “where” steps can be combined into a unified framework and learned end-to-end, leading to an efficient video grounding system. Extensive experiments on Charades-STA, ActivityNet-Captions, and TACoS benchmarks clearly demonstrate the effectiveness of our framework.

Feature-Based Generalized Gaussian Distribution Method for NLoS Detection in Ultra-Wideband (UWB) Indoor Positioning System

Non-Line-of-Sight (NLoS) propagation condition is a crucial factor affecting the precision of the localization in the Ultra-Wideband (UWB) Indoor Positioning System (IPS). Numerous supervised Machine Learning (ML) approaches have been applied for NLoS identification to improve the accuracy of the IPS. However, it is difficult for existing ML approaches to maintain a high classification accuracy when the database contains a small number of NLoS signals and a large number of Line-of-Sight (LoS) signals. The inaccurate localization of the target node caused by this small number of NLoS signals can still be problematic. To solve this issue, we propose feature-based Gaussian Distribution (GD) and Generalized Gaussian Distribution (GGD) NLoS detection algorithms. By employing our detection algorithm for the imbalanced dataset, a classification accuracy of $96.7\%$ and $98.0\%$ can be achieved. We also compared the proposed algorithm with the existing cutting-edge such as Support-Vector-Machine (SVM), Decision Tree (DT), Naive Bayes (NB), and Neural Network (NN), which can achieve an accuracy of $92.6\%$, $92.8\%$, $93.2\%$, and $95.5\%$, respectively. The results demonstrate that the GGD algorithm can achieve high classification accuracy with the imbalanced dataset. Finally, the proposed algorithm can also achieve a higher classification accuracy for different ratios of LoS and NLoS signals which proves the robustness and effectiveness of the proposed method.