Target Object Research Articles

Multi-Objective Performance Optimization of Machine Learning Models in Healthcare.

Multi-objective optimization holds particular significance for medical applications, wherein enhancing sensitivity is crucial to avoid costly missed diagnoses, and maintaining high specificity is imperative to prevent unnecessary procedures. In particular, when optimizing machine learning architectures for clinical diagnostics, it becomes essential to balance target quality measures such as accuracy, sensitivity, and specificity. Therefore, we developed MOOF, a multi-objective optimization framework that employs NSGA-II and TOPSIS to simultaneously optimize the model parameters of three selected ML algorithms: random forest, support vector machine, and multilayer perceptron. Finally, we evaluated the performance of the optimized MOOF models compared to gold standard methods such as multi-score grid search and single objective optimizations. Our results show that MOOF generally outperforms other approaches by inherently providing optimal solutions, representing the trade-offs between the target objectives. In conclusion, the study supports the importance of multi-objective optimization in medical informatics, with MOOF as a powerful tool for precise ML models, potentially improving patient care and clinical decision support systems.

DART: An automated end-to-end object detection pipeline with data Diversification, open-vocabulary bounding box Annotation, pseudo-label Review, and model Training

Accurate real-time object detection is vital across numerous industrial applications, from safety monitoring to quality control. Traditional approaches, however, are hindered by arduous manual annotation and data collection, struggling to adapt to ever-changing environments and novel target objects. To address these limitations, this paper presents DART, an innovative automated end-to-end pipeline that revolutionizes object detection workflows from data collection to model evaluation. It eliminates the need for laborious human labeling and extensive data collection while achieving outstanding accuracy across diverse scenarios. DART encompasses four key stages: (1) Data Diversification using subject-driven image generation (DreamBooth with SDXL), (2) Annotation via open-vocabulary object detection (Grounding DINO) to generate bounding box and class labels, (3) Review of generated images and pseudo-labels by large multimodal models (InternVL-1.5 and GPT-4o) to guarantee credibility, and (4) Training of real-time object detectors (YOLOv8 and YOLOv10) using the verified data. We apply DART to a self-collected dataset of construction machines named Liebherr Product, which contains over 15K high-quality images across 23 categories. The current instantiation of DART significantly increases average precision (AP) from 0.064 to 0.832. Its modular design ensures easy exchangeability and extensibility, allowing for future algorithm upgrades, seamless integration of new object categories, and adaptability to customized environments without manual labeling and additional data collection. The code and dataset are released at https://github.com/chen-xin-94/DART.

Remote Sensing of Target Object Detection and Identification II

Remote Sensing of Target Object Detection and Identification II

Visual perspective taking and action understanding

Understanding what others are doing is a fundamental aspect of social cognition and a skill that is arguably linked to visuospatial perspective taking (VPT), the ability to apprehend the spatial layout of a scene from another's perspective. Yet, with few and notable exceptions, action understanding and VPT are rarely studied together. Participants (43 females, 37 males) made judgements about the spatial layout of objects in a scene from the perspective of an avatar who was positioned at 0°, 90°, 270° or 180° relative to the participant. In a variant of a traditional VPT task, the avatar either interacted with the objects in the scene, by pointing to or reaching for them, or was present but did not engage with the objects. Although the task was identical across all conditions - to say whether a target object is to the right or left of a control object - we show that the avatar's actions modulates performance. Specifically, participants were more accurate when the avatar engaged with the target object, and correspondingly, less accurate and slower when the avatar interacted with the control objects. As these effects were independent of the angular disparity between participant and avatar perspectives, we conclude that action understanding and VPT are likely linked via the rapid deployment of two separate cognitive mechanisms. All participants provided a measure of self-reported empathy and we show that response times decrease with increasing empathy scores for female but not for male participants. However, within the range of ‘typical’ empathy scores, defined here as the interquartile range where 50 % of the data lie, females were faster than males. These findings lend further insight into the relationship between spatial and social perspective taking.

