Adaptive 3D Research Articles

668: Daily 4DCBT-based dose accumulation in adaptive 4D lung SBRT

668: Daily 4DCBT-based dose accumulation in adaptive 4D lung SBRT

An Adaptive 3D Neighbor Discovery and Tracking Algorithm in Battlefield Flying Ad Hoc Networks with Directional Antennas.

Neighbor discovery and tracking with directional antennas in flying ad hoc networks (FANETs) is a challenging issue because of dispersed node distribution and irregular maneuvers in three-dimensional (3D) space. In this paper, we propose an adaptive 3D neighbor discovery and tracking algorithm in battlefield FANETs with directional antennas. With time synchronization, a flying node transmits/receives the neighbor discovery packets sequentially in each beam around it to execute a two-way handshake for neighbor discovery. The transmitting or receiving status of each discovery slot depends on the binary code corresponding to the identification of the node. Discovered neighbor nodes exchange their 3D positions in tracking slots periodically for node tracking, and the maximum tracking period is determined by node velocity, beamwidth, and the minimum distance between nodes. By configuring the relevant parameters, the proposed algorithm can also apply to two-dimensional planar ad hoc networks. The simulation results suggest that the proposed algorithm can achieve shorter neighbor discovery time and longer link survival time in comparison with the random scanning algorithm in scenarios with narrow beamwidth and wide moving area. When the frame length increases, the protocol overhead decreases but the average neighbor discovery time increases. The suitable frame length should be determined based on the network range, node count, beamwidth, and node mobility characteristics.

Adaptive 3D Mesh Steganography Based on Feature-Preserving Distortion.

Current 3D mesh steganography algorithms relying on geometric modification are prone to detection by steganalyzers. In traditional steganography, adaptive steganography has proven to be an efficient means of enhancing steganography security. Taking inspiration from this, we propose a highly adaptive embedding algorithm, guided by the principle of minimizing a carefully crafted distortion through efficient steganography codes. Specifically, we tailor a payload-limited embedding optimization problem for 3D settings and devise a feature-preserving distortion (FPD) to measure the impact of message embedding. The distortion takes on an additive form and is defined as a weighted difference of the effective steganalytic subfeatures utilized by the current 3D steganalyzers. With practicality in mind, we refine the distortion to enhance robustness and computational efficiency. By minimizing the FPD, our algorithm can preserve mesh features to a considerable extent, including steganalytic and geometric features, while achieving a high embedding capacity. During the practical embedding phase, we employ the Q-layered syndrome trellis code (STC). However, calculating the bit modification probability (BMP) for each layer of the Q-layered STC, given the variation of Q, can be cumbersome. To address this issue, we design a universal and automatic approach for the BMP calculation. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in countering 3D steganalysis.

Deep learning for intracranial aneurysm segmentation using CT angiography

Objective. This study aimed to employ a two-stage deep learning method to accurately detect small aneurysms (4–10 mm in size) in computed tomography angiography images. Approach. This study included 956 patients from 6 hospitals and a public dataset obtained with 6 CT scanners from different manufacturers. The proposed method consists of two components: a lightweight and fast head region selection (HRS) algorithm and an adaptive 3D nnU-Net network, which is used as the main architecture for segmenting aneurysms. Segments generated by the deep neural network were compared with expert-generated manual segmentation results and assessed using Dice scores. Main Results. The area under the curve (AUC) exceeded 79% across all datasets. In particular, the precision and AUC reached 85.2% and 87.6%, respectively, on certain datasets. The experimental results demonstrated the promising performance of this approach, which reduced the inference time by more than 50% compared to direct inference without HRS. Significance. Compared with a model without HRS, the deep learning approach we developed can accurately segment aneurysms by automatically localizing brain regions and can accelerate aneurysm inference by more than 50%.

