Imprecise Localization Research Articles

Multi-sample joint localization method for intrusion sources around underground pipelines based on cross-correlation convolutional neural networks

Improving the safety monitoring of underground pipelines is crucial for maintaining the structural integrity of critical infrastructure systems. This study introduces an innovative multi-sample joint localization method (MSJLM) based on cross-correlation convolutional neural networks (CC-CNNs) to identify intrusion sources in the vicinity of underground pipelines. Traditional approaches to detecting and locating pipeline intrusions often rely on a solitary sensor monitoring point, making them susceptible to errors and limitations. Presently, widely used distributed optical fiber testing methods tend to yield imprecise localization. In contrast, the MSJLM proposed in this study harnesses data from multiple samples effectively and combines them via correlation analyses to enhance precision and reliability. The CC-CNN framework used to process the collected data is demonstrated to be highly effective in extracting spatial features and recognizing patterns.

Image convolution techniques integrated with YOLOv3 algorithm in motion object data filtering and detection.

In order to address the challenges of identifying, detecting, and tracking moving objects in video surveillance, this paper emphasizes image-based dynamic entity detection. It delves into the complexities of numerous moving objects, dense targets, and intricate backgrounds. Leveraging the You Only Look Once (YOLOv3) algorithm framework, this paper proposes improvements in image segmentation and data filtering to address these challenges. These enhancements form a novel multi-object detection algorithm based on an improved YOLOv3 framework, specifically designed for video applications. Experimental validation demonstrates the feasibility of this algorithm, with success rates exceeding 60% for videos such as "jogging", "subway", "video 1", and "video 2". Notably, the detection success rates for "jogging" and "video 1" consistently surpass 80%, indicating outstanding detection performance. Although the accuracy slightly decreases for "Bolt" and "Walking2", success rates still hover around 70%. Comparative analysis with other algorithms reveals that this method's tracking accuracy surpasses that of particle filters, Discriminative Scale Space Tracker (DSST), and Scale Adaptive Multiple Features (SAMF) algorithms, with an accuracy of 0.822. This indicates superior overall performance in target tracking. Therefore, the improved YOLOv3-based multi-object detection and tracking algorithm demonstrates robust filtering and detection capabilities in noise-resistant experiments, making it highly suitable for various detection tasks in practical applications. It can address inherent limitations such as missed detections, false positives, and imprecise localization. These improvements significantly enhance the efficiency and accuracy of target detection, providing valuable insights for researchers in the field of object detection, tracking, and recognition in video surveillance.

Open-Pit Granite Mining Area Extraction Using UAV Aerial Images and the Novel GIPNet

The ability to rapidly and accurately delineate open-pit granite mining areas is pivotal for effective production planning and environmental impact assessment. Over the years, advancements in remote sensing techniques, including the utilization of satellite imagery, LiDAR technology and unmanned aerial vehicles, have revolutionized the way mining areas are monitored and managed. Simultaneously, in the context of the open-pit mining area extraction task, deep learning-based automatic recognition is gradually replacing manual visual interpretation. Leveraging the potential of unmanned aerial vehicles (UAVs) for real-time, low-risk remote sensing, this study employs UAV-derived orthophotos for mining area extraction. Central to the proposed approach is the novel Gather–Injection–Perception (GIP) module, designed to overcome the information loss typically associated with conventional feature pyramid modules during feature fusion. The GIP module effectively enriches semantic features, addressing a crucial information limitation in existing methodologies. Furthermore, the network introduces the Boundary Perception (BP) module, uniquely tailored to tackle the challenges of blurred boundaries and imprecise localization in mining areas. This module capitalizes on attention mechanisms to accentuate critical high-frequency boundary details in the feature map and synergistically utilizes both high- and low-dimensional feature map data for deep supervised learning. The suggested method demonstrates its superiority in a series of comparative experiments on a specially assembled dataset of research area images. The results are compelling, with the proposed approach achieving 90.67% precision, 92.00% recall, 91.33% F1-score, and 84.04% IoU. These figures not only underscore the effectiveness of suggested model in enhancing the extraction of open-pit granite mining areas but also provides a new idea for the subsequent application of UAV data in the mining scene.