Dual temporal memory network with high-order spatio-temporal graph learning for video object segmentation

Typically, Video Object Segmentation (VOS) always has the semi-supervised setting in the testing phase. The VOS aims to track and segment one or several target objects in the following frames in the sequence, only given the ground-truth segmentation mask in the initial frame. A fundamental issue in VOS is how to best utilize the temporal information to improve the accuracy. To address the aforementioned issue, we provide an end-to-end framework that simultaneously extracts long-term and short-term historical sequential information to current frame as temporal memories. The integrated temporal architecture consists of a short-term and a long-term memory modules. Specifically, the short-term memory module leverages a high-order graph-based learning framework to simulate the fine-grained spatial–temporal interactions between local regions across neighboring frames in a video, thereby maintaining the spatio-temporal visual consistency on local regions. Meanwhile, to relieve the occlusion and drift issues, the long-term memory module employs a Simplified Gated Recurrent Unit (S-GRU) to model the long evolutions in a video. Furthermore, we design a novel direction-aware attention module to complementarily augment the object representation for more robust segmentation. Our experiments on three mainstream VOS benchmarks, containing DAVIS 2017, DAVIS 2016, and Youtube-VOS, demonstrate that our proposed solution provides a fair tradeoff performance between both speed and accuracy.

Detection of low-contrast objects by electrical prospecting methods

Many geological problems cannot be solved by electrical prospecting methods. Often the reason for this is a slight difference in the electrical resistivity of target objects from that of the host medium. At the same time, the use of the transverse magnetic (TM) type field makes it possible to identify low-contrast objects and delineate their boundaries with high accuracy. TM-type prospecting is more efficient since its signal is much more strongly affected by changes in resistivity and other electrodynamic parameters. The article examines one of the difficult cases – a search for kimberlite pipes in Yakutia. Such objects differ very little from the host medium in terms of the horizontal resistivity. Exploration works to search for kimberlite pipes in Yakutia, carried out by conventional electrical prospecting methods, have many problems. The article considers the results of successful TM-type prospecting field surveys where kimberlite pipes stood out very prominently. Also presented are the results of modeling an even more complex situation in which the pipes are located at depths of over 140 m and overlain by traps; there are many objects in the area that create additional anomalies.

Near-Infrared Response Organic Synaptic Transistor for Dynamic Trace Extraction.

The development of neuromorphic hardware capable of detecting and recognizing moving targets through an in-sensor computing strategy is considered to be an important component of the construction of edge computing systems with distributed computation. In addition to responsiveness to visible light, the implementation of neuromorphic hardware should also demonstrate the ability to sense and process nonvisible light, which is essential for tracking target object trajectories in specialized environments. In this work, we fabricated an organic synaptic transistor with a near-infrared (NIR) response by incorporating doped LaF3: Yb/Ho upconversion quantum dots (UCQDs) into the channel of a Poly3-hexylthiophene (P3HT)-based organic field effect transistor (FET), serving as charge trapping and infrared sensing sites. The obtained synaptic transistor not only replicates common synaptic behaviors when exposed to NIR illumination but also demonstrates potential applications for the dynamic trajectory recognition of animals in the dark. Compared to other monitoring technologies, P3HT transistors doped with LaF3: Yb/Ho UCQDs exhibit distinct advantages, including a NIR response, high-efficiency computing, and sensitivity, which provide an experimental foundation and a design reference for the development of next-generation intelligent dynamic image recognition systems.

U-TAG: Electromagnetic Wireless Sensing System for Robotic Hand Pre-Grasping.

In order to perform complex manipulation and grasp tasks, robotic hands require sensors that can handle increasingly demanding functionality and degrees of freedom. This research paper proposes a radiofrequency sensor that uses a wireless connection between a probe and a tag. A compact and low-profile antenna is mounted on the hand and functions as a probe to read a printed passive resonator on the plastic object being targeted, operating within a pre-touch sensing range. The grasping strategy consists of four stages that involve planar alignment in up-to-down and left-to-right directions between the probe and tag, the search for an appropriate distance from the object, and rotational (angular) alignment. The real and imaginary components of the probe-input impedance are analyzed for different orientation strategies and positioning between the resonator on the object and the probe. These data are used to deduce the orientation of the hand relative to the target object and to determine the optimal position for grasping.

Finite-Time Convergence Guidance Law for Hypersonic Morphing Vehicle

Aiming at the interception constraint posed by defensive aircrafts against hypersonic morphing vehicles (HMVs) during the terminal guidance phase, this paper designed a guidance law with the finite-time convergence theory and control allocation methods based on the event-triggered theory, achieving evasion of the defensive aircraft and targeting objectives for a morphing vehicle in the terminal guidance phase. Firstly, this paper established the aircraft motion model; the relative motion relationships between HMV, defensive aircraft, and target; and the control equations for the guidance system. Secondly, a guidance law with finite-time convergence was designed, establishing a controller with the angle between the aircraft–target–defense aircraft triplet as the state variable and lift as the control variable. By ensuring the angle was non-zero, the aircraft maintained a certain relative distance from the defense aircraft, achieving evasion of interception. The delay characteristic of the aircraft’s flight controller was considered, analyzing its delay stability and applying control compensation. Thirdly, a multi-model switching control allocation method based on an event-triggered mechanism was designed. Optimal attack and bank angles were determined based on acceleration control variables, considering different sweep angles. Finally, simulations were conducted to validate the effectiveness and robustness of the designed guidance laws.