Failure envelopes of rigid tripod pile foundation under combined vertical-horizontal-moment loadings in clay

The problem considered in this computational study is for the bearing capacity determination of three-dimensional (3D) rigid tripod-pile groups subjected to combined vertical (V), horizontal (H), and bending moment (M) loads. Using the adaptive 3D finite element limit analysis (FELA) coupled with lower bound, upper bound and mixed Gauss element formulations, numerical results are compared with those of the previous study under a single-component loading (V, or H, or M). The failure envelope in the 3D V–H–M loading space is then constructed, and several failure mechanisms presented to complement the discussions on the complex 3D responses. This is followed by a parametric study for the various factors such as the pile length, pile spacing, pile-soil adhesion factors as well as the loading direction angle. Finally, a closed-form design expression of failure envelopes considering the abovementioned influential parameters and the combined load are derived. Noting that the current industry-based design procedures for tripod-pile groups are rarely found, the outcome of the present study can be used with great confidence in design practice.

Feature-preserving adaptive 3D scene multi-model simplification algorithm

In a complex 3D scene, which typically contains multiple models with distinct feature differences, determining how to set appropriate simplification rates for each model so that the 3D scene maintains its characteristics well while achieving the desired simplification rate is a challenging task. To address this, this paper proposes a 3D scene simplification algorithm that integrates neural networks to accomplish this task. The algorithm is divided into two stages: the first stage extracts local and global features of each model in the 3D scene to form feature vectors, and the second stage combines neural networks to construct a multi-layer perceptron that predicts the simplification labels for each model in the 3D scene and calculates the simplification weights for each model based on these labels. Experiments have proven that this algorithm not only maintains a good appearance of the 3D scene but also has a smaller overall simplification error compared to the traditional QEM algorithm.

Adaptive Block-Matching and 3D Denoising for Φ-OTDR Under Ultra-Low SNR Conditions

Adaptive Block-Matching and 3D Denoising for Φ-OTDR Under Ultra-Low SNR Conditions

Innovative Adaptive Multiscale 3D Simulation Platform for the Yellow River Using Sphere Geodesic Octree Grid Techniques

Earth system simulation technology is fundamental for ecological protection and high-quality development in the Yellow River Basin. To address the lack of a Yellow River simulation platform, this study proposes an adaptive multiscale true 3D crust simulation platform using the Sphere Geodesic Octree Grid (SGOG). Twelve models in four categories were designed: single fine-scale models, geomorphic zone-based models, and models using both top-down and bottom-up approaches. The models were evaluated based on terrain feature representation and computational efficiency. The results show that single fine-scale models preserve detailed terrain features but are computationally intensive. They are suitable for the precise simulation of surface processes. Top-down and bottom-up models balance terrain detail and efficiency, and are thereby widely applicable. Geomorphic zone-based models provide detailed focal area representation and higher computational efficiency, being more targeted. Various methods offer flexible scale transformations, each with its own strengths, allowing researchers to select a method according to practical application needs. Consequently, this research demonstrates that spherical discrete grids offer reliable support for constructing basin simulation platforms, providing new technological and scientific insights for the Yellow River Basin’s ecological protection and development.

Computed Tomography Effective Dose and Image Quality in Deep Learning Image Reconstruction in Intensive Care Patients Compared to Iterative Algorithms.

Deep learning image reconstruction (DLIR) algorithms employ convolutional neural networks (CNNs) for CT image reconstruction to produce CT images with a very low noise level, even at a low radiation dose. The aim of this study was to assess whether the DLIR algorithm reduces the CT effective dose (ED) and improves CT image quality in comparison with filtered back projection (FBP) and iterative reconstruction (IR) algorithms in intensive care unit (ICU) patients. We identified all consecutive patients referred to the ICU of a single hospital who underwent at least two consecutive chest and/or abdominal contrast-enhanced CT scans within a time period of 30 days using DLIR and subsequently the FBP or IR algorithm (Advanced Modeled Iterative Reconstruction [ADMIRE] model-based algorithm or Adaptive Iterative Dose Reduction 3D [AIDR 3D] hybrid algorithm) for CT image reconstruction. The radiation ED, noise level, and signal-to-noise ratio (SNR) were compared between the different CT scanners. The non-parametric Wilcoxon test was used for statistical comparison. Statistical significance was set at p < 0.05. A total of 83 patients (mean age, 59 ± 15 years [standard deviation]; 56 men) were included. DLIR vs. FBP reduced the ED (18.45 ± 13.16 mSv vs. 22.06 ± 9.55 mSv, p < 0.05), while DLIR vs. FBP and vs. ADMIRE and AIDR 3D IR algorithms reduced image noise (8.45 ± 3.24 vs. 14.85 ± 2.73 vs. 14.77 ± 32.77 and 11.17 ± 32.77, p < 0.05) and increased the SNR (11.53 ± 9.28 vs. 3.99 ± 1.23 vs. 5.84 ± 2.74 and 3.58 ± 2.74, p < 0.05). CT scanners employing DLIR improved the SNR compared to CT scanners using FBP or IR algorithms in ICU patients despite maintaining a reduced ED.

