Target Shape Research Articles

Object Detection of UAV Images from Orthographic Perspective Based on Improved YOLOv5s

Object detection methods of UAV (Unmanned Aerial Vehicle) images are greatly improved with the development of UAV technology. In comparison, the existing object detection methods of UAV images lack outstanding performance in the face of challenges such as small targets, dense scenes, sparse distribution, occlusion, and complex background, especially prominent in the task of vehicle detection. This paper proposed an improved YOLOv5s method to perform vehicle detection of UAV images. The CA (Coordinate Attention) is first applied to the neck of YOLOv5s to generate direction-aware and position-sensitive feature maps, respectively, to improve the detection accuracy of sparsely distributed vehicle targets in complex backgrounds. Then, an improved PAFPN (Path Aggregation Feature Pyramid Network) at the neck of YOLOv5s is proposed for more efficient detection of small and dense vehicle targets. Finally, the CIoU (Complete Intersection Over Union) loss function was used to calculate the bounding box regression to obtain a more comprehensive overlap measure to accommodate different shapes of vehicle targets. We conducted extensive experiments on the self-built UAV-OP (Unmanned Aerial Vehicle from Orthographic Perspective) dataset. The experimental results show that our method achieves the best detection accuracy with a small quantity of calculation increase compared with YOLOv5s. The mAP50 improved by 3%, and the mAP50:95 improved by 1.7% with a 0.3 GFlops increase.

OptCtrlPoints: Finding the Optimal Control Points for Biharmonic 3D Shape Deformation

AbstractWe propose OptCtrlPoints, a data‐driven framework designed to identify the optimal sparse set of control points for reproducing target shapes using biharmonic 3D shape deformation. Control‐point‐based 3D deformation methods are widely utilized for interactive shape editing, and their usability is enhanced when the control points are sparse yet strategically distributed across the shape. With this objective in mind, we introduce a data‐driven approach that can determine the most suitable set of control points, assuming that we have a given set of possible shape variations. The challenges associated with this task primarily stem from the computationally demanding nature of the problem. Two main factors contribute to this complexity: solving a large linear system for the biharmonic weight computation and addressing the combinatorial problem of finding the optimal subset of mesh vertices. To overcome these challenges, we propose a reformulation of the biharmonic computation that reduces the matrix size, making it dependent on the number of control points rather than the number of vertices. Additionally, we present an efficient search algorithm that significantly reduces the time complexity while still delivering a nearly optimal solution. Experiments on SMPL, SMAL, and DeformingThings4D datasets demonstrate the efficacy of our method. Our control points achieve better template‐to‐target fit than FPS, random search, and neural‐network‐based prediction. We also highlight the significant reduction in computation time from days to approximately 3 minutes.

Statistical learning of target and distractor spatial probability shape a common attentional priority computation

Converging evidence recently put forward the notion that dedicated neurocognitive mechanisms do exist for the suppression of salient, but irrelevant distractors. Along this line, it is plausible to hypothesize that, in appropriate contexts, experience-dependent forms of attentional learning might selectively induce plastic changes within this dedicated circuitry, thus allowing an independent shaping of priorities at the service of attentional filtering. Conversely, previous work suggested that statistical learning (SL) of both target and distractor spatial probability distributions converge in adjusting only the overall attentional priority of locations: in fact, in the presence of an independent manipulation, either related to the target or to the distractor only, SL induces indirect effects (e.g., changes in filtering efficiency due to an uneven distribution of targets), suggesting that SL-induced plastic changes affect a shared neural substrate. Here we tested whether, when (conflicting) target- and distractor-related manipulations are concurrently applied to the very same locations, dedicated mechanisms might support the selective encoding of spatial priority in relation to the specific attentional operation involved. In three related experiments, human healthy participants discriminated the direction of a target arrow, while ignoring a salient distractor, if present; both target and distractor spatial probability distributions were concurrently manipulated in relation to each single location. Critically, the selection bias produced by the target-related SL was marginally reduced by an adverse distractor contingency, and the suppression bias generated by the distractor-related SL was erased, or even reversed, by an adverse target contingency. Our results suggest that even conflicting target- and distractor-related SL manipulations result in the adjustment of a unique spatial priority computation, likely because the process directly relies on direct plastic alterations of shared spatial priority map(s).