Infrared and Harsh Light Visible Image Fusion Using an Environmental Light Perception Network.

The complementary combination of emphasizing target objects in infrared images and rich texture details in visible images can effectively enhance the information entropy of fused images, thereby providing substantial assistance for downstream composite high-level vision tasks, such as nighttime vehicle intelligent driving. However, mainstream fusion algorithms lack specific research on the contradiction between the low information entropy and high pixel intensity of visible images under harsh light nighttime road environments. As a result, fusion algorithms that perform well in normal conditions can only produce low information entropy fusion images similar to the information distribution of visible images under harsh light interference. In response to these problems, we designed an image fusion network resilient to harsh light environment interference, incorporating entropy and information theory principles to enhance robustness and information retention. Specifically, an edge feature extraction module was designed to extract key edge features of salient targets to optimize fusion information entropy. Additionally, a harsh light environment aware (HLEA) module was proposed to avoid the decrease in fusion image quality caused by the contradiction between low information entropy and high pixel intensity based on the information distribution characteristics of harsh light visible images. Finally, an edge-guided hierarchical fusion (EGHF) module was designed to achieve robust feature fusion, minimizing irrelevant noise entropy and maximizing useful information entropy. Extensive experiments demonstrate that, compared to other advanced algorithms, the method proposed fusion results contain more useful information and have significant advantages in high-level vision tasks under harsh nighttime lighting conditions.

Amphibious Hybrid Laser Tweezers for Fluid and Solid Domains.

Optical trapping is a potent tool for achieving precise and noninvasive manipulation of small objects in a vacuum and liquids. However, due to the substantial disparity between optical forces and interfacial adhesion, target objects should be suspended in fluid environments, rendering solid contact surfaces a restricted area for conventional optical tweezers. In this work, by relying on a single continuous wave (CW) laser, we demonstrate an optical manipulation system applicable for both fluid and solid domains, namely, amphibious hybrid laser tweezers. The key to our system lies in modulating the intensity of the CW laser with duration shorter than the dynamic thermal equilibrium time within objects, wherein strong thermal gradient forces with ∼6 orders of magnitude higher than the forces in optical tweezers are produced, enabling moving and trapping micro/nano-objects on solid interfaces. Thereby, CW laser-based optical tweezers and pulsed laser-based photothermal shock tweezers are seamlessly fused with the advantages of cost-effectiveness and simplicity. Our concept breaks the stereotype that CW lasers are limited to generating tiny forces and instead achieve ultrawide force generation spanning from femto-newtons (10-15 N) to (10-6 N). Our work expands the horizon of optical manipulation by seamlessly bridging its applications in fluid and solid environments and holds promise for inspiring optical manipulation techniques to perform more challenging tasks, which may unearth application scenarios in diverse fields such as fundamental physical research, nanofabrication, micro/nanorobotics, biomedicine, and cytology.

Audio-guided implicit neural representation for local image stylization

We present a novel framework for audio-guided localized image stylization. Sound often provides information about the specific context of a scene and is closely related to a certain part of the scene or object. However, existing image stylization works have focused on stylizing the entire image using an image or text input. Stylizing a particular part of the image based on audio input is natural but challenging. This work proposes a framework in which a user provides an audio input to localize the target in the input image and another to locally stylize the target object or scene. We first produce a fine localization map using an audio-visual localization network leveraging CLIP embedding space. We then utilize an implicit neural representation (INR) along with the predicted localization map to stylize the target based on sound information. The INR manipulates local pixel values to be semantically consistent with the provided audio input. Our experiments show that the proposed framework outperforms other audio-guided stylization methods. Moreover, we observe that our method constructs concise localization maps and naturally manipulates the target object or scene in accordance with the given audio input.