Aluminum Surface Defect Detection Algorithm Based on Improved YOLOv5

AbstractIndustrial defect detection is an important aspect of object detection. Aluminum is an indispensable material in the industrial field, but the complexity of surface defects on aluminum makes detection challenging. Therefore, the paper proposes the YOLOv5‐ESP algorithm based on the YOLOv5 algorithm. First, the problem of poor signal quality and small data samples is addressed through data enhancement. Second, the YOLOv5‐ESP incorporates the Efficient Channel Attention‐C3 (ECA‐C3) module in the Backbone structure to enhance attention toward defect regions. The Spatial Pooling Pyramid Cross‐Stage Partial Convolution (SPPCSPC) module is introduced to extract multi‐scale features of defects. The Poly‐scale Convolution (PSConv) is applied at the end of the Neck structure to resolve the problem of imprecise localization resulting from significant differences in the scale of defect features. Soft Non‐Maximum Suppression (Soft‐NMS) is utilized in the Head structure to optimize the prediction boxes. Experimental results show that the proposed YOLOv5‐ESP achieves a mean Average Precision (mAP) value of 94%, outperforming YOLOv5 and other classical algorithms. Furthermore, it maintains an average recognition time of 0.019 s per image, which meets the requirements of accuracy and real‐time performance in the industry.

Few-Shot Object Detection with Local Feature Enhancement and Feature Interrelation

Few-shot object detection (FSOD) aims at designing models that can accurately detect targets of novel classes in a scarce data regime. Existing research has improved detection performance with meta-learning-based models. However, existing methods continue to exhibit certain imperfections: (1) Only the interacting global features of query and support images lead to ignoring local critical features in the imprecise localization of objects from new categories. (2) Convolutional neural networks (CNNs) encounter difficulty in learning diverse pose features from exceedingly limited labeled samples of unseen classes. (3) Local context information is not fully utilized in a global attention mechanism, which means the attention modules need to be improved. As a result, the detection performance of novel-class objects is compromised. To overcome these challenges, a few-shot object detection network is proposed with a local feature enhancement module and an intrinsic feature transformation module. In this paper, a local feature enhancement module (LFEM) is designed to raise the importance of intrinsic features of the novel-class samples. In addition, an Intrinsic Feature Transform Module (IFTM) is explored to enhance the feature representation of novel-class samples, which enriches the feature space of novel classes. Finally, a more effective cross-attention module, called Global Cross-Attention Network (GCAN), which fully aggregates local and global context information between query and support images, is proposed in this paper. The crucial features of novel-class objects are extracted effectively by our model before the feature fusion between query images and support images. Our proposed method increases, on average, the detection performance by 0.93 (nAP) in comparison with previous models on the PASCAL VOC FSOD benchmark dataset. Extensive experiments demonstrate the effectiveness of our modules under various experimental settings.

Rodent ultrasonic vocal interaction resolved with millimeter precision using hybrid beamforming.

Ultrasonic vocalizations (USVs) fulfill an important role in communication and navigation in many species. Because of their social and affective significance, rodent USVs are increasingly used as a behavioral measure in neurodevelopmental and neurolinguistic research. Reliably attributing USVs to their emitter during close interactions has emerged as a difficult, key challenge. If addressed, all subsequent analyses gain substantial confidence. We present a hybrid ultrasonic tracking system, Hybrid Vocalization Localizer (HyVL), that synergistically integrates a high-resolution acoustic camera with high-quality ultrasonic microphones. HyVL is the first to achieve millimeter precision (~3.4-4.8 mm, 91% assigned) in localizing USVs, ~3× better than other systems, approaching the physical limits (mouse snout ~10 mm). We analyze mouse courtship interactions and demonstrate that males and females vocalize in starkly different relative spatial positions, and that the fraction of female vocalizations has likely been overestimated previously due to imprecise localization. Further, we find that when two male mice interact with one female, one of the males takes a dominant role in the interaction both in terms of the vocalization rate and the location relative to the female. HyVL substantially improves the precision with which social communication between rodents can be studied. It is also affordable, open-source, easy to set up, can be integrated with existing setups, and reduces the required number of experiments and animals.