Design of Ground Target Based on RedEdge MX-Dual Multispectral Camera

Ground target plays an indispensable role in UAV near-earth remote sensing geometric positioning, geographic registration, correction and improvement of remote sensing image accuracy and accuracy. Traditional ground targets are markers with distinct features, shapes and textures, and their dimensions are usually fixed. The UAV can provide high-resolution multi-spectral data with multi-spectral camera, so the target resolution will change as the UAV height increases and the camera band increases, in some bands of the multi-spectral camera, there will be non-response, which will affect the accuracy of target recognition and positioning. Based on the color, material, size and shape of target, a set of targets suitable for target recognition and location of multi-spectral camera is designed in this paper. In order to judge whether the target performance meets the requirements, this paper verifies the positioning accuracy of the target and its response in each channel of the camera. It is proved that the target plane error is about 10mm at 20 ~ 100m altitude, and the height error is about 40mm, and it can respond in ten channels, it provides experience and ideas for the design and development of multi-spectral camera targets.

Arbitrary curvature programming of thermo-active liquid crystal elastomer via topology optimization

Plants can change their morphology upon environmental variations such as temperature. Inspired by plants’ morphological adaptability, we present a computational inverse design framework for systematically creating optimized thermo-active liquid crystal elastomers (LCEs) that spontaneously morph into arbitrary programmed geometries upon temperature changes. The proposed framework is based on multiphysics topology optimization and a statistical mechanics-based LCE model to realize arbitrary curvature programming for LCE composites under large deformations. We propose a curvature-based optimization formulation that enables rotation-invariant and size-insensitive programmability of LCE, accounting for its highly nonlinear deformed shape. We demonstrate that the programmed LCE composites can accurately morph into a wide range of complex target shapes and curvatures, such as those of numbers, letters, flowers, and various objects. The resulting optimized designs exhibit highly irregular material distributions, which surpass intuition-based designs, and precisely produce desired deformed geometries upon temperature increase. The computational inverse design technique holds promise for a wide array of applications requiring function- and performance-driven design of active materials.

MRI-Guided Radiation Therapy for Prostate Cancer: The Next Frontier in Ultrahypofractionation.

Technological advances in MRI-guided radiation therapy (MRIgRT) have improved real-time visualization of the prostate and its surrounding structures over CT-guided radiation therapy. Seminal studies have demonstrated safe dose escalation achieved through ultrahypofractionation with MRIgRT due to planning target volume (PTV) margin reduction and treatment gating. On-table adaptation with MRI-based technologies can also incorporate real-time changes in target shape and volume and can reduce high doses of radiation to sensitive surrounding structures that may move into the treatment field. Ongoing clinical trials seek to refine ultrahypofractionated radiotherapy treatments for prostate cancer using MRIgRT. Though these studies have the potential to demonstrate improved biochemical control and reduced side effects, limitations concerning patient treatment times and operational workflows may preclude wide adoption of this technology outside of centers of excellence. In this review, we discuss the advantages and limitations of MRIgRT for prostate cancer, as well as clinical trials testing the efficacy and toxicity of ultrafractionation in patients with localized or post-prostatectomy recurrent prostate cancer.

