Time-Sensitive Networking (TSN) offers deterministic communication for time-sensitive applications, using Cyclic Queuing and Forwarding (CQF) to manage time-triggered flows (TT flows). Scheduling TT flows is essential for optimizing network resource utilization and scheduling success rates. Existing works prefer heuristic algorithms due to their favorable trade off between computational overhead and performance. However, they overlook two critical factors during design: search space approximation efficiency and the impact of routing policy. In this study, we present H-GATS (Hybrid Genetic Algorithm and Tabu Search) for CQF-based TSN flow routing and scheduling. H-GATS combines the global search of Genetic Algorithms with the local search of Tabu Search, achieving fine-grained search efficiency and reduced execution time in complex networks. Moreover, H-GATS considers the offset and routing of flows, further improving scheduling performance. Compared to GA, Tabu, and JRS-LB, H-GATS is 5.8×, 3.05×, and 1.6× faster, respectively, in achieving the same success rates. Additionally, H-GATS improves the success rate by 5.5%, 9.6%, and 3.9% and enhances the resource utilization rate by 18%, 13.3%, and 3.3% over these baselines.

Discontinuous pulse-width modulation (DPWM) of neutral-point-clamped (NPC)NPC three-level inverter can effectively reduce a large amount of switching losses in high-frequency applications by controlling single phase switch to not operate within 1/3 carrier period. However, the traditional over-zero clamped type DPWM (DPWMA) strategy with unchangeable clamped interval has high low-order harmonics in output current contains, and has poor neutral-point voltage balancing ability with a single redundant small vector. A new carrier-based DPWM (CB-DPWM) scheme is proposed to decrease the current low-order harmonics and optimize neutral-point voltage balancing ability, which has variable clamped interval. The proposed CB-DPWM method judges the relationship between the three-phase sine modulation wave and bias voltage after left and right phase shifting, and has adjustable zero crossing and peak clamped interval. Simulation and experimental verification were carried out on a three-level NPC inverter platform, verifying the correctness of the theory. Compared with DPWMA, the proposed method has better output current quality, better neutral-point voltage balancing ability and dynamic performance.

Restoring high-fidelity textures for 3D reconstructed models are an increasing demand in AR/VR, cultural heritage protection, entertainment, and other relevant fields. Due to geometric errors and camera pose drifting, existing texture mapping algorithms are either plagued by blurring and ghosting or suffer from undesirable visual seams. In this paper, we propose a novel tri-directional similarity texture synthesis method to eliminate the texture inconsistency in RGB-D 3D reconstruction and generate visually realistic texture mapping results. In addition to RGB color information, we incorporate a novel color image texture detail layer serving as an additional context to improve the effectiveness and robustness of the proposed method. First, we select an optimal texture image for each triangle face of the reconstructed model to avoid texture blurring and ghosting. During the selection procedure, the texture details are weighted to avoid generating texture chart partitions across high-frequency areas. Then, we optimize the camera pose of each texture image to align with the reconstructed 3D shape. Next, we propose a tri-directional similarity function to resynthesize the image context within the boundary stripe of texture charts, which can significantly diminish the occurrence of texture seams. Finally, we introduce a global color harmonization method to address the color inconsistency between texture images captured from different viewpoints. The experimental results demonstrate that the proposed method outperforms state-of-the-art texture mapping methods and effectively overcomes texture tearing, blurring, and ghosting artifacts.

Point cloud shape completion plays a central role in diverse 3D vision and robotics applications. Early methods used to generate global shapes without local detail refinement. Current methods tend to leverage local features to preserve the observed geometric details. However, they usually adopt the convolutional architecture over the incomplete point cloud to extract local features to restore the diverse information of both latent shape skeleton and geometric details, where long-distance correlation among the skeleton and details is ignored. In this work, we present a coarse-to-fine completion framework, which makes full use of both neighboring and long-distance region cues for point cloud completion. Our network leverages a Skeleton-Detail Transformer, which contains cross-attention and self-attention layers, to fully explore the correlation from local patterns to global shape and utilize it to enhance the overall skeleton. Also, we propose a selective attention mechanism to save memory usage in the attention process without significantly affecting performance. We conduct extensive experiments on the ShapeNet dataset and real-scanned datasets. Qualitative and quantitative evaluations demonstrate that our proposed network outperforms current state-of-the-art methods.