A deep learning framework for target localization in error-prone environment

The use of Internet of Things (IoT) in environment monitoring has led to the development of Smart Environmental Monitoring (SEM) paradigm. Target or source localization, that determines the underlying cause of environmental occurrences, is an important aspect of SEM. To prevent an environmental event in becoming a potential disaster, swift and early localization of its source is crucial. Target localization is performed with the help of IoT sensors, which are typically deployed in hazardous environments and are not easily serviceable, making energy efficiency a requirement for SEM systems. Furthermore, IoT sensors may provide anomalous readings due to low battery, low sensor sensitivity, faults, or malicious attacks. This alters the decision-making process and leads to inaccurate localization of the source. Hence, detecting and dealing with anomalies, while utilizing a limited number of sensor nodes, are key factors in addressing reliability and energy efficiency issues. The current works are iterative in nature, employs redundant nodes, do not efficiently address anomalous readings, which leads to slow and imprecise localization, while increasing energy consumption. Moreover, they are application specific, making them less adaptable to other sensing tasks. Therefore, this work proposes a comprehensive and novel deep learning-based system that — (a) repopulates missing data from inactive sensors, (b) detects and rectifies anomalous data, and (c) instantly localizes a target. The efficacy of the proposed approach is validated in a radioactive environment and compared to existing benchmark. The results show that the proposed approach achieves precise, rapid, and efficient localization by achieving 5 times better accuracy, 50 times faster speeds, and 3 times lesser energy consumption.

COMPRA: A COMPact Reactive Autonomy Framework for Subterranean MAV Based Search-And-Rescue Operations

This work establishes COMPRA, a compact and reactive autonomy framework for fast deployment of Micro Aerial Vehicles (MAVs) in subterranean Search-and- Rescue (SAR) missions. A COMPRA-enabled MAV is able to autonomously explore previously unknown areas while specific mission criteria are considered e.g. an object of interest is identified and localized, the remaining useful battery life, the overall desired exploration mission duration. The proposed architecture follows a low-complexity algorithmic design to facilitate fully on-board computations, including nonlinear control, state-estimation, navigation, exploration behavior and object localization capabilities. The framework is mainly structured around a reactive local avoidance planner, based on enhanced Potential Field concepts and using instantaneous 3D pointclouds, as well as a computationally efficient heading regulation technique, based on depth images from an instantaneous camera stream. Those techniques decouple the collision-free path generation from the dependency of a global map and are capable of handling imprecise localization occasions. Field experimental verification of the overall architecture is performed in relevant unknown Global Positioning System (GPS)-denied environments.

Where has Hohenbergia burle‐marxii been? Taxonomy, ecology and geographic range of a rare endemic bromeliad from Bahia, Brazil

Hohenbergia burle‐marxii is one of the rarest species of Hohenbergia (Bromeliaceae), until recently known only by the holotype and its clones. The species had been recorded only once in an imprecise locality in Bahia's south region. After extensive field work we refound the species and we here present a new geographic range of Hohenbergia burle‐marxii, at the same time adding information about its morphology and ecological traits, including a map and photographs of living plants.

Energy-Optimal 3D Path Planning for MAV with Motion Uncertainty

Practical applications of microaerial vehicle face significant challenges including imprecise localization, limited on-board energy, and motion uncertainty. This paper focuses on the latter two issues. The core of proposed energy-optimal path planning algorithm is an energy consumption model deriving from real measurements of a specific quadrotor and utilizing a 2D Gaussian distribution function to simulate the uncertainty of random drift. Based on these two models, we formulate the optimal path traversing the 3D map with minimum energy consumption using a heuristic ant colony optimization. Multiple sets of contrast experiments demonstrate the effectiveness and efficiency of the proposed algorithm.

Multi-Robot Workspace Allocation with Hopfield Networks and Imprecise Localization

Multi-Robot Workspace Allocation with Hopfield Networks and Imprecise Localization

On Temnocephala axenos Monticelli, 1898 (Platyhelminthes, Temnocephalida): taxonomic status and designation of a neotype.