Synthesis, crystal structure, Hirshfeld surface analysis, DFT, molecular docking and in vitro antitumor studies of (2E)-2-[4-(diethylamino)benzylidene]-N-ethylhydrazinecarbothioamide

The crystal structure and spectral characterization of a new proligand, (2E)-2-[4-(diethylamino)benzylidene]-N-ethylhydrazinecarbothioamide is described. The compound was crystallized in the monoclinic space group P21/c; Z = 8, V = 3192.7(8) Å3 with unit cell parameters a = 26.232(4) Å, b = 7.9196(10) Å, c = 15.369(3) Å,α = 90°, β = 90.217(6)° and γ = 90°. There are two independent molecules in the asymmetric unit. The crystal structure reveals that the compound exists in the thione form and S1 and N2 are at E configuration to each other with respect to N3–C12 bond. Similarly, S2 and N6 are trans to each other with respect to N7–C26 bond in the second molecule of the asymmetric unit. The packing of the molecules in the crystal lattice is stabilized by intermolecular hydrogen bonds, which are quantified with Hirshfeld surface analysis. The synthesized compound was characterized by IR, UV–vis, 1H and 13C NMR spectra. DFT study indicates the molecular chemical stability with a HOMO-LUMO energy gap of 3.79 eV. The molecule is soft with preference for NS coordination mode. The azomethine nitrogen and thione sulfur region are electron rich and can act as a nucleophilic site to bind with the electrophilic regions of DNA or protein receptors. The in silico docking study with 1BNA suggests that the compound can fit comfortably in the curved shape of the DNA target like a minor groove mode of binding. The in vitro cytotoxicity of the compound, which was screened for DLA tumour cells aspirated from the peritoneal cavity of tumor bearing mice, is indicative of its antitumor potential.

The Design Space of Kirchhoff Rods

The Kirchhoff rod model describes the bending and twisting of slender elastic rods in three dimensions and has been widely studied to enable the prediction of how a rod will deform, given its geometry and boundary conditions. In this work, we study a number of inverse problems with the goal of computing the geometry of a straight rod that will automatically deform to match a curved target shape after attaching its endpoints to a support structure. Our solution lets us finely control the static equilibrium state of a rod by varying the cross-sectional profiles along its length. We also show that the set of physically realizable equilibrium states admits a concise geometric description in terms of linear line complexes, which leads to very efficient computational design algorithms. Implemented in an interactive software tool, they allow us to convert three-dimensional hand-drawn spline curves to elastic rods and give feedback about the feasibility and practicality of a design in real time. We demonstrate the efficacy of our method by designing and manufacturing several physical prototypes with applications to interior design and soft robotics.

Dynamic Management of Capital Levels in a Company as a Multi-Stage Decision-Making Process

An investor makes investment decisions under conditions of uncertainty, i.e. when the effect of the investment cannot be predicted in advance. In order to achieve the desired outcome of the action, the decision-maker has to make a series of consecutive decisions. The decision-maker is guided by his or her own investment objective, and at each stage decides on an investment strategy. Depending on the strategy adopted, the investment returns can vary. Decisions related to giving the capital structure a target shape require a prior careful analysis of many factors, which are characterised by variability both in time and space. For this reason, it can be assumed that the capital structure is not fixed, as it changes according to the strength and direction of these factors. This article proposes a method for managing a company's capital level in a multi-stage decision-making process. For this purpose, the so-called recursive preferences of the decision-maker were used. A multi-stage model of capital management or the management of a given asset by an investor was considered. It was assumed that the dynamics of the capital level process from period to period is described by a certain recursive equation, which can be deterministic or stochastic.

Design of ultra-lightweight and energy-efficient civil structures through shape morphing

This paper gives a new formulation to synthesize load-responsive structures through shape morphing. The design method is based on the minimization of the whole-life energy, which comprises an embodied share in the material and an operational share for adaptation. Target shapes that counteract the effect of the design loads are obtained through geometry and sizing optimization. Adaptation through shape morphing enables effective stress redistribution so that the design is not dominated by peak loads with long return periods. Material utilization is maximized, and therefore embodied energy is significantly reduced. The geometry is controlled through length changes of optimally-placed linear actuators. The actuator commands are computed through minimization of the operational energy to satisfy safety and serviceability criteria. Minimum energy solutions are obtained through a univariate optimization process in which embodied and operational energy minimization are nested. Numerical benchmarks between adaptive and mass-optimized passive solutions are provided on a truss bridge and multi-story frame configurations. Parametric studies show that mass and energy savings are significant for slender structures and when the live load is dominant over the permanent load. Generally, larger shape bounds result in a greater reduction of mass and embodied energy at the cost of a larger operational energy.