Time-independent relationship between digits closure velocity and hand transport acceleration during reach-to-grasp movements

Prehension movements in primates have been extensively studied for decades, and hand transport and hand grip adjustment are usually considered as the main components of any object reach-to-grasp action. Evident temporal patterns were found for the velocity of the hand during the transport phase and for the digits kinematics during pre-shaping and enclosing phases. However, such kinematics were always analysed separately in regard to time, and never studied in terms of dependence one from another. Nevertheless, if a reliable one-to-one relationship is proven, it would allow reconstructing the digit velocity (and position) simply by knowing the hand acceleration during reaching motions towards the target object, ceasing the usual dependence seen in literature from time of movement and distance from the target. In this study, the aim was precisely to analyse reach-to-grasp motions to explore if such relationship exists and how it can be formulated. Offline and real-time results not only seem to suggest the existence of a time-independent, one-to-one relationship between hand transport and hand grip adjustment, but also that such relationship is quite resilient to the different intrinsic and extrinsic properties of the target objects such as size, shape and position.

Readiness and Barriers Toward Voice Therapy Among Indian Classical Singers and Western Singers – A Scoping Review

ABSTRACT This scoping review explored the literature on different barriers and readiness toward voice therapy among singers. For the search, key terms were formulated, and six databases (Medline, PubMed, Scopus, SpringerLink, Web of Science, and Google Scholar) were used. After title and abstract-level screening, 12 full-length articles that identified barriers were reviewed and compiled using the PRISMA flow chart. However, no research related to readiness for voice therapy among singers was identified. The barriers were categorized into two broad categories (internal and external) and eight subcategories. Twenty-five barriers were categorized into nine sub-themes, such as awareness, knowledge of voice therapy, mental status of the singer, referral, financial reasons, perceptions of voice therapy by music teachers, perceptions of voice therapy by singers, logistic reasons, and accessibility. From the 12 full-length articles, informations such as target population, study design, objectives, and methods used to elicit the barriers were analyzed, and lacunae in the method used to obtain barriers were identified. These findings would be beneficial in developing tools to assess the barriers and readiness for voice therapy among singers and can be applied to improve compliance and concordance with voice interventions.

Forensic research of satellite images forgery: a comprehensive survey

Satellite imagery is a significant and attractive area in remote sensing applications, widely applied in monitoring, managing, and tracking natural disasters. Due to the proliferation of commercial satellites, there is an increasing availability of high-resolution satellite images. However, the ubiquity of image editing tools and the advancement of image processing technologies have made satellite image forgery relatively easy, allowing for the arbitrary addition, removal, or modification of target objects. In recent years, satellite image forgery has caused significant negative effects and potential threats to the nation, society, and individuals, drawing the attention of many scholars. Although forensics of satellite image tampering is an emerging research field that offers new insights into the field of information security, there has been a scarcity of comprehensive surveys in this area. This paper aims to fill this gap and investigates recent advances in satellite image forensics, focusing on tampering strategies and forensic methodologies. First, we discuss the concept of satellite images, the definition of satellite image forgery from global and local perspectives, and the datasets commonly used for satellite image forensics. We then detail each tampering detection and localization method, including their characteristics, advantages, disadvantages, and performance in detection or localization across various notable datasets. We also compare some representative forensic networks using evaluation metrics and public datasets. Finally, the anticipated future directions for satellite image forgery forensics are discussed.

Adaptive similarity-guided self-merging network for few-shot semantic segmentation

Few-shot Semantic Segmentation (FSS) attempts to segment the new category with only a few labeled samples, presenting a significant challenge. Existing approaches primarily focus on leveraging category information from the support set to identify objects of the new category in the query image. However, these models often struggle when confronted with substantial differences between paired images. To address issues stemming from scenario differences and intra-class diversity, this paper proposes an adaptive similarity-guided self-merging network. Firstly, style differences of multi-level features are introduced to alleviate the network's sensitivity to scenario variations and learn an adaptive weight for the K-shot scheme. Secondly, a feature-mask bi-aggregation module is designed to learn an enhanced feature and an initial mask for the query image. Within this module, dynamic correlations cover all the spatial locations, providing global information crucial for feature and mask aggregation. Subsequently, a self-merging module is proposed to alleviate prototype bias. It merges a self-prototype derived from the initial mask with an adaptive weighted support prototype obtained from K support images. Finally, the target object is segmented using the enhanced feature and merging prototype, and segmentation results are further refined by predictions of base categories and an adjustment factor derived from multi-level style differences. The proposed method achieves 69.1% (1-shot) and 72.3% (5-shot) mIoU on the PASCAL-5i dataset, and 47.4% (1-shot) and 52.1% (5-shot) mIoU on the COCO-20i dataset. These results demonstrate state-of-the-art segmentation performance compared to mainstream methods.© 2017 Elsevier Inc. All rights reserved.