Temnocephala axenos Monticelli, 1898 was described based on specimens from an unidentified host collected in Blumenau, Santa Catarina, Brazil. Information about type locality was imprecise and the host was later identified as Aegla laevis (Latreille, 1818). However, it is known that A. laevis is not present on the eastern side of the Andes. Also, only histological preparations from one specimen studied by Monticelli are currently available in the Museum für Naturkunde Berlin, but it showed none of the taxonomic characters needed for the characterization of the species. Although the updated description of the species based on Uruguayan specimens, neither the author nor the several previous studies about the species showed a search for the type material, a resolution for the misidentification of the type host or the imprecise type locality due to the subsequent geographical division of the municipality cited in the description. The Uruguayan specimens were not even geographically close to the type locality and a neotype was not designed to validate the species' taxonomic status again. Specimens from Santa Catarina and Paraná States, Brazil, were studied, as well as restudied Argentinean specimens. The new data were compared with the update description of the species. The historical background and the discussion about geographical origins and hosts of the species, as well as a designation of a neotype, allow comparative material of the type locality and type host to exist, eliminating doubts about the identification of T. axenos.

Do target detection and target localization always go together? Extracting information from briefly presented displays.

The human visual system is capable of processing an enormous amount of information in a short time. Although rapid target detection has been explored extensively, less is known about target localization. Here we used natural scenes and explored the relationship between being able to detect a target (present vs. absent) and being able to localize it. Across four presentation durations (~ 33-199 ms), participants viewed scenes taken from two superordinate categories (natural and manmade), each containing exemplars from four basic scene categories. In a two-interval forced choice task, observers were asked to detect a Gabor target inserted in one of the two scenes. This was followed by one of two different localization tasks. Participants were asked either to discriminate whether the target was on the left or the right side of the display or to click on the exact location where they had seen the target. Targets could be detected and localized at our shortest exposure duration (~ 33 ms), with a predictable improvement in performance with increasing exposure duration. We saw some evidence at this shortest duration of detection without localization, but further analyses demonstrated that these trials typically reflected coarse or imprecise localization information, rather than its complete absence. Experiment 2 replicated our main findings while exploring the effect of the level of "openness" in the scene. Our results are consistent with the notion that when we are able to extract what objects are present in a scene, we also have information about where each object is, which provides crucial guidance for our goal-directed actions.

Visual Area Coverage by Heterogeneous Aerial Agents Under Imprecise Localization

A control scheme for the coverage of a convex region by a team of mobile aerial agents (MAAs) under positioning uncertainty is presented in this letter. Each MAA is outfitted with a downwards facing camera, the field of view of which differs among agents, resulting in a sensed area which depends on the MAA's altitude and the view angle of its camera. Additionally, the MAAs' projections on the ground and altitudes are assumed to be known with varying uncertainty. In order to take into account the MAAs' positioning uncertainty as well as their varying sensed areas, an additively weighted guaranteed Voronoi partitioning of the region is utilized. Based on this partitioning scheme, a gradient-based algorithm is derived in order to guarantee monotonic increase of an area coverage metric, despite the positioning uncertainty, while also constraining the MAAs' altitudes. The proposed scheme is evaluated through simulation studies.

Redescription and phylogenetic position of Ctenomys dorsalis Thomas 1900, an enigmatic tuco tuco (Rodentia, Ctenomyidae) from the Paraguayan Chaco

Abstract Ctenomys dorsalis is known only from its type specimen, a female preserved as skin without skull (except for the upper incisors) from an imprecise locality in the “Northern Chaco of Paraguay”. Here, we report additional individuals of this species housed, since the 1940s, at the Field Museum of Natural History (Chicago, USA). Based on these specimens, which fully match the original description of this rodent, we provide novel information regarding its phylogenetic position, external and cranial morphology, and distribution. The analysis of mtDNA sequences supports the distinctiveness of this taxon and suggests its placement within the boliviensis group of Ctenomys. Our study highlights once more the importance of museum collections as repositories of biodiversity.