Boosting fish counting in sonar images with global attention and point supervision

Automatically counting fish in sonar images has been attracting increasing attention in recent years because extreme efforts are needed in manual counting. Density map regression provides a promising approach in the counting field, but two obstacles are placed in front of fish counting in low resolution sonar images: the difficulty in distinguishing fish from the similar background noise and the inconsistency between the strip-shaped fishes in input images and dot-shaped ground truth density map. To address these issues, we present GPNet, a novel encoder-decoder network with global attention and point supervision, to boost sonar image-based fish counting accuracy. To alleviate the impact of background noise, we incorporate a segmentation module (SM) with global self-attention to the neck of the network to identify the fish region and space out background noise. Furthermore, feature enhancement modules (FEM) with a global receptive field are introduced to the encoder to enhance the feature representation and discrimination. To break down the performance upper bound resulting from target shape inconsistency between input and ground truth, we leverage fish center coordinates instead of the Gaussian density map to supervise the network training directly. Extensive experiments on a challenging public sonar image-based fish counting dataset, the ARIS dataset, demonstrate that GPNet achieves state-of-the-art performance both in counting accuracy and noise removal.

Design principles for 3D-printed thermally activated shape-morphing structures

Morphing structures can change their shape in response to thermal excitation and are commonly used to enhance the performance of actuators, soft robotics, and biomedical devices. One of the main challenges is the inverse design problem, in which a deformed target shape is prescribed and the initial material properties, distribution, and geometry are to be determined. To tackle this challenge, a model for the thermo-mechanical response of free standing multi-layered struts that experience moderate to large deflections is developed. The model is validated through thermally activated 3D-printed bi-layer beams. Next, the model is exploited to develop an efficient inverse design algorithm that accepts a target function as an input and computes the referential configuration that can achieve the required thermally-activated deformations. It is shown that the solution to the inverse problem is not unique, thus providing flexibility in design. The merit of the algorithm is illustrated through the inverse design of three thermally-activated strut-based target shapes. The simplicity and robustness of the algorithm reveals fundamental principle guidelines for inverse design of thermally activated shape morphing structures and enables its extension to other stimuli.

Adaptive tracking of non-ellipsoidal extended target with varying number of sub-objects based on variational Bayesian

High-resolution sensors make it less difficult to detect the true shape of an extended target, and the method of using a single ellipsoid to approximate the extended state of the target is no longer applicable. We can use multiple ellipsoids to approximate the shape of non-ellipsoidal extended targets, but the method of fixing number of sub-objects again fails due to changes in the target shape. In this work, we propose a novel variational Bayesian adaptive filter for non-ellipsoidal extended target tracking (NETT) with a varying number of sub-objects called VN-NETT-VBAF. The proposed filter is used to estimate the motion, extended states, and mixture probabilities of sub-objects describing a non-ellipsoidal extended target. First, the framework of VN-NETT-VBAF is established based on the spawning and combination of sub-objects. Second, the inverse Gamma (IG) distribution is used to model the unknown measurement noise covariance. Based on the variational Bayesian theory, the joint posterior probability density function (PDF) of the system parameters is iteratively updated to achieve the joint estimation of the extended target state and the measurement noise covariance. Finally, an adaptive forgetting factor is designed to update the noise covariance to further improve the robustness of the algorithm to abrupt noise. The simulation results show that the algorithm in this paper can reasonably change the number of sub-objects to adapt to the change of the target extended state, and effectively deal with the abrupt noise to obtain higher filtering accuracy.

