Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian primitives, which complicates the shape extraction. While recent techniques like 2D GS have attempted to improve shape reconstruction, they often reformulate the Gaussian primitives in ways that reduce both rendering quality and computational efficiency. To address these problems, our work introduces a rasterized approach to render the depth maps and surface normal maps of general 3D Gaussian primitives. Our method not only significantly enhances shape reconstruction accuracy but also maintains the computational efficiency intrinsic to Gaussian Splatting. It achieves a Chamfer distance error comparable to Neuralangelo Li et al. [ 2023 ] on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods. Our method is a significant advancement in Gaussian Splatting and can be directly integrated into existing Gaussian Splatting-based methods.

Text-driven 3D indoor scene generation is useful for gaming, film industry, and AR/VR applications. However, existing methods cannot faithfully capture the scene layout based on text descriptions, nor do they allow flexible editing of individual objects in the room. To address these problems, we present Ctrl-Room, which can generate convincing 3D rooms with designer-style layouts and high-fidelity textures from just a text prompt. Our key insight is to separate the modeling of layouts and appearance. Our proposed method consists of two stages: a Layout Generation Stage and an Appearance Generation Stage. The Layout Generation Stage trains a text-conditional diffusion model to learn the layout distribution with our holistic scene code parameterization. Next, the Appearance Generation Stage employs a fine-tuned ControlNet to produce a vivid panoramic image of the room guided by the 3D scene layout, then further upgrades to a panoramic NeRF model. Benefiting from the scene code parameterization, we can easily edit the generated room model through our mask-guided editing module, without expensive edit-specific training. Extensive experiments on the Structured3D dataset demonstrate that our method outperforms existing methods in producing more reasonable, view-consistent, and editable 3D rooms from text prompts.

Context: Detecting fatigue in drivers has become increasingly important for safe driving, especially with the use of more smart devices and Internet-connected vehicles. While sharing data between vehicles can enhance fatigue detection systems, privacy concerns pose significant barriers to this sharing process. We propose a Federated Learning (FL) approach for monitoring fatigue-driven behavior to address these challenges. However, there is a concern that the drivers' private information might be leaked in the FL system. In this paper, we introduce PRIV-DRIVE, a novel approach for privacy-enhanced fatigue detection applications. Our method integrates Paillier homo-morphic encryption (PHE) with a top-k parameter selection technique, bolstering privacy and confidentiality in federated fatigue detection systems. This approach reduces communication and computation overhead while ensuring model accuracy. To the best of our knowledge, this is the first paper to implement PHE in FL setups for fatigue detection applications. We ran several experiments and evaluated the PRIV-DRIVE method. The results show substantial efficiency gains with different HE key sizes, reducing computation time by up to 96% and communication traffic by up to 95%. Importantly, these improvements have minimal impact on accuracy, effectively meeting the requirements of fatigue detection applications.

In smart electric grid systems, various sensors and Internet of Things (IoT) devices are used to collect electrical data at substations. In a traditional system, a multitude of energy-related data from substations needs to be migrated to central storage, such as Cloud or edge devices, for knowledge extraction that might impose severe data misuse, data manipulation, or privacy leakage. This motivates to propose anomaly detection system to detect threats and Federated Learning to resolve the issues of data silos and privacy of data. In this article, we present a framework to identify anomalies in industrial data that are gathered from the remote terminal devices deployed at the substations in the smart electric grid system. The anomaly detection system is based on Long Short-Term Memory (LSTM) and autoencoders that employs Mean Standard Deviation (MSD) and Median Absolute Deviation (MAD) approaches for detecting anomalies. We deploy Federated Learning (FL) to preserve the privacy of the data generated by the substations. FL enables energy providers to train shared AI models cooperatively without disclosing the data to the server. In order to further enhance the security and privacy properties of the proposed framework, we implemented homomorphic encryption based on the Paillier algorithm for preserving data privacy. The proposed security model performs better with MSD approach using HE-128 bit key providing 97% F1-score and 98% accuracy for K=5 with low computation overhead as compared with HE-256 bit key.