Multiscale 3D printing via active nozzle size and shape control.

Three-dimensional (3D) printers extruding filaments through a fixed nozzle encounter a conflict between high resolution, requiring small diameters, and high speed, requiring large diameters. This limitation is especially pronounced in multiscale architectures featuring both bulk and intricate elements. Here, we introduce adaptive nozzle 3D printing (AN3DP), a technique enabling dynamic alteration of nozzle diameter and cross-sectional shape during printing. The AN3DP nozzle consists of eight independently controllable, tendon-driven pins arrayed around a flexible, pressure-resistant membrane. The design incorporates a tapered angle optimized for extruding shear-thinning inks and a pointed tip suitable for constrained-space printing, such as conformal and embedded printing. AN3DP's efficacy is demonstrated through the fabrication of components with continuous gradients, eliminating the need for discretization, and achieving enhanced density and contour precision compared to traditional 3D printing methods. This platform substantially expands the scope of extrusion-based 3D printers, thus facilitating diverse applications, including bioprinting cell-laden and hierarchical implants with bone-like microarchitecture.

Multi-vehicle adaptive 3D mapping for targeted ocean sampling.

Expanding spatial presentation from two-dimensional profile transects to three-dimensional ocean mapping is key for a better understanding of ocean processes. Phytoplankton distributions can be highly patchy and the accurate identification of these patches with the context, variability, and uncertainty of measurements on relevant scales is difficult to achieve. Traditional sampling methods, such as plankton nets, water samplers and in-situ vertical sensors, provide a snapshot and often miss the fine-scale horizontal and temporal variability. Here, we show how two autonomous underwater vehicles measured, adapted to, and reported real-time chlorophyll a measurements, giving insights into the spatiotemporal distribution of phytoplankton biomass and patchiness. To gain the maximum available information within their sensing scope, the vehicles moved in an adaptive fashion, looking for the regions of the highest predicted chlorophyll a concentration, the greatest uncertainty, and the least possibility of collision with other underwater vehicles and ships. The vehicles collaborated by exchanging data with each other and operators via satellite, using a common segmentation of the area to maximize information exchange over the limited bandwidth of the satellite. Importantly, the use of multiple autonomous underwater vehicles reporting real-time data combined with targeted sampling can provide better match with sampling towards understanding of plankton patchiness and ocean processes.

Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking

The goal of 3D mesh watermarking is to embed the message in 3D meshes that can withstand various attacks imperceptibly and reconstruct the message accurately from watermarked meshes. The watermarking algorithm is supposed to withstand multiple attacks, and the complexity should not grow significantly with the mesh size. Unfortunately, previous methods are less robust against attacks and lack of adaptability. In this paper, we propose a robust and adaptable deep 3D mesh watermarking Deep3DMark that leverages attention-based convolutions in watermarking tasks to embed binary messages in vertex distributions without texture assistance. Furthermore, our Deep3DMark exploits the property that simplified meshes inherit similar relations from the original ones, where the relation is the offset vector directed from one vertex to its neighbor. By doing so, our method can be trained on simplified meshes but remains effective on large size meshes (size adaptable) and unseen categories of meshes (geometry adaptable). Extensive experiments demonstrate our method remains efficient and effective even if the mesh size is 190× increased. Under mesh attacks, Deep3DMark achieves 10%∼50% higher accuracy than traditional methods, and 2× higher SNR and 8% higher accuracy than previous DNN-based methods.