Vessel Detection with SDGSAT-1 Nighttime Light Images

The Sustainable Development Goals Science Satellite-1 (SDGSAT-1) Glimmer Imager for Urbanization (GIU) data is very sensitive to low radiation and capable of detecting weak light sources from vessels at night while significantly improving the spatial resolution compared to similar products. Most existing methods fail to use the relevant characteristics of vessels effectively, and it is difficult to deal with the complex shape of vessels in high-resolution Nighttime Light (NTL) data, resulting in unsatisfactory detection results. Considering the overall sparse distribution of vessels and the light source diffusion phenomenon, a novel vessel detection method is proposed in this paper, utilizing the high spatial resolution of the SDGSAT-1. More specifically, noise separation is completed based on a local contrast-weighted RPCA. Then, artificial light sources are detected based on a density clustering algorithm, and an inter-cluster merging method is utilized to realize vessel detection further. We selected three research areas, namely, the Bohai Sea, the East China Sea, and the Gulf of Mexico, to establish a vessel dataset and applied the algorithm to the dataset. The results show that the total detection accuracy and the recall rate of the detection algorithm in our dataset are 96.84% and 96.67%, which is significantly better performance than other methods used for comparison in the experiment. The algorithm overcomes the dataset’s complex target shapes and noise conditions and achieves good results, which proves the applicability of the algorithm.

Staged Embankment Construction in Geotechnical Centrifuges

Abstract This study develops a novel apparatus to simulate the staged, automatic construction of embankments in geotechnical centrifuges with improved measurement accuracy. Modular test equipment was designed to incorporate the functionality of controllable and precise sand release; its structural components include a box-like sand storage module, a push-pull sand release module, and a stepper motor control module. Emphasis was placed on the design of segmented deflectors, the angles of which were derived with rigorous mathematical analysis to mitigate the Coriolis effect on falling sand. Calibration tests demonstrate that the post-construction embankment geometry approximates its target shape with a relative error of 0.72 to 7.37 % in different construction phases at an acceleration of 60 g. A trial was conducted on a staged embankment over the deformable ground, and the displacement of this system was monitored and characterized by tracking reflective marker technology. The results indicate that the proposed method is effective and reflects real-life situations.

Extended object tracking when irregular star convex mutations

In this paper, for extended object tracking in the case of mutation of irregular stars convex shape, using Random Hypersurface Model (RHM ) to model the object, then the target shape is expressed as parameter by radial function. Considering that using circle as a prior shape information requires a long filter consumption time, the RHM-CC-IOU-UKF algorithm proposed in this paper uses the center contour method to correct the prior shape information of the object, and then uses the Intersection over Union (IOU) method to improve the object tracking accuracy in the mutation case. The object estimation shape is updated when combined with a simple filtering algorithm. Eventually, the effectiveness of this algorithm is demonstrated by simulation experiments in two scenarios.

Expected distractor context biases the attentional template for target shapes.

Visual search is supported by an internal representation of the target, the attentional template. However, which features are diagnostic of target presence critically depends on the distractors. Accordingly, previous research showed that consistent distractor context shapes the attentional template for simple targets, with the template emphasizing diagnostic dimensions (e.g., color or orientation) in blocks of trials. Here, we investigated how distractor expectations bias attentional templates for complex shapes, and tested whether such biases reflect intertrial priming or can be instantiated flexibly. Participants searched for novel shapes (cued by name) in two probabilistic distractor contexts: Either the target's orientation or rectilinearity was unique (80% validity). Across four experiments, performance was better when the distractor context was expected, indicating that target features in the expected diagnostic dimension were emphasized. Attentional templates were biased by distractor expectations when distractor context was blocked, also for participants reporting no awareness of the manipulation. Interestingly, attentional templates were also biased when distractor context was cued on a trial-by-trial basis, but only when the two contexts were consistently presented at distinct spatial locations. These results show that attentional templates can flexibly and adaptively incorporate expectations about target-distractor relations when looking for the same object in different contexts. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