Point cloud-based place recognition is a fundamental part of the localization task, and it can be achieved through a retrieval process. Reranking is a critical step in improving the retrieval accuracy, yet little effort has been devoted to reranking in point cloud retrieval. In this paper, we investigate the versatility of rigid registration in reranking the point cloud retrieval results. Specifically, after obtaining the initial retrieval list based on the global point cloud feature distance, we perform registration between the query and point clouds in the retrieval list. We propose an efficient strategy based on visual consistency to evaluate each registration with a registration score in an unsupervised manner. The final reranked list is computed by considering both the original global feature distance and the registration score. In addition, we find that the registration score between two point clouds can also be used as a pseudo label to judge whether they represent the same place. Thus, we can create a self-supervised training dataset when there is no ground truth of positional information. Moreover, we develop a new probability-based loss to obtain more discriminative descriptors. The proposed reranking approach and the probability-based loss can be easily applied to current point cloud retrieval baselines to improve the retrieval accuracy. Experiments on various benchmark datasets show that both the reranking registration method and probability-based loss can significantly improve the current state-of-the-art baselines.

Reconstructing 3D models for single objects with complex backgrounds has wide applications like 3D printing, AR/VR, and so on. It is necessary to consider the tradeoff between capturing data at low cost and getting high-quality reconstruction results. In this work, we propose a voxel-based modeling pipeline with sparse RGB-D images to effectively and efficiently reconstruct a single real object without the geometrical post-processing operation on background removal. First, referring to the idea of VisualHull, useless and inconsistent voxels of a targeted object are clipped. It helps focus on the target object and rectify the voxel projection information. Second, a modified TSDF calculation and voxel filling operations are proposed to alleviate the problem of depth missing in the depth images. They can improve TSDF value completeness for voxels on the surface of the object. After the mesh is generated by the MarchingCube, texture mapping is optimized with view selection, color optimization, and camera parameters fine-tuning. Experiments on Kinect capturing dataset, TUM public dataset, and virtual environment dataset validate the effectiveness and flexibility of our proposed pipeline.

This study proposes a short-term traffic flow prediction framework. The vector autoregression (VAR) model based on econometric theory and the CNN-LSTM hybrid neural network model based on deep learning are employed in the analysis. An intrinsic association among traffic variables is first evaluated using the VAR model, and the predictable relationship of these variables is determined. Then the multi-features speed prediction for one spatial location using the CNN-LSTM hybrid neural network model is conducted, the prediction results prove that prediction with multi-feature is better than that with a single feature. Subsequently, several popular deep learning models and other shallow predicted models are proposed to be compared with the constructed CNN-LSTM network model, and the comparison illustrates that the model performance of the developed CNN-LSTM network model is superior to other models in forecasting the short-term traffic flow. Then the multi-feature speed predictions for a group of spatial locations are further conducted using the CNN-LSTM model. The result demonstrates the predictive accuracies are associated with the spatial correlation of traffic flow. Finally, a heatmap is produced to visualize the predicted speed, from which the spatial-temporal traffic condition can be presented clearly. The research results have the potential to be applied to the travel information releasing and traffic congestion management.

Triangle count is a critical parameter in mining relationships among people in social networks. However, directly publishing the findings obtained from triangle counts may bring potential privacy concern, which raises great challenges and opportunities for privacy-preserving triangle counting. In this paper, we choose to use differential privacy to protect triangle counting for large scale graphs. To reduce the large sensitivity caused in large graphs, we propose a novel graph projection method that can be used to obtain an upper bound for sensitivity in different distributions. In particular, we publish the triangle counts satisfying the node-differential privacy with two kinds of histograms: the triangle count distribution and the cumulative distribution. Moreover, we extend the research on privacy preserving triangle counting to one of its applications, the local clustering coefficient. Experimental results show that the cumulative distribution can fit the real statistical information better, and our proposed mechanism has achieved better accuracy for triangle counts while maintaining the requirement of differential privacy.