Incorporating a-priori information in deep learning models for quantitative susceptibility mapping via adaptive convolution.

Quantitative susceptibility mapping (QSM) has attracted considerable interest for tissue characterization (e.g., iron and calcium accumulation, myelination, venous vasculature) in the human brain and relies on extensive data processing of gradient-echo MRI phase images. While deep learning-based field-to-susceptibility inversion has shown great potential, the acquisition parameters applied in clinical settings such as image resolution or image orientation with respect to the magnetic field have not been fully accounted for. Furthermore, the lack of comprehensive training data covering a wide range of acquisition parameters further limits the current QSM deep learning approaches. Here, we propose the integration of a priori information of imaging parameters into convolutional neural networks with our approach, adaptive convolution, that learns the mapping between the additional presented information (acquisition parameters) and the changes in the phase images associated with these varying acquisition parameters. By associating a-priori information with the network parameters itself, the optimal set of convolution weights is selected based on data-specific attributes, leading to generalizability towards changes in acquisition parameters. Moreover, we demonstrate the feasibility of pre-training on synthetic data and transfer learning to clinical brain data to achieve substantial improvements in the computation of susceptibility maps. The adaptive convolution 3D U-Net demonstrated generalizability in acquisition parameters on synthetic and in-vivo data and outperformed models lacking adaptive convolution or transfer learning. Further experiments demonstrate the impact of the side information on the adaptive model and assessed susceptibility map computation on simulated pathologic data sets and measured phase data.

Underwater image enhancement using Divide-and-Conquer network.

Underwater image enhancement has become the requirement for more people to have a better visual experience or to extract information. However, underwater images often suffer from the mixture of color distortion and blurred quality degradation due to the external environment (light attenuation, background noise and the type of water). To solve the above problem, we design a Divide-and-Conquer network (DC-net) for enhancing underwater image, which mainly consists of a texture network, a color network and a refinement network. Specifically, the multi-axis attention block is presented in the texture network, which combine different region/channel features into a single stream structure. And the color network employs an adaptive 3D look-up table method to obtain the color enhanced results. Meanwhile, the refinement network is presented to focus on image features of ground truth. Compared to state-of-the-art (SOTA) underwater image enhance methods, our proposed method can obtain the better visual quality of underwater images and better qualitative and quantitative performance. The code is publicly available at https://github.com/zhengshijian1993/DC-Net.

Domain Adaptive Subterranean 3D Pedestrian Detection via Instance Transfer and Confidence Guidance

With the exploration of subterranean scenes, determining how to ensure the safety of subterranean pedestrians has gradually become a hot research topic. Considering the poor illumination and lack of annotated data in subterranean scenes, it is essential to explore the LiDAR-based domain adaptive detectors for localizing the spatial location of pedestrians, thus providing instruction for evacuation and rescue. In this paper, a novel domain adaptive subterranean 3D pedestrian detection method is proposed to adapt pre-trained detectors from the annotated road scenes to the unannotated subterranean scenes. Specifically, an instance transfer-based scene updating strategy is designed to update the subterranean scenes by transferring instances from the road scenes to the subterranean scenes, aiming to create sufficient high-quality pseudo labels for fine-tuning the pre-trained detector. In addition, a pseudo label confidence-guided learning mechanism is constructed to fully utilize pseudo labels of different qualities under the guidance of confidence scores. Extensive experiments validate the superiority of our proposed domain adaptive subterranean 3D pedestrian detection method.

Revolutionizing Robotic Depalletizing: AI-Enhanced Parcel Detecting with Adaptive 3D Machine Vision and RGB-D Imaging for Automated Unloading.

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively.