Distributed area coverage control with imprecise robot localization

This article examines the static area coverage problem by a network of mobile, sensor-equipped agents with imprecise localization. Each agent has uniform radial sensing ability and is governed by first-order kinodynamics. To partition the region of interest, a novel partitioning scheme, the Additively Weighted Guaranteed Voronoi diagram is introduced which takes into account both the agents’ positioning uncertainty and their heterogeneous sensing performance. Each agent’s region of responsibility corresponds to its Additively Weighted Guaranteed Voronoi cell, bounded by hyperbolic arcs. An appropriate gradient ascent-based control scheme is derived so that it guarantees monotonic increase of a coverage objective and is extended with collision avoidance properties. Additionally, a computationally efficient simplified control scheme is offered that is able to achieve comparable performance. Several simulation studies are offered to evaluate the performance of the two control schemes. Finally, two experiments using small differential drive-like robots and an ultra-wideband positioning system were conducted, highlighting the performance of the proposed control scheme in a real world scenario.

S149 Video-EEG monitoring in young children

Video-EEG monitoring, the synchronous recording of the ictal EEG pattern and the paroxysmal behaviour, is used to confirm the epileptic origine, to classify the seizure type(s) and the electro-clinical syndrome, and to assess seizure frequency and eventual precipitating factors. It is an essential diagnostic procedure in the presurgical evaluation of children with refractory focal epilepsy, in order to establish surgical candidacy, and to define localization and extent of the epileptogenic zone and its relationship to eloquent function. Although it is preferable to record seizures without modifying the anti-seizure medication, treatment reduction may be necessary along with other provocative procedures as i.e. sleep deprivation. Interpretation is based on the seizure semiology, the localization of the onset of the ictal discharge, EEG and clinical symptoms in the postictal phase, and the interictal EEG anomalies. Additional electrodes to the usual 10/20 system may be indicated, particularly important in mesial temporal discharges, using inferior temporal and anterior temporal surface electrodes. Refractory epilepsy in the pediatric population represents a particular challenge because of the wide variety of etiologies compounded to the brain maturation, very fast during infancy and early childhood, leading to a complex evolution of the clinical presentation. Especially genetically determined epilepsies may mimick structural focal epilepsies. Video-EEG recording is still the most widely available and useful test in evaluating the candidacy for a surgical treatment, with however limitations as imprecise localization or inability to detect deep or tangentially orientated foci. Therefore presurgical evaluation is multimodal combining scalp video EEG recording, electrical and magnetic source imaging, anatomical MRI, Arterial Spin Labelling (ASL) MRI, EEG-triggered functional MRI, and FDG-PET studies.

Endoscopically Placed Fiducial Markers Aid in Insulinoma Resection

Case: A 47-year-old female presented with hypoglycemia for 1 year. The 72-hour fast was terminated for hypoglycemic symptoms and glucose of 40 mg/dL. Laboratories revealed low insulin level and low–normal C-peptide with elevated proinsulin, suggesting proinsulin-secreting neuroendocrine tumor (NET). Insulinoma is the most common functioning pancreatic NET and presents with symptoms of hypoglycemia. CT was negative for pancreatic mass. Endoscopic ultrasonography (EUS) revealed an 8 × 7 mm midbody pancreatic mass and biopsy confirmed NET. Fiducial markers were placed with EUS guidance to aid intraoperative localization during partial pancreatectomy. Intraoperative fluoroscopy (IOF) and laparoscopic ultrasonography (LUS) localized the peritumoral fiducials. The mass was close to the splenic vessels and nearly abutting the pancreatic duct. A 60-mm laparoscopic stapler was inserted, and the fiducials were used to achieve ≥1 cm surgical margin (video). The total laparoscopic distal pancreatectomy was completed with a spleen-sparing technique. Postoperatively, the hypoglycemia resolved. Discussion: Most NETs are intrapancreatic, 90% are solitary, 90% are <2 cm in diameter, and tumors are found equally throughout the pancreas.1 EUS, utilized in diagnosis and localization in this case, has recognized advantages over other observation techniques. As seen in this study, diagnosis of pancreatic tumors is possible despite negative CT.2 Sensitivity of EUS ranges from 37% to 94% regardless of the functional state of the insulinoma, and is largely dependent on the location of the lesion. EUS is best at detecting tumors in the head and worst at detecting those in the tail of the pancreas.3 EUS has low complication rates and has a relative ease of use with a skilled operator.4 Localization before surgery is desired because most tumors are not palpable at the time of surgery, and type of surgery can be determined based on location.5 Using EUS for preoperative staging of pancreatic tumors has been in practice for several years, although it is usually achieved through tattoos and dyes.6,7 Preoperative localization of pancreatic endocrine tumors with tattoos and dyes has been shown to decrease operative time and blood transfusion requirement.8 Most data regarding localization of pancreatic tumors concern insulinomas, although proinsulinomas have been localized with tattoos.9 Tattoos and dyes have potential complications of absorption into surrounding tissues, peritonitis, infection, and allergic reaction.10 Fiducial markers are radiopaque 3 mm gold particles often endoscopically placed through 22 gauge needle. They are observed with LUS and IOF during resection, and shorten operative time by revealing the location of nonpalpable tumors or tumors that are poorly observed through LUS alone. By shortening operative time, it reduces perioperative complications, reduces need for reoperation, and increases likelihood of an effective outcome.11 Fiducials are superior to ink/tattoos by eliminating imprecise localization from ink absorption into surrounding tissues.12 Reported complications include most common abdominal pain, followed by cholangitis, pancreatitis, minor bleeding, fever, and elevated liver enzymes.13–16 No competing financial interests exist. Runtime of video: 7 mins 48 secs Presented as Poster Abstract at American College of Gastroenterologists Annual Scientific Meeting 2014, Philadelphia.