The evolution of sustainable renovation of existing buildings: from integrated seismic and environmental retrofitting strategies to a life cycle thinking approach

The sustainable renovation of existing buildings is currently at the top of the agenda of the European Union. Sustainability is typically defined as the result of the interaction of environmental, economic, and social aspects, and it is now considered a major target objective in all sectors of our economy, including the construction one. The concept of sustainable renovation has changed significantly over time, leading to the current interpretation that considers the need to simultaneously improve safety and resilience against natural hazards and minimise energy and resource consumption, as well as to reduce impacts along the life cycle of the building. This manuscript presents insights into combined/integrated environmental and seismic retrofitting techniques and assessment methods for the sustainable renovation of the existing building stock, specifically focussing on those conceived according to a Life Cycle Thinking (LCT) approach. This manuscript goes beyond the current available state of the art by highlighting the evolution of the concept of building sustainability throughout time, as well as defining a comprehensive taxonomy of available retrofitting strategies, while also identifying common clusters among available research papers. This research effort is part of the mission of the European Association of Earthquake Engineering (EAEE) Working Group 15 (WG15), which focusses on ‘combined seismic and environmental upgrading of existing buildings”.

Template‐Refine Network for Siamese Object Tracking

Various mainstream target tracking algorithms based on Siamese networks are gradually becoming a trend in the field of deep learning tracking due to their concurrent advantages of accuracy and speed. Most Siamese network‐based trackers describe the tracking of a target object as a similar matching problem, and these trackers have achieved more advanced performance in several public tests. Most trackers often suffer from tracking drift or performance degradation owing to the non‐updating of the template in the first frame and the target appearance encounters disturbing environments such as occlusion and drastic deformation. Therefore, to address this problem, this paper introduces a template updating mechanism and proposes a refine structure network based on the template updating of Siamese networks as well as the greater similarity of target features in two adjacent frames, which improves the tracking accuracy while limiting the amount of computation using an anchor‐free method in order not to lose the tracking speed, and only needs to be trained by selecting the most suitable pre‐training network, thus greatly reducing the amount of network computation. Meanwhile, in the application of the refine structure, with the aim of making the weight design of the target localisation module more reasonable, we propose a new Refine Head section and analyze and design the update threshold to optimize the overall network. This method is practiced in SiamFC++ algorithm, which firstly designs the template refine module, inputs the image that needs to be improved, and then outputs it to the Refine Head to complete the template update and applies it to the tracking of the subsequent frames, thereby constituting the SiamTRN (Template‐Refine Network). According to the experiments, the improved structure of the method can effectively implement the refine module function and enhance the performance of the tracker on public datasets, such as OTB100, VOT2016, UAV123 and GOT‐10 k. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Effects of Context Changes on Memory Reactivation.

While the influence of context on long-term memory (LTM) is well documented, its effects on the interaction between working memory (WM) and LTM remain less understood. In this study, we explored these interactions using a delayed match-to-sample task, where participants (6 males, 16 females) encountered the same target object across six consecutive trials, facilitating the transition from WM to LTM. During half of these target repetitions, the background color changed. We measured the WM storage of the target using the contralateral delay activity in electroencephalography. Our results reveal that task-irrelevant context changes trigger the reactivation of long-term memories in WM. This reactivation may be attributed to content-context binding in WM and hippocampal pattern separation.

Vision-based relative position and attitude determination of non-cooperative spacecraft using a generative model architecture

A wide range of spacecraft operations in orbit relies on the precise and accurate estimation of the relative attitude and position of target objects. This requirement is especially critical during missions involving non-cooperative targets, where even minor errors can result in mission failure or catastrophic collisions. This paper presents an innovative approach that integrates a novel Point Cloud Reconstruction Generative Adversarial Network (PCR-GAN) with a Generalized Iterative Closest Point (GICP) algorithm to enhance pose estimation of known non-cooperative targets using stereo-camera data. Initially, a machine learning algorithm is employed to extract feature points from the stereo images of the target spacecraft. The PCR-GAN model then is used to improve the resolution and distribution of the point clouds generated, which are subsequently aligned using the GICP algorithm. Experimental results from a testbed implementation demonstrate that this architecture significantly enhances the accuracy of attitude and position estimation, thereby representing a potential tool for improving the efficiency and safety of proximity operations in space.