Enhancing Image Denoising Efficiency: Dynamic Transformations in BM3D Algorithm

This research aims to enhance the performance of image-denoising algorithms, particularly in the context of Block Matching 3D (BM3D) usage, focusing on improving image quality and retaining important information in noisy images. The novelty of this research lies in developing more effective and efficient image-denoising techniques by considering the characteristics of image blocks to improve denoising results. The method employed in this research involves the development of a new approach enabling the application of adaptive 2D and 3D transformations depending on the characteristics of the image block being processed. The research develops a new approach enabling the application of adaptive 2D and 3D transformations depending on the characteristics of the image block being processed. The results of this research indicate that the proposed adaptive approach in the BM3D image denoising algorithm can significantly improve denoising performance. Experimental results show that performing 2D transformations on blocks that do not have sufficiently similar blocks can yield better denoising results, especially at high noise levels.

Adaptive Unsupervised Learning-Based 3D Spatiotemporal Filter for Event-Driven Cameras.

In the evolving landscape of robotics and visual navigation, event cameras have gained important traction, notably for their exceptional dynamic range, efficient power consumption, and low latency. Despite these advantages, conventional processing methods oversimplify the data into 2 dimensions, neglecting critical temporal information. To overcome this limitation, we propose a novel method that treats events as 3D time-discrete signals. Drawing inspiration from the intricate biological filtering systems inherent to the human visual apparatus, we have developed a 3D spatiotemporal filter based on unsupervised machine learning algorithm. This filter effectively reduces noise levels and performs data size reduction, with its parameters being dynamically adjusted based on population activity. This ensures adaptability and precision under various conditions, like changes in motion velocity and ambient lighting. In our novel validation approach, we first identify the noise type and determine its power spectral density in the event stream. We then apply a one-dimensional discrete fast Fourier transform to assess the filtered event data within the frequency domain, ensuring that the targeted noise frequencies are adequately reduced. Our research also delved into the impact of indoor lighting on event stream noise. Remarkably, our method led to a 37% decrease in the data point cloud, improving data quality in diverse outdoor settings.

Multiscale simulation of highly heterogeneous subsurface flow with physically adaptive 3D unstructured grids

The multiscale finite volume framework is extended with physical-based grid adaptation (MSFV-GA) for three-dimensional fully unstructured grids. The MSFV method produces large errors for highly heterogeneous and anisotropic problems on standard coarse grids generated based on geometrical features. Adding constraints based on the fine-scale physical properties to construct coarse grids can increase the accuracy and robustness of the MSFV solutions. A novel and automated coarse grid generation strategy adaptable to the reservoir heterogeneity for 3D unstructured grids is presented. Adaptive coarse grids are generated based on local variations of fine scale permeability field. The proposed procedure is very flexible respect to the local physical and geometrical limitations in coarse blocks. Multiscale coarse grid adaptation notably improves the basis functions calculations. The performance of the MSFV-GA in handling challenging problems involving high media contrasts or impermeable shale layers is assessed. The results are very promising and show that the MSFV-GA can accurately approximate complex physics problems. The presented 3D unstructured procedure can notably improve the applicability of the multiscale finite volume method and provide a promising framework for the next generation of reservoir flow simulators.

An Adaptive Two-Dimensional Voxel Terrain Mapping Method for Structured Environment

Accurate terrain mapping information is very important for foot landing planning and motion control in foot robots. Therefore, a terrain mapping method suitable for an indoor structured environment is proposed in this paper. Firstly, by constructing a terrain mapping framework and adding the estimation of the robot’s pose, the algorithm converts the distance sensor measurement results into terrain height information and maps them into the voxel grid, and effectively reducing the influence of pose uncertainty in a robot system. Secondly, the height information mapped into the voxel grid is downsampled to reduce information redundancy. Finally, a preemptive random sample consistency (preemptive RANSAC) algorithm is used to divide the plane from the height information of the environment and merge the voxel grid in the extracted plane to realize the adaptive resolution 2D voxel terrain mapping (ARVTM) in the structured environment. Experiments show that the proposed mapping algorithm reduces the error of terrain mapping by 62.7% and increases the speed of terrain mapping by 25.1%. The algorithm can effectively identify and extract plane features in a structured environment, reducing the complexity of terrain mapping information, and improving the speed of terrain mapping.