(Invited) a Dynamically Reprogrammable Surface with Self-Evolving Shape Morphing

Shape-morphing soft materials are ubiquitous in living systems. They are of increasing relevance to emerging technologies in soft machines, flexible electronics, and smart medicine. The past decade has witnessed phenomenal investment in developing active materials that can shift their shapes, and henceforth their performing functions. However, creating schemes to swiftly reprogram target shapes after fabrication remains challenging. Complexities associated with the operating physics and disturbances from the environment can stop the use of deterministic theoretical models to guide inverse design and control strategies. In this work, we describe a dynamically reprogrammable metasurface with embedded actuation, sensing, and feedback control. The voltage-controlled electromagnetic force drives a flexible, conductive 2D mesh into a diverse set of complex 3D surfaces in the presence of a static magnetic field. The unusual construction of the metasurface from a matrix of filamentary metal traces enables the system to adopt an approximately linear model for inverse design. Implementing an in-situ stereo-imaging feedback strategy with a digitally controlled actuation scheme guided by an optimization algorithm yields surfaces that can morph into target shapes without any presuming models. The closed-loop self-evolving inverse design approach opens opportunities for physical simulations for non-linear or non-ideal systems.

Efficient and high precision target‐driven fluid simulation based on spatial geometry features

SummaryWe proposed a novel target‐driven fluid simulation method based on the weighted control model derived from the spatial geometric features of the target shape. First, the spatial geometric characteristics of the target model are taken into account to set the color field weights of control particles. This enabled the full expression of geometric characteristics of the target model, and improve the shape accuracy of controlled fluid. Then, the fluid is controlled to form the target shape under driving constraints, wherein we proposed a new adaptive constraint mechanism that enables efficient target shape generation. Finally, a new density constraint between the control particles and the controlled fluid particles is proposed to ensure the incompressibility of fluid during control. Compared to the state‐of‐the‐art target‐driven fluid control methods, our method achieves higher precision fluid control with higher efficiency.

Microdosimetric assessment about proton spread-out Bragg peak at different depths based on the normal human mesh-type cell population model.

Objective.In clinical proton therapy, the spread-out Bragg peak (SOBP) is commonly used to fit the target shape. Dose depositions at microscopic sites vary, even with a consistent absorbed dose (D) in SOBP. In the present study, monolayer mesh-type cell population models were developed for microdosimetric assessment at different SOBP depths.Approach.Normal human bronchial epithelial (BEAS-2B) and hepatocytes (L-O2) mesh-type cell models were constructed based on fluorescence tomography images of normal human cells. Particle transport simulation in cell populations was performed coupled with Monte Carlo software PHITS. The relationship between microdosimetry and macrodosimetry of SOBP at different depths was described by analyzing the microdosimetric indicators such as specific energyz,specific energy distributionfz,D,and relative standard deviationσz/z¯within cells. Additionally, the microdosimetric distributions characteristics and their contributing factors were also discussed.Main results.The microscopic dose distribution is strongly influenced by cellular size, shape, and material. The mean specific energyz¯of nucleus and cytoplasm in the cell population is greater than the overall absorbed dose of the cell population model (Dp), with a maximumz¯/Dpof 1.1. The cellular dose distribution is different between the BEAS-2B mesh-type model and its concentric ellipsoid geometry-type model, which difference inz¯is about 10.3% for the nucleus and about 7.5% for the cytoplasm with the SOBP depth of 15 cm. WhenD= 2 Gy, the maximumzof L-O2 nucleus reaches 2.8 Gy andσz/z¯is 5.1% at the mid-depth SOBP (16-18 cm); while the maximumzof the BEAS-2B nucleus reaches 2.2 Gy with only 2.7% ofσz/z¯.Significance.The significant variation of microdosimetric distributions of SOBP different depths indicates the necessity to use mesh-type cell population models, which have the potential to be compared with biological results and build the bio-physical model.