Standard visual localization methods build a priori 3D model of a scene which is used to establish correspondences against the 2D keypoints in a query image. Storing these pre-built 3D scene models can be prohibitively expensive for large-scale environments, especially on mobile devices with limited storage and communication bandwidth. We design a novel framework that compresses a scene while still maintaining localization accuracy. The scene is compressed in three stages: first, the database frames are clustered using pairwise co-visibility information. Then, a learned point selection module prunes the points in each cluster taking into account the final pose estimation accuracy. In the final stage, the features of the selected points are further compressed using learned quantization. Query image registration is done using only the compressed scene points. To the best of our knowledge, we are the first to propose learned scene compression for visual localization. We also demonstrate the effectiveness and efficiency of our method on various outdoor datasets where it can perform accurate localization with low memory consumption.

Driven by the megatrend of aerial vehicles, there is an enormous increase in Unmanned Aerial Vehicles (UAVs) that opens up a new field of possibilities, applications, and services to the industry and public. The technological advancements along with the use of electronic control units in UAVs increase complexity. It requires high computing power, power management, and robust electrical and electronic architecture than they are currently used. There is no existing Electrical/Electronics (E/E) architecture standard for UAVs. In this paper, we design a novel E/E architecture for UAVs. The new E/E architecture for UAVs allows for the integration of more complicated and sophisticated functionalities inboard UAVs, including low battery consumption management, efficient navigation, high-performance, chassis, stability control, etc. We also presented future UAV E/E architecture based on zones for safe operations.

The use of an unlicensed band has significantly boosted the capacity of cellular technology via LTE in unlicensed band, license assisted access, and new radio in unlicensed band. Likewise, cellular vehicle to everything in the shared band is also gaining momentum for intelligent transportation systems. Nevertheless, the cellular operator has to wisely decide the proper allocation of this unlicensed band as well as its licensed band, to its users. As the cellular operator cannot guarantee the quality of service in the unlicensed band, motivating the users to offload into the unlicensed band is one of the challenging tasks for the operator. In this paper, we propose an economical approach to encourage users to offload in the unlicensed band while maximizing the utility function for the users and revenue for the operator. Under the proposed scheme, fairness with legacy WiFi users operating in common channel is considered. We investigate the interaction between the operator and the user using a Stackelberg game. We derive the best response function for both operator and user to maximize its utility under complete information, such as service contract and usage pattern. However, it is not always practical to know the comprehensive knowledge of the user in a highly dynamic environment. Thus, a various multi-armed bandit algorithms are used and compared to drive convergence towards an optimal solution. Simulation results have been presented to compare and verify the performance of our proposed scheme.

Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process. These color image semantics only implicitly encode 3D information, potentially limiting the accuracy of the generated shapes. In this paper we propose a multi-view mesh generation method which incorporates geometry information explicitly by using the features from intermediate depth representations of multi-view stereo and regularizing the 3D shapes against these depth images. First, our system predicts a coarse 3D volume from the color images by probabilistically merging voxel occupancy grids from the prediction of individual views. Then the depth images from multi-view stereo along with the rendered depth images of the coarse shape are used as a contrastive input whose features guide the refinement of the coarse shape through a series of graph convolution networks. Notably, we achieve superior results than state-of-the-art multi-view shape generation methods with 34% decrease in Chamfer distance to ground truth and 14% increase in F1-score on ShapeNet dataset.

We demonstrate an autonomous ground robot capable of exploring unknown indoor environments for reconstructing their 2D maps. This problem has been traditionally tackled by geometric heuristics and information theory. More recently, deep learning and reinforcement learning based approaches have been proposed to learn exploration behavior in an end-to-end manner. We present a method that combines the strengths of these different approaches. Specifically, we employ a state-of-the-art generative neural network to predict unknown regions of a partially explored map, and use the prediction to enhance the exploration in an information-theoretic manner. We evaluate our system in simulation using floor plans of real buildings. We also present comparisons with traditional methods which demonstrate the advantage of our method in terms of exploration efficiency. We retain an advantage over end-to-end learned exploration methods in that the robot's behavior is easily explicable in terms of the predicted map.