Systematic revision of the Malagasy chameleons Calumma boettgeri and C. linotum (Squamata: Chamaeleonidae).

We revise the taxonomic status of two species of Madagascan chameleons in light of a recent molecular phylogenetic study on the Calumma nasutum group. The investigation of morphological and osteological characters led to a clear delineation between two species within the C. boettgeri complex, C. boettgeri and C. linotum. Calumma linotum has been considered either a synonym of C. boettgeri or a dubious, poorly defined taxon. So far it has only been known from the male holotype with the imprecise locality 'Madagascar'. Based on pholidosis, morphological measurements and characters of the skull that were analyzed using micro-X-ray computed tomography (micro-CT) scans, we ascribe the population of chameleons from Montagne d'Ambre, formerly assigned to C. boettgeri, to C. linotum. Calumma linotum differs from C. boettgeri in the larger size of tubercle scales on the extremities and rostral appendage, the larger diameter of the extremities relative to the body size, the presence of a parietal crest as well as the form of the nasal bones and the anterior tip of the frontal. The life colouration of the males is also characteristic, with a blue rostral appendage and greenish turquoise extremities. The body and rostral appendage of C. boettgeri in contrast are inconspicuously yellowish brown coloured. All confirmed distribution records of C. boettgeri are confined to the biogeographic Sambirano region whereas C. linotum is only known from Montagne d'Ambre and a locality at the base of the Tsaratanana massif. Additional literature records of C. boettgeri and C. linotum from northeastern Madagascar are in need of confirmation. We also confirm the synonymy of Chamaeleo macrorhinus (described from a female holotype with an unknown locality) with Calumma boettgeri. The use of micro-CT exposed further characteristics for species delimitation in an integrative taxonomic approach. In addition to the skull, we also micro-CT scanned the hemipenes of C. boettgeri and C. linotum, using an iodine-based tissue stain, and provide 3D PDF models of these organs. This method enables detailed illustration and the detection of variation in particular characters, and might be an important tool in further taxonomic studies on the C. nasutum group and other squamate reptiles.

Capture and Printing of Fixed Stromal Cell Membranes for Bioactive Display on PDMS Surfaces

Poly(dimethylsiloxane) (PDMS) has emerged as an extremely useful polymer for various biological applications. The conjugation of PDMS with bioactive molecules to create functional surfaces is feasible yet limited to a single-molecule display with imprecise localization of the molecules on PDMS. Here we report a robust technique that can transfer and print the membrane surface of glutaraldehyde-fixed stromal cells intact onto a PDMS substrate using an intermediate polyvinylalcohol (PVA) film as a transporter system. The cell-PVA film capturing the entirety of surface molecules can be peeled off and subsequently printed onto PDMS while maintaining the spatial display of the original cell surface molecules. Proof-of-concept studies are described using human bone marrow stromal cell membranes including a demonstration of the bioactivity of transferred membranes to capture and adhere hematopoietic cells. The presented process is applicable to virtually any adherent cell and can broaden the functional display of biomolecules on PDMS for biotechnology applications.