This paper demonstrates an autonomous mobile robot that follows a walking user while staying ahead of them. Despite several useful applications for autonomous push-carts, this problem has received much less attention than the easier problem of following from behind. In contrast to previous work, we use multi-modal person detection and a human-motion model that considers obstacles to predict the future path of the user. We implement the system with a modular architecture of obstacle mapper, human tracker, human motion model, robot motion planner and robot motion controller. We report on the performance of the robot in real-world experiments. We believe that approaches to this largely overlooked problem could be useful in real industrial, domestic and entertainment applications in the near future.

In VANET, each vehicle near an event location actively collects and disseminates critical event information to adjacent vehicles. Most of the existing message trustworthiness schemes are not suitable for VANET. In this paper, we propose an efficient message trustworthiness scheme to disseminate trustworthy event messages in a timely manner in VANET. We compare our scheme with the Waze in a qualitative way and explain the main advantages of our scheme compared to the Waze.

Vehicular ad hoc networks (VANETs) have been studied intensively due to their wide variety of applications and services, such as passenger safety, enhanced traffic efficiency, and infotainment. With the evolution of technology and sudden growth in the number of smart vehicles, traditional VANETs face several technical challenges in deployment and management due to less flexibility, scalability, poor connectivity, and inadequate intelligence. Cloud computing is considered a way to satisfy these requirements in VANETs. However, next‐generation VANETs will have special requirements of autonomous vehicles with high mobility, low latency, real‐time applications, and connectivity, which may not be resolved by conventional cloud computing. Hence, merging of fog computing with the conventional cloud for VANETs is discussed as a potential solution for several issues in current and future VANETs. In addition, fog computing can be enhanced by integrating Software‐Defined Network (SDN), which provides flexibility, programmability, and global knowledge of the network. We present two example scenarios for timely dissemination of safety messages in future VANETs based on fog and a combination of fog and SDN. We also explained the issues that need to be resolved for the deployment of three different cloud‐based approaches.

Long Term Evolution (LTE) in unlicensed spectrum, Licensed Assisted Access (LAA), has been considered as an effective complement in offloading growing traffic. The LAA is expected to be deployed initially through the small cell integrated under LTE macro cell. Therefore, LTE users under the coverage of LAA small cell must decide to connect one of the co-located networks either LTE or LAA to maximize their performance. In this scenario, we model a network selection game for LTE users using mixed strategy game theoretic approach. Afterwards, we formulate behavior of strategic users toward network selection as a function of the number of nearby users. The simulation results show that increasing number of nearby users make a user less likely to switch to LAA small cell. Additionally, more users nearby make it less likely that LAA resources is being utilized.

One of the challenging issues in wireless network is rogue access point (RAP) detection and mitigation. The authors propose a new access point (AP) selection mechanism to keep wireless users from RAPs. A centralised server called AP registration centre (APRC) maintains a list of authorised APs, and a wireless user can check if a specific AP is legitimate by querying APRC about its legitimacy in a secure way using the concept of voting and signal strength‐based authentication. The authors compare their scheme with a timing‐based scheme and the experiment results show that our scheme detects RAPs accurately with lower false positives and false negatives.

Intrusion detection System forms a vital component of internet security. To keep pace with the growing trends, there is a critical need to replace single layer detection technology with multi layer detection. Different types of Denial of Service (DoS) attacks thwart authorized users from gaining access to the networks and we tried to detect as well as alleviate some of those attacks. In this paper, we have proposed a novel cross layer intrusion detection architecture to discover the malicious nodes and different types of DoS attacks by exploiting the information available across different layers of protocol stack in order to improve the accuracy of detection. We have used cooperative anomaly intrusion detection with data mining technique to enhance the proposed architecture. We have implemented fixed width clustering algorithm for efficient detection of the anomalies in the MANET traffic and also generated different types of attacks in the network. The simulation of the proposed architecture is performed in OPNET simulator and we got the result